Search

Tilman Hickethier,1,* Kamal Mammadov,1,* Bettina Baeßler,1 Thorsten Lichtenstein,1 Jochen Hinkelbein,2 Lucy Smith,3 Patrick Sven Plum,4 Seung-Hun Chon,4 David Maintz,1 De-Hua Chang1 1Department of Radiology, University Hospital of Cologne, Cologne, Germany; 2Department of Anesthesiology and Intensive Care Medicine, University Hospital of Cologne, Cologne, Germany; 3Faculty of Medicine, Memorial University of Newfoundland, St. John’s, Canada; 4Department of General, Visceral and Cancer Surgery, University Hospital of Cologne, Cologne, Germany *These authors contributed equally to this work Background: The study was conducted to compare examination time and artifact vulnerability of whole-body computed tomographies (wbCTs) for trauma patients using conventional or optimized patient positioning. Patients and methods: Examination time was measured in 100 patients scanned with conventional protocol (Group A: arms positioned alongside the body for head and neck imaging and over the head for trunk imaging) and 100 patients scanned with optimized protocol (Group B: arms flexed on a chest pillow without repositioning). Additionally, influence of two different scanning protocols on image quality in the most relevant body regions was assessed by two blinded readers. Results: Total wbCT duration was about 35% or 3:46 min shorter in B than in A. Artifacts in aorta (27 vs 6%), liver (40 vs 8%) and spleen (27 vs 5%) occurred significantly more often in B than in A. No incident of non-diagnostic image quality was reported, and no significant differences for lungs and spine were found. Conclusion: An optimized wbCT positioning protocol for trauma patients allows a significant reduction of examination time while still maintaining diagnostic image quality. Keywords: CT scan, polytrauma, acute care, time requirement, positioning

Objectives: Achieving a consensus on a definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, to assess the perspective of experts on important challenges for a successful clinical workflow implementation., Materials and Methods: The consensus was achieved by a multi-stage process. Stage 1 comprised a definition screening, a retrospective analysis with semantic mapping of terms found in 22 workflow definitions, and the compilation of an initial baseline definition. Stages 2 and 3 consisted of a Delphi process with over 45 experts hailing from sites participating in the German Research Foundation (DFG) Priority Program 2177. Stage 2 aimed to achieve a broad consensus for a definition proposal, while stage 3 identified the importance of translational challenges., Results: Workflow definitions from 22 publications (published 2012-2020) were analyzed. Sixty-nine definition terms were extracted, mapped, and semantic ambiguities (e.g., homonymous and synonymous terms) were identified and resolved. The consensus definition was developed via a Delphi process. The final definition comprising seven phases and 37 aspects reached a high overall consensus (> 89% of experts "agree" or "strongly agree"). Two aspects reached no strong consensus. In addition, the Delphi process identified and characterized from the participating experts' perspective the ten most important challenges in radiomics workflows., Conclusion: To overcome semantic inconsistencies between existing definitions and offer a well-defined, broad, referenceable terminology, a consensus workflow definition for radiomics-based setups and a terms mapping to existing literature was compiled. Moreover, the most relevant challenges towards clinical application were characterized., Critical Relevance Statement: Lack of standardization represents one major obstacle to successful clinical translation of radiomics. Here, we report a consensus workflow definition on different aspects of radiomics studies and highlight important challenges to advance the clinical adoption of radiomics., Key Points: Published radiomics workflow terminologies are inconsistent, hindering standardization and translation. A consensus radiomics workflow definition proposal with high agreement was developed. Publicly available result resources for further exploitation by the scientific community., (© 2024. The Author(s).)

Purpose: To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies., Methods: We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members to identify the items to be voted; and Stage#3, four rounds of the modified Delphi exercise by panelists to determine the items eligible for the METRICS and their weights. The consensus threshold was 75%. Based on the median ranks derived from expert panel opinion and their rank-sum based conversion to importance scores, the category and item weights were calculated., Result: In total, 59 panelists from 19 countries participated in selection and ranking of the items and categories. Final METRICS tool included 30 items within 9 categories. According to their weights, the categories were in descending order of importance: study design, imaging data, image processing and feature extraction, metrics and comparison, testing, feature processing, preparation for modeling, segmentation, and open science. A web application and a repository were developed to streamline the calculation of the METRICS score and to collect feedback from the radiomics community., Conclusion: In this work, we developed a scoring tool for assessing the methodological quality of the radiomics research, with a large international panel and a modified Delphi protocol. With its conditional format to cover methodological variations, it provides a well-constructed framework for the key methodological concepts to assess the quality of radiomic research papers., Critical Relevance Statement: A quality assessment tool, METhodological RadiomICs Score (METRICS), is made available by a large group of international domain experts, with transparent methodology, aiming at evaluating and improving research quality in radiomics and machine learning., Key Points: • A methodological scoring tool, METRICS, was developed for assessing the quality of radiomics research, with a large international expert panel and a modified Delphi protocol. • The proposed scoring tool presents expert opinion-based importance weights of categories and items with a transparent methodology for the first time. • METRICS accounts for varying use cases, from handcrafted radiomics to entirely deep learning-based pipelines. • A web application has been developed to help with the calculation of the METRICS score ( https://metricsscore.github.io/metrics/METRICS.html ) and a repository created to collect feedback from the radiomics community ( https://github.com/metricsscore/metrics )., (© 2024. The Author(s).)

Background: Myocardial mapping techniques can be used to quantitatively assess alterations in myocardial tissue properties. This study aims to evaluate the influence of spatial resolution on quantitative results and reproducibility of native myocardial T1 mapping in cardiac magnetic resonance imaging (MRI)., Methods: In this cross-sectional study with prospective data collection between October 2019 and February 2020, 50 healthy adults underwent two identical cardiac MRI examinations in the radiology department on the same day. T1 mapping was performed using a MOLLI 5(3)3 sequence with higher (1.4 mm × 1.4 mm) and lower (1.9 mm × 1.9 mm) in-plane spatial resolution. Global quantitative results of T1 mapping were compared between high-resolution and low-resolution acquisitions using paired t -test. Intra-class correlation coefficient (ICC) and Bland-Altman statistics (absolute and percentage differences as means ± SD) were used for assessing test-retest reproducibility., Results: There was no significant difference between global quantitative results acquired with high vs. low-resolution T1 mapping. The reproducibility of global T1 values was good for high-resolution (ICC: 0.88) and excellent for low-resolution T1 mapping (ICC: 0.95, P=0.003). In subgroup analyses, inferior test-retest reproducibility was observed for high spatial resolution in women compared to low spatial resolution (ICC: 0.71 vs. 0.91, P=0.001) and heart rates >77 bpm (ICC: 0.53 vs. 0.88, P=0.004). Apical segments had higher T1 values and variability compared to other segments. Regional T1 values for basal (ICC: 0.81 vs. 0.89, P=0.023) and apical slices (ICC: 0.86 vs. 0.92, P=0.024) showed significantly higher reproducibility in low-resolution compared to high-resolution acquisitions but without differences for midventricular slice (ICC: 0.91 vs. 0.92, P=0.402)., Conclusions: Based on our data, we recommend a spatial resolution on the order of 1.9 mm × 1.9 mm for native myocardial T1 mapping using a MOLLI 5(3)3 sequence at 1.5 T particularly in individuals with higher heart rates and women., Competing Interests: Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://qims.amegroups.com/article/view/10.21037/qims-23-943/coif). F.G.M. received a research grant from GE HealthCare and speaker honoraria from GE HealthCare, Circle Cardiovascular Imaging and Bayer Vital. The other authors have no conflicts of interest to declare., (2024 Quantitative Imaging in Medicine and Surgery. All rights reserved.)

Objectives: Open-access cancer imaging datasets have become integral for evaluating novel AI approaches in radiology. However, their use in quantitative analysis with radiomics features presents unique challenges, such as incomplete documentation, low visibility, non-uniform data formats, data inhomogeneity, and complex preprocessing. These issues may cause problems with reproducibility and standardization in radiomics studies., Methods: We systematically reviewed imaging datasets with public copyright licenses, published up to March 2023 across four large online cancer imaging archives. We included only datasets with tomographic images (CT, MRI, or PET), segmentations, and clinical annotations, specifically identifying those suitable for radiomics research. Reproducible preprocessing and feature extraction were performed for each dataset to enable their easy reuse., Results: We discovered 29 datasets with corresponding segmentations and labels in the form of health outcomes, tumor pathology, staging, imaging-based scores, genetic markers, or repeated imaging. We compiled a repository encompassing 10,354 patients and 49,515 scans. Of the 29 datasets, 15 were licensed under Creative Commons licenses, allowing both non-commercial and commercial usage and redistribution, while others featured custom or restricted licenses. Studies spanned from the early 1990s to 2021, with the majority concluding after 2013. Seven different formats were used for the imaging data. Preprocessing and feature extraction were successfully performed for each dataset., Conclusion: RadiomicsHub is a comprehensive public repository with radiomics features derived from a systematic review of public cancer imaging datasets. By converting all datasets to a standardized format and ensuring reproducible and traceable processing, RadiomicsHub addresses key reproducibility and standardization challenges in radiomics., Critical Relevance Statement: This study critically addresses the challenges associated with locating, preprocessing, and extracting quantitative features from open-access datasets, to facilitate more robust and reliable evaluations of radiomics models., Key Points: - Through a systematic review, we identified 29 cancer imaging datasets suitable for radiomics research. - A public repository with collection overview and radiomics features, encompassing 10,354 patients and 49,515 scans, was compiled. - Most datasets can be shared, used, and built upon freely under a Creative Commons license. - All 29 identified datasets have been converted into a common format to enable reproducible radiomics feature extraction., (© 2023. The Author(s).)

Background: In the management of cancer patients, determination of TNM status is essential for treatment decision-making and therefore closely linked to clinical outcome and survival. Here, we developed a tool for automatic three-dimensional (3D) localization and segmentation of cervical lymph nodes (LNs) on contrast-enhanced computed tomography (CECT) examinations., Methods: In this IRB-approved retrospective single-center study, 187 CECT examinations of the head and neck region from patients with various primary diseases were collected from our local database, and 3656 LNs (19.5 ± 14.9 LNs/CECT, mean ± standard deviation) with a short-axis diameter (SAD) ≥ 5 mm were segmented manually by expert physicians. With these data, we trained an independent fully convolutional neural network based on 3D foveal patches. Testing was performed on 30 independent CECTs with 925 segmented LNs with an SAD ≥ 5 mm., Results: In total, 4,581 LNs were segmented in 217 CECTs. The model achieved an average localization rate (LR), i.e., percentage of localized LNs/CECT, of 78.0% in the validation dataset. In the test dataset, average LR was 81.1% with a mean Dice coefficient of 0.71. For enlarged LNs with a SAD ≥ 10 mm, LR was 96.2%. In the test dataset, the false-positive rate was 2.4 LNs/CECT., Conclusions: Our trained AI model demonstrated a good overall performance in the consistent automatic localization and 3D segmentation of physiological and metastatic cervical LNs with a SAD ≥ 5 mm on CECTs. This could aid clinical localization and automatic 3D segmentation, which can benefit clinical care and radiomics research., Relevance Statement: Our AI model is a time-saving tool for 3D segmentation of cervical lymph nodes on contrast-enhanced CT scans and serves as a solid base for N staging in clinical practice and further radiomics research., Key Points: • Determination of N status in TNM staging is essential for therapy planning in oncology. • Segmenting cervical lymph nodes manually is highly time-consuming in clinical practice. • Our model provides a robust, automated 3D segmentation of cervical lymph nodes. • It achieves a high accuracy for localization especially of enlarged lymph nodes. • These segmentations should assist clinical care and radiomics research., (© 2023. The Author(s).)

Objectives: Positron emission tomography (PET) is currently considered the non-invasive reference standard for lymph node (N-)staging in lung cancer. However, not all patients can undergo this diagnostic procedure due to high costs, limited availability, and additional radiation exposure. The purpose of this study was to predict the PET result from traditional contrast-enhanced computed tomography (CT) and to test different feature extraction strategies., Methods: In this study, 100 lung cancer patients underwent a contrast-enhanced 18 F-fluorodeoxyglucose (FDG) PET/CT scan between August 2012 and December 2019. We trained machine learning models to predict FDG uptake in the subsequent PET scan. Model inputs were composed of (i) traditional "hand-crafted" radiomics features from the segmented lymph nodes, (ii) deep features derived from a pretrained EfficientNet-CNN, and (iii) a hybrid approach combining (i) and (ii)., Results: In total, 2734 lymph nodes [555 (20.3%) PET-positive] from 100 patients [49% female; mean age 65, SD: 14] with lung cancer (60% adenocarcinoma, 21% plate epithelial carcinoma, 8% small-cell lung cancer) were included in this study. The area under the receiver operating characteristic curve (AUC) ranged from 0.79 to 0.87, and the scaled Brier score (SBS) ranged from 16 to 36%. The random forest model (iii) yielded the best results [AUC 0.871 (0.865-0.878), SBS 35.8 (34.2-37.2)] and had significantly higher model performance than both approaches alone (AUC: p < 0.001, z = 8.8 and z = 22.4; SBS: p < 0.001, z = 11.4 and z = 26.6, against (i) and (ii), respectively)., Conclusion: Both traditional radiomics features and transfer-learning deep radiomics features provide relevant and complementary information for non-invasive N-staging in lung cancer.

Recent advances in computer vision have shown promising results in image generation. Diffusion probabilistic models have generated realistic images from textual input, as demonstrated by DALL-E 2, Imagen, and Stable Diffusion. However, their use in medicine, where imaging data typically comprises three-dimensional volumes, has not been systematically evaluated. Synthetic images may play a crucial role in privacy-preserving artificial intelligence and can also be used to augment small datasets. We show that diffusion probabilistic models can synthesize high-quality medical data for magnetic resonance imaging (MRI) and computed tomography (CT). For quantitative evaluation, two radiologists rated the quality of the synthesized images regarding "realistic image appearance", "anatomical correctness", and "consistency between slices". Furthermore, we demonstrate that synthetic images can be used in self-supervised pre-training and improve the performance of breast segmentation models when data is scarce (Dice scores, 0.91 [without synthetic data], 0.95 [with synthetic data])., (© 2023. The Author(s).)

Even though radiomics can hold great potential for supporting clinical decision-making, its current use is mostly limited to academic research, without applications in routine clinical practice. The workflow of radiomics is complex due to several methodological steps and nuances, which often leads to inadequate reporting and evaluation, and poor reproducibility. Available reporting guidelines and checklists for artificial intelligence and predictive modeling include relevant good practices, but they are not tailored to radiomic research. There is a clear need for a complete radiomics checklist for study planning, manuscript writing, and evaluation during the review process to facilitate the repeatability and reproducibility of studies. We here present a documentation standard for radiomic research that can guide authors and reviewers. Our motivation is to improve the quality and reliability and, in turn, the reproducibility of radiomic research. We name the checklist CLEAR (CheckList for EvaluAtion of Radiomics research), to convey the idea of being more transparent. With its 58 items, the CLEAR checklist should be considered a standardization tool providing the minimum requirements for presenting clinical radiomics research. In addition to a dynamic online version of the checklist, a public repository has also been set up to allow the radiomics community to comment on the checklist items and adapt the checklist for future versions. Prepared and revised by an international group of experts using a modified Delphi method, we hope the CLEAR checklist will serve well as a single and complete scientific documentation tool for authors and reviewers to improve the radiomics literature., (© 2023. The Author(s).)

Background Automation bias (the propensity for humans to favor suggestions from automated decision-making systems) is a known source of error in human-machine interactions, but its implications regarding artificial intelligence (AI)-aided mammography reading are unknown. Purpose To determine how automation bias can affect inexperienced, moderately experienced, and very experienced radiologists when reading mammograms with the aid of an artificial intelligence (AI) system. Materials and Methods In this prospective experiment, 27 radiologists read 50 mammograms and provided their Breast Imaging Reporting and Data System (BI-RADS) assessment assisted by a purported AI system. Mammograms were obtained between January 2017 and December 2019 and were presented in two randomized sets. The first was a training set of 10 mammograms, with the correct BI-RADS category suggested by the AI system. The second was a set of 40 mammograms in which an incorrect BI-RADS category was suggested for 12 mammograms. Reader performance, degree of bias in BI-RADS scoring, perceived accuracy of the AI system, and reader confidence in their own BI-RADS ratings were assessed using analysis of variance (ANOVA) and repeated-measures ANOVA followed by post hoc tests and Kruskal-Wallis tests followed by the Dunn post hoc test. Results The percentage of correctly rated mammograms by inexperienced (mean, 79.7% ± 11.7 [SD] vs 19.8% ± 14.0; P < .001; r = 0.93), moderately experienced (mean, 81.3% ± 10.1 vs 24.8% ± 11.6; P < .001; r = 0.96), and very experienced (mean, 82.3% ± 4.2 vs 45.5% ± 9.1; P = .003; r = 0.97) radiologists was significantly impacted by the correctness of the AI prediction of BI-RADS category. Inexperienced radiologists were significantly more likely to follow the suggestions of the purported AI when it incorrectly suggested a higher BI-RADS category than the actual ground truth compared with both moderately (mean degree of bias, 4.0 ± 1.8 vs 2.4 ± 1.5; P = .044; r = 0.46) and very (mean degree of bias, 4.0 ± 1.8 vs 1.2 ± 0.8; P = .009; r = 0.65) experienced readers. Conclusion The results show that inexperienced, moderately experienced, and very experienced radiologists reading mammograms are prone to automation bias when being supported by an AI-based system. This and other effects of human and machine interaction must be considered to ensure safe deployment and accurate diagnostic performance when combining human readers and AI. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Baltzer in this issue.

Clinical audit is an important quality improvement activity and has significant benefits for patients in terms of enhanced care, safety, experience and outcomes. Clinical audit in support of radiation protection is mandated within the European Council Basic Safety Standards Directive (BSSD), 2013/59/Euratom. The European Society of Radiology (ESR) has recognised clinical audit as an area of particular importance in the delivery of safe and effective health care. The ESR, alongside other European organisations and professional bodies, has developed a range of clinical audit-related initiatives to support European radiology departments in developing a clinical audit infrastructure and fulfilling their legal obligations. However, work by the European Commission, the ESR and other agencies has demonstrated a persisting variability in clinical audit uptake and implementation across Europe and a lack of awareness of the BSSD clinical audit requirements. In recognition of these findings, the European Commission supported the QuADRANT project, led by the ESR and in partnership with ESTRO (European Association of Radiotherapy and Oncology) and EANM (European Association of Nuclear Medicine). QuADRANT was a 30-month project which completed in Summer 2022, aiming to provide an overview of the status of European clinical audit and identifying barriers and challenges to clinical audit uptake and implementation. This paper summarises the current position of European radiological clinical audit and considers the barriers and challenges that exist. Reference is made to the QuADRANT project, and a range of potential solutions are suggested to enhance radiological clinical audit across Europe., (© 2023. The Author(s).)

Coronary computed tomography angiography (CCTA) is increasingly the cornerstone in the management of patients with chronic coronary syndromes. This fact is reflected by current guidelines, which show a fundamental shift towards non-invasive imaging - especially CCTA. The guidelines for acute and stable coronary artery disease (CAD) of the European Society of Cardiology from 2019 and 2020 emphasize this shift. However, to fulfill this new role, a broader availability in adjunct with increased robustness of data acquisition and speed of data reporting of CCTA is needed. Artificial intelligence (AI) has made enormous progress for all imaging methodologies concerning (semi)-automatic tools for data acquisition and data post-processing, with outreach toward decision support systems. Besides onco- and neuroimaging, cardiac imaging is one of the main areas of application. Most current AI developments in the scenario of cardiac imaging are related to data postprocessing. However, AI applications (including radiomics) for CCTA also should enclose data acquisition (especially the fact of dose reduction) and data interpretation (presence and extent of CAD). The main effort will be to integrate these AI-driven processes into the clinical workflow, and to combine imaging data/results with further clinical data, thus - beyond the diagnosis of CAD- enabling prediction and forecast of morbidity and mortality. Furthermore, data fusing for therapy planning (e.g., invasive angiography/TAVI planning) will be warranted. The aim of this review is to present a holistic overview of AI applications in CCTA (including radiomics) under the umbrella of clinical workflows and clinical decision-making. The review first summarizes and analyzes applications for the main role of CCTA, i.e., to non-invasively rule out stable coronary artery disease. In the second step, AI applications for additional diagnostic purposes, i.e., to improve diagnostic power (CAC = coronary artery classifications), improve differential diagnosis (CT-FFR and CT perfusion), and finally improve prognosis (again CAC plus epi- and pericardial fat analysis) are reviewed., Competing Interests: CA is the inventor of patents US10,695,023B2, PCT/GB2017/053262, GB2018/1818049.7, GR20180100490, and GR20180100510, as well as the founder, shareholder, and director of Caristo Diagnostics Ltd. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Baeßler, Götz, Antoniades, Heidenreich, Leiner and Beer.)

Background: Imaging-based total kidney volume (TKV) and total liver volume (TLV) are major prognostic factors in autosomal dominant polycystic kidney disease (ADPKD) and end points for clinical trials. However, volumetry is time consuming and reader dependent in clinical practice. Our aim was to develop a fully automated method for joint kidney and liver segmentation in magnetic resonance imaging (MRI) and to evaluate its performance in a multisequence, multicenter setting., Methods: The convolutional neural network was trained on a large multicenter dataset consisting of 992 MRI scans of 327 patients. Manual segmentation delivered ground-truth labels. The model's performance was evaluated in a separate test dataset of 93 patients (350 MRI scans) as well as a heterogeneous external dataset of 831 MRI scans from 323 patients., Results: The segmentation model yielded excellent performance, achieving a median per study Dice coefficient of 0.92-0.97 for the kidneys and 0.96 for the liver. Automatically computed TKV correlated highly with manual measurements (intraclass correlation coefficient [ICC]: 0.996-0.999) with low bias and high precision (-0.2%±4% for axial images and 0.5%±4% for coronal images). TLV estimation showed an ICC of 0.999 and bias/precision of -0.5%±3%. For the external dataset, the automated TKV demonstrated bias and precision of -1%±7%., Conclusions: Our deep learning model enabled accurate segmentation of kidneys and liver and objective assessment of TKV and TLV. Importantly, this approach was validated with axial and coronal MRI scans from 40 different scanners, making implementation in clinical routine care feasible. Clinical Trial registry name and registration number: The German ADPKD Tolvaptan Treatment Registry (AD[H]PKD), NCT02497521., (Copyright © 2022 by the American Society of Nephrology.)

Purpose: Machine learning based on radiomics features has seen huge success in a variety of clinical applications. However, the need for standardization and reproducibility has been increasingly recognized as a necessary step for future clinical translation. We developed a novel, intuitive open-source framework to facilitate all data analysis steps of a radiomics workflow in an easy and reproducible manner and evaluated it by reproducing classification results in eight available open-source datasets from different clinical entities., Methods: The framework performs image preprocessing, feature extraction, feature selection, modeling, and model evaluation, and can automatically choose the optimal parameters for a given task. All analysis steps can be reproduced with a web application, which offers an interactive user interface and does not require programming skills. We evaluated our method in seven different clinical applications using eight public datasets: six datasets from the recently published WORC database, and two prostate MRI datasets-Prostate MRI and Ultrasound With Pathology and Coordinates of Tracked Biopsy (Prostate-UCLA) and PROSTATEx., Results: In the analyzed datasets, AutoRadiomics successfully created and optimized models using radiomics features. For WORC datasets, we achieved AUCs ranging from 0.56 for lung melanoma metastases detection to 0.93 for liposarcoma detection and thereby managed to replicate the previously reported results. No significant overfitting between training and test sets was observed. For the prostate cancer detection task, results were better in the PROSTATEx dataset (AUC = 0.73 for prostate and 0.72 for lesion mask) than in the Prostate-UCLA dataset (AUC 0.61 for prostate and 0.65 for lesion mask), with external validation results varying from AUC = 0.51 to AUC = 0.77., Conclusion: AutoRadiomics is a robust tool for radiomic studies, which can be used as a comprehensive solution, one of the analysis steps, or an exploratory tool. Its wide applicability was confirmed by the results obtained in the diverse analyzed datasets. The framework, as well as code for this analysis, are publicly available under https://github.com/pwoznicki/AutoRadiomics., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Woznicki, Laqua, Bley and Baeßler.)

Objectives: To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG)., Methods: Patients with histologically confirmed TET in the years 2000-2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance., Results: 105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22-82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3-94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9-93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8-79.5)., Conclusions: CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage., Competing Interests: The authors have declared that no competing interests exist.

Background: The coronavirus disease 2019 (COVID-19) pandemic led to far-reaching restrictions of social and professional life, affecting societies all over the world. To contain the virus, medical schools had to restructure their curriculum by switching to online learning. However, only few medical schools had implemented such novel learning concepts. We aimed to evaluate students' attitudes to online learning to provide a broad scientific basis to guide future development of medical education., Methods: Overall, 3286 medical students from 12 different countries participated in this cross-sectional, web-based study investigating various aspects of online learning in medical education. On a 7-point Likert scale, participants rated the online learning situation during the pandemic at their medical schools, technical and social aspects, and the current and future role of online learning in medical education., Results: The majority of medical schools managed the rapid switch to online learning (78%) and most students were satisfied with the quantity (67%) and quality (62%) of the courses. Online learning provided greater flexibility (84%) and led to unchanged or even higher attendance of courses (70%). Possible downsides included motivational problems (42%), insufficient possibilities for interaction with fellow students (67%) and thus the risk of social isolation (64%). The vast majority felt comfortable using the software solutions (80%). Most were convinced that medical education lags behind current capabilities regarding online learning (78%) and estimated the proportion of online learning before the pandemic at only 14%. In order to improve the current curriculum, they wish for a more balanced ratio with at least 40% of online teaching compared to on-site teaching., Conclusion: This study demonstrates the positive attitude of medical students towards online learning. Furthermore, it reveals a considerable discrepancy between what students demand and what the curriculum offers. Thus, the COVID-19 pandemic might be the long-awaited catalyst for a new "online era" in medical education., Competing Interests: The authors have declared that no competing interests exist.

The purpose of this study was to (i) evaluate the test-retest repeatability and reproducibility of radiomic features in virtual monoenergetic images (VMI) from dual-energy CT (DECT) depending on VMI energy (40, 50, 75, 120, 190 keV), radiation dose (5 and 15 mGy), and DECT approach (dual-source and split-filter DECT) in a phantom (ex vivo), and (ii) to assess the impact of VMI energy and feature repeatability on machine-learning-based classification in vivo in 72 patients with 72 hypodense liver lesions. Feature repeatability and reproducibility were determined by concordance-correlation-coefficient (CCC) and dynamic range (DR) ≥0.9. Test-retest repeatability was high within the same VMI energies and scan conditions (percentage of repeatable features ranging from 74% for SFDE mode at 40 keV and 15 mGy to 86% for DSDE at 190 keV and 15 mGy), while reproducibility varied substantially across different VMI energies and DECTs (percentage of reproducible features ranging from 32.8% for SFDE at 5 mGy comparing 40 with 190 keV to 99.2% for DSDE at 15 mGy comparing 40 with 50 keV). No major differences were observed between the two radiation doses (<10%) in all pair-wise comparisons. In vivo, machine learning classification using penalized regression and random forests resulted in the best discrimination of hemangiomas and metastases at low-energy VMI (40 keV), and for cysts at high-energy VMI (120 keV). Feature selection based on feature repeatability did not improve classification performance. Our results demonstrate the high repeatability of radiomics features when keeping scan and reconstruction conditions constant. Reproducibility diminished when using different VMI energies or DECT approaches. The choice of optimal VMI energy improved lesion classification in vivo and should hence be adapted to the specific task.

Rationale and Objectives: To quantify the contribution of lesion location and patient positioning, dual-energy approach, patient size, and radiation dose to the error of dual-energy CT-based iodine quantification (DECT-IQ) in liver tumors., Materials and Methods: A phantom with four liver lesions (diameter 15 mm; iodine concentration 0-5 mgI/mL) and two sizes was used. One lesion emulated a subdiaphragmatic lesion. Both sizes were imaged in dual-energy mode on (1) a dual-source DECT (DS-DE) at 100/Sn150 kV and (2) a single-source split-filter DECT (SF-DE) at AuSn120 kV at two radiation doses (8 and 12 mGy). Scans were performed at seven different vertical table positions (from -6 to + 6 cm from the gantry isocenter). Iodine concentration was repeatedly measured and absolute errors (error abs ) were calculated. Errors were compared using robust repeated-measures ANOVAs with post-hoc comparisons. A linear mixed effect model was used to determine the factors influencing the error of DECT-IQ., Results: The linear mixed effect models showed that errors were significantly influenced by DECT approach, phantom size, and lesion location (all p < 0.001). The impact of lesion location on the error was stronger in SF-DE compared to DS-DE. Radiation dose did not significantly influence error (p = 0.22). When averaged across all setups, error abs was significantly higher for SF-DE (2.08 ± 1.92 mgI/mL) compared to DS-DE (0.37 ± 0.29 mgI/mL) (all p < 0.001). Artefacts were found in the subdiaphragmatic lesion for SF-DE with significantly increased error abs compared to DS-DE (p < 0.001). Error abs was significantly higher in the large compared to the medium phantom for DS-DE (0.30 ± 0.23 mgI/mL vs. 0.43 ± 0.33 mgI/mL) and SF-DE (1.68 ± 1.99 vs. 2.36 ± 1.81 mgI/mL) (p < 0.001)., Conclusion: The dual-energy approach, patient size, and lesion location modified by patient position significantly impacted DECT-IQ in simulated liver tumors., (Copyright © 2020 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.)

Background: In oncology, the correct determination of nodal metastatic disease is essential for patient management, as patient treatment and prognosis are closely linked to the stage of the disease. The aim of the study was to develop a tool for automatic 3D detection and segmentation of lymph nodes (LNs) in computed tomography (CT) scans of the thorax using a fully convolutional neural network based on 3D foveal patches., Methods: The training dataset was collected from the Computed Tomography Lymph Nodes Collection of the Cancer Imaging Archive, containing 89 contrast-enhanced CT scans of the thorax. A total number of 4275 LNs was segmented semi-automatically by a radiologist, assessing the entire 3D volume of the LNs. Using this data, a fully convolutional neuronal network based on 3D foveal patches was trained with fourfold cross-validation. Testing was performed on an unseen dataset containing 15 contrast-enhanced CT scans of patients who were referred upon suspicion or for staging of bronchial carcinoma., Results: The algorithm achieved a good overall performance with a total detection rate of 76.9% for enlarged LNs during fourfold cross-validation in the training dataset with 10.3 false-positives per volume and of 69.9% in the unseen testing dataset. In the training dataset a better detection rate was observed for enlarged LNs compared to smaller LNs, the detection rate for LNs with a short-axis diameter (SAD) ≥ 20 mm and SAD 5-10 mm being 91.6% and 62.2% (p < 0.001), respectively. Best detection rates were obtained for LNs located in Level 4R (83.6%) and Level 7 (80.4%)., Conclusions: The proposed 3D deep learning approach achieves an overall good performance in the automatic detection and segmentation of thoracic LNs and shows reasonable generalizability, yielding the potential to facilitate detection during routine clinical work and to enable radiomics research without observer-bias.

Radiomics may increase the diagnostic accuracy of medical imaging for localized and metastatic RCC (mRCC). A systematic review and meta-analysis was performed. Doing so, we comprehensively searched literature databases until May 2020. Studies investigating the diagnostic value of radiomics in differentiation of localized renal tumors and assessment of treatment response to ST in mRCC were included and assessed with respect to their quality using the radiomics quality score (RQS). A total of 113 out of 1098 identified studies met the criteria and were included in qualitative synthesis. Median RQS of all studies was 13.9% (5.0 points, IQR 0.25-7.0 points), and RQS increased over time. Thirty studies were included into the quantitative synthesis: For distinguishing angiomyolipoma, oncocytoma or unspecified benign tumors from RCC, the random effects model showed a log odds ratio (OR) of 2.89 (95%-CI 2.40-3.39, p < 0.001), 3.08 (95%-CI 2.09-4.06, p < 0.001) and 3.57 (95%-CI 2.69-4.45, p < 0.001), respectively. For the general discrimination of benign tumors from RCC log OR was 3.17 (95%-CI 2.73-3.62, p < 0.001). Inhomogeneity of the available studies assessing treatment response in mRCC prevented any meaningful meta-analysis. The application of radiomics seems promising for discrimination of renal tumor dignity. Shared data and open science may assist in improving reproducibility of future studies.

Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced mathematical analysis. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information by using analysis methods from the field of artificial intelligence. Various studies from different fields in imaging have been published so far, highlighting the potential of radiomics to enhance clinical decision-making. However, the field faces several important challenges, which are mainly caused by the various technical factors influencing the extracted radiomic features.The aim of the present review is twofold: first, we present the typical workflow of a radiomics analysis and deliver a practical "how-to" guide for a typical radiomics analysis. Second, we discuss the current limitations of radiomics, suggest potential improvements, and summarize relevant literature on the subject.

Objectives: To compare objective and subjective image quality of bronchial structures between a 512-pixel and a 1024-pixel image matrix for chest CT in phantoms and in patients., Materials and Methods: First, a two-size chest phantom was imaged at two radiation doses on a 192-slice CT scanner. Datasets were reconstructed with 512-, 768-, and 1024-pixel image matrices and a sharp reconstruction kernel (Bl64). Image sharpness and normalized noise power spectrum (nNPS) were quantified. Second, chest CT images of 100 patients were reconstructed with 512- and 1024-pixel matrices and two blinded readers independently assessed objective and subjective image quality. In each patient dataset, the highest number of visible bronchi was counted for each lobe of the right lung. A linear mixed effects model was applied in the phantom study and a Welch's t-test in the patient study., Results: Objective image sharpness and image noise increased with increasing matrix size and were highest for the 1024-matrix in phantoms and patients (all, P<0.001). nNPS was comparable among the three matrices. Objective image noise was on average 16% higher for the 1024-matrix compared to the 512-matrix in patients (P<0.0001). Subjective evaluation in patients yielded improved sharpness but increased image noise for the 1024- compared to the 512-matrix (both, P<0.001). There was no significant difference between highest-order visible bronchi (P>0.07) and the overall bronchial image quality between the two matrices (P>0.22)., Conclusion: Our study demonstrated superior image sharpness and higher image noise for a 1024- compared to a 512-pixel matrix, while there was no significant difference in the depiction and subjective image quality of bronchial structures for chest CT., Competing Interests: Dr. Friederike Schoeck is an employee of Siemens Healthcare GmbH. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. No funding or grant support was received for this study. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

Cardiac imaging plays an important role in the diagnosis of cardiovascular disease (CVD). Until now, its role has been limited to visual and quantitative assessment of cardiac structure and function. However, with the advent of big data and machine learning, new opportunities are emerging to build artificial intelligence tools that will directly assist the clinician in the diagnosis of CVDs. This paper presents a thorough review of recent works in this field and provide the reader with a detailed presentation of the machine learning methods that can be further exploited to enable more automated, precise and early diagnosis of most CVDs., (Copyright © 2020 Martin-Isla, Campello, Izquierdo, Raisi-Estabragh, Baeßler, Petersen and Lekadir.)

Machine learning (ML) is making a dramatic impact on cardiovascular magnetic resonance (CMR) in many ways. This review seeks to highlight the major areas in CMR where ML, and deep learning in particular, can assist clinicians and engineers in improving imaging efficiency, quality, image analysis and interpretation, as well as patient evaluation. We discuss recent developments in the field of ML relevant to CMR in the areas of image acquisition & reconstruction, image analysis, diagnostic evaluation and derivation of prognostic information. To date, the main impact of ML in CMR has been to significantly reduce the time required for image segmentation and analysis. Accurate and reproducible fully automated quantification of left and right ventricular mass and volume is now available in commercial products. Active research areas include reduction of image acquisition and reconstruction time, improving spatial and temporal resolution, and analysis of perfusion and myocardial mapping. Although large cohort studies are providing valuable data sets for ML training, care must be taken in extending applications to specific patient groups. Since ML algorithms can fail in unpredictable ways, it is important to mitigate this by open source publication of computational processes and datasets. Furthermore, controlled trials are needed to evaluate methods across multiple centers and patient groups.

Background: Data used for training of deep learning networks usually needs large amounts of accurate labels. These labels are usually extracted from reports using natural language processing or by time-consuming manual review. The aim of this study was therefore to develop and evaluate a workflow for using data from structured reports as labels to be used in a deep learning application., Materials and Methods: We included all plain anteriorposterior radiographs of the ankle for which structured reports were available. A workflow was designed and implemented where a script was used to automatically retrieve, convert, and anonymize the respective radiographs of cases where fractures were either present or absent from the institution's picture archiving and communication system (PACS). These images were then used to retrain a pretrained deep convolutional neural network. Finally, performance was evaluated on a set of previously unseen radiographs., Results: Once implemented and configured, completion of the whole workflow took under 1 h. A total of 157 structured reports were retrieved from the reporting platform. For all structured reports, corresponding radiographs were successfully retrieved from the PACS and fed into the training process. On an unseen validation subset, the model showed a satisfactory performance with an area under the curve of 0.850 (95% CI 0.634-1.000) for detection of fractures., Conclusion: We demonstrate that data obtained from structured reports written in clinical routine can be used to successfully train deep learning algorithms. This highlights the potential role of structured reporting for the future of radiology, especially in the context of deep learning.

The past few years have seen a considerable rise in interest towards artificial intelligence and machine learning applications in radiology. However, in order for such systems to perform adequately, large amounts of training data are required. These data should ideally be standardised and of adequate quality to allow for further usage in training of artificial intelligence algorithms. Unfortunately, in many current clinical and radiological information technology ecosystems, access to relevant pieces of information is difficult. This is mostly because a significant portion of information is handled as a collection of narrative texts and interoperability is still lacking. This review aims at giving a brief overview on how structured reporting can help to facilitate research in artificial intelligence and the context of big data.

Cardiovascular involvement is a well-known feature of inflammatory rheumatic diseases, although often clinically silent, so early cardiovascular involvement may remain unrecognised. Thus, increased awareness and improved insights into the pathomechanisms of heart disease in the context of inflammatory rheumatic disease has led to an emerging role of cardiovascular magnetic resonance (CMR) as an accurate and non-invasive diagnostic test for detection of early (as well as late) cardiovascular involvement in inflammatory rheumatic disease. The present article will review the current potential as well as the limitations of established and emerging, qualitative and quantitative CMR techniques in the setting of inflammatory rheumatic disease and shed some light onto current developments in the field.

Polycystic kidney disease (PKD) is among the leading causes of end-stage renal disease. Increasing evidence exists that molecular therapeutic strategies targeted to cyst formation and growth might be more efficacious in early disease stages, highlighting the growing need for sensitive biomarkers. Here we apply quantitative magnetic resonance imaging techniques of T2 mapping and diffusion-weighted imaging in the jck mouse model for PKD using a clinical 3.0 T scanner. We tested whether kidney T2 values and the apparent diffusion coefficient (ADC) are superior to anatomical imaging parameters in the detection of early cystogenesis, as shown on macro- and histopathology. We also tested whether kidney T2 values and ADC have the potential to monitor early treatment effects of therapy with the V2 receptor antagonist Mozavaptane. Kidney T2 values and to a lesser degree ADC were found to be highly sensitive markers of early cystogenesis and superior to anatomical-based imaging parameters. Furthermore, kidney T2 values exhibited a nearly perfect correlation to the histological cystic index, allowing a clear separation of the two mouse genotypes. Additionally, kidney T2 values and ADC were able to monitor early treatment effects in the jck mouse model in a proof-of-principle experiment. Thus, given the superiority of kidney T2 values and ADC over anatomical-based imaging in mice, further studies are needed to evaluate the translational impact of these techniques in patients with PKD., (Copyright © 2017 International Society of Nephrology. Published by Elsevier Inc. All rights reserved.)

Background: The aim of this study was to evaluate the diagnostic potential of a novel cardiovascular magnetic resonance (CMR) based multiparametric imaging approach in suspected myocarditis and to compare it to traditional Lake Louise criteria (LLC)., Methods: CMR data from 67 patients with suspected acute myocarditis were retrospectively analyzed. Seventeen age- and gender-matched healthy subjects served as control. T2-mapping data were acquired using a Gradient-Spin-Echo T2-mapping sequence in short-axis orientation. T2-maps were segmented according to the 16-segments AHA-model and segmental T2 values and pixel-standard deviation (SD) were recorded. Afterwards, the parameters maxT2 (the highest segmental T2 value) and madSD (the mean absolute deviation (MAD) of the pixel-SDs) were calculated for each subject. Cine sequences in three long axes and a stack of short-axis views covering the left and right ventricle were analyzed using a dedicated feature tracking algorithm., Results: A multiparametric imaging model containing madSD and LV global circumferential strain (GCS LV ) resulted in the highest diagnostic performance in receiver operating curve analyses (area under the curve [AUC] 0.84) when compared to any model containing a single imaging parameter or to LLC (AUC 0.79). Adding late gadolinium enhancement (LGE) to the model resulted in a further increased diagnostic performance (AUC 0.93) and yielded the highest diagnostic sensitivity of 97% and specificity of 77%., Conclusions: A multiparametric CMR imaging model including the novel T2-mapping derived parameter madSD, the feature tracking derived strain parameter GCS LV and LGE yields superior diagnostic sensitivity in suspected acute myocarditis when compared to any imaging parameter alone and to LLC.

Background: Radiological imaging plays an important role in the setting of staging, follow-up, and imaging-guided treatment of colorectal carcinoma (CRC)., Methods: This review aims to summarize the current state of the art of the different radiological imaging procedures in CRC including an overview over recently published national and European guidelines and consensus statements concerning the imaging of CRC patients., Results and Conclusion: Radiological imaging is widely embedded in national and international guidelines, and structured reporting is recommended.

Background: The purpose of the present study was to investigate the diagnostic value of T2-mapping in acute myocarditis (ACM) and to define cut-off values for edema detection., Methods: Cardiovascular magnetic resonance (CMR) data of 31 patients with ACM were retrospectively analyzed. 30 healthy volunteers (HV) served as a control. Additionally to the routine CMR protocol, T2-mapping data were acquired at 1.5 T using a breathhold Gradient-Spin-Echo T2-mapping sequence in six short axis slices. T2-maps were segmented according to the 16-segments AHA-model and segmental T2 values as well as the segmental pixel-standard deviation (SD) were analyzed., Results: Mean differences of global myocardial T2 or pixel-SD between HV and ACM patients were only small, lying in the normal range of HV. In contrast, variation of segmental T2 values and pixel-SD was much larger in ACM patients compared to HV. In random forests and multiple logistic regression analyses, the combination of the highest segmental T2 value within each patient (maxT2) and the mean absolute deviation (MAD) of log-transformed pixel-SD (madSD) over all 16 segments within each patient proved to be the best discriminators between HV and ACM patients with an AUC of 0.85 in ROC-analysis. In classification trees, a combined cut-off of 0.22 for madSD and of 68 ms for maxT2 resulted in 83% specificity and 81% sensitivity for detection of ACM., Conclusions: The proposed cut-off values for maxT2 and madSD in the setting of ACM allow edema detection with high sensitivity and specificity and therefore have the potential to overcome the hurdles of T2-mapping for its integration into clinical routine.

Background: The aim of this study was the evaluation of a fast Gradient Spin Echo Technique (GraSE) for cardiac T2-mapping, combining a robust estimation of T2 relaxation times with short acquisition times. The sequence was compared against two previously introduced T2-mapping techniques in a phantom and in vivo., Methods: Phantom experiments were performed at 1.5 T using a commercially available cylindrical gel phantom. Three different T2-mapping techniques were compared: a Multi Echo Spin Echo (MESE; serving as a reference), a T2-prepared balanced Steady State Free Precession (T2prep) and a Gradient Spin Echo sequence. For the subsequent in vivo study, 12 healthy volunteers were examined on a clinical 1.5 T scanner. The three T2-mapping sequences were performed at three short-axis slices. Global myocardial T2 relaxation times were calculated and statistical analysis was performed. For assessment of pixel-by-pixel homogeneity, the number of segments showing an inhomogeneous T2 value distribution, as defined by a pixel SD exceeding 20 % of the corresponding observed T2 time, was counted., Results: Phantom experiments showed a greater difference of measured T2 values between T2prep and MESE than between GraSE and MESE, especially for species with low T1 values. Both, GraSE and T2prep resulted in an overestimation of T2 times compared to MESE. In vivo, significant differences between mean T2 times were observed. In general, T2prep resulted in lowest (52.4 ± 2.8 ms) and GraSE in highest T2 estimates (59.3 ± 4.0 ms). Analysis of pixel-by-pixel homogeneity revealed the least number of segments with inhomogeneous T2 distribution for GraSE-derived T2 maps., Conclusions: The GraSE sequence is a fast and robust sequence, combining advantages of both MESE and T2prep techniques, which promises to enable improved clinical applicability of T2-mapping in the future. Our study revealed significant differences of derived mean T2 values when applying different sequence designs. Therefore, a systematic comparison of different cardiac T2-mapping sequences and the establishment of dedicated reference values should be the goal of future studies.