|
Investigative Radiology
Journal Prestige (SJR): 3.774  Citation Impact (citeScore): 6 Number of Followers: 7  Hybrid journal (It can contain Open Access articles)ISSN (Print) 0020-9996 - ISSN (Online) 1536-0210 Published by LWW Wolters Kluwer  [330 journals]
|
- Amplifying the Effects of Contrast Agents on Magnetic Resonance Images
Using a Deep Learning Method Trained on Synthetic Data-
Free pre-print version: Loading...
Authors: Fringuello Mingo; Alberto; Colombo Serra, Sonia; Macula, Anna; Bella, Davide; La Cava, Francesca; Alì, Marco; Papa, Sergio; Tedoldi, Fabio; Smits, Marion; Bifone, Angelo; Valbusa, Giovanni
Abstract:
Objectives Artificial intelligence (AI) methods can be applied to enhance contrast in diagnostic images beyond that attainable with the standard doses of contrast agents (CAs) normally used in the clinic, thus potentially increasing diagnostic power and sensitivity. Deep learning–based AI relies on training data sets, which should be sufficiently large and diverse to effectively adjust network parameters, avoid biases, and enable generalization of the outcome. However, large sets of diagnostic images acquired at doses of CA outside the standard-of-care are not commonly available. Here, we propose a method to generate synthetic data sets to train an “AI agent” designed to amplify the effects of CAs in magnetic resonance (MR) images. The method was fine-tuned and validated in a preclinical study in a murine model of brain glioma, and extended to a large, retrospective clinical human data set.Materials and Methods A physical model was applied to simulate different levels of MR contrast from a gadolinium-based CA. The simulated data were used to train a neural network that predicts image contrast at higher doses. A preclinical MR study at multiple CA doses in a rat model of glioma was performed to tune model parameters and to assess fidelity of the virtual contrast images against ground-truth MR and histological data. Two different scanners (3 T and 7 T, respectively) were used to assess the effects of field strength. The approach was then applied to a retrospective clinical study comprising 1990 examinations in patients affected by a variety of brain diseases, including glioma, multiple sclerosis, and metastatic cancer. Images were evaluated in terms of contrast-to-noise ratio and lesion-to-brain ratio, and qualitative scores.Results In the preclinical study, virtual double-dose images showed high degrees of similarity to experimental double-dose images for both peak signal-to-noise ratio and structural similarity index (29.49 dB and 0.914 dB at 7 T, respectively, and 31.32 dB and 0.942 dB at 3 T) and significant improvement over standard contrast dose (ie, 0.1 mmol Gd/kg) images at both field strengths. In the clinical study, contrast-to-noise ratio and lesion-to-brain ratio increased by an average 155% and 34% in virtual contrast images compared with standard-dose images. Blind scoring of AI-enhanced images by 2 neuroradiologists showed significantly better sensitivity to small brain lesions compared with standard-dose images (4.46/5 vs 3.51/5).Conclusions Synthetic data generated by a physical model of contrast enhancement provided effective training for a deep learning model for contrast amplification. Contrast above that attainable at standard doses of gadolinium-based CA can be generated through this approach, with significant advantages in the detection of small low-enhancing brain lesions.
PubDate: Fri, 28 Jul 2023 00:00:00 GMT-
-
- A Comprehensive Machine Learning Benchmark Study for Radiomics-Based
Survival Analysis of CT Imaging Data in Patients With Hepatic Metastases
of CRC-
Free pre-print version: Loading...
Authors: Stüber; Anna Theresa; Coors, Stefan; Schachtner, Balthasar; Weber, Tobias; Rügamer, David; Bender, Andreas; Mittermeier, Andreas; Öcal, Osman; Seidensticker, Max; Ricke, Jens; Bischl, Bernd; Ingrisch, Michael
Abstract:
Objectives Optimizing a machine learning (ML) pipeline for radiomics analysis involves numerous choices in data set composition, preprocessing, and model selection. Objective identification of the optimal setup is complicated by correlated features, interdependency structures, and a multitude of available ML algorithms. Therefore, we present a radiomics-based benchmarking framework to optimize a comprehensive ML pipeline for the prediction of overall survival. This study is conducted on an image set of patients with hepatic metastases of colorectal cancer, for which radiomics features of the whole liver and of metastases from computed tomography images were calculated. A mixed model approach was used to find the optimal pipeline configuration and to identify the added prognostic value of radiomics features.Materials and Methods In this study, a large-scale ML benchmark pipeline consisting of preprocessing, feature selection, dimensionality reduction, hyperparameter optimization, and training of different models was developed for radiomics-based survival analysis. Portal-venous computed tomography imaging data from a previous prospective randomized trial evaluating radioembolization of liver metastases of colorectal cancer were quantitatively accessible through a radiomics approach. One thousand two hundred eighteen radiomics features of hepatic metastases and the whole liver were calculated, and 19 clinical parameters (age, sex, laboratory values, and treatment) were available for each patient. Three ML algorithms—a regression model with elastic net regularization (glmnet), a random survival forest (RSF), and a gradient tree-boosting technique (xgboost)—were evaluated for 5 combinations of clinical data, tumor radiomics, and whole-liver features. Hyperparameter optimization and model evaluation were optimized toward the performance metric integrated Brier score via nested cross-validation. To address dependency structures in the benchmark setup, a mixed-model approach was developed to compare ML and data configurations and to identify the best-performing model.Results Within our radiomics-based benchmark experiment, 60 ML pipeline variations were evaluated on clinical data and radiomics features from 491 patients. Descriptive analysis of the benchmark results showed a preference for RSF-based pipelines, especially for the combination of clinical data with radiomics features. This observation was supported by the quantitative analysis via a linear mixed model approach, computed to differentiate the effect of data sets and pipeline configurations on the resulting performance. This revealed the RSF pipelines to consistently perform similar or better than glmnet and xgboost. Further, for the RSF, there was no significantly better-performing pipeline composition regarding the sort of preprocessing or hyperparameter optimization.Conclusions Our study introduces a benchmark framework for radiomics-based survival analysis, aimed at identifying the optimal settings with respect to different radiomics data sources and various ML pipeline variations, including preprocessing techniques and learning algorithms. A suitable analysis tool for the benchmark results is provided via a mixed model approach, which showed for our study on patients with intrahepatic liver metastases, that radiomics features captured the patients' clinical situation in a manner comparable to the provided information solely from clinical parameters. However, we did not observe a relevant additional prognostic value obtained by these radiomics features.
PubDate: Fri, 28 Jul 2023 00:00:00 GMT-
-
- A Multiclass Radiomics Method–Based WHO Severity Scale for Improving
COVID-19 Patient Assessment and Disease Characterization From CT Scans-
Free pre-print version: Loading...
Authors: Henao; John Anderson Garcia; Depotter, Arno; Bower, Danielle V.; Bajercius, Herkus; Todorova, Plamena Teodosieva; Saint-James, Hugo; de Mortanges, Aurélie Pahud; Barroso, Maria Cecilia; He, Jianchun; Yang, Junlin; You, Chenyu; Staib, Lawrence H.; Gange, Christopher; Ledda, Roberta Eufrasia; Caminiti, Caterina; Silva, Mario; Cortopassi, Isabel Oliva; Dela Cruz, Charles S.; Hautz, Wolf; Bonel, Harald M.; Sverzellati, Nicola; Duncan, James S.; Reyes, Mauricio; Poellinger, Alexander
Abstract:
Objectives The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans.Materials and Methods The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19–induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19–positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19–positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion.Results AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95.Conclusions A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.
PubDate: Thu, 27 Jul 2023 00:00:00 GMT-
-
- In Vivo Validation of Modulated Acoustic Radiation Force–Based Imaging
in Murine Model of Abdominal Aortic Aneurysm Using VEGFR-2–Targeted
Microbubbles-
Free pre-print version: Loading...
Authors: Huang; Yi; Herbst, Elizabeth B.; Xie, Yanjun; Yin, Li; Islam, Zain H.; Kent, Eric W.; Wang, Bowen; Klibanov, Alexander L.; Hossack, John A.
Abstract:
Objectives The objective of this study is to validate the modulated acoustic radiation force (mARF)–based imaging method in the detection of abdominal aortic aneurysm (AAA) in murine models using vascular endothelial growth factor receptor 2 (VEGFR-2)–targeted microbubbles (MBs).Materials and Methods The mouse AAA model was prepared using the subcutaneous angiotensin II (Ang II) infusion combined with the β-aminopropionitrile monofumarate solution dissolved in drinking water. The ultrasound imaging session was performed at 7 days, 14 days, 21 days, and 28 days after the osmotic pump implantation. For each imaging session, 10 C57BL/6 mice were implanted with Ang II–filled osmotic pumps, and 5 C57BL/6 mice received saline infusion only as the control group. Biotinylated lipid MBs conjugated to either anti–mouse VEGFR-2 antibody (targeted MBs) or isotype control antibody (control MBs) were prepared before each imaging session and were injected into mice via tail vein catheter. Two separate transducers were colocalized to image the AAA and apply ARF to translate MBs simultaneously. After each imaging session, tissue was harvested and the aortas were used for VEGFR-2 immunostaining analysis. From the collected ultrasound image data, the signal magnitude response of the adherent targeted MBs was analyzed, and a parameter, residual-to-saturation ratio (Rres − sat), was defined to measure the enhancement in the adherent targeted MBs signal after the cessation of ARF compared with the initial signal intensity. Statistical analysis was performed with the Welch t test and analysis of variance test.Results The Rres − sat of abdominal aortic segments from Ang II–challenged mice was significantly higher compared with that in the saline-infused control group (P < 0.001) at all 4 time points after osmotic pump implantation (1 week to 4 weeks). In control mice, the Rres − sat values were 2.13%, 1.85%, 3.26%, and 4.85% at 1, 2, 3, and 4 weeks postimplantation, respectively. In stark contrast, the Rres − sat values for the mice with Ang II–induced AAA lesions were 9.20%, 20.6%, 22.7%, and 31.8%, respectively. It is worth noting that there was a significant difference between the Rres − sat for Ang II–infused mice at all 4 time points (P < 0.005), a finding not present in the saline-infused mice. Immunostaining results revealed the VEGFR-2 expression was increased in the abdominal aortic segments of Ang II–infused mice compared with the control group.Conclusions The mARF-based imaging technique was validated in vivo using a murine model of AAA and VEGFR-2–targeted MBs. Results in this study indicated that the mARF-based imaging technique has the ability to detect and assess AAA growth at early stages based on the signal intensity of adherent targeted MBs, which is correlated with the expression level of the desired molecular biomarker. The results may suggest, in very long term, a pathway toward eventual clinical implementation for an ultrasound molecular imaging–based approach to AAA risk assessment in asymptomatic patients.
PubDate: Wed, 12 Jul 2023 00:00:00 GMT-
-
- Accelerated Diffusion-Weighted Imaging in 3 T Breast MRI Using a Deep
Learning Reconstruction Algorithm With Superresolution Processing: A
Prospective Comparative Study-
Free pre-print version: Loading...
Authors: Wilpert; Caroline; Neubauer, Claudia; Rau, Alexander; Schneider, Hannah; Benkert, Thomas; Weiland, Elisabeth; Strecker, Ralph; Reisert, Marco; Benndorf, Matthias; Weiss, Jakob; Bamberg, Fabian; Windfuhr-Blum, Marisa; Neubauer, Jakob
Abstract:
Objectives Diffusion-weighted imaging (DWI) enhances specificity in multiparametric breast MRI but is associated with longer acquisition time. Deep learning (DL) reconstruction may significantly shorten acquisition time and improve spatial resolution. In this prospective study, we evaluated acquisition time and image quality of a DL-accelerated DWI sequence with superresolution processing (DWIDL) in comparison to standard imaging including analysis of lesion conspicuity and contrast of invasive breast cancers (IBCs), benign lesions (BEs), and cysts.Materials and Methods This institutional review board–approved prospective monocentric study enrolled participants who underwent 3 T breast MRI between August and December 2022. Standard DWI (DWISTD; single-shot echo-planar DWI combined with reduced field-of-view excitation; b-values: 50 and 800 s/mm2) was followed by DWIDL with similar acquisition parameters and reduced averages. Quantitative image quality was analyzed for region of interest–based signal-to-noise ratio (SNR) on breast tissue. Apparent diffusion coefficient (ADC), SNR, contrast-to-noise ratio, and contrast (C) values were calculated for biopsy-proven IBCs, BEs, and for cysts. Two radiologists independently assessed image quality, artifacts, and lesion conspicuity in a blinded independent manner. Univariate analysis was performed to test differences and interrater reliability.Results Among 65 participants (54 ± 13 years, 64 women) enrolled in the study, the prevalence of breast cancer was 23%. Average acquisition time was 5:02 minutes for DWISTD and 2:44 minutes for DWIDL (P < 0.001). Signal-to-noise ratio measured in breast tissue was higher for DWISTD (P < 0.001). The mean ADC values for IBC were 0.77 × 10−3 ± 0.13 mm2/s in DWISTD and 0.75 × 10−3 ± 0.12 mm2/s in DWIDL without significant difference when sequences were compared (P = 0.32). Benign lesions presented with mean ADC values of 1.32 × 10−3 ± 0.48 mm2/s in DWISTD and 1.39 × 10−3 ± 0.54 mm2/s in DWIDL (P = 0.12), and cysts presented with 2.18 × 10−3 ± 0.49 mm2/s in DWISTD and 2.31 × 10−3 ± 0.43 mm2/s in DWIDL. All lesions presented with significantly higher contrast in the DWIDL (P < 0.001), whereas SNR and contrast-to-noise ratio did not differ significantly between DWISTD and DWIDL regardless of lesion type. Both sequences demonstrated a high subjective image quality (29/65 for DWISTD vs 20/65 for DWIDL; P < 0.001). The highest lesion conspicuity score was observed more often for DWIDL (P < 0.001) for all lesion types. Artifacts were scored higher for DWIDL (P < 0.001). In general, no additional artifacts were noted in DWIDL. Interrater reliability was substantial to excellent (k = 0.68 to 1.0).Conclusions DWIDL in breast MRI significantly reduced scan time by nearly one half while improving lesion conspicuity and maintaining overall image quality in a prospective clinical cohort.
PubDate: Tue, 11 Jul 2023 00:00:00 GMT-
-
- Liver Cancer Vascularity Driven by Extracellular Matrix Stiffness:
Implications for Imaging Research-
Free pre-print version: Loading...
Authors: Taiji; Ryosuke; Cortes, Andrea C.; Zaske, Ana Maria; Williams, Malea; Dupuis, Crystal; Tanaka, Toshihiro; Nishiofuku, Hideyuki; Chintalapani, Gouthami; Peterson, Christine B.; Avritscher, Rony
Abstract:
Background Extracellular matrix stiffness represents a barrier to effective local and systemic drug delivery. Increasing stiffness disrupts newly formed vessel architecture and integrity, leading to tumor-like vasculature. The resulting vascular phenotypes are manifested through different cross-sectional imaging features. Contrast-enhanced studies can help elucidate the interplay between liver tumor stiffness and different vascular phenotypes.Purpose This study aims to correlate extracellular matrix stiffness, dynamic contrast-enhanced computed tomography, and dynamic contrast-enhancement ultrasound imaging features of 2 rat hepatocellular carcinoma tumor models.Methods and Materials Buffalo-McA-RH7777 and Sprague Dawley (SD)–N1S1 tumor models were used to evaluate tumor stiffness by 2-dimensional shear wave elastography, along with tumor perfusion by dynamic contrast-enhanced ultrasonography and contrast-enhanced computed tomography. Atomic force microscopy was used to calculate tumor stiffness at a submicron scale. Computer-aided image analyses were performed to evaluate tumor necrosis, as well as the percentage, distribution, and thickness of CD34+ blood vessels.Results Distinct tissue signatures between models were observed according to the distribution of the stiffness values by 2-dimensional shear wave elastography and atomic force microscopy (P < 0.05). Higher stiffness values were attributed to SD-N1S1 tumors, also associated with a scant microvascular network (P ≤ 0.001). Opposite results were observed in the Buffalo-McA-RH7777 model, exhibiting lower stiffness values and richer tumor vasculature with predominantly peripheral distribution (P = 0.03). Consistent with these findings, tumor enhancement was significantly greater in the Buffalo-McA-RH7777 tumor model than in the SD-N1S1 on both dynamic contrast-enhanced ultrasonography and contrast-enhanced computed tomography (P < 0.005). A statistically significant positive correlation was observed between tumor perfusion on dynamic contrast-enhanced ultrasonography and contrast-enhanced computed tomography in terms of the total area under the curve and % microvessel tumor coverage (P < 0.05).Conclusions The stiffness signatures translated into different tumor vascular phenotypes. Two-dimensional shear wave elastography and dynamic contrast-enhanced ultrasonography adequately depicted different stromal patterns, which resulted in unique imaging perfusion parameters with significantly greater contrast enhancement observed in softer tumors.
PubDate: Wed, 05 Jul 2023 00:00:00 GMT-
-
- Breast DWI Analyzed Before and After Gadolinium Contrast
Administration—An Intrapatient Analysis on 1.5 T and 3.0 T-
Free pre-print version: Loading...
Authors: van der Hoogt; Kay J.J.; Schipper, Robert-Jan; Wessels, Ronni; ter Beek, Leon C.; Beets-Tan, Regina G.H.; Mann, Ritse M.
Abstract:
Objectives Diffusion-weighted magnetic resonance imaging (MRI) is gaining popularity as an addition to standard dynamic contrast-enhanced breast MRI. Although adding diffusion-weighted imaging (DWI) to the standard protocol design would require increased scanning-time, implementation during the contrast-enhanced phase could offer a multiparametric MRI protocol without any additional scanning time. However, gadolinium within a region of interest (ROI) might affect assessments of DWI. This study aims to determine if acquiring DWI postcontrast, incorporated in an abbreviated MRI protocol, would statistically significantly affect lesion classification. In addition, the effect of postcontrast DWI on breast parenchyma was studied.Materials and Methods Screening or preoperative MRIs (1.5 T/3 T) were included for this study. Diffusion-weighted imaging was acquired with single-shot spin echo–echo planar imaging before and at approximately 2 minutes after gadoterate meglumine injection. Apparent diffusion coefficients (ADCs) based on 2-dimensional ROIs of fibroglandular tissue, as well as benign and malignant lesions at 1.5 T/3.0 T, were compared with a Wilcoxon signed rank test. Diffusivity levels were compared between precontrast and postcontrast DWI with weighted κ. An overall P ≤ 0.05 was considered statistically significant.Results No significant changes were observed in ADCmean after contrast administration in 21 patients with 37 ROI of healthy fibroglandular tissue and in the 93 patients with 93 (malignant and benign) lesions. This effect remained after stratification on B0. In 18% of all lesions, a diffusion level shift was observed, with an overall weighted κ of 0.75.Conclusions This study supports incorporating DWI at 2 minutes postcontrast when ADC is calculated based on b150-b800 with 15 mL 0.5 M gadoterate meglumine in an abbreviated multiparametric MRI protocol without requiring extra scan time.
PubDate: Fri, 30 Jun 2023 00:00:00 GMT-
-
- Development and Evaluation of Machine Learning in Whole-Body Magnetic
Resonance Imaging for Detecting Metastases in Patients With Lung or Colon
Cancer: A Diagnostic Test Accuracy Study-
Free pre-print version: Loading...
Authors: Rockall; Andrea G.; Li, Xingfeng; Johnson, Nicholas; Lavdas, Ioannis; Santhakumaran, Shalini; Prevost, A. Toby; Punwani, Shonit; Goh, Vicky; Barwick, Tara D.; Bharwani, Nishat; Sandhu, Amandeep; Sidhu, Harbir; Plumb, Andrew; Burn, James; Fagan, Aisling; Wengert, Georg J.; Koh, Dow-Mu; Reczko, Krystyna; Dou, Qi; Warwick, Jane; Liu, Xinxue; Messiou, Christina; Tunariu, Nina; Boavida, Peter; Soneji, Neil; Johnston, Edward W.; Kelly-Morland, Christian; De Paepe, Katja N.; Sokhi, Heminder; Wallitt, Kathryn; Lakhani, Amish; Russell, James; Salib, Miriam; Vinnicombe, Sarah; Haq, Adam; Aboagye, Eric O.; Taylor, Stuart; Glocker, Ben
Abstract:
Objectives Whole-body magnetic resonance imaging (WB-MRI) has been demonstrated to be efficient and cost-effective for cancer staging. The study aim was to develop a machine learning (ML) algorithm to improve radiologists' sensitivity and specificity for metastasis detection and reduce reading times.Materials and Methods A retrospective analysis of 438 prospectively collected WB-MRI scans from multicenter Streamline studies (February 2013–September 2016) was undertaken. Disease sites were manually labeled using Streamline reference standard. Whole-body MRI scans were randomly allocated to training and testing sets. A model for malignant lesion detection was developed based on convolutional neural networks and a 2-stage training strategy. The final algorithm generated lesion probability heat maps. Using a concurrent reader paradigm, 25 radiologists (18 experienced, 7 inexperienced in WB-/MRI) were randomly allocated WB-MRI scans with or without ML support to detect malignant lesions over 2 or 3 reading rounds. Reads were undertaken in the setting of a diagnostic radiology reading room between November 2019 and March 2020. Reading times were recorded by a scribe. Prespecified analysis included sensitivity, specificity, interobserver agreement, and reading time of radiology readers to detect metastases with or without ML support. Reader performance for detection of the primary tumor was also evaluated.Results Four hundred thirty-three evaluable WB-MRI scans were allocated to algorithm training (245) or radiology testing (50 patients with metastases, from primary 117 colon [n = 117] or lung [n = 71] cancer). Among a total 562 reads by experienced radiologists over 2 reading rounds, per-patient specificity was 86.2% (ML) and 87.7% (non-ML) (−1.5% difference; 95% confidence interval [CI], −6.4%, 3.5%; P = 0.39). Sensitivity was 66.0% (ML) and 70.0% (non-ML) (−4.0% difference; 95% CI, −13.5%, 5.5%; P = 0.344). Among 161 reads by inexperienced readers, per-patient specificity in both groups was 76.3% (0% difference; 95% CI, −15.0%, 15.0%; P = 0.613), with sensitivity of 73.3% (ML) and 60.0% (non-ML) (13.3% difference; 95% CI, −7.9%, 34.5%; P = 0.313). Per-site specificity was high (>90%) for all metastatic sites and experience levels. There was high sensitivity for the detection of primary tumors (lung cancer detection rate of 98.6% with and without ML [0.0% difference; 95% CI, −2.0%, 2.0%; P = 1.00], colon cancer detection rate of 89.0% with and 90.6% without ML [−1.7% difference; 95% CI, −5.6%, 2.2%; P = 0.65]). When combining all reads from rounds 1 and 2, reading times fell by 6.2% (95% CI, −22.8%, 10.0%) when using ML. Round 2 read-times fell by 32% (95% CI, 20.8%, 42.8%) compared with round 1. Within round 2, there was a significant decrease in read-time when using ML support, estimated as 286 seconds (or 11%) quicker (P = 0.0281), using regression analysis to account for reader experience, read round, and tumor type. Interobserver variance suggests moderate agreement, Cohen κ = 0.64; 95% CI, 0.47, 0.81 (with ML), and Cohen κ = 0.66; 95% CI, 0.47, 0.81 (without ML).Conclusions There was no evidence of a significant difference in per-patient sensitivity and specificity for detecting metastases or the primary tumor using concurrent ML compared with standard WB-MRI. Radiology read-times with or without ML support fell for round 2 reads compared with round 1, suggesting that readers familiarized themselves with the study reading method. During the second reading round, there was a significant reduction in reading time when using ML support.
PubDate: Mon, 26 Jun 2023 00:00:00 GMT-
-
