for Journals by Title or ISSN
for Articles by Keywords
Journal Cover Biocybernetics and Biological Engineering
  [SJR: 0.279]   [H-I: 8]   [4 followers]  Follow
   Full-text available via subscription Subscription journal  (Not entitled to full-text)
   ISSN (Print) 0208-5216
   Published by Elsevier Homepage  [3040 journals]
  • Simplification of breast deformation modelling to support breast cancer
           treatment planning
    • Authors: Marta Danch-Wierzchowska; Damian Borys; Barbara Bobek-Billewicz; Michal Jarzab; Andrzej Swierniak
      Pages: 531 - 536
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 4
      Author(s): Marta Danch-Wierzchowska, Damian Borys, Barbara Bobek-Billewicz, Michal Jarzab, Andrzej Swierniak
      The exact delineation of tumour boundaries is of utmost importance in the planning of cancer therapy, either surgery or pre- or post-operative radiation treatment. In the case of breast cancer one of the most advanced modalities is magnetic resonance imaging (MRI). Although MRI scans provide wealth of information about the structure of a tumour and the surrounding tissues, the data obtained represent the patient in a prone position, with breast, in a coil while surgery is performed in a supine position, on lying breast. There is no doubt that a patient's breast in both positions has a different shape and that this influences the intra-breast relations. Our present preliminary study introduces a simple breast model developed from prone images. The model should be built rapidly and by a simple procedure, based only on essential structures, and the goal is to prove its usefulness in treatment planning.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.06.001
  • Multi-sequence texture analysis in classification of in vivo MR images of
           the prostate
    • Authors: Dorota Duda; Marek Kretowski; Romain Mathieu; Renaud de Crevoisier; Johanne Bezy-Wendling
      Pages: 537 - 552
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 4
      Author(s): Dorota Duda, Marek Kretowski, Romain Mathieu, Renaud de Crevoisier, Johanne Bezy-Wendling
      The aim of the study is to investigate the potential of multi-sequence texture analysis in the characterization of prostatic tissues from in vivo Magnetic Resonance Images (MRI). The approach consists in simultaneous analysis of several images, each acquired under different conditions, but representing the same part of the organ. First, the texture of each image is characterized independently of the others. Then the feature values corresponding to different acquisition conditions are combined in one vector, characterizing a combination of textures derived from several sequences. Three MRI sequences are considered: T1-weighted, T2-weighted, and diffusion-weighted. Their textures are characterized using six methods (statistical and model-based). In total, 30 tissue descriptors are calculated for each sequence. The feature space is reduced using a modified Monte Carlo feature selection, combined with wrapper methods, and Principal Components Analysis. Six classifiers were used in the work. Multi-sequence texture analysis led to better classification results than single-sequence analysis. The subsets of features selected with the Monte Carlo method guaranteed the highest classification accuracies.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.05.002
  • Generative Model-Driven Feature Learning for dysarthric speech recognition
    • Authors: N. Rajeswari; S. Chandrakala
      Pages: 553 - 561
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 4
      Author(s): N. Rajeswari, S. Chandrakala
      Recognition of speech uttered by severe dysarthric speakers needs a robust learning technique. One of the commonly used generative model-based classifiers for speech recognition is a hidden Markov model. Generative model-based classifiers do not do well for overlapping classes and due to insufficient training data. Dysarthric speech is normally partial or incomplete that leads to improper learning of temporal dynamics. To overcome these issues, we focus on learning features for dysarthric speech recognition that involves recognizing the sequential patterns of varying length utterances. We propose a Generative Model-Driven Feature Learning based discriminative framework that maps the sequence of feature vectors to fixed dimension vector spaces induced by the generative models. The discriminative classifier is built in that vector space. The proposed HMM-based fixed dimensional vector representation provides better discrimination for dysarthric speech than the conventional HMM. We examine the performance of the proposed method to recognize the isolated utterances from the UA-Speech database. The recognition accuracy of the proposed model is better than the conventional hidden Markov model-based approach.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.05.003
  • Evaluating the fetal heart rate baseline estimation algorithms by their
           influence on detection of clinically important patterns
    • Authors: Janusz Jezewski; Krzysztof Horoba; Dawid Roj; Janusz Wrobel; Tomasz Kupka; Adam Matonia
      Pages: 562 - 573
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 4
      Author(s): Janusz Jezewski, Krzysztof Horoba, Dawid Roj, Janusz Wrobel, Tomasz Kupka, Adam Matonia
      A correctly estimated component of fetal heart rate signal (FHR) – so called baseline – is a precondition for proper recognition of acceleration and deceleration patterns. A number of various algorithms for estimating the FHR baseline was proposed so far. However, there is no reference standard enabling their objective evaluation, and thus no methodology of comparing the different algorithms still exists. In this paper we propose a method for evaluation of automatically determined baseline in reference to a set of experts, based on ten separate groups of signals comprising typical variability patterns observed in the fetal heart rate. As it was proposed earlier [1], the given algorithm is evaluated based on the characteristic patterns detected using the obtained baseline, instead of direct analysis of the baseline shape. For the purpose of quantitative assessment of the estimated baseline a new synthetic inconsistency coefficient was applied. The proposed methodology enabled to evaluate eleven well-known algorithms. We believe that the method will be a valuable tool for assessment of the existing algorithms, as well as for developing the new ones.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.06.003
  • Early predicting a risk of preterm labour by analysis of antepartum
           electrohysterograhic signals
    • Authors: Krzysztof Horoba; Janusz Jezewski; Adam Matonia; Janusz Wrobel; Robert Czabanski; Michal Jezewski
      Pages: 574 - 583
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 4
      Author(s): Krzysztof Horoba, Janusz Jezewski, Adam Matonia, Janusz Wrobel, Robert Czabanski, Michal Jezewski
      This study is aimed at evaluation of the capability to indicate the preterm labour risk by analysing the features extracted from the signals of electrical uterine activity. Free access database was used with 300 signals acquired in two groups of pregnant women who delivered at term (262 cases) and preterm (38 cases). Signal features comprised classical time domain description, spectral parameters and nonlinear measures of contractile activity. Their mean values were calculated for all the contraction episodes detected in each record and their statistical significance for recognition of two groups of recordings was provided. Obtained results were related to the previous study where the same features were applied but they were determined for entire signals. Influence of electrodes location, band-pass filter settings and gestation week was investigated. The obtained results showed that a spectral parameter – the median frequency was the most promising indicator of the preterm labour risk.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.06.004
  • Automatic segmentation of cell nuclei using Krill Herd optimization based
           multi-thresholding and Localized Active Contour Model
    • Authors: Sabeena Beevi K.; Madhu S. Nair; G.R. Bindu
      Pages: 584 - 596
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 4
      Author(s): Sabeena Beevi K., Madhu S. Nair, G.R. Bindu
      Analysis of tissue components in histopathology image stays on as the gold standard in detecting different types of cancers. Active Contour Models (ACM) serve as a widely useful tool in object segmentation in pathology images. Since the ACMs are susceptible to initial contour placement, efficiency of object detection is very much influenced by the selection of primary curve placement technique. In this paper, in order to handle diffused intensities present along object boundaries in histopathology images, segmentation of nuclei from breast histopathology images are carried out by Localized Active Contour Model (LACM) utilizing bio-inspired optimization techniques in the detection stage. Krill Herd Algorithm (KHA) based optimal curve placement provides better initial boundaries compared with other detection techniques. The segmentation performance is investigated based on Housdorff (HD) and Maximum Absolute Distance (MAD) measures. The algorithm also shows comparable performance with other state-of-the-art techniques in terms of quantitative measures such as Precision, Accuracy and Touching Nuclei Resolution when applied to complex images of stained breast biopsy slides.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.06.005
  • MIAP – Web-based platform for the computer analysis of microscopic
           images to support the pathological diagnosis
    • Authors: Tomasz Markiewicz; Anna Korzynska; Andrzej Kowalski; Zaneta Swiderska-Chadaj; Piotr Murawski; Bartlomiej Grala; Malgorzata Lorent; Marek Wdowiak; Jakub Zak; Lukasz Roszkowiak; Wojciech Kozlowski; Dorota Pijanowska
      Pages: 597 - 609
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 4
      Author(s): Tomasz Markiewicz, Anna Korzynska, Andrzej Kowalski, Zaneta Swiderska-Chadaj, Piotr Murawski, Bartlomiej Grala, Malgorzata Lorent, Marek Wdowiak, Jakub Zak, Lukasz Roszkowiak, Wojciech Kozlowski, Dorota Pijanowska
      The aim of the project is to design and to implement a web-based platform for the computer analysis of microscopic images which support the pathological diagnosis. The use of the platform will be free of charge. It offers: quantitative analysis of staining tissue sample’ images, archiving microscopic images, peer consultation, and join work independently from distance between scientific collaborating centers to registered doctors, scientists and students. The use of proposed platform allows: (i) to save pathologists’ time spend on quantitative analysis, (ii) to reduce consulting costs by replacing sending of the physical preparations by placing their images (mostly virtual slide) on the platform server, (iii) to increase reproducibility, comparability and objectivity of quantitative evaluations. These effects have a direct impact on improving the effectiveness and decreasing the costs of patients’ treatment. This paper presents the main ideas of the project which deliver web-based system working as multi-functional, integrated, modular and scalable computer system. The details of hardware solutions, concept of the workflow in the platform, the programming language and interpreters, the specific tools and algorithms, and the user interfaces are described below. The practical solutions for web-based services in the area of medical image analysis, storage and retrieval are also presented and discussed.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.06.006
  • Computer simulation of mucosal waves on vibrating human vocal folds
    • Authors: Tomáš Vampola; Jaromír Horáček; Ivo Klepáček
      Pages: 451 - 465
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Tomáš Vampola, Jaromír Horáček, Ivo Klepáček
      A three-dimensional (3D) finite element (FE) fully parametric model of the human larynx based on computer tomografy measurements was developed and specially adapted for numerical simulation of vocal folds vibrations with collisions. The complex model consists of the vocal folds, arytenoids, thyroid and cricoid cartilages. The vocal fold tissue is modeled as a three layered transversal isotropic material composed of the cover, ligament and muscle and compared with a four layered material where part of the cover was substituted by a liquid layer modelling the superficial layer of lamina propria. First, the basic frequency-modal properties of the model are presented for a given pretension of the vocal folds. The results of numerical simulation of the vocal folds oscillations excited by a prescribed intraglottal aerodynamic pressure are then presented. The results computed in time domain show the 3D motion of the vocal folds in all three directions (horizontal, vertical and anterior-posterior) and the mucosal waves are clearly modeled in the medial cross-section of the vocal folds. The proper orthogonal decomposition (POD) analysis of the excited modes of vibration shows that when taking account of the superficial sub-layer inside the lamina propria with liquid like properties the POD modes are in better agreement with the empirical eigenfunctions (EEF) obtained from measurements performed on excised human larynges. Finally, the usability of the POD analysis for simulation of pathological situations is demonstrated considering a vocal fold nodule located on the upper cranial margin of the right vocal fold.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.03.004
  • Using support vector regression in gene selection and fuzzy rule
           generation for relapse time prediction of breast cancer
    • Authors: Hamid Mahmoodian; Leila Ebrahimian
      Pages: 466 - 472
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Hamid Mahmoodian, Leila Ebrahimian
      Gene expression profiles have been recently used in survival analysis, tumor classification and ER status identification. The prediction of breast cancer recurrence based on gene expression profile has been regarded in some previous studies in which the procedures were based on the concept of regression functions and fuzzy systems. In this study, a method based on the combination of these two concepts is presented; not only a method for gene selection, but also a systematic way to create fuzzy rules are going to be offered. Due to the ability of type-2 fuzzy systems in handling of uncertain systems, the proposed model is developed to type-2. The results show that this model has been improved in comparison to previous ones.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.03.003
  • Hybrid cardiovascular simulator as a tool for physical reproduction of the
           conditions prevailing in the apex of the heart
    • Authors: Alicja Siewnicka; Krzysztof Janiszowski; Tadeusz Pałko; Paweł Wnuk
      Pages: 473 - 481
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Alicja Siewnicka, Krzysztof Janiszowski, Tadeusz Pałko, Paweł Wnuk
      This paper presents the results of research focused on the adaptation of a hybrid simulator of the human circulatory system to the physical reproduction of the haemodynamic conditions prevailing in the apex of the heart. This report describes the principle of operation of the hybrid simulator and presents two methods of its modification. The work includes analysis of the algorithm verification and describes problems that appeared during research. A comparison of the results obtained for both modification methods is shown, as well as preliminary simulation results for a constant-flow ventricle assist device joined to the hybrid simulator operating in the apex of the heart-aorta configuration.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.03.006
  • Percutaneous double lumen cannula for right ventricle assist device
           system: A computational fluid dynamics study
    • Authors: Francesca Condemi; Dongfang Wang; Gionata Fragomeni; Fuqian Yang; Guangfeng Zhao; Cameron Jones; Cherry Ballard-Croft; Joseph B. Zwischenberger
      Pages: 482 - 490
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Francesca Condemi, Dongfang Wang, Gionata Fragomeni, Fuqian Yang, Guangfeng Zhao, Cameron Jones, Cherry Ballard-Croft, Joseph B. Zwischenberger
      Objectives Our goal is to develop a double lumen cannula (DLC) for a percutaneous right ventricular assist device (pRVAD) in order to eliminate two open chest surgeries for RVAD installation and removal. The objective of this study was to evaluate the performance, flow pattern, blood hemolysis, and thrombosis potential of the pRVAD DLC. Methods Computational fluid dynamics (CFD), using the finite volume method, was performed on the pRVAD DLC. For Reynolds numbers <4000, the laminar model was used to describe the blood flow behavior, while shear-stress transport k–ω model was used for Reynolds numbers >4000. Bench testing with a 27Fr prototype was performed to validate the CFD calculations. Results There was <1.3% difference between the CFD and experimental pressure drop results. The Lagrangian approach revealed a low index of hemolysis (0.012% in drainage lumen and 0.0073% in infusion lumen) at 5l/min flow rate. Blood stagnancy and recirculation regions were found in the CFD analysis, indicating a potential risk for thrombosis. Conclusions The pRVAD DLC can handle up to 5l/min flow with limited potential hemolysis. Further modification of the pRVAD DLC is needed to address blood stagnancy and recirculation.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.04.002
  • Non-linear viscoelastic constitutive model for bovine cortical bone tissue
    • Authors: Marek Pawlikowski; Katarzyna Barcz
      Pages: 491 - 498
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Marek Pawlikowski, Katarzyna Barcz
      In the paper a constitutive law formulation for bovine cortical bone tissue is presented. The formulation is based on experimental studies performed on bovine cortical bone samples. Bone tissue is regarded as a non-linear viscoelastic material. The constitutive law is derived from the postulated strain energy function. The model captures typical viscoelastic effects, i.e. hysteresis, stress relaxation and rate-dependence. The elastic and rheological constants were identified on the basis of experimental tests, i.e. relaxation tests and monotonic uniaxial tests at three different strain rates, i.e. λ ˙ = 0.1  min − 1 , λ ˙ = 0.5  min − 1 and λ ˙ = 1.0  min − 1 . In order to numerically validate the constitutive model the fourth-order stiffness tensor was analytically derived and introduced to Abaqus® finite element (FE) software by means of UMAT subroutine. The model was experimentally validated. The validation results show that the derived constitutive law is adequate to model stress–strain behaviour of the considered bone tissue. The constitutive model, although formulated in the strain rate range λ ˙ = 0.1 − 1.0  min − 1 , is also valid for the strain rate values slightly higher than λ ˙ = 1.0  min − 1 . The work presented in the paper proves that the formulated constitutive model is very useful in modelling compressive behaviour of bone under various ranges of load.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.03.005
  • An efficient algorithm of ECG signal denoising using the adaptive dual
           threshold filter and the discrete wavelet transform
    • Authors: Wissam Jenkal; Rachid Latif; Ahmed Toumanari; Azzedine Dliou; Oussama El B’charri; Fadel M.R. Maoulainine
      Pages: 499 - 508
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Wissam Jenkal, Rachid Latif, Ahmed Toumanari, Azzedine Dliou, Oussama El B’charri, Fadel M.R. Maoulainine
      This paper proposes an efficient method of ECG signal denoising using the adaptive dual threshold filter (ADTF) and the discrete wavelet transform (DWT). The aim of this method is to bring together the advantages of these methods in order to improve the filtering of the ECG signal. The aim of the proposed method is to deal with the EMG noises, the power line interferences and the high frequency noises that could perturb the ECG signal. This algorithm is based on three steps of denoising, namely, the DWT decomposition, the ADTF step and the highest peaks correction step. This paper presents certain applications of this algorithm on some of the MIT-BIH Arrhythmia database's signals. The results of these applications allow observing the high performance of the proposed method comparing to some other techniques recently published.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.04.001
  • Prediction of binding peptides to class I Major Histocompatibility Complex
           using modified scoring matrices and data splitting strategies
    • Authors: Dina A. Salem; Rania A. Abul Seoud; Yasser M. Kadah
      Pages: 509 - 520
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Dina A. Salem, Rania A. Abul Seoud, Yasser M. Kadah
      Predicting peptides that can bind to MHC class I molecules is an important step in the vaccine design process. Computational approaches have potential to provide good predictive models that save both time and cost of the process. Position Specific Scoring Matrix (PSSM) is a reliable approach when dealing with amino acid sequences. PSSM formation involves carefully selecting its constructing data and parameters. In this work, we apply three different data splitting strategies and propose alternative values for the embedded PSSM parameters. The basic principle of data splitting is to choose train data that is able to represent the whole data. We propose using the Kennard–Stone algorithm to highlight the importance of choosing the data constituting the PSSM. Furthermore, this work proposes modifications to PSSM parameters and studies the model behavior in response to each change. The model is applied to experimental data for the Major Histocompatibility Complex of class I. Performance of modified parameters show either comparable or better results to conventional parameters. Moreover, Kennard–Stone data splitting algorithm contributed to significant model performance enhancement.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.04.003
  • A novel feature extraction approach based on ensemble feature selection
           and modified discriminant independent component analysis for microarray
           data classification
    • Authors: Maryam Mollaee; Mohammad Hossein Moattar
      Pages: 521 - 529
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 3
      Author(s): Maryam Mollaee, Mohammad Hossein Moattar
      Microarray data play critical role in cancer classification. However, with respect to the samples scarcity compared to intrinsic high dimensionality, most approaches fail to classify small subset of genes. Feature selection techniques can reduce the dimension of the problem, which can reduce computational cost of the microarray data classification. However, previous studies have shown that feature extraction methods can also be useful in improving the performance of data classification. In this paper, we propose an ensemble schema for cancer diagnosis and classification that has three stages. At first, a hybrid filter-based feature selection method using modified Bayesian logistic regression (BLogReg), Ttest and Fisher ratio is applied for selecting genes. In the second stage, selected genes are mapped via the proposed PSO-dICA method which is a modification of dICA. Finally, mapped features are classified using SVM classifier. To demonstrate the effectiveness of the proposed method, some traditional microarray data including Colon, Lung cancer, DLBCL, SRBCT, Leukemia-ALL and Prostate Tumor datasets are used. Experimental results show the efficiency and effectiveness of the proposed method.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.05.001
  • Automatic voice pathology detection and classification using vocal tract
           area irregularity
    • Authors: Ghulam Muhammad; Ghadir Altuwaijri; Mansour Alsulaiman; Zulfiqar Ali; Tamer A. Mesallam; Mohamed Farahat; Khalid H. Malki; Ahmed Al-nasheri
      Pages: 309 - 317
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Ghulam Muhammad, Ghadir Altuwaijri, Mansour Alsulaiman, Zulfiqar Ali, Tamer A. Mesallam, Mohamed Farahat, Khalid H. Malki, Ahmed Al-nasheri
      In this paper, an automatic voice pathology detection (VPD) system based on voice production theory is developed. More specifically, features are extracted from vocal tract area, which is connected to the glottis. Voice pathology is related to a vocal fold problem, and hence the vocal tract area which is connected to vocal folds or glottis should exhibit irregular patterns over frames in case of a sustained vowel for a pathological voice. This irregular pattern is quantified in the form of different moments across the frames to distinguish between normal and pathological voices. The proposed VPD system is evaluated on the Massachusetts Eye and Ear Infirmary (MEEI) database and Saarbrucken Voice Database (SVD) with sustained vowel samples. Vocal tract irregularity features and support vector machine classifier are used in the proposed system. The proposed system achieves 99.22%±0.01 accuracy on the MEEI database and 94.7%±0.21 accuracy on the SVD. The results indicate that vocal tract irregularity measures can be used effectively in automatic voice pathology detection.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.01.004
  • Human impedance parameter estimation using artificial neural network for
           modelling physiotherapist motion
    • Authors: Uğur Demir; Sıtkı Kocaoğlu; Erhan Akdoğan
      Pages: 318 - 326
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Uğur Demir, Sıtkı Kocaoğlu, Erhan Akdoğan
      Physiotherapy (physical therapy) is a form of therapy aimed at regaining patients their bodily limb motor functions. The use of what are called therapeutic exercise robots for such purposes is gradually increasing. Therapeutic exercise robots have been developed for lower and upper limbs. These robots lighten the workload of physiotherapists (PTs) by providing the movements on patients’ relevant limbs. In order to get robots to perform the movements that the PT expects the patient to perform, it is required to determine the mechanical impedance parameters (inertia, stiffness and damping) due to the contact between the PT and patient's limb's, and to ensure that the robot moves according to these parameters. The aim of this study is to estimate these impedance parameters by using artificial neural networks (ANNs). Data from experiments on real subjects were used to train the network, and success was obtained using new data not presented to the network before. Subsequently, the previously acquired output was re-directed to the network with the purpose of developing a network, which can learn more accurately. Results have provided the designed ANN structure can generate necessary impedance parameter value to imitate PT motions.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.01.002
  • Numerical prediction of the effect of aortic Left Ventricular Assist
           Device outflow-graft anastomosis location
    • Authors: Rosario Mazzitelli; Fergal Boyle; Eoin Murphy; Attilio Renzulli; Gionata Fragomeni
      Pages: 327 - 343
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Rosario Mazzitelli, Fergal Boyle, Eoin Murphy, Attilio Renzulli, Gionata Fragomeni
      A Left Ventricular Assist Device (LVAD) is used to provide haemodynamic support to patients with critical cardiac failure. As LVADs generate continuous flow to better understand the haemodynamic effects of these devices under different working conditions, and particularly in relation to possible outflow-graft anastomosis location, we performed 3D one-way-coupled fluid–structure-interaction (FSI) for three different LVAD working conditions and with the anastomosis location in the ascending aorta and in the descending aorta. The anatomical model used in this study is a patient-specific geometry reconstructed from computed tomography images and the mechanical support considered is similar to the Jarvik 2000® Heart LVAD. Endothelial cells can be influenced by wall stress generated from the blood flow in the artery, so they can produce vascular complications. For this reason, the second aim of this study is to evaluate and analyse, using different mechanical indicators, the wall shear distribution upon the luminal surface of the aorta generated by an LVAD. These numerical investigations demonstrate the utility of one-way-coupled FSI models to compare the haemodynamic conditions for the two LVAD outflow-grafts anastomosis locations and how both affect the aorta and its wall stress. Furthermore, the mechanical indicators allow the identification of wall regions at greater risk of atherosclerosis. The results of this study indicate that an LVAD outflow-graft anastomosis location in the ascending aorta is the optimal configuration.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.01.005
  • A new diagnostic IR-thermal imaging method for evaluation of cardiosurgery
    • Authors: Mariusz Kaczmarek
      Pages: 344 - 354
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Mariusz Kaczmarek
      Two methods for monitoring the state of the myocardium during cardiosurgical interventions based on thermal IR imaging are presented below. These methods, called static thermography and active dynamic thermography (ADT), use information about the distribution of temperature on the surface, and an external excitation source to induce thermal transient processes in a tested object. Recording the time series of thermograms allows calculating parametric images – the distribution of the thermal time constant on the visible surface of the myocardium – correlated with the physiological state of the tested tissues. The temperature allows monitoring of vascularization in each phase of cardiosurgical interventions. This is a perfect method for the evaluation of the quality of the inserted graft, as well as the efficiency of cardioplegia, and the quality of many surgical procedures in clinical practice. Such monitoring is prompt, easy and objective, especially if dynamic processes are investigated. During LAD occlusion, the ADT procedure was applied using a cooling external excitation source. In summary, the calculated time constant images provide data of the tested structure and functional information of myocardium infarct. This allows tracking changes in the blood flow in the myocardium and enables the inspection of the quality of the intervention during cardiosurgical procedures.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.01.007
  • A new baroreflex sensitivity index based on improved Hilbert–Huang
           transform for assessment of baroreflex in supine and standing postures
    • Authors: Amritpal Singh; Barjinder Singh Saini; Dilbag Singh
      Pages: 355 - 365
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Amritpal Singh, Barjinder Singh Saini, Dilbag Singh
      The aim of this study is to propose a new baroreflex sensitivity (BRS) index using improved Hilbert–Huang transform (HHT) using weighted coherence (CW) criterion and apply it to assess baroreflex in supine and standing postures. Improved HHT is obtained by addressing the mode mixing and end effect problems associated with empirical mode decomposition which is a required step in the computation of HHT and thus mitigating the unwanted low frequency component from the power spectrum. This study was first performed on synthetic signals generated using integral pulse frequency model and further extended to real RR interval and systolic blood pressure records of 50 healthy subjects, 20 post acute myocardial infarction patients undergoing postural stress from supine to standing position. Evaluation is also performed on standard EuroBaVar database, comprising of 21 subjects, under supine and standing positions. The results are (i) enhanced values of supine-to-standing low frequency BRS index (α-LF) equal to 1.78 and high frequency BRS index (α-HF) equal to 2.48 are obtained using improved HHT compared to standard HHT (α-LF=1.54, α-HF=2.36) and traditional power spectral density (α-LF=1.55, α-HF=2.34) for healthy subjects, (ii) there is an increased rate of change of LF/HF power ratios from supine to standing positions, and (iii) number of BRS responses obtained using CW criterion are greater than those obtained by using mean coherence criterion. In conclusion, the new BRS index takes into consideration the non-linear nature of interactions between heart rate variability and systolic blood pressure variability.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.01.006
  • A portable system for autoregulation and wireless control of sensorized
           left ventricular assist devices
    • Authors: Rossella Fontana; Giuseppe Tortora; M. Silvestri; M. Vatteroni; Paolo Dario; M.G. Trivella
      Pages: 366 - 374
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Rossella Fontana, Giuseppe Tortora, M. Silvestri, M. Vatteroni, Paolo Dario, M.G. Trivella
      End stage heart failure patients could benefit from left ventricular assist device (LVAD) implantation as bridge to heart transplantation or as destination therapy. However, LVAD suffers from several limitations, including the presence of a battery as power supply, the need for cabled connection from inside to outside the patient, and the lack of autonomous adaptation to the patient metabolic demand during daily activity. The authors, in this wide scenario, aim to contribute to advancement of the LVAD therapy by developing the hardware and the firmware of a portable autoregulation unit (ARU), able to fulfill the needs of sensorized VAD in terms of physic/physiological data storing, continuous monitoring, wireless control from the external environment and automatic adaptation to patient activities trough the implementation of autoregulation algorithms. Moreover, in order to answer the rules and safety requirements for implantable biomedical devices, a user control interface (UCI), was developed and associated to the ARU for an external manual safe control. The ARU and UCI functionalities and autoregulation algorithms have been successfully tested on bench and on animal, with a response time of 1s for activating autoregulation algorithms. Animal experiments showed as the presence of the ARU do not affect the animal cardiovascular system, giving a proof of concept of its applicability in vivo.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.02.001
  • Epileptic seizure detection based on improved wavelet neural networks in
           long-term intracranial EEG
    • Authors: Dongyun Geng; Weidong Zhou; Yanli Zhang; Shujuan Geng
      Pages: 375 - 384
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Dongyun Geng, Weidong Zhou, Yanli Zhang, Shujuan Geng
      Automatic seizure detection is of great importance for speeding up the inspection process and relieving the workload of medical staff in the analysis of EEG recordings. In this study, a method based on an improved wavelet neural network (WNN) is proposed for automatic seizure detection in long-term intracranial EEG. WNN combines the traditional back propagation neural network (BPNN) with wavelet transform. Compared with classic WNN architectures, a modified point symmetry-based fuzzy c-means (MSFCM) algorithm is applied to the initialization of wavelet transform's translations, which has been successful in multiclass cancer classification. In addition, Fast-decaying Morlet wavelet is chosen as the activation function to make the WNN learn faster. Relative amplitude and relative fluctuation index are extracted as a feature vector to describe the variation of EEG signals, and the feature vector is then fed into WNN for classification. At last, post-processing including smoothing, channel fusion and collar technique is adopted to achieve more accurate and stable results. This system performs efficiently with the average sensitivity of 96.72%, specificity of 98.91% and false-detection rate of 0.27h−1. The proposed approach achieves high sensitivity and low false detection rate, which demonstrates its potential for clinical usage.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.03.001
  • Three-dimensional finite element simulation of intrusion of the maxillary
           central incisor
    • Authors: Wojciech Ryniewicz; Anna M. Ryniewicz; Łukasz Bojko; Piotr Pełka; Jolanta Filipek; Stephen Williams; Bartłomiej W. Loster
      Pages: 385 - 390
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Wojciech Ryniewicz, Anna M. Ryniewicz, Łukasz Bojko, Piotr Pełka, Jolanta Filipek, Stephen Williams, Bartłomiej W. Loster
      Purpose The aim of this study is to generate a global digital model of treatment, analysis of stress distribution and displacements: in a construction of the bracket, in the incisor with bonded bracket, in tissues of the incisor, in a periodontal membrane and in an alveolus. Methods An orthodontic therapy was provided with a three-dimensional model of a unique Cannon Ultra bracket. The placement of the bracket to the incisor was provided according to clinical standards. Composite material was placed between the rough surface of the bracket's base and labial incisor surface – which, in a digital model, resulted in contact without displacement. The bracket was loaded. An orthodontic arch wire was free to move in a wing slot of the bracket. For simplification, a force vector was parallel to the longitudinal axis of the incisor. A clamper was set on the surface of the cortical bone of the alveolus. The model was divided into a finite number of tetrahedral elements. To calculate the distribution of stress Ansys Workbench software was used. Results The stress values indicate that there were no tissue overloaded areas. The stress distribution was regular in the periodontal ligament. Slight movements were observed with maximal values in the area of apex. Conclusions This study simulation proves that tissues surrounding the tooth were influenced mechanically by the force loaded on the bracket. According to the results of the study, the simulated treatment should be successful. The bracket transferred the load from the wire to the alveolar ridge.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.02.003
  • Gait patterns classification based on cluster and bicluster analysis
    • Authors: J. Pauk; K. Minta-Bielecka
      Pages: 391 - 396
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): J. Pauk, K. Minta-Bielecka
      Gait patterns of hemiplegia patients have many potential applications such as assistance in diagnosis or clinical decision-making. Many techniques were developed to classify gait patterns in past years; however, these methods have some limitations. The main goal of the study was to present the performance evaluation results of the new biclustering algorithm called KMB. The second objective was to compare clustering and biclustering methods. The study was performed based on the gait patterns of 41 hemiplegia patients over 12 months post-stroke, at the age of 48.6±19.6 years. Spatial–temporal gait parameters and joint moments were measured using motion capture system and force plates. Clustering and biclustering algorithms were applied for data consisting of joint moments of lower limbs. The obtained results of this study based on joint moments, clustering, and biclustering can be applied to evaluate patient condition and treatment effectiveness. We suggest that the biclustering algorithm compared to clustering algorithms better characterizes the specific traits and abnormalities of the joint moments, especially in case of hemiplegia patients.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.03.002
  • Altered modular organization in schizophrenia patients and analysis using
           supervised association rule mining
    • Authors: R. GeethaRamani; K. Sivaselvi
      Pages: 397 - 412
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): R. GeethaRamani, K. Sivaselvi
      Complex neuro-degenerative disorders affect the intrinsic topological architecture of brain connectivity. There are very few studies concentrating on the occurrence of modular changes in the structural and functional connectome of people diagnosed with Schizophrenia. In this study, group averaged analysis on modular organization of 15 healthy and 12 Schizophrenic subjects were performed to understand the topological alterations occurring in brain networks of diseased against normal. The major contributing regions for changes in optimal brain architecture were also identified. It also involves the investigation of individual subject's functional connectivity and the attempts were made to extract the modular specific roles of brain regions through supervised association rule mining. On comparison with group average measurements, it was found to produce similar results and it was understood that inter and intra-module connections evidently varied in Schizophrenia because of alterations in extremely organized modular architecture. This is believed to provide new insights in understanding the complex neuro-degenerative disorder through analysis on modular organization of functional brain networks. Highly influential regions were also determined. These regions were found to be potential biomarkers for Schizophrenia diagnosis.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.02.002
  • Segmentation of brain MR images using rough set based intuitionistic fuzzy
    • Authors: Yogita K. Dubey; Miind M. Mushrif; Kajal Mitra
      Pages: 413 - 426
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Yogita K. Dubey, Miind M. Mushrif, Kajal Mitra
      Intuitionistic fuzzy sets and rough sets are widely used for medical image segmentation, and recently combined together to deal with uncertainty and vagueness in medical images. In this paper, a rough set based intuitionistic fuzzy c-means (RIFCM) clustering algorithm is proposed for segmentation of the magnetic resonance (MR) brain images. Firstly, we proposed a new automated method to determine the initial values of cluster centroid using intuitionistic fuzzy roughness measure, obtained by considering intuitionistic fuzzy histon as upper approximation of rough set and fuzzy histogram as lower approximation of rough set. A new intuitionistic fuzzy complement function is proposed for intuitionistic fuzzy image representation to take into account intensity inhomogeneity and noise in brain MR images. The results of segmentation of proposed algorithm are compared with the existing rough set based fuzzy clustering algorithms, intuitionistic fuzzy clustering and bias corrected fuzzy clustering algorithm. Experimental results demonstrate the superiority of proposed algorithm.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.01.001
  • Classification of auditory brainstem response using wavelet decomposition
           and SVM network
    • Authors: Andrzej Dobrowolski; Michał Suchocki; Kazimierz Tomczykiewicz; Ewelina Majda-Zdancewicz
      Pages: 427 - 436
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Andrzej Dobrowolski, Michał Suchocki, Kazimierz Tomczykiewicz, Ewelina Majda-Zdancewicz
      In electrophysiological hearing assessment and diagnosis of brain stem lesions are most often used auditory brainstem evoked potentials of short latency. They are characterized by successively arranged maxima as a function of time, called waves. Morphology of the course, in particular, the timing and amplitude of each wave, allow neurologist diagnosis, which is not an easy task. Neurologist requires experience, attention and very good perception. In order to support the diagnostic process, the authors have developed an algorithm implementing the automated classification of auditory evoked potentials to the group of pathological and physiological cases. The sensitivity and specificity of group numbering of 130 cases are respectively 95% and 98% and classification accuracy is equal to 97%. The procedures developed by the authors for generation of distinctive features based on wavelet decomposition with a SVM network-based classifier have been integrated into a diagnostic application directly interoperable with Nicolet Viking Select (Natus Medical Inc., USA) system data files.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.01.003
  • Knee bone segmentation from MRI: A classification and literature review
    • Authors: Andrea Aprovitola; Luigi Gallo
      Pages: 437 - 449
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 2
      Author(s): Andrea Aprovitola, Luigi Gallo
      Segmentation of cartilage from Magnetic Resonance (MR) images has evolved as a tool for the diagnosis of knee joint pathologies. However, accuracy and reproducibility of automated methods of cartilage segmentation may require the prior extraction of bone surfaces from MR imaging sequences specifically designed to evidence the cartilage and not the bone. Thus a priori knowledge of knee joint structures and fully automated segmentation methods are adopted to provide reliable detection of bone surfaces. In this paper, we review knee bone segmentation methods from MR images. We classified the methods proposed in literature according to the level of a priori knowledge, the level of automation and the level of manual user interaction. Furthermore we discuss the segmentation results in literature in relation to the MR sequences used to image the bone.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2015.12.007
  • Treatment of patients with type 1 diabetes – Insulin pumps or
           multiple injections'
    • Authors: Janusz Krzymien; Monika Rachuta; Iwona Kozlowska; Piotr Ladyzynski; Piotr Foltynski
      Pages: 1 - 8
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 1
      Author(s): Janusz Krzymien, Monika Rachuta, Iwona Kozlowska, Piotr Ladyzynski, Piotr Foltynski
      In theory, the continuous subcutaneous insulin infusion (CSII) has a few advantages over the multiple daily insulin injections (MDI) that should lead to improved glycemic control and lower risk of hypoglycemia. In practice, both treatment regimens allow for adequate control of glycemia. The objective of this review is to discuss the most important factors contributing to this situation. We made a comprehensive evidence-based review of the factors affecting effectiveness of CSII and MDI, with a special attention to algorithms for insulin dose adjustments and the automatic bolus calculators. Regardless of the treatment regimen that is used a few different interdependent factors influence the final result of the intensive insulin therapy. These factors comprise: patients’ education, attitude, emotional stability and compliance, and careful analysis of the treatment results by a physician establishing the appropriate rate of basal insulin infusion or the basal dose of insulin and adjusting insulin doses to: the meals, the planned physical activity and the actual and target glucose levels. Our study implies that good glycemic control in patients with type 1 diabetes requires not only a thorough patient education and complying with medical recommendations, but also an individual determination of therapy goals and ways of achieving them. That is why, regardless of the treatment method that is applied, it is the choice of appropriate algorithms and adjusting them to the patient's way of life what allow for achieving pre-specified therapeutic goals. Technical means such as automatic bolus calculators might supplement but they cannot replace patients education and compliance.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2015.10.002
  • Effects of various typical electrodes and electrode gels combinations on
           MRI signal-to-noise ratio and safety issues in EEG-fMRI recording
    • Authors: Dongrui Gao; Mingzhe Li; Jianfu Li; Zhixuan Liu; Dezhong Yao; Guangli Li; Tiejun Liu
      Pages: 9 - 18
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 1
      Author(s): Dongrui Gao, Mingzhe Li, Jianfu Li, Zhixuan Liu, Dezhong Yao, Guangli Li, Tiejun Liu
      To compare the effects of typical Ag/AgCl electrodes and electrode gels on MR images and assess safety hazards for patients during the electroencephalogram (EEG) data simultaneously with functional MRI (fMRI) recordings. So the measurements were conducted to compare the effects of three electrodes, three electrode gels and their combinations on the signal-to-noise ratio (SNR) of MR images at 3T. Local temperature variation of the phantom for all conditions was also measured in the scanner. Results show that combination of silver-plated copper electrode and electrode gel (composed of carbomer as its main ingredient, with 85% moisture) is best for EEG-fMRI experiments. A sintered Ag/AgCl electrode could also be used as the material of EEG cap if infra-slow EEG-events need to be acquired in EEG-fMRI recording. Additionally, there is no significant heat induction detected. Overall, the methods and results of this study can be used for selecting appropriate EEG electrodes and electrode gels in EEG-fMRI experiments.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2015.11.007
  • On ultrasound classification of stroke risk factors from randomly chosen
           respondents using non-invasive multispectral ultrasonic brain measurements
           and adaptive profiles
    • Authors: Miroslaw Wrobel; Andrzej Dabrowski; Adam Kolany; Anna Olak-Popko; Robert Olszewski; Pawel Karlowicz
      Pages: 19 - 28
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 1
      Author(s): Miroslaw Wrobel, Andrzej Dabrowski, Adam Kolany, Anna Olak-Popko, Robert Olszewski, Pawel Karlowicz
      In this paper, we present a new brain diagnostic method based on a computer aided multispectral ultrasound diagnostics method (CAMUD). We explored the standard values of the relative time of flight (RIT), as well as the attenuation, ATN, of multispectral longitudinal ultrasound waves propagated non-invasively through the brains of a standard Caucasian volunteer population across different ages and genders. For the interpretation of the volunteers health questionnaire and ultrasound data we explored various clustering and classification algorithms, such as PCA and ANOVA. We showed that the RIT and ATN values provide very good estimators of possible physiological changes in the brain tissue and can differentiate the possible high-risk groups obtained by other groups and methods (Russo et al. [1]; Lloyd-Jones et al. [2]; Medscape [3]). Special attention should be given to the subgroup which included almost 39% of the volunteers. Respondents in this group have a significantly increased minimum ATN value (see Classification Trees). These values are strongly correlated with the identified risk of stroke factors being: age, increased alcohol consumption, cases of heart disease and stroke in the family as already shown by Rusco and as incorporated into Lloyd-Jones et al., “Heart Disease and Stroke Statistics – 2009 Update”, by the American Heart Association (AHA) and American Stroke Association (ASA), as updated recently in the 2015 “Stroke Prevention Guidelines”.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2015.10.004
  • Immunosensors for human cardiac troponins and CRP, in particular
           amperometric cTnI immunosensor
    • Authors: B. Kazimierczak; D.G. Pijanowska; A. Baraniecka; M. Dawgul; J. Kruk; W. Torbicz
      Pages: 29 - 41
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 1
      Author(s): B. Kazimierczak, D.G. Pijanowska, A. Baraniecka, M. Dawgul, J. Kruk, W. Torbicz
      In this paper, the review of immunosensors for selected cardiovascular disease markers: human cardiac troponins and human C-reactive protein (CRP) is presented. In particular, (cTnI) amperometric immunosensor for cTnI measurements in the concentration range useful in medical diagnostics, based on the developed earlier human CRP amperometric immunosensor, is described. The human cTnI is recommended as one of specific myocardial damage biomarkers, and is considered as the “gold standard”, whereas the human CRP is used as the powerful, nonspecific, supplementary biomarker of cardiovascular disease. Carbon, graphite and platinum pastes, used for fabrication of our immunosensor working electrode (WE), were investigated. In the developed simple measuring procedure, based on a direct solid phase enzyme-linked immunosorbent assay (ELISA), for the first time ascorbic acid monophosphate was used for cTnI detection as a substrate in enzymatic reaction of alkaline phosphatase labelling antibodies. Disposable amperometric graphite immunosensors, made on polyester film by means of microdispensing robot, suitable for determination of cTnI in the concentration range 0–35μg/L with the sensitivity 0.67μA/(μg/L) and linear correlation coefficient 0.91 were obtained.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2015.11.008
  • Computer aided diagnosis system for abdomen diseases in computed
           tomography images
    • Authors: Gaurav Sethi; Barjinder S. Saini
      Pages: 42 - 55
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 1
      Author(s): Gaurav Sethi, Barjinder S. Saini
      In this paper, a computer aided diagnostic (CAD) system for classification of abdomen diseases from computed tomography (CT) images is presented. The methodology used in this paper is to select the most appropriate machine learning technique of segmentation, feature extraction and classification for each module of proposed CAD. The methodology of selecting appropriate machine learning technique for each module of CAD results in accurate and efficient system. Regions of interest are segmented from CT images of tumor, cyst, calculi and normal liver using active contour models, region growing and thresholding. The CAD presented in this research work exploits the discriminating power of features for classifying abdominal diseases. Therefore, feature extraction module extracts statistical texture descriptors using three kinds of feature extraction methods i.e. Gray-Level co-occurrence matrices (GLCM), Discrete Wavelet Transform (DWT) and Discrete Curvelet Transform (DCT). At the next stage, effective and optimum features of ROIs are selected using Genetic Algorithm (GA). Further, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are used to assess the capability of features for classification of diseases of abdomen. The study is performed on 120 CT images of abdomen (30 normal, 30 tumor, 30 cyst and 30 calculi). It is observed from the results that proposed CAD consists of edge based active contour model combined with optimized statistical texture descriptors using DCT along with ANN as classifier achieves the best diagnostic performance of 95.1%. It is also shown in results that proposed CAD achieves highest sensitivity, specificity of 95% and 98% respectively.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2015.10.008
  • Classification of abnormalities in mammograms by new asymmetric fractal
    • Authors: S.M.A. Beheshti; H. Ahmadi Noubari; E. Fatemizadeh; M. Khalili
      Pages: 56 - 65
      Abstract: Publication date: 2016
      Source:Biocybernetics and Biomedical Engineering, Volume 36, Issue 1
      Author(s): S.M.A. Beheshti, H. Ahmadi Noubari, E. Fatemizadeh, M. Khalili
      In this paper we use fractal method for detection and diagnosis of abnormalities in mammograms. We have used 168 images that were carefully selected by a radiologist and their abnormalities were also confirmed by biopsy. These images included asymmetric lesions, architectural distortion, normal tissue and mass lesion where in case of mass lesion they included circumscribed benign, ill-defined and spiculated malignant masses. At first, by using wavelet transform and piecewise linear coefficient mapping, image enhancement were done. Secondly detection of lesions was done by fractal method as a ROI. Since in investigation of breast cancer, it is important that fibroglandular tissues in both breasts be symmetric and for each asymmetric density, evaluation for malignancy is necessary, we define new fractal features based on extracting asymmetric information from lesions. The fractal features were evaluated on 5 data sets using SVM classifier which enabled to achieve high accuracy in classification of mammograms and diagnostic results. We have also investigated the performance of image enhancement in classification of each data set which shows different effects of enhancement on different lesion types.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2015.07.002
  • Detection of hard exudates using mean shift and normalized cut method
    • Authors: Sreeparna Banerjee; Diptoneel Kayal
      Abstract: Publication date: Available online 18 October 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Sreeparna Banerjee, Diptoneel Kayal
      As diabetic retinopathy (DR) is one of the main causes of loss of vision among diabetic patients, an early detection using automated detection techniques can prevent blindness among diabetic patients. Hard exudates constitute one of the early symptoms of DR and this paper describes a method for its detection using fundus images of retina, employing a combination of morphological operations, mean shift (MS), normalized cut (NC) and Canny's operation. This combined technique avoids over segmentation and at the same time reduces the time complexity while clearly delineating the exudates. Output of the proposed method is evaluated using public databases and produces sensitivity, specificity and accuracy as 98.80%, 98.25% and 98.65%, respectively. The ROC curve gives 0.984 as area under curve. The sensitivity, specificity, accuracy and area under curve of ROC indicate the effectiveness of the method.

      PubDate: 2016-11-05T03:37:59Z
      DOI: 10.1016/j.bbe.2016.07.001
  • Customized porous implants by additive manufacturing for zygomatic
    • Authors: Khaja Moiduddin; Abdulrahman Al-Ahmari; Mohammed Al Kindi; Emad S. Abouel Nasr; Ashfaq Mohammad; Sundar Ramalingam
      Abstract: Publication date: Available online 19 October 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Khaja Moiduddin, Abdulrahman Al-Ahmari, Mohammed Al Kindi, Emad S. Abouel Nasr, Mohammed Ashfaq, Sundar Ramalingam
      Background Moderate to severe facial esthetic problems challenge the surgeons to discover alternate ways, to rehabilitate the patients using customized porous designs. Porous metal implants are available for over 30 years, but the pore architecture, is constantly changing to improve the stability and longevity of the implant. Objective To evaluate a customized porous implant produced from electron beam melting and to restore the zygomatic functionality. Methods Two customized zygomatic reconstruction implants-bulk and porous, are designed based on the bone contours and manufactured using state of art-electron beam melting technology. The two designed implants are evaluated based on strength, weight and porosity for the better osseointegration and rehabilitation of the patient. Results Porous structures due to their light weight, low volume and high surface area provided better specific strength and young's modulus closer to the bone. Microscopic and CT scanning confirmed that the EBM produced porous structures are highly regular and interconnected without any major internal defects. Conclusions The customized porous implants satisfies the need of lighter implants with an adequate mechanical strength, restoring better functionality and esthetic outcomes for the patients.

      PubDate: 2016-11-05T03:37:59Z
      DOI: 10.1016/j.bbe.2016.07.005
  • Automatic epilepsy detection using wavelet-based nonlinear analysis and
           optimized SVM
    • Authors: Mingyang Li; Wanzhong Chen; Tao Zhang
      Abstract: Publication date: Available online 21 October 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Mingyang Li, Wanzhong Chen, Tao Zhang
      Aiming at the problems of low accuracy, poor universality and functional singleness for seizure detection, an effective approach using wavelet-based non-linear analysis and genetic algorithm optimized support vector machine (GA-SVM) is proposed to deal with five challenging classification problems in this study. Instead of the traditional discrete wavelet transform (DWT), we attempt to explore the ability of double-density discrete wavelet transform (DD-DWT) to decompose the original EEG into specific sub-bands. The Hurst exponent (HE) and fuzzy entropy (FuzzyEn) are extracted as input features and then fed into two classifiers. On using these ranking non-linear features, the GA-SVM configured with fewer features is found to achieve the prominent classification performance for various combinations such as AB-CD-E, A-D-E, ABCD-E, C-E and D-E, achieving accuracies of 99.36%, 99.60%, 99.40%, 100% and 100%, respectively. The results have indicated that our scheme is not only appropriate in solving problems with multiple classes but also of lower complexity and better expansibility. These characteristics would make this method become an attractive alternative for actual clinical diagnosis.

      PubDate: 2016-11-05T03:37:59Z
      DOI: 10.1016/j.bbe.2016.07.004
  • Feature projection k-NN classifier model for imbalanced and incomplete
           medical data
    • Authors: Piotr Porwik; Tomasz Orczyk; Marcin Lewandowski; Marcin Cholewa
      Abstract: Publication date: Available online 2 November 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Piotr Porwik, Tomasz Orczyk, Marcin Lewandowski, Marcin Cholewa
      Many datasets, especially various historical medical data are incomplete. Various qualities of data can significantly hamper medical diagnosis and are bottlenecks of medical support systems. Nowadays, such systems are often used in medical diagnosis. Even great number of data can be unsuitable when data is imbalanced, missing or corrupted. In some cases these troubles can be overcome by machine learning algorithms designed for predictive modeling. Proposed approach was tested on real medical data and some benchmarks dataset form UCI repository. The liver fibrosis disease from a medical point of view is difficult to treatment and has a significant social and economic impact. Stages of liver fibrosis are diagnosed by clinical observation and evaluations, coupled with a so-called METAVIR rating scale. However, these methods may be insufficient, especially in the recognition of phase of the disease. This paper describes a newly developed algorithm to non-invasive fibrosis stage recognition using machine learning methods – a classification model based on feature projection k-NN classifier. This solution allows extracting data characteristics from the historical data which may be incomplete and may contain imbalance (unequal) sets of patients. Proposed novel solution is based on peripheral blood analysis without using any specialized biomarkers, and can be successfully included to medical diagnosis support systems and might be a powerful tool for effective estimation of liver fibrosis stages.

      PubDate: 2016-11-05T03:37:59Z
      DOI: 10.1016/j.bbe.2016.08.002
  • Development of a fuzzy-driven system for ovarian tumor diagnosis
    • Authors: Patryk Żywica; Krzysztof Dyczkowski; Andrzej Wójtowicz; Anna Stachowiak; Sebastian Szubert; Rafał Moszyński
      Abstract: Publication date: Available online 2 October 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Patryk Żywica, Krzysztof Dyczkowski, Andrzej Wójtowicz, Anna Stachowiak, Sebastian Szubert, Rafał Moszyński
      In this paper we present OvaExpert, an intelligent system for ovarian tumor diagnosis. We give an overview of its features and main design assumptions. As a theoretical framework the system uses fuzzy set theory and other soft computing techniques. This makes it possible to handle uncertainty and incompleteness of the data, which is a unique feature of the developed system. The main advantage of OvaExpert is its modular architecture which allows seamless extension of system capabilities. Three diagnostic modules are described, along with examples. The first module is based on aggregation of existing prognostic models for ovarian tumor. The second presents the novel concept of an Interval-Valued Fuzzy Classifier which is able to operate under data incompleteness and uncertainty. The third approach draws from cardinality theory of fuzzy sets and IVFSs and leads to a bipolar result that supports or rejects certain diagnoses.

      PubDate: 2016-10-08T09:24:31Z
      DOI: 10.1016/j.bbe.2016.08.003
  • Early stage of chronic kidney disease by using statistical evaluation of
           the previous measurement results
    • Authors: Selahaddin Batuhan Akben
      Abstract: Publication date: Available online 4 October 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Selahaddin Batuhan Akben
      Chronic kidney disease (CKD) that causes the progressive losses in kidney functions is one of the major public health problems. Expert medical doctors can diagnose the CKD through symptoms, blood and urine tests in its early stages. However, the diagnosis of CKD might be difficult for expert medical doctors in case of the questionable measurement result. Therefore a new mathematical method that would be helpful to the expert medical doctors is required. It can be said that there is no studies related with automatic diagnosis of CKD in the literature. This study aims to remedy this shortcoming in the literature. In this study, for each of test and symptom values, averages of measurement results were calculated separately for healthy subjects and patients. Then the measured values were marked as “0” or “1” (healthy or patient) according to closeness to average values. Finally, the classification was performed by averaging the values marked for each subject. The success rate of the proposed method is between 96% and 98% according to the age ranges. In conclusion section of the study, how to implement the proposed method in real life is offered.

      PubDate: 2016-10-08T09:24:31Z
      DOI: 10.1016/j.bbe.2016.08.004
  • Automated detection of uterine contractions in tocography signals –
           Comparison of algorithms
    • Authors: Krzysztof Horoba; Janusz Wrobel; Janusz Jezewski; Tomasz Kupka; Dawid Roj; Michal Jezewski
      Abstract: Publication date: Available online 4 October 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Krzysztof Horoba, Janusz Wrobel, Janusz Jezewski, Tomasz Kupka, Dawid Roj, Michal Jezewski
      Monitoring of uterine contractile activity enables to control the progress of labor. Automated detection of contractions is an integral part of the signal analysis implemented in computer-aided fetal surveillance system. Comparison of four algorithms for automated detection of uterine contractions in the signal of uterine mechanical activity is presented. Three algorithms are based generally on analysis of the frequency distribution of signal values. The fourth method relies on analyzing the rate of changes of the uterine activity signal. The reference data in form of beginning and end of contraction episodes were provided by human experts. Obtained results show that all algorithms were capable to detect above 91% reference contractions, and less than 7% of recognized patterns were false. Two algorithms can be distinguished as providing a higher performance expressed by the sensitivity of 95% and the positive predictive value of 97%. Such results could be obtained by optimization of contraction validation criteria.

      PubDate: 2016-10-08T09:24:31Z
      DOI: 10.1016/j.bbe.2016.08.005
  • Multiclassifier systems applied to the computer-aided sequential medical
    • Authors: Marek Kurzyński; Marcin Majak; Andrzej Żołnierek
      Abstract: Publication date: Available online 4 October 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Marek Kurzyński, Marcin Majak, Andrzej Żołnierek
      The diagnosis of patient's state based on results of successive examinations is common task in the medicine. In computer-aided algorithms taking into account the patient's history in order to improve the quality of classification seems to be very reasonable solution. In this study, two original multiclassifier systems (MC) for the computer-aided sequential diagnosis are developed, which differ with decision scheme and the methods of combining of base classifiers. The first MC system is based on dynamic ensemble selection scheme and works in two-level structure. The second MC system in combining procedure uses original concept of meta-Bayes classifier and produces decision according to the Bayes rule. Both MC systems were practically applied to the diagnosis of human acid–base equilibrium states and compared with some state-of-the-art sequential diagnosis methods. Results obtained in experimental investigations imply that MC system is effective approach, which improves recognition accuracy in sequential diagnosis scheme.

      PubDate: 2016-10-08T09:24:31Z
      DOI: 10.1016/j.bbe.2016.08.001
  • Analysis of the parameters of respiration patterns extracted from thermal
           image sequences
    • Authors: Jacek
      Abstract: Publication date: Available online 20 August 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Jacek Rumiński
      Remote estimation of vital signs is an important and active area of research. The goal of this work was to analyze the feasibility of estimating respiration parameters from video sequences of faces recorded using a mobile thermal camera. Different estimators were analyzed and experimentally verified. It was demonstrated that the respiration rate, periodicity of respiration, and presence and length of apnea periods could be reliably estimated from signals recorded using a portable thermal camera. The size of the camera and efficiency of the methods allow the implementation of this method in smart glasses.

      PubDate: 2016-08-21T13:17:21Z
  • An attempt to localize brain electrical activity sources using EEG with
           limited number of electrodes
    • Authors: Andrzej Majkowski; Łukasz Oskwarek; Marcin Kołodziej; Remigiusz J. Rak
      Abstract: Publication date: Available online 29 July 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Andrzej Majkowski, Łukasz Oskwarek, Marcin Kołodziej, Remigiusz J. Rak
      A very interesting research goal is to find underlying sources generating the EEG signal – referred to as the “EEG inverse problem”. Its aim is to determine spatial distribution of brain activity, described by local brain currents density, on the basis of potentials measured on the scalp as EEG signal. The purpose of the research presented in the article was to check whether the results of the inverse problem solution, obtained by the LORETA algorithm for the reduced set of 8 electrodes selected by the authors will be close to the results for the initial set of 32 electrodes. EEG signals were registered during the BCI operation based on ERD/ERS potentials. Obtained results showed no significant differences in the location of the most important sources in both cases. It is worth emphasizing that reducing the number of electrodes would have a significant impact on an BCI ergonomics.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.07.002
  • Hierarchical classification of normal, fatty and heterogeneous liver
           diseases from ultrasound images using serial and parallel feature fusion
    • Authors: Alaleh Alivar; Habibollah Danyali; Mohammad Sadegh Helfroush
      Abstract: Publication date: Available online 28 July 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Alaleh Alivar, Habibollah Danyali, Mohammad Sadegh Helfroush
      This study presents a computer-aided diagnostic system for hierarchical classification of normal, fatty, and heterogeneous liver ultrasound images using feature fusion techniques. Both spatial and transform domain based features are used in the classification, since they have positive effects on the classification accuracy. After extracting gray level co-occurrence matrix and completed local binary pattern features as spatial domain features and a number of statistical features of 2-D wavelet packet transform sub-images and 2-D Gabor filter banks transformed images as transform domain features, particle swarm optimization algorithm is used to select dominant features of the parallel and serial fused feature spaces. Classification is performed in two steps: First, focal livers are classified from the diffused ones and second, normal livers are distinguished from the fatty ones. For the used database, the maximum classification accuracy of 100% and 98.86% is achieved by serial and parallel feature fusion modes, respectively, using leave-one-out cross validation (LOOCV) method and support vector machine (SVM) classifier.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.07.003
  • Automated object and image level classification of TB images using support
           vector neural network classifier
    • Authors: Ebenezer Priya; Subramanian Srinivasan
      Abstract: Publication date: Available online 9 July 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): Ebenezer Priya, Subramanian Srinivasan
      In this work, digital Tuberculosis (TB) images have been considered for object and image level classification using Multi Layer Perceptron (MLP) neural network activated by Support Vector Machine (SVM) learning algorithm. The sputum smear images are recorded under standard image acquisition protocol. The TB objects which include bacilli and outliers in the considered images are segmented using active contour method. The boundary of the segmented objects is described by fifteen Fourier Descriptors (FDs). The prominent FDs are selected using fuzzy entropy measures. These selected FDs of the TB objects are fed as input to the SVM learning algorithm of the MLP Neural Network (SVNN) and the result is compared with the state-of-the-art approach, Back Propagation Neural Network (BPNN). Results show that the segmentation method identifies the bacilli which retain their shape in-spite of artifacts present in the images. The methodology adopted has significantly enhanced the SVNN accuracy to 91.3% for object and 92.5% for image level classification than BPNN.

      PubDate: 2016-08-16T12:47:25Z
      DOI: 10.1016/j.bbe.2016.06.008
  • Multi-step process in computer assisted diagnosis of posterior cruciate
    • Authors: Zarychta
      Abstract: Publication date: Available online 30 June 2016
      Source:Biocybernetics and Biomedical Engineering
      Author(s): P. Zarychta
      A multi-step methodology resulting in a three-dimensional visualization and construction of feature vector of posterior cruciate ligament is presented. In the first step the location of the posterior cruciate ligament is established using the fuzzy image concept. The fuzzy image concept is based on the entropy measure of fuzziness extended to two dimensions. In order to reduce the area of analysis, the region of interest including the ligament structures is detected. In this case, the fuzzy C-means algorithm with median modification helping to reduce blurred edges was implemented. After finding the region of interest, the fuzzy connectedness procedure was performed. This procedure permitted to extract the ligament structures. On the basis of the extracted posterior cruciate ligament structures, the three-dimensional visualization of this ligament was built and, with the support of experts’ knowledge, an appropriate feature vector was constructed and its values assigned for normal and pathological cases. Correct results were obtained for over 88% of 97 cases.

      PubDate: 2016-08-16T12:47:25Z
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-2016