Subjects -> ENGINEERING (Total: 2844 journals)     - CHEMICAL ENGINEERING (259 journals)    - CIVIL ENGINEERING (255 journals)    - ELECTRICAL ENGINEERING (182 journals)    - ENGINEERING (1420 journals)    - ENGINEERING MECHANICS AND MATERIALS (454 journals)    - HYDRAULIC ENGINEERING (60 journals)    - INDUSTRIAL ENGINEERING (101 journals)    - MECHANICAL ENGINEERING (113 journals) ENGINEERING (1420 journals)                  1 2 3 4 5 6 7 8 | Last
Similar Journals
 Australasian Physical & Engineering Sciences in MedicineJournal Prestige (SJR): 0.336 Citation Impact (citeScore): 1Number of Followers: 1      Hybrid journal (It can contain Open Access articles) ISSN (Print) 0158-9938 - ISSN (Online) 1879-5447 Published by Springer-Verlag  [2658 journals]
• Estimating subjective evaluation of low-contrast resolution using
convolutional neural networks

Abstract: Abstract To develop a convolutional neural network-based method for the subjective evaluation of computed tomography (CT) images having low-contrast resolution due to imaging conditions and nonlinear image processing. Four radiological technologists visually evaluated CT images that were reconstructed using three nonlinear noise reduction processes (AIDR 3D, AIDR 3D Enhanced, AiCE) on a CT system manufactured by CANON. The visual evaluation consisted of two items: low contrast detectability (score: 0–9) and texture pattern (score: 1–5). Four AI models with different convolutional and max pooling layers were constructed and trained on pairs of CANON CT images and average visual assessment scores of four radiological technologists. CANON CT images not used for training were used to evaluate prediction performance. In addition, CT images scanned with a SIEMENS CT system were input to each AI model for external validation. The mean absolute error and correlation coefficients were used as evaluation metrics. Our proposed AI model can evaluate low-contrast detectability and texture patterns with high accuracy, which varies with the dose administered and the nonlinear noise reduction process. The proposed AI model is also expected to be suitable for upcoming reconstruction algorithms that will be released in the future.
PubDate: 2021-10-11

• Comparison of non-coplanar optimization of static beams and arc
trajectories for intensity-modulated treatments of meningioma cases

Abstract: Abstract Two methods for non-coplanar beam direction optimization, one for static beams and another for arc trajectories, were proposed for intracranial tumours. The results of the beam angle optimizations were compared with the beam directions used in the clinical plans. Ten meningioma cases already treated were selected for this retrospective planning study. Algorithms for non-coplanar beam angle optimization (BAO) and arc trajectory optimization (ATO) were used to generate the corresponding plans. A plan quality score, calculated by a graphical method for plan assessment and comparison, was used to guide the beam angle optimization process. For each patient, the clinical plans (CLIN), created with the static beam orientations used for treatment, and coplanar VMAT approximated plans (VMAT) were also generated. To make fair plan comparisons, all plan optimizations were performed in an automated multicriteria calculation engine and the dosimetric plan quality was assessed. BAO and ATO plans presented, on average, moderate global plan score improvements over VMAT and CLIN plans. Nevertheless, while BAO and CLIN plans assured a more efficient OARs sparing, the ATO and VMAT plans presented a higher coverage and conformity of the PTV. Globally, all plans presented high-quality dose distributions. No statistically significant quality differences were found, on average, between BAO, ATO and CLIN plans. However, automated plan solution optimizations (BAO or ATO) may improve plan generation efficiency and standardization. In some individual patients, plan quality improvements were achieved with ATO plans, demonstrating the possible benefits of this automated optimized delivery technique.
PubDate: 2021-10-07

• AI-based diagnosis of COVID-19 patients using X-ray scans with stochastic
ensemble of CNNs

Abstract: Abstract According to the World Health Organization (WHO), novel coronavirus (COVID-19) is an infectious disease and has a significant social and economic impact. The main challenge in fighting against this disease is its scale. Due to the outbreak, medical facilities are under pressure due to case numbers. A quick diagnosis system is required to address these challenges. To this end, a stochastic deep learning model is proposed. The main idea is to constrain the deep-representations over a Gaussian prior to reinforce the discriminability in feature space. The model can work on chest X-ray or CT-scan images. It provides a fast diagnosis of COVID-19 and can scale seamlessly. The work presents a comprehensive evaluation of previously proposed approaches for X-ray based disease diagnosis. The approach works by learning a latent space over X-ray image distribution from the ensemble of state-of-the-art convolutional-nets, and then linearly regressing the predictions from an ensemble of classifiers which take the latent vector as input. We experimented with publicly available datasets having three classes: COVID-19, normal and pneumonia yielding an overall accuracy and AUC of 0.91 and 0.97, respectively. Moreover, for robust evaluation, experiments were performed on a large chest X-ray dataset to classify among Atelectasis, Effusion, Infiltration, Nodule, and Pneumonia classes. The results demonstrate that the proposed model has better understanding of the X-ray images which make the network more generic to be later used with other domains of medical image analysis.
PubDate: 2021-10-05

• Effect of foam insertion in aneurysm sac on flow structures in parent
lumen: relating vortex structures with disturbed shear

Abstract: Abstract Numerous studies suggest that disturbed shear, causing endothelium dysfunction, can be related to neighboring vortex structures. With this motivation, this study presents a methodology to characterize the vortex structures. Precisely, we use mapping and characterization of vortex structures' changes to relate it with the hemodynamic indicators of disturbed shear. Topological features of vortex core lines (VCLs) are used to quantify the changes in vortex structures. We use the Sujudi-Haimes algorithm to extract the VCLs from the flow simulation results. The idea of relating vortex structures with disturbed shear is demonstrated for cerebral arteries with aneurysms virtually treated by inserting foam in the sac. To get physiologically realistic flow fields, we simulate blood flow in two patient-specific geometries before and after foam insertion, with realistic velocity waveform imposed at the inlet, using the Carreau-Yasuda model to mimic the shear-thinning behavior. With homogenous porous medium assumption, flow through the foam is modeled using the Forchheimer-Brinkman extended Darcy model. Results show that foam insertion increases the number of VCLs in the parent lumen. The average length of VCL increases by 168.9% and 55.6% in both geometries. For both geometries under consideration, results demonstrate that the region with increased disturbed shear lies in the same arterial segment exhibiting an increase in the number of oblique VCLs. Based on the findings, we conjecture that an increase in oblique VCLs is related to increased disturbed shear at the neighboring portion of the arterial wall.
PubDate: 2021-09-28

• A deep neural network approach for P300 detection-based BCI using
single-channel EEG scalogram images

Abstract: Abstract Brain–computer interfaces (BCIs) acquire electroencephalogram (EEG) signals and interpret them into a command that helps people with severe motor disabilities using single channel. The goal of BCI is to achieve a prototype that supports disabled people to develop the relevant function. Various studies have been implemented in the literature to achieve a superior design using multi-channel EEG signals. This paper proposed a novel framework for the automatic P300 detection-based BCI model using a single EEG electrode. In the present study, we introduced a denoising approach using the bandpass filter technique followed by the transformation of scalogram images using continuous wavelet transform. The derived images were trained and validated using a deep neural network based on the transfer learning approach. This paper presents a BCI model based on the deep network that delivers higher performance in terms of classification accuracy and bitrate for disabled subjects using a single-channel EEG signal. The proposed P300 based BCI model has the highest average information transfer rates of 13.23 to 26.48 bits/min for disabled subjects. The classification performance has shown that the deep network based on the transfer learning approach can offer comparable performance with other state-of-the-art-method.
PubDate: 2021-09-22

• Dosimetric characteristics of a thin bolus made of variable shape

Abstract: Abstract In this study, we aim to clarify the dosimetric characteristics of a real time variable shape rubber containing tungsten (STR) as a thin bolus in 6-MV photon radiotherapy. The percentage depth doses (PDDs) and lateral dose profiles (irradiation field = 10 × 10  cm2) in the water-equivalent phantom were measured and compared between no bolus, a commercial 5-mm gel bolus, and 0.5-, 1-, 2-, and 3-mm STR boluses. The characteristics of the PDDs were evaluated according to relative doses at 1 mm depth (D1mm) and depth of maximum dose (dmax). To determine the distance of the shift caused by the STR bolus, the PDD value at a depth of 100 mm without a bolus was obtained. For each STR thickness, the difference between the depth corresponding to this PDD value and 100 mm was calculated. The penumbra size and width of the 50% dose were evaluated using lateral dose profiles. The D1mm with no bolus, 5-mm gel bolus, and 0.5-, 1-, 2-, and 3-mm STR boluses were 47.6%, 91.5%, 78.2%, 86.6%, 89.3%, and 89.4%, respectively, and the respective dmax values were 15, 10, 13, 12, 11, and 10 mm. The shifting distance of the 0.5-, 1-, 2-, and 3-mm STR boluses were 2.7, 4.4, 4.8, and 4.9 mm, respectively. There were no differences for those in lateral dose profiles. The 1-mm-thick STR thin bolus shifted the depth dose profile by 4.4 mm and could be used as a customized bolus for photon radiotherapy.
PubDate: 2021-09-20

• Determining tolerance levels for quality assurance of 3D printed bolus for
modulated arc radiotherapy of the nose

Abstract: Abstract Given the existing literature on the subject, there is obviously a need for specific advice on quality assurance (QA) tolerances for departments using or implementing 3D printed bolus for radiotherapy treatments. With a view to providing initial suggested QA tolerances for 3D printed bolus, this study evaluated the dosimetric effects of changes in bolus geometry and density, for a particularly common and challenging clinical situation: specifically, volumetric modulated arc therapy (VMAT) treatment of the nose. Film-based dose verification measurements demonstrated that both the AAA and the AXB algorithms used by the Varian Eclipse treatment planning system (Varian Medical Systems, Palo Alto, USA) were capable of providing sufficiently accurate dose calculations to allow this planning system to be used to evaluate the effects of bolus errors on dose distributions from VMAT treatments of the nose. Thereafter, the AAA and AXB algorithms were used to calculate the dosimetric effects of applying a range of simulated errors to the design of a virtual bolus, to identify QA tolerances that could be used to avoid clinically significant effects from common printing errors. Results were generally consistent, whether the treatment target was superficial and treated with counter-rotating coplanar arcs or more-penetrating and treated with noncoplanar arcs, and whether the dose was calculated using the AAA algorithm or the AXB algorithm. The results of this study suggest the following QA tolerances are advisable, when 3D printed bolus is fabricated for use in photon VMAT treatments of the nose: bolus relative electron density variation within $$\pm 5\%$$ (although an action level at $$\pm 10\%$$ may be permissible); bolus thickness variation within $$\pm 1$$ mm (or 0.5 mm variation on opposite sides); and air gap between bolus and skin $$\le 5$$ mm. These tolerances should be investigated for validity with respect to other treatment modalities and anatomical sites. This study provides a set of baselines for future comparisons and a useful method for identifying additional or alternative 3D printed bolus QA tolerances.
PubDate: 2021-09-16

• Migraine detection from EEG signals using tunable Q-factor wavelet
transform and ensemble learning techniques

Abstract: Abstract Migraine is one of the major neurovascular diseases that recur, can persist for a long time, cripple or weaken the brain. This study uses electroencephalogram (EEG) signals for the diagnosis of migraine, and a computer-aided diagnosis system is presented to support expert opinion. A tunable Q-factor wavelet transform (TQWT) based method is proposed for the analysis of the oscillatory structure of EEG signals. With TQWT, EEG signals are decomposed into sub bands. Then, the features are statistically calculated from these bands. The success of the obtained features in distinguishing between migraine patients and healthy control subjects was performed using the Kruskal Wallis test. Feature values ​​obtained from each sub band were classified using well-known ensemble learning techniques and their classification performances were tested. Among the evaluated classifiers, the highest classification performance was achieved as 89.6% by using the Rotation Forest algorithm with the features obtained with Sub band 2. These results reveal the potential of the study as a tool that will support expert opinion in the diagnosis of migraine.
PubDate: 2021-09-10

• CT slice alignment to whole-body reference geometry by convolutional
neural network

Abstract: Abstract Volumetric medical imaging lacks a standardised coordinate geometry which links image frame-of-reference to specific anatomical regions. This results in an inability to locate anatomy in medical images without visual assessment and precludes a variety of image analysis tasks which could benefit from a standardised, machine-readable coordinate system. In this work, a proposed geometric system that scales based on patient size is described and applied to a variety of cases in computed tomography imaging. Subsequently, a convolutional neural network is trained to associate axial slice CT image appearance with the standardised coordinate value along the patient superior-inferior axis. The trained neural network showed an accuracy of ± 12 mm in the ability to predict per-slice reference location and was relatively stable across all annotated regions ranging from brain to thighs. A version of the trained model along with scripts to perform network training in other applications are made available. Finally, a selection of potential use applications are illustrated including organ localisation, image registration initialisation, and scan length determination for auditing diagnostic reference levels.
PubDate: 2021-09-10

• A novel 3D printed curved monopole microstrip antenna design for
biomedical applications

Abstract: Abstract This paper proposes a novel and compact monopole microstrip antenna design with a three-dimensional (3D) printed curved substrate for biomedical applications. A curved substrate was formed by inserting a semi-cylinder structure in the middle of the planar substrate consisting of polylactic acid. The antenna was fed with a microstrip line, and a partial ground plane was formed at the bottom side of the substrate. The copper plane with two triangular slots is arranged on the curved semi-cylinder structure of the substrate. The physical dimensions of the radiating plane and ground plane were optimally determined with the use of the sparrow search algorithm to provide a wide—10 dB bandwidth between 3 and 12 GHz. A total of six microstrip antennas having different parameters related to physical dimensions were designed and simulated to compare the performance of the proposed antenna with the help of full-wave electromagnetic simulation software called CST Microwave Studio. The proposed curved antenna was fabricated, and a PNA network analyzer was used to measure the S11 of the proposed antenna. It was demonstrated that the measured S11 covers the desired frequency range.
PubDate: 2021-09-04

• AI Notes: A new article type in Physical and Engineering Sciences in
Medicine

PubDate: 2021-09-01

• Winning images from the Photography in Medical Physics (PiMP) competition

PubDate: 2021-09-01

• Book review: Science fictions: exposing fraud, bias, negligence and hype
in science by Stuart J. Ritchie

PubDate: 2021-09-01

• Book review: The Modern Technology of Radiation Oncology—a Compendium
for Medical Physicists and Radiation Oncologists (Volume 4) edited by
Jacob Van Dyk

PubDate: 2021-09-01

• Deep learning based smart health monitoring for automated prediction of
epileptic seizures using spectral analysis of scalp EEG

Abstract: Abstract Being one of the most prevalent neurological disorders, epilepsy affects the lives of patients through the infrequent occurrence of spontaneous seizures. These seizures can result in serious injuries or unexpected deaths in individuals due to accidents. So, there exists a crucial need for an automatic prediction of epileptic seizures to alert the patients well before the onset of seizures, enabling them to have a healthier quality of life. In this era, the Internet of Things (IoT) technologies are being used in a cloud-fog integrated environment to address such healthcare challenges using deep learning approaches. The present paper also proposes a smart health monitoring approach for automated prediction of epileptic seizures using deep learning-based spectral analysis of EEG signals. This approach processes EEG signals using filtering, segmentation into short duration segments and spectral-domain transformation. These signals are then analysed spectrally by separating them into several spectral bands, such as delta, theta, alpha, beta, and sub-bands of gamma. Furthermore, the mean spectral amplitude and spectral power features are retrieved from each spectral band to characterize various seizure states, which are fed to the proposed LSTM and CNN models. The results of the proposed CNN model show a maximum accuracy of 98.3% and 97.4% to obtain a binary classification of preictal and interictal seizure states for two different spectral band combinations respectively. Thus, the proposed CNN architecture accompanied by spectral analysis of EEG signals provides a viable method for reliable and real-time prediction of epileptic seizures.
PubDate: 2021-09-01

• EPSM 2020, Engineering and Physical Sciences in Medicine

PubDate: 2021-09-01

• Development of a sit-to-stand assistive device with pressure sensor for
elderly and disabled: a feasibility test

Abstract: Abstract Elderly patients face difficulty in performing the sit-to-stand motion; hence, their dependency on assistive devices for activities of daily living is increasing. However, the existing devices do not provide support according to the individual’s characteristics. This study aimed to develop a sit-to-stand motion assistive chair that detects the user’s weight using a load sensor and assists them to stand up by adjusting the speed themselves as per their weight and preference. Additionally, we investigated the feasibility of the developed device. A device for assisting patients in the sit-to-stand motion in rising up from the chair by electrical motorization was developed. This device senses the load on the seat plate using the load sensor and transmits it to the display through which the users can control the speed themselves using the speed control device. To test its feasibility, the electromyographic muscle activation was analyzed for the erector spinae, quadriceps, tibialis anterior, and gastrocnemius muscles in the sit-to-stand motion using this device in five healthy adults. When compared with the non-use of the device, the use of the developed assistive chair device significantly decreased the muscle activation of the erector spinae, quadriceps, tibialis anterior, and gastrocnemius by 37.27%, 20.44%, 14.50%, and 10.56% on the left and by 17.98%, 24.48%, 32.61%, and 6.05% on the right, respectively. The assistive device with a pressure sensor can effectively assist elderly patients with reduced muscle strength and balance in performing the sit-to-stand motion.
PubDate: 2021-09-01

• A review of dosimetric impact of implementation of model-based dose
calculation algorithms (MBDCAs) for HDR brachytherapy

Abstract: Abstract To obtain dose distributions more physically representative to the patient anatomy in brachytherapy, calculation algorithms that can account for heterogeneity are required. The current standard AAPM Task Group No 43 (TG-43) dose calculation formalism has some clinically relevant dosimetric limitations. Lack of tissue heterogeneity and scattered dose corrections are the major weaknesses of the TG-43 formalism and could lead to systematic dose errors in target volumes and organs at risk. Over the last decade, model-based dose calculation algorithms (MBDCAs) have been clinically offered as complementary algorithms beyond the TG43 formalism for high dose rate (HDR) brachytherapy treatment planning. These algorithms provide enhanced dose calculation accuracy by using the information in the patient’s computed tomography images, which allows modeling the patient’s geometry, material compositions, and the treatment applicator. Several researchers have investigated the implementation of MBDCAs in HDR brachytherapy for dose optimization, but moving toward using them as primary algorithms for dose calculations is still lagging. Therefore, an overview of up-to-date research is needed to familiarize clinicians with the current status of the MBDCAs for different cancers in HDR brachytherapy. In this paper, we review the MBDCAs for HDR brachytherapy from a dosimetric perspective. Treatment sites covered include breast, gynecological, lung, head and neck, esophagus, liver, prostate, and skin cancers. Moreover, we discuss the current status of implementation of MBDCAs and the challenges.
PubDate: 2021-09-01

• Bi-parametric magnetic resonance imaging based radiomics for the
identification of benign and malignant prostate lesions: cross-vendor
validation

PubDate: 2021-09-01

• The perceptions of medical physicists towards relevance and impact of
artificial intelligence

Abstract: Abstract Artificial intelligence (AI) is an innovative tool with the potential to impact medical physicists’ clinical practices, research, and the profession. The relevance of AI and its impact on the clinical practice and routine of professionals in medical physics were evaluated by medical physicists and researchers in this field. An online survey questionnaire was designed for distribution to professionals and students in medical physics around the world. In addition to demographics questions, we surveyed opinions on the role of AI in medical physicists’ practices, the possibility of AI threatening/disrupting the medical physicists’ practices and career, the need for medical physicists to acquire knowledge on AI, and the need for teaching AI in postgraduate medical physics programmes. The level of knowledge of medical physicists on AI was also consulted. A total of 1019 respondents from 94 countries participated. More than 85% of the respondents agreed that AI would play an essential role in medical physicists’ practices. AI should be taught in the postgraduate medical physics programmes, and that more applications such as quality control (QC), treatment planning would be performed by AI. Half of the respondents thought AI would not threaten/disrupt the medical physicists’ practices. AI knowledge was mainly acquired through self-taught and work-related activities. Nonetheless, many (40%) reported that they have no skill in AI. The general perception of medical physicists was that AI is here to stay, influencing our practices. Medical physicists should be prepared with education and training for this new reality.
PubDate: 2021-09-01

JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762