Radiological age assessment based on clavicle ossification in CT: enhanced accuracy through deep learning.

BACKGROUND: Radiological age assessment using reference studies is inherently limited in accuracy due to a finite number of assignable skeletal maturation stages. To overcome this limitation, we present a deep learning approach for continuous age assessment based on clavicle ossification in computed tomography (CT). METHODS: Thoracic CT scans were retrospectively collected from the picture archiving and communication system. Individuals aged 15.0 to 30.0 years examined in routine clinical practice were included. All scans were automatically cropped around the medial clavicular epiphyseal cartilages. A deep learning model was trained to predict a person's chronological age based on these scans. Performance was evaluated using mean absolute error (MAE). Model performance was compared to an optimistic human reader performance estimate for an established reference study method. RESULTS: The deep learning model was trained on 4,400 scans of 1,935 patients (training set: mean age = 24.2 years ± 4.0, 1132 female) and evaluated on 300 scans of 300 patients with a balanced age and sex distribution (test set: mean age = 22.5 years ± 4.4, 150 female). Model MAE was 1.65 years, and the highest absolute error was 6.40 years for females and 7.32 years for males. However, performance could be attributed to norm-variants or pathologic disorders. Human reader estimate MAE was 1.84 years and the highest absolute error was 3.40 years for females and 3.78 years for males. CONCLUSIONS: We present a deep learning approach for continuous age predictions using CT volumes highlighting the medial clavicular epiphyseal cartilage with performance comparable to the human reader estimate.

Artificial Intelligence in Oncological Hybrid Imaging.

BACKGROUND: Artificial intelligence (AI) applications have become increasingly relevant across a broad spectrum of settings in medical imaging. Due to the large amount of imaging data that is generated in oncological hybrid imaging, AI applications are desirable for lesion detection and characterization in primary staging, therapy monitoring, and recurrence detection. Given the rapid developments in machine learning (ML) and deep learning (DL) methods, the role of AI will have significant impact on the imaging workflow and will eventually improve clinical decision making and outcomes. METHODS AND RESULTS: The first part of this narrative review discusses current research with an introduction to artificial intelligence in oncological hybrid imaging and key concepts in data science. The second part reviews relevant examples with a focus on applications in oncology as well as discussion of challenges and current limitations. CONCLUSION: AI applications have the potential to leverage the diagnostic data stream with high efficiency and depth to facilitate automated lesion detection, characterization, and therapy monitoring to ultimately improve quality and efficiency throughout the medical imaging workflow. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based therapy guidance in oncology. However, significant challenges remain regarding application development, benchmarking, and clinical implementation. KEY POINTS: · Hybrid imaging generates a large amount of multimodality medical imaging data with high complexity and depth.. · Advanced tools are required to enable fast and cost-efficient processing along the whole radiology value chain.. · AI applications promise to facilitate the assessment of oncological disease in hybrid imaging with high quality and efficiency for lesion detection, characterization, and response assessment. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based oncological therapy guidance.. · Selected applications in three oncological entities (lung, prostate, and neuroendocrine tumors) demonstrate how AI algorithms may impact imaging-based tasks in hybrid imaging and potentially guide clinical decision making..

ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports.

OBJECTIVES: To assess the quality of simplified radiology reports generated with the large language model (LLM) ChatGPT and to discuss challenges and chances of ChatGPT-like LLMs for medical text simplification. METHODS: In this exploratory case study, a radiologist created three fictitious radiology reports which we simplified by prompting ChatGPT with "Explain this medical report to a child using simple language." In a questionnaire, we tasked 15 radiologists to rate the quality of the simplified radiology reports with respect to their factual correctness, completeness, and potential harm for patients. We used Likert scale analysis and inductive free-text categorization to assess the quality of the simplified reports. RESULTS: Most radiologists agreed that the simplified reports were factually correct, complete, and not potentially harmful to the patient. Nevertheless, instances of incorrect statements, missed relevant medical information, and potentially harmful passages were reported. CONCLUSION: While we see a need for further adaption to the medical field, the initial insights of this study indicate a tremendous potential in using LLMs like ChatGPT to improve patient-centered care in radiology and other medical domains. CLINICAL RELEVANCE STATEMENT: Patients have started to use ChatGPT to simplify and explain their medical reports, which is expected to affect patient-doctor interaction. This phenomenon raises several opportunities and challenges for clinical routine. KEY POINTS: • Patients have started to use ChatGPT to simplify their medical reports, but their quality was unknown. • In a questionnaire, most participating radiologists overall asserted good quality to radiology reports simplified with ChatGPT. However, they also highlighted a notable presence of errors, potentially leading patients to draw harmful conclusions. • Large language models such as ChatGPT have vast potential to enhance patient-centered care in radiology and other medical domains. To realize this potential while minimizing harm, they need supervision by medical experts and adaption to the medical field.

Integration of clinical parameters and CT-based radiomics improves machine learning assisted subtyping of primary hyperaldosteronism.

Objectives: The aim of this study was to investigate an integrated diagnostics approach for prediction of the source of aldosterone overproduction in primary hyperaldosteronism (PA). Methods: 269 patients from the prospective German Conn Registry with PA were included in this study. After segmentation of adrenal glands in native CT images, radiomic features were calculated. The study population consisted of a training (n = 215) and a validation (n = 54) cohort. The k = 25 best radiomic features, selected using maximum-relevance minimum-redundancy (MRMR) feature selection, were used to train a baseline random forest model to predict the result of AVS from imaging alone. In a second step, clinical parameters were integrated. Model performance was assessed via area under the receiver operating characteristic curve (ROC AUC). Permutation feature importance was used to assess the predictive value of selected features. Results: Radiomics features alone allowed only for moderate discrimination of the location of aldosterone overproduction with a ROC AUC of 0.57 for unilateral left (UL), 0.61 for unilateral right (UR), and 0.50 for bilateral (BI) aldosterone overproduction (total 0.56, 95% CI: 0.45-0.65). Integration of clinical parameters into the model substantially improved ROC AUC values (0.61 UL, 0.68 UR, and 0.73 for BI, total 0.67, 95% CI: 0.57-0.77). According to permutation feature importance, lowest potassium value at baseline and saline infusion test (SIT) were the two most important features. Conclusion: Integration of clinical parameters into a radiomics machine learning model improves prediction of the source of aldosterone overproduction and subtyping in patients with PA.

A Comprehensive Machine Learning Benchmark Study for Radiomics-Based Survival Analysis of CT Imaging Data in Patients With Hepatic Metastases of CRC.

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.

Automated localization of the medial clavicular epiphyseal cartilages using an object detection network: a step towards deep learning-based forensic age assessment.

BACKGROUND: Deep learning is a promising technique to improve radiological age assessment. However, expensive manual annotation by experts poses a bottleneck for creating large datasets to appropriately train deep neural networks. We propose an object detection approach to automatically annotate the medial clavicular epiphyseal cartilages in computed tomography (CT) scans. METHODS: The sternoclavicular joints were selected as structure-of-interest (SOI) in chest CT scans and served as an easy-to-identify proxy for the actual medial clavicular epiphyseal cartilages. CT slices containing the SOI were manually annotated with bounding boxes around the SOI. All slices in the training set were used to train the object detection network RetinaNet. Afterwards, the network was applied individually to all slices of the test scans for SOI detection. Bounding box and slice position of the detection with the highest classification score were used as the location estimate for the medial clavicular epiphyseal cartilages inside the CT scan. RESULTS: From 100 CT scans of 82 patients, 29,656 slices were used for training and 30,846 slices from 110 CT scans of 110 different patients for testing the object detection network. The location estimate from the deep learning approach for the SOI was in a correct slice in 97/110 (88%), misplaced by one slice in 5/110 (5%), and missing in 8/110 (7%) test scans. No estimate was misplaced by more than one slice. CONCLUSIONS: We demonstrated a robust automated approach for annotating the medial clavicular epiphyseal cartilages. This enables training and testing of deep neural networks for age assessment.

Artificial Intelligence in Oncological Hybrid Imaging.

BACKGROUND: Artificial intelligence (AI) applications have become increasingly relevant across a broad spectrum of settings in medical imaging. Due to the large amount of imaging data that is generated in oncological hybrid imaging, AI applications are desirable for lesion detection and characterization in primary staging, therapy monitoring, and recurrence detection. Given the rapid developments in machine learning (ML) and deep learning (DL) methods, the role of AI will have significant impact on the imaging workflow and will eventually improve clinical decision making and outcomes. METHODS AND RESULTS: The first part of this narrative review discusses current research with an introduction to artificial intelligence in oncological hybrid imaging and key concepts in data science. The second part reviews relevant examples with a focus on applications in oncology as well as discussion of challenges and current limitations. CONCLUSION: AI applications have the potential to leverage the diagnostic data stream with high efficiency and depth to facilitate automated lesion detection, characterization, and therapy monitoring to ultimately improve quality and efficiency throughout the medical imaging workflow. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based therapy guidance in oncology. However, significant challenges remain regarding application development, benchmarking, and clinical implementation. KEY POINTS: · Hybrid imaging generates a large amount of multimodality medical imaging data with high complexity and depth.. · Advanced tools are required to enable fast and cost-efficient processing along the whole radiology value chain.. · AI applications promise to facilitate the assessment of oncological disease in hybrid imaging with high quality and efficiency for lesion detection, characterization, and response assessment. The goal is to generate reproducible, structured, quantitative diagnostic data for evidence-based oncological therapy guidance.. · Selected applications in three oncological entities (lung, prostate, and neuroendocrine tumors) demonstrate how AI algorithms may impact imaging-based tasks in hybrid imaging and potentially guide clinical decision making.. CITATION FORMAT: · Feuerecker B, Heimer M, Geyer T et al. Artificial Intelligence in Oncological Hybrid Imaging. Fortschr Röntgenstr 2023; 195: 105 - 114.

Performance variability of radiomics machine learning models for the detection of clinically significant prostate cancer in heterogeneous MRI datasets.

Background: Radiomics promises to enhance the discriminative performance for clinically significant prostate cancer (csPCa), but still lacks validation in real-life scenarios. This study investigates the classification performance and robustness of machine learning radiomics models in heterogeneous MRI datasets to characterize suspicious prostate lesions for non-invasive prediction of prostate cancer (PCa) aggressiveness compared to conventional imaging biomarkers. Methods: A total of 142 patients with clinical suspicion of PCa underwent 1.5T or 3T biparametric MRI (7 scanner types, 14 institutions) and exhibited suspicious lesions [prostate Imaging Reporting and Data System (PI-RADS) score ≥3] in peripheral or transitional zones. Whole-gland and index-lesion segmentations were performed semi-automatically. A total of 1,482 quantitative morphologic, shape, texture, and intensity-based radiomics features were extracted from T2-weighted and apparent diffusion coefficient (ADC)-images and assessed using random forest and logistic regression models. Five-fold cross-validation performance in terms of area under the ROC curve was compared to mean ADC (mADC), PI-RADS and prostate-specific antigen density (PSAD). Bias mitigation techniques targeting the high-dimensional feature space and inherent class imbalance were applied and robustness of results was systematically evaluated. Results: Trained models showed mean area under the curves (AUCs) ranging from 0.78 to 0.83 in csPCa classification. Despite using mitigation techniques, high performance variability of results could be demonstrated. Trained models achieved on average numerically higher classification performance compared to clinical parameters PI-RADS (AUC =0.78), mADC (AUC =0.71) and PSAD (AUC =0.63). Conclusions: Radiomics models' classification performance of csPCa was numerically but not significantly higher than PI-RADS scoring. Overall, clinical applicability in heterogeneous MRI datasets is limited because of high variability of results. Performance variability, robustness and reproducibility of radiomics-based measures should be addressed more transparently in future research to enable broad clinical application.

Clinically focused multi-cohort benchmarking as a tool for external validation of artificial intelligence algorithm performance in basic chest radiography analysis.

Artificial intelligence (AI) algorithms evaluating [supine] chest radiographs ([S]CXRs) have remarkably increased in number recently. Since training and validation are often performed on subsets of the same overall dataset, external validation is mandatory to reproduce results and reveal potential training errors. We applied a multicohort benchmarking to the publicly accessible (S)CXR analyzing AI algorithm CheXNet, comprising three clinically relevant study cohorts which differ in patient positioning ([S]CXRs), the applied reference standards (CT-/[S]CXR-based) and the possibility to also compare algorithm classification with different medical experts' reading performance. The study cohorts include [1] a cohort, characterized by 563 CXRs acquired in the emergency unit that were evaluated by 9 readers (radiologists and non-radiologists) in terms of 4 common pathologies, [2] a collection of 6,248 SCXRs annotated by radiologists in terms of pneumothorax presence, its size and presence of inserted thoracic tube material which allowed for subgroup and confounding bias analysis and [3] a cohort consisting of 166 patients with SCXRs that were evaluated by radiologists for underlying causes of basal lung opacities, all of those cases having been correlated to a timely acquired computed tomography scan (SCXR and CT within < 90 min). CheXNet non-significantly exceeded the radiology resident (RR) consensus in the detection of suspicious lung nodules (cohort [1], AUC AI/RR: 0.851/0.839, p = 0.793) and the radiological readers in the detection of basal pneumonia (cohort [3], AUC AI/reader consensus: 0.825/0.782, p = 0.390) and basal pleural effusion (cohort [3], AUC AI/reader consensus: 0.762/0.710, p = 0.336) in SCXR, partly with AUC values higher than originally published ("Nodule": 0.780, "Infiltration": 0.735, "Effusion": 0.864). The classifier "Infiltration" turned out to be very dependent on patient positioning (best in CXR, worst in SCXR). The pneumothorax SCXR cohort [2] revealed poor algorithm performance in CXRs without inserted thoracic material and in the detection of small pneumothoraces, which can be explained by a known systematic confounding error in the algorithm training process. The benefit of clinically relevant external validation is demonstrated by the differences in algorithm performance as compared to the original publication. Our multi-cohort benchmarking finally enables the consideration of confounders, different reference standards and patient positioning as well as the AI performance comparison with differentially qualified medical readers.

End-to-End Deep Learning Approach for Perfusion Data: A Proof-of-Concept Study to Classify Core Volume in Stroke CT.

(1) Background: CT perfusion (CTP) is used to quantify cerebral hypoperfusion in acute ischemic stroke. Conventional attenuation curve analysis is not standardized and might require input from expert users, hampering clinical application. This study aims to bypass conventional tracer-kinetic analysis with an end-to-end deep learning model to directly categorize patients by stroke core volume from raw, slice-reduced CTP data. (2) Methods: In this retrospective analysis, we included patients with acute ischemic stroke due to proximal occlusion of the anterior circulation who underwent CTP imaging. A novel convolutional neural network was implemented to extract spatial and temporal features from time-resolved imaging data. In a classification task, the network categorized patients into small or large core. In ten-fold cross-validation, the network was repeatedly trained, evaluated, and tested, using the area under the receiver operating characteristic curve (ROC-AUC). A final model was created in an ensemble approach and independently validated on an external dataset. (3) Results: 217 patients were included in the training cohort and 23 patients in the independent test cohort. Median core volume was 32.4 mL and was used as threshold value for the binary classification task. Model performance yielded a mean (SD) ROC-AUC of 0.72 (0.10) for the test folds. External independent validation resulted in an ensembled mean ROC-AUC of 0.61. (4) Conclusions: In this proof-of-concept study, the proposed end-to-end deep learning approach bypasses conventional perfusion analysis and allows to predict dichotomized infarction core volume solely from slice-reduced CTP images without underlying tracer kinetic assumptions. Further studies can easily extend to additional clinically relevant endpoints.

Nationwide Provision of Radiologically-guided Interventional Measures for the Supportive Treatment of Tumor Diseases in Germany - An Analysis of the DeGIR Registry Data. / Flächendeckende Versorgung mit radiologisch-interventionellen supportiven Maßnahmen bei Tumorerkrankungen und anderen Erkrankungen (DeGIR-Modul C) in Deutschland ­ Eine Analyse der DeGIR-Registerdaten.

PURPOSE: In addition to direct oncologic therapy, interventional radiology plays an important supportive role in oncologic therapy primarily guided by other disciplines. These supporting measures include diagnostic punctures, drainages, biliary interventions, central venous access including port implantations, osteoplasties, pain therapies etc.). This study investigated the extent to which these radiologically guided supportive measures are available in Germany. MATERIAL AND METHODS: All interventional procedures documented in the DeGIR-registry (excluding transhepatic portosystemic shunts) of the years 2018 and 2019 were recorded (DeGIR-module C). A breakdown of the documented interventions was performed based on federal states as well as 40 individual regions (administrative districts and former administrative districts). RESULTS: A total of 136,328 procedures were recorded at 216 centers in DeGIR Module C in 2018 and 2019. On average, 389 cases were documented per hospital in 2018 and 394 cases in 2019; the increase per hospital from 2019 is not statistically significant but is relevant in the aggregate when new participating centers are included, with an overall increase of 10 % (6,554 more cases than the previous year). Normalized to one million inhabitants, an average of 781 procedures took place across Germany in 2018 and 860 in 2019. Districts with no registered procedures are not found for Module C.Indications for Module C interventions were mostly interdisciplinary in 2018 and 2019. In this context, the quality of outcome was very high; for the procedures drain placement, marking and biopsy the technical success was 99 %, while the complication rate was lower than 1 %. CONCLUSION: The structural analysis of this work concludes that in Germany there is good nationwide availability of radiologically guided supportive measures in oncological therapy. Accordingly, the training situation for prospective interventional radiologists is good, as the distribution to centers with high experience is excellent. In addition, the overall outcome quality of radiology-guided interventions is very high. KEY POINTS: · In Germany, there is good nationwide coverage of radiologically guided supportive interventions in oncological therapy.. · The training situation for prospective interventional radiologists is good, as the distribution to centers with high experience is excellent.. · The overall outcome quality of radiology-guided interventions is very high.. CITATION FORMAT: · Nadjiri J, Schachtner B, Bücker A et al. Nationwide Provision of Radiologically-guided Interventional Measures for the Supportive Treatment of Tumor Diseases in Germany - An Analysis of the DeGIR Registry Data. Fortschr Röntgenstr 2022; 194: 993 - 1002.

Availability of Interventional Oncology in Germany in the Years 2018 and 2019 - Results from a Nationwide Database (DeGIR Registry Data). / Flächendeckende Versorgung mit radiologisch durchgeführten Verfahren zur interventionell-onkologischen Tumortherapie in Deutschland in den Jahren 2018 und 2019 dargestellt anhand der DeGIR-Registerdaten.

OBJECTIVE: Over the past few decades, radiology has established itself in tumor therapy through interventional oncology including innovative and efficient procedures for minimalinvasive treatment of various tumor entities besides the "classic" therapeutic options such as surgery, chemotherapy and radiotherapy.Aim of this study was to evaluate the extent to which interventional oncology can provide nationwide care using the data from the register of the German Society for Interventional Radiology and Minimally Invasive Therapy (DeGIR registry), which records radiological interventions as part of quality assurance. METHODS: The numbers of interventions of participating clinics, which were recorded as part of module D (oncological procedures including TACE or other tumor-specific embolization, ablation, percutaneous tumor therapy) and identified by the DeGIR registry between 2018 and 2019, were analyzed retrospectively. The collected intervention data were evaluated regarding federal states and 40 smaller regions (administrative districts and former administrative districts). RESULTS: In 2018, 11 653 oncological interventions in 187 clinics were recorded by the DeGIR registry. In 2019, the number of participating clinics rose to 216 and the number of oncological interventions increased by 6 % to 12 323. The average number of oncological interventions per clinic decreased slightly from 62.5 (2018) to 57.1 (2019). The DeGIR requirement for being certified as a training center was met by 116 clinics in 2018 including 31 clinics with more than 100 interventions and 129 clinics in 2019 including 36 with more than 100 interventions. Oncological interventions have been performed in each of the 40 regions. An average of 599 interventions per region (standard deviation of 414) was recorded in the period between 2018 and 2019. CONCLUSION: Based on the distribution of the documented oncological interventions at federal state level as well as the district level, the supply of interventional tumor therapy depends on the geographical location. Therefore, the demand of oncological interventions might not be sufficiently covered in some regions. KEY POINTS: · Interventional-oncological tumor therapies are performed throughout Germany. · Looking at the notable geographical differences, the need for interventional oncological procedures does not seem to be sufficiently met.. · In order to improve the comprehensive provision of oncological interventions, the training of interventional radiologists should be promoted further.. CITATION FORMAT: · Radosa CG, Nadjiri J, Mahnken AH et al. Availability of Interventional Oncology in Germany in the Years 2018 and 2019 - Results from a Nationwide Database (DeGIR Registry Data). Fortschr Röntgenstr 2022; 194: 755 - 761.

Deep learning in CT colonography: differentiating premalignant from benign colorectal polyps.

OBJECTIVES: To investigate the differentiation of premalignant from benign colorectal polyps detected by CT colonography using deep learning. METHODS: In this retrospective analysis of an average risk colorectal cancer screening sample, polyps of all size categories and morphologies were manually segmented on supine and prone CT colonography images and classified as premalignant (adenoma) or benign (hyperplastic polyp or regular mucosa) according to histopathology. Two deep learning models SEG and noSEG were trained on 3D CT colonography image subvolumes to predict polyp class, and model SEG was additionally trained with polyp segmentation masks. Diagnostic performance was validated in an independent external multicentre test sample. Predictions were analysed with the visualisation technique Grad-CAM++. RESULTS: The training set consisted of 107 colorectal polyps in 63 patients (mean age: 63 ± 8 years, 40 men) comprising 169 polyp segmentations. The external test set included 77 polyps in 59 patients comprising 118 polyp segmentations. Model SEG achieved a ROC-AUC of 0.83 and 80% sensitivity at 69% specificity for differentiating premalignant from benign polyps. Model noSEG yielded a ROC-AUC of 0.75, 80% sensitivity at 44% specificity, and an average Grad-CAM++ heatmap score of ≥ 0.25 in 90% of polyp tissue. CONCLUSIONS: In this proof-of-concept study, deep learning enabled the differentiation of premalignant from benign colorectal polyps detected with CT colonography and the visualisation of image regions important for predictions. The approach did not require polyp segmentation and thus has the potential to facilitate the identification of high-risk polyps as an automated second reader. KEY POINTS: • Non-invasive deep learning image analysis may differentiate premalignant from benign colorectal polyps found in CT colonography scans. • Deep learning autonomously learned to focus on polyp tissue for predictions without the need for prior polyp segmentation by experts. • Deep learning potentially improves the diagnostic accuracy of CT colonography in colorectal cancer screening by allowing for a more precise selection of patients who would benefit from endoscopic polypectomy, especially for patients with polyps of 6-9 mm size.

Availability of interventional-radiological revascularization procedures in Germany - an analysis of the DeGIR Registry Data 2018/19. / Versorgungslage mit interventionell-radiologischer Gefäßrevaskularisation in Deutschland ­ eine Analyse der DEGIR-Registerdaten 2018/19.

PURPOSE: Peripheral artery disease (PAD) is a common condition with high socio-economic relevance. Therefore, qualified nationwide provision of interventional treatments of PAD is important for maintaining a high quality medical service in Germany. MATERIALS AND METHODS: All data on revascularization procedures from the quality management system of the German interventional radiological society (DeGIR) for the years 2018 and 2019 were retrospectively analysed. Number and distribution of DeGIR certified endovascular specialists and treatment centres was mapped. Documented procedures were broken down to the level of administrative districts. Absolute number of revascularization procedures and normalized number per one million inhabitants were computed. RESULTS: In 2019 there were 57 732 revascularization procedures from 228 participating centres performed by DeGIR certified interventional radiologists. A median of 62 recanalization procedures were documented per centre. 36 centres were considered to be high volume centres, with more than 500 procedures each. On a regional level in the years 2018 and 2019 combined a median (range) of 2324 (323-12 518) revascularization procedures per administrative district were performed by DeGIR certified interventional radiologist. CONCLUSION: There is a comprehensive nationwide high quality interventional-radiology service for the provision of revascularization procedures available in Germany. KEY POINTS: · In Germany there is a nationwide comprehensive infratsructure for the interventional-radiological treatment of PAD. · The volume of interventional-radiological treatments for PAD is growing. · There is a sufficient number of training and treatment centres for the delivery of interventional radiology procedures. CITATION FORMAT: · Mahnken AH, Nadjiri J, Schachtner B et al. Availability of interventional-radiological revascularization procedures in Germany - an analysis of the DeGIR Registry Data 2018/19. Fortschr Röntgenstr 2022; 194: 160 - 168.

Pneumothorax detection in chest radiographs: optimizing artificial intelligence system for accuracy and confounding bias reduction using in-image annotations in algorithm training.

OBJECTIVES: Diagnostic accuracy of artificial intelligence (AI) pneumothorax (PTX) detection in chest radiographs (CXR) is limited by the noisy annotation quality of public training data and confounding thoracic tubes (TT). We hypothesize that in-image annotations of the dehiscent visceral pleura for algorithm training boosts algorithm's performance and suppresses confounders. METHODS: Our single-center evaluation cohort of 3062 supine CXRs includes 760 PTX-positive cases with radiological annotations of PTX size and inserted TTs. Three step-by-step improved algorithms (differing in algorithm architecture, training data from public datasets/clinical sites, and in-image annotations included in algorithm training) were characterized by area under the receiver operating characteristics (AUROC) in detailed subgroup analyses and referenced to the well-established "CheXNet" algorithm. RESULTS: Performances of established algorithms exclusively trained on publicly available data without in-image annotations are limited to AUROCs of 0.778 and strongly biased towards TTs that can completely eliminate algorithm's discriminative power in individual subgroups. Contrarily, our final "algorithm 2" which was trained on a lower number of images but additionally with in-image annotations of the dehiscent pleura achieved an overall AUROC of 0.877 for unilateral PTX detection with a significantly reduced TT-related confounding bias. CONCLUSIONS: We demonstrated strong limitations of an established PTX-detecting AI algorithm that can be significantly reduced by designing an AI system capable of learning to both classify and localize PTX. Our results are aimed at drawing attention to the necessity of high-quality in-image localization in training data to reduce the risks of unintentionally biasing the training process of pathology-detecting AI algorithms. KEY POINTS: • Established pneumothorax-detecting artificial intelligence algorithms trained on public training data are strongly limited and biased by confounding thoracic tubes. • We used high-quality in-image annotated training data to effectively boost algorithm performance and suppress the impact of confounding thoracic tubes. • Based on our results, we hypothesize that even hidden confounders might be effectively addressed by in-image annotations of pathology-related image features.

Joint Imaging Platform for Federated Clinical Data Analytics.

PURPOSE: Image analysis is one of the most promising applications of artificial intelligence (AI) in health care, potentially improving prediction, diagnosis, and treatment of diseases. Although scientific advances in this area critically depend on the accessibility of large-volume and high-quality data, sharing data between institutions faces various ethical and legal constraints as well as organizational and technical obstacles. METHODS: The Joint Imaging Platform (JIP) of the German Cancer Consortium (DKTK) addresses these issues by providing federated data analysis technology in a secure and compliant way. Using the JIP, medical image data remain in the originator institutions, but analysis and AI algorithms are shared and jointly used. Common standards and interfaces to local systems ensure permanent data sovereignty of participating institutions. RESULTS: The JIP is established in the radiology and nuclear medicine departments of 10 university hospitals in Germany (DKTK partner sites). In multiple complementary use cases, we show that the platform fulfills all relevant requirements to serve as a foundation for multicenter medical imaging trials and research on large cohorts, including the harmonization and integration of data, interactive analysis, automatic analysis, federated machine learning, and extensibility and maintenance processes, which are elementary for the sustainability of such a platform. CONCLUSION: The results demonstrate the feasibility of using the JIP as a federated data analytics platform in heterogeneous clinical information technology and software landscapes, solving an important bottleneck for the application of AI to large-scale clinical imaging data.

Availability of Transcatheter Vessel Occlusion Performed by Interventional Radiologists to Treat Bleeding in Germany in the Years 2016 and 2017 - An Analysis of the DeGIR Registry Data. / Flächendeckende Versorgung mit radiologisch durchgeführten gefäßverschließenden Maßnahmen zur interventionellen Behandlung von Blutungen in Deutschland in den Jahren 2016 und 2017 ­ Eine Analyse der DeGIR-Registerdaten.

PURPOSE: Acute bleeding is a life-threatening condition that can be effectively treated minimally invasively by interventional radiologists using transcatheter vessel occlusion (TCVO). The purpose of this study was to evaluate the availability of TCVO performed by interventional radiologists in Germany based on the DeGIR registry. MATERIALS AND METHODS: TCVO interventions from the years 2016 and 2017 were included (DeGIR module B). The number of interventions was assessed by state and region. RESULTS: TCVO interventions were reported by 242 clinics in Germany. 16 763 module B interventions were reported in 2016 and 16 399 in 2017. DeGIR requirements for certification as a training center were fulfilled by 160 facilities in 2016 and by 162 facilities in 2017. Normalized to one million citizens, an average of 211 TCVO interventions were performed in 2016 and 200 in 2017 (standard deviation was 101 and 109); the median was 202 and 222, respectively. In all regions TCVO interventions were reported. Only a minimal number of small regions showed a lower number of clinics offering TCVO interventions. CONCLUSION: The results from the DeGIR registry indicate comprehensive nationwide availability of TCVO performed by interventional radiologists with the necessary experience in Germany on the state level for the treatment of acute bleeding. Furthermore, the distribution of facilities fulfilling the requirements of training centers allows for good educational possibilities for young interventional radiologists in Germany. Only the distribution of clinics offering TCVO in a few small regions might lead to increased transfer times in the case of acute bleeding. KEY POINTS: · As a treatment for life-threatening acute bleeding in Germany, transcatheter vessel occlusion led by interventional radiologists is readily available on the state level.. · Furthermore, the distribution of facilities fulfilling the requirements of training centers allows for good educational possibilities for young interventional radiologists in Germany.. · Due to the good training conditions in Germany, it might be possible to further improve the situation in smaller regions by training more interventional radiologists and employing them in regions with less coverage.. CITATION FORMAT: · Nadjiri J, Schachtner B, Bücker A et al. Availability of Transcatheter Vessel Occlusion Performed by Interventional Radiologists to Treat Bleeding in Germany in the Years 2016 and 2017 - An Analysis of the DeGIR Registry Data. Fortschr Röntgenstr 2020; 192: 952 - 960.

Impact of Confounding Thoracic Tubes and Pleural Dehiscence Extent on Artificial Intelligence Pneumothorax Detection in Chest Radiographs.

OBJECTIVES: We hypothesized that published performances of algorithms for artificial intelligence (AI) pneumothorax (PTX) detection in chest radiographs (CXRs) do not sufficiently consider the influence of PTX size and confounding effects caused by thoracic tubes (TTs). Therefore, we established a radiologically annotated benchmarking cohort (n = 6446) allowing for a detailed subgroup analysis. MATERIALS AND METHODS: We retrospectively identified 6434 supine CXRs, among them 1652 PTX-positive cases and 4782 PTX-negative cases. Supine CXRs were radiologically annotated for PTX size, PTX location, and inserted TTs. The diagnostic performances of 2 AI algorithms ("AI_CheXNet" [Rajpurkar et al], "AI_1.5" [Guendel et al]), both trained on publicly available datasets with labels obtained from automatic report interpretation, were quantified. The algorithms' discriminative power for PTX detection was quantified by the area under the receiver operating characteristics (AUROC), and significance analysis was based on the corresponding 95% confidence interval. A detailed subgroup analysis was performed to quantify the influence of PTX size and the confounding effects caused by inserted TTs. RESULTS: Algorithm performance was quantified as follows: overall performance with AUROCs of 0.704 (AI_1.5) / 0.765 (AI_CheXNet) for unilateral PTXs, AUROCs of 0.666 (AI_1.5) / 0.722 (AI_CheXNet) for unilateral PTXs smaller than 1 cm, and AUROCs of 0.735 (AI_1.5) / 0.818 (AI_CheXNet) for unilateral PTXs larger than 2 cm. Subgroup analysis identified TTs to be strong confounders that significantly influence algorithm performance: Discriminative power is completely eliminated by analyzing PTX-positive cases without TTs referenced to control PTX-negative cases with inserted TTs. Contrarily, AUROCs increased up to 0.875 (AI_CheXNet) for large PTX-positive cases with inserted TTs referenced to control cases without TTs. CONCLUSIONS: Our detailed subgroup analysis demonstrated that the performance of established AI algorithms for PTX detection trained on public datasets strongly depends on PTX size and is significantly biased by confounding image features, such as inserted TTS. Our established, clinically relevant and radiologically annotated benchmarking cohort might be of great benefit for ongoing algorithm development.