Dominika Skwierawska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Dominika Skwierawska has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
Michael Uder
Institute of Radiology, Universitätsklinikum Erlangen, Friedrich‐Alexander‐Universität Erlangen‐Nürnberg (FAU) Erlangen Germany
6 shared publications- Lorenz A. Kapsner
Medical Informatics, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91058 Erlangen, Germany
5 shared publications Dominique Hadler
Institute of Radiology, Universitätsklinikum Erlangen, Friedrich‐Alexander‐Universität Erlangen‐Nürnberg (FAU) Erlangen Germany
4 shared publications- Frederik Bernd Laun
Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91054 Erlangen, Germany
4 shared publications - Sabine Ohlmeyer
Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), 91054 Erlangen, Germany
4 shared publications Sebastian Bickelhaupt
Institute of Radiology, Universitätsklinikum Erlangen, Friedrich‐Alexander‐Universität Erlangen‐Nürnberg (FAU) Erlangen Germany
4 shared publications
Latest Publications
- Open Access
- 5 October 2026
- Published by Wiley in Journal of Magnetic Resonance Imaging
- Vol. 64 (6) , 1737-1748
Slice‐Wise Quality Assessment of High b Value Breast DWI via Deep Learning‐Based Artifact Detection
Background: Diffusion‐weighted imaging (DWI) can support lesion detection and characterization in breast MRI. Therefore, DWI is increasingly being incorporated into breast MRI protocols to address some of the shortcomings of routine clinical breast MRI. However, especially high b value DWI can be prone to intensity artifacts that can affect diagnostic image assessment. Purpose: To detect hyper‐ and hypointense artifacts on high b value DWI ( b = 1500 s/mm 2 ) using deep learning, employing either a binary classification (artifact presence) or a multiclass classification (artifact intensity) approach on a slice‐wise dataset. Study Type: Retrospective. Study Population: 11,806 DWI slices were acquired from 156 examinations performed on female patients between 2022 and mid‐2023. For both hyper‐ and hypointense artifact classification, the slices were split into test, validation, and holdout test set with 8164/1806/1836 and 8164/1820/1822 slices in these sets respectively. Field Strength/Sequence: 3 T spin‐echo planar diffusion‐weighted sequence with b values: 50, 750, and 1500 s/mm 2 . Assessment: Three convolutional neural network (CNN) architectures (DenseNet121, ResNet18, and SEResNet50) were trained for binary classification of hyper‐ and hypointense artifacts on slice‐wise labeled data. The best performing model (DenseNet121) was applied to an independent holdout test set and further trained separately for multiclass classification. Statistical Tests: Performance of the networks was evaluated using accuracy, precision, recall, and areas under the receiver operating characteristic curve (AUROC) and under the precision recall curve (AUPRC). Radiologist evaluated bounding box positions on a 5‐point Likert‐like scale across 150 slices for validation and 200 slices for the holdout test set, derived from the network's Grad‐CAM heatmaps. Results: DenseNet121 achieved AUROCs of 0.91 and 0.95 for hyper‐ and hypointense artifact detection, respectively, and weighted AUROCs of 0.84 and 0.90 for multiclass classification on single‐slice high b value diffusion‐weighted images, achieving mean scores of 3.52 ± 0.81 for hyperintense artifacts and 3.62 ± 0.65 for hypointense artifacts. Data Conclusion: Hyper‐ and hypointense artifact detection in slice‐wise breast DWI MRI dataset ( b = 1500 s/mm 2 ) using CNNs, particularly DenseNet121, suggests potential reliability and requires further validation. Evidence Level: 3. Technical Efficacy: Stage 3.
- 5 October 2026
- Published by Wiley in Journal of Magnetic Resonance Imaging
- Vol. 64 (6) , 1737-1748
Open AccessSlice‐Wise Quality Assessment of High b Value Breast DWI via Deep Learning‐Based Artifact Detection
Background: Diffusion‐weighted imaging (DWI) can support lesion detection and characterization in breast MRI. Therefore, DWI is increasingly being incorporated into breast MRI protocols to address some of the shortcomings of routine clinical breast MRI. However, especially high b value DWI can be prone to intensity artifacts that can affect diagnostic image assessment. Purpose: To detect hyper‐ and hypointense artifacts on high b value DWI ( b = 1500 s/mm 2 ) using deep learning, employing either a binary classification (artifact presence) or a multiclass classification (artifact intensity) approach on a slice‐wise dataset. Study Type: Retrospective. Study Population: 11,806 DWI slices were acquired from 156 examinations performed on female patients between 2022 and mid‐2023. For both hyper‐ and hypointense artifact classification, the slices were split into test, validation, and holdout test set with 8164/1806/1836 and 8164/1820/1822 slices in these sets respectively. Field Strength/Sequence: 3 T spin‐echo planar diffusion‐weighted sequence with b values: 50, 750, and 1500 s/mm 2 . Assessment: Three convolutional neural network (CNN) architectures (DenseNet121, ResNet18, and SEResNet50) were trained for binary classification of hyper‐ and hypointense artifacts on slice‐wise labeled data. The best performing model (DenseNet121) was applied to an independent holdout test set and further trained separately for multiclass classification. Statistical Tests: Performance of the networks was evaluated using accuracy, precision, recall, and areas under the receiver operating characteristic curve (AUROC) and under the precision recall curve (AUPRC). Radiologist evaluated bounding box positions on a 5‐point Likert‐like scale across 150 slices for validation and 200 slices for the holdout test set, derived from the network's Grad‐CAM heatmaps. Results: DenseNet121 achieved AUROCs of 0.91 and 0.95 for hyper‐ and hypointense artifact detection, respectively, and weighted AUROCs of 0.84 and 0.90 for multiclass classification on single‐slice high b value diffusion‐weighted images, achieving mean scores of 3.52 ± 0.81 for hyperintense artifacts and 3.62 ± 0.65 for hypointense artifacts. Data Conclusion: Hyper‐ and hypointense artifact detection in slice‐wise breast DWI MRI dataset ( b = 1500 s/mm 2 ) using CNNs, particularly DenseNet121, suggests potential reliability and requires further validation. Evidence Level: 3. Technical Efficacy: Stage 3.
- Open Access
- 16 July 2026
- Published by MDPI AG in Tomography
- Vol. 12 (7) , 105
Can AI Detect What Is Not Injected? Evaluation of Lesion Detection in Virtual Contrast-Enhanced Breast MRI Using a Large-Scale AI Model Trained on GBCA-Enhanced Data
Background/Objectives: Artificial intelligence (AI) can support lesion detection in gadolinium-based contrast agent-enhanced (GBCA-enhanced) breast MRI. However, its effectiveness on virtual contrast-enhanced (vCE) images remains unclear. This feasibility study evaluated the publicly available MAMA-MIA nnU-Net model trained on GBCA-enhanced data using an independent cohort of both GBCA-enhanced and vCE breast MRI. Methods: This IRB-approved retrospective study included the publicly available nnU-Net model trained on n = 1506 MAMA-MIA breast MRI scans and a cohort of n = 2126 in-house 3T breast MRI scans. A generative adversarial network (Pix2Pix-GAN) was developed on n = 1870 of the in-house scans and used to generate vCE data on the remaining independent n = 256 in-house cases. The MAMA-MIA nnU-net was applied to both GBCA-enhanced (GBCA) and corresponding vCE images. Ground-truth segmentations of malignant lesions served to calculate the Dice score, Hausdorff distance, and lesion dimension differences. Results: The final test set comprised n = 250 cases (n = 69 malignant, n = 181 benign). Lesion detection rates were 91% (n = 63/n = 69; 95% confidence interval (CI): 82.3–96.0%) for GBCA and 84% (n = 58/n = 69; 95% CI: 73.7–90.9%) for vCE. Two lesions missed in GBCA were identified by vCE. The Hausdorff distances were similar (GBCA: 6.4 (IQR: 3.2–9.3; 95% CI: 5.2–7.8) mm; vCE: 6.7 (IQR: 3.9–9.7; 95% CI: 5.3–8.0) mm, p = 0.564). The Dice scores showed minor differences (GBCA: 0.829 (IQR: 0.723–0.900; 95% CI: 0.786–0.865) vs. vCE: 0.826 (IQR: 0.720–0.857; 95% CI: 0.770–0.836); p < 0.001). vCE images had slightly higher non-target tissue segmentation (median 6072 mm3 vs. 5754 mm3). Conclusions: A GBCA-trained algorithm demonstrated some cross-domain transferability to vCE images, albeit with a reduced case-level sensitivity of 84% (95% CI: 73.7–90.9%) vs. 91% (95% CI: 82.3–96.0%). Based on these preliminary results, further research, including larger cohorts and more diverse datasets, is warranted.
- 16 July 2026
- Published by MDPI AG in Tomography
- Vol. 12 (7) , 105
Open AccessCan AI Detect What Is Not Injected? Evaluation of Lesion Detection in Virtual Contrast-Enhanced Breast MRI Using a Large-Scale AI Model Trained on GBCA-Enhanced Data
Background/Objectives: Artificial intelligence (AI) can support lesion detection in gadolinium-based contrast agent-enhanced (GBCA-enhanced) breast MRI. However, its effectiveness on virtual contrast-enhanced (vCE) images remains unclear. This feasibility study evaluated the publicly available MAMA-MIA nnU-Net model trained on GBCA-enhanced data using an independent cohort of both GBCA-enhanced and vCE breast MRI. Methods: This IRB-approved retrospective study included the publicly available nnU-Net model trained on n = 1506 MAMA-MIA breast MRI scans and a cohort of n = 2126 in-house 3T breast MRI scans. A generative adversarial network (Pix2Pix-GAN) was developed on n = 1870 of the in-house scans and used to generate vCE data on the remaining independent n = 256 in-house cases. The MAMA-MIA nnU-net was applied to both GBCA-enhanced (GBCA) and corresponding vCE images. Ground-truth segmentations of malignant lesions served to calculate the Dice score, Hausdorff distance, and lesion dimension differences. Results: The final test set comprised n = 250 cases (n = 69 malignant, n = 181 benign). Lesion detection rates were 91% (n = 63/n = 69; 95% confidence interval (CI): 82.3–96.0%) for GBCA and 84% (n = 58/n = 69; 95% CI: 73.7–90.9%) for vCE. Two lesions missed in GBCA were identified by vCE. The Hausdorff distances were similar (GBCA: 6.4 (IQR: 3.2–9.3; 95% CI: 5.2–7.8) mm; vCE: 6.7 (IQR: 3.9–9.7; 95% CI: 5.3–8.0) mm, p = 0.564). The Dice scores showed minor differences (GBCA: 0.829 (IQR: 0.723–0.900; 95% CI: 0.786–0.865) vs. vCE: 0.826 (IQR: 0.720–0.857; 95% CI: 0.770–0.836); p < 0.001). vCE images had slightly higher non-target tissue segmentation (median 6072 mm3 vs. 5754 mm3). Conclusions: A GBCA-trained algorithm demonstrated some cross-domain transferability to vCE images, albeit with a reduced case-level sensitivity of 84% (95% CI: 73.7–90.9%) vs. 91% (95% CI: 82.3–96.0%). Based on these preliminary results, further research, including larger cohorts and more diverse datasets, is warranted.
- Open Access
- 4 June 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (6) , e0341201
Finite sample size errors in the context of multiple error sources in quantitative medical imaging: An evaluation for breast magnetic resonance diffusion-weighted imaging
Background: Selecting appropriate sample sizes in magnetic resonance imaging studies is a complex process that requires to balance statistical rigor with the practical challenges of measuring a large patient population. In this Institutional Review Board approved study, we evaluate the dominant error types (“finite N” errors versus precision errors) for apparent diffusion coefficient (ADC)-based lesion characterization in diffusion-weighted magnetic resonance imaging (DWI) of the female breast in a local dataset and compare our results with current literature. Methods: First, in a literature review including 24 published breast DWI studies, the standard error of the area under the receiver operating characteristic curve as a measure of sample size-related errors (finite N errors) was estimated for the reported ADC values and compared to the values, derived from expert readings of a university hospital’s cohort of 171 patients with suspicious breast lesions. Second, precision errors were assessed based on published analyses of the coefficient of variation of ADC values, measured in breast DWI exams. Results: Finite N errors were dominant in the in-house study and most of the 24 reviewed studies. The median sample size at which finite N errors and precision errors were equal was determined to be n = 932. Discussion: This analysis of dominant error types shows that the required sample sizes for the considered use case are not unreasonably large and that reducing sample sizes may not be justified based on the merits of the conducted analysis. Nonetheless, incorporating dominant error type assessments into future studies may provide valuable insights for optimizing study design and improving methodological rigor.
- 4 June 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (6) , e0341201
Open AccessFinite sample size errors in the context of multiple error sources in quantitative medical imaging: An evaluation for breast magnetic resonance diffusion-weighted imaging
Background: Selecting appropriate sample sizes in magnetic resonance imaging studies is a complex process that requires to balance statistical rigor with the practical challenges of measuring a large patient population. In this Institutional Review Board approved study, we evaluate the dominant error types (“finite N” errors versus precision errors) for apparent diffusion coefficient (ADC)-based lesion characterization in diffusion-weighted magnetic resonance imaging (DWI) of the female breast in a local dataset and compare our results with current literature. Methods: First, in a literature review including 24 published breast DWI studies, the standard error of the area under the receiver operating characteristic curve as a measure of sample size-related errors (finite N errors) was estimated for the reported ADC values and compared to the values, derived from expert readings of a university hospital’s cohort of 171 patients with suspicious breast lesions. Second, precision errors were assessed based on published analyses of the coefficient of variation of ADC values, measured in breast DWI exams. Results: Finite N errors were dominant in the in-house study and most of the 24 reviewed studies. The median sample size at which finite N errors and precision errors were equal was determined to be n = 932. Discussion: This analysis of dominant error types shows that the required sample sizes for the considered use case are not unreasonably large and that reducing sample sizes may not be justified based on the merits of the conducted analysis. Nonetheless, incorporating dominant error type assessments into future studies may provide valuable insights for optimizing study design and improving methodological rigor.
- 15 May 2026
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 61 (12) , 875-886
Artificial Intelligence-enhanced Identification of Incidental Findings in Prostate MRI
Objectives: The use of prostate magnetic resonance imaging (MRI) is increasing, and coverage often captures substantial portions of the pelvis, visualizing findings outside the prostate gland. The objective of this study was to evaluate the feasibility of automated detection and segmentation of high-prevalence incidental findings in prostate MRI. Materials and Methods: This IRB-approved, retrospective study included n=465 prostate MRI examinations (1.5 and 3.0 T), comprising n=315 internal cases from our institution and n=150 external cases from 3 independent data sets. Manual segmentations were performed for perirectal lymph nodes, sigmoid diverticulosis, urinary bladder diverticula, bladder wall thickenings, inguinal hernias, periarticular bone changes of the hip, prominent synovial compartments of the hip, and hydroceles testis on axial T 2 -weighted (T2w) images for n=265 internal cases (n=520 ROIs). An nnU-Net model was trained on n=213 of these cases. The remaining n=52 independent cases (quantitative test set) were used for the quantitative evaluation of model performance using Dice score, intersection over union (IoU), Hausdorff distance (HD), mean surface distance (MSD), confusion matrices, sensitivity, specificity, and accuracy. Furthermore, n=200 additional examinations (reader test set), comprising n=50 internal, n=150 from 3 independent external data sets, were evaluated by 2 radiologists in an AI-assisted evaluation. Readers assessed the presence of incidental findings (step 1) and the correctness of the nnU-Net-predicted findings (step 2), based on the AI-predicted segmentations. Results: Segmentation performance varied between the incidental findings. Evaluation of the independent quantitative test set revealed that the highest mean Dice scores were achieved for sigmoid diverticulosis (0.80±0.14), hydroceles testis (0.76±0.20), and periarticular bone changes of the hip (0.70±0.07). Radiologists’ evaluation of AI predictions on an independent reader test set comprising 1 internal and 3 external data sets demonstrated high agreement in AI-assisted evaluation for most incidental findings. Accuracies per data set (PROSTATEx/Ai4ar/internal/Prostate-3T) were 0.94/0.62/0.96/0.94 for perirectal lymph nodes, 0.82/0.80/0.80/0.84 for sigmoid diverticulosis, 0.86/0.86/0.98/0.98 for urinary bladder diverticula, 0.96/0.82/0.88/0.72 for bladder wall thickenings, 0.94/0.82/0.78/0.86 for inguinal hernias, 0.90/0.80/0.82/0.84 for periarticular bone changes of the hip, 0.90/0.82/0.84/0.96 for prominent synovial compartments of the hip, 0.98/0.80/0.96/0.96 for hydroceles testis. Inter-reader agreement for the AI-assisted evaluation of the presence of incidental findings on T2w images was high, with Cohen κ values ranging from 0.74 to 0.92 for most findings. Conclusions: The nnU-Net-based AI model was able to capture and segment frequent incidental findings in prostate MRI across 4 independent data sets, demonstrating potential to support radiologists in consistent reporting. This supports further research with larger, more diverse data sets, including additional annotations and clinical targets.
- 15 May 2026
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 61 (12) , 875-886
Artificial Intelligence-enhanced Identification of Incidental Findings in Prostate MRI
Objectives: The use of prostate magnetic resonance imaging (MRI) is increasing, and coverage often captures substantial portions of the pelvis, visualizing findings outside the prostate gland. The objective of this study was to evaluate the feasibility of automated detection and segmentation of high-prevalence incidental findings in prostate MRI. Materials and Methods: This IRB-approved, retrospective study included n=465 prostate MRI examinations (1.5 and 3.0 T), comprising n=315 internal cases from our institution and n=150 external cases from 3 independent data sets. Manual segmentations were performed for perirectal lymph nodes, sigmoid diverticulosis, urinary bladder diverticula, bladder wall thickenings, inguinal hernias, periarticular bone changes of the hip, prominent synovial compartments of the hip, and hydroceles testis on axial T 2 -weighted (T2w) images for n=265 internal cases (n=520 ROIs). An nnU-Net model was trained on n=213 of these cases. The remaining n=52 independent cases (quantitative test set) were used for the quantitative evaluation of model performance using Dice score, intersection over union (IoU), Hausdorff distance (HD), mean surface distance (MSD), confusion matrices, sensitivity, specificity, and accuracy. Furthermore, n=200 additional examinations (reader test set), comprising n=50 internal, n=150 from 3 independent external data sets, were evaluated by 2 radiologists in an AI-assisted evaluation. Readers assessed the presence of incidental findings (step 1) and the correctness of the nnU-Net-predicted findings (step 2), based on the AI-predicted segmentations. Results: Segmentation performance varied between the incidental findings. Evaluation of the independent quantitative test set revealed that the highest mean Dice scores were achieved for sigmoid diverticulosis (0.80±0.14), hydroceles testis (0.76±0.20), and periarticular bone changes of the hip (0.70±0.07). Radiologists’ evaluation of AI predictions on an independent reader test set comprising 1 internal and 3 external data sets demonstrated high agreement in AI-assisted evaluation for most incidental findings. Accuracies per data set (PROSTATEx/Ai4ar/internal/Prostate-3T) were 0.94/0.62/0.96/0.94 for perirectal lymph nodes, 0.82/0.80/0.80/0.84 for sigmoid diverticulosis, 0.86/0.86/0.98/0.98 for urinary bladder diverticula, 0.96/0.82/0.88/0.72 for bladder wall thickenings, 0.94/0.82/0.78/0.86 for inguinal hernias, 0.90/0.80/0.82/0.84 for periarticular bone changes of the hip, 0.90/0.82/0.84/0.96 for prominent synovial compartments of the hip, 0.98/0.80/0.96/0.96 for hydroceles testis. Inter-reader agreement for the AI-assisted evaluation of the presence of incidental findings on T2w images was high, with Cohen κ values ranging from 0.74 to 0.92 for most findings. Conclusions: The nnU-Net-based AI model was able to capture and segment frequent incidental findings in prostate MRI across 4 independent data sets, demonstrating potential to support radiologists in consistent reporting. This supports further research with larger, more diverse data sets, including additional annotations and clinical targets.
- Open Access
- 16 January 2026
- Published by MDPI AG in Tomography
- Vol. 12 (1) , 11
Overestimation of the Apparent Diffusion Coefficient in Diffusion-Weighted Imaging Due to Residual Fat Signal and Out-of-Phase Conditions
Background/Objectives: Diffusion-weighted imaging (DWI) is a magnetic resonance technique used to map the apparent diffusion coefficient () of water in human tissue. assessment plays a central role in clinical diagnostics, as malignant tissues typically exhibit reduced water mobility and, thus, lower values. Accurately measuring the requires effective fat suppression to prevent contamination from the residual fat signal, which is commonly believed to cause underestimation. This study aimed to demonstrate that overestimation may occur as well. Methods: Our theoretical analysis shows that out-of-phase conditions between fat and water signals lead to overestimations. We performed demonstration experiments on fat–water phantoms and the breasts of 10 healthy female volunteers. In particular, we considered three out-of-phase conditions: First and second, short-time inversion recovery (STIR) fat suppression with incorrect inversion time and incorrect flip angle, respectively. Third, phase differences due to spectral fat saturation. The values were assessed in regions of interest (ROIs) that included both water and residual fat signals. Results: In the phantoms and the volunteer data, ROIs containing both fat and water signals consistently exhibited lower values under in-phase conditions and higher values under out-of-phase conditions. Conclusions: We demonstrated that out-of-phase conditions can result in overestimation in the presence of residual fat signals, potentially resulting in false-negative classifications where malignant lesions are misinterpreted as benign due to an elevated . Out-of-phase fat and water signals might also reduce lesion conspicuity in high b-value images, potentially masking clinically relevant findings.- 16 January 2026
- Published by MDPI AG in Tomography
- Vol. 12 (1) , 11
Open AccessOverestimation of the Apparent Diffusion Coefficient in Diffusion-Weighted Imaging Due to Residual Fat Signal and Out-of-Phase Conditions
Background/Objectives: Diffusion-weighted imaging (DWI) is a magnetic resonance technique used to map the apparent diffusion coefficient () of water in human tissue. assessment plays a central role in clinical diagnostics, as malignant tissues typically exhibit reduced water mobility and, thus, lower values. Accurately measuring the requires effective fat suppression to prevent contamination from the residual fat signal, which is commonly believed to cause underestimation. This study aimed to demonstrate that overestimation may occur as well. Methods: Our theoretical analysis shows that out-of-phase conditions between fat and water signals lead to overestimations. We performed demonstration experiments on fat–water phantoms and the breasts of 10 healthy female volunteers. In particular, we considered three out-of-phase conditions: First and second, short-time inversion recovery (STIR) fat suppression with incorrect inversion time and incorrect flip angle, respectively. Third, phase differences due to spectral fat saturation. The values were assessed in regions of interest (ROIs) that included both water and residual fat signals. Results: In the phantoms and the volunteer data, ROIs containing both fat and water signals consistently exhibited lower values under in-phase conditions and higher values under out-of-phase conditions. Conclusions: We demonstrated that out-of-phase conditions can result in overestimation in the presence of residual fat signals, potentially resulting in false-negative classifications where malignant lesions are misinterpreted as benign due to an elevated . Out-of-phase fat and water signals might also reduce lesion conspicuity in high b-value images, potentially masking clinically relevant findings. - Open Access
- 12 June 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-16
AI-Based screening for thoracic aortic aneurysms in routine breast MRI
Prognosis for thoracic aortic aneurysms is significantly worse for women than men, with a higher mortality rate observed among female patients. The increasing use of magnetic resonance breast imaging (MRI) offers a unique opportunity for simultaneous detection of both breast cancer and thoracic aortic aneurysms. We retrospectively validate a fully-automated artificial neural network (ANN) pipeline on 5057 breast MRI examinations from public (Duke University Hospital/EA1141 trial) and in-house (Erlangen University Hospital) data. The ANN, benchmarked against 3D-ground-truth segmentations, clinical reports, and a multireader panel, demonstrates high technical robustness (dice/clDice 0.88-0.91/0.97-0.99) across different vendors and field strengths. The ANN improves aneurysm detection rates by 3.5-fold compared with routine clinical readings, highlighting its potential to improve early diagnosis and patient outcomes. Notably, a higher odds ratio (OR = 2.29, CI: [0.55,9.61]) for thoracic aortic aneurysms is observed in women with breast cancer or breast cancer history, suggesting potential further benefits from integrated simultaneous assessment for cancer and aortic aneurysms.
- 12 June 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-16
Open AccessAI-Based screening for thoracic aortic aneurysms in routine breast MRI
Prognosis for thoracic aortic aneurysms is significantly worse for women than men, with a higher mortality rate observed among female patients. The increasing use of magnetic resonance breast imaging (MRI) offers a unique opportunity for simultaneous detection of both breast cancer and thoracic aortic aneurysms. We retrospectively validate a fully-automated artificial neural network (ANN) pipeline on 5057 breast MRI examinations from public (Duke University Hospital/EA1141 trial) and in-house (Erlangen University Hospital) data. The ANN, benchmarked against 3D-ground-truth segmentations, clinical reports, and a multireader panel, demonstrates high technical robustness (dice/clDice 0.88-0.91/0.97-0.99) across different vendors and field strengths. The ANN improves aneurysm detection rates by 3.5-fold compared with routine clinical readings, highlighting its potential to improve early diagnosis and patient outcomes. Notably, a higher odds ratio (OR = 2.29, CI: [0.55,9.61]) for thoracic aortic aneurysms is observed in women with breast cancer or breast cancer history, suggesting potential further benefits from integrated simultaneous assessment for cancer and aortic aneurysms.
- 28 February 2025
- Published by Wolters Kluwer Health in Investigative Radiology
Pros and Cons of High-Performance Gradient Enabled Short-TE Prostate DWI
Objectives: Recent advances in high-performance gradient technology have enabled shorter echo times (TEs) for diffusion-weighted prostate MRI. Short TE may improve the conspicuity of the usually T2 hypointense lesions but may also influence the diagnostic performance of the apparent diffusion coefficient (ADC) due to a changed weighting of subcompartments, including prostate fluid and tissues. The purpose of this study was to evaluate the influence of TE on prostate diffusion-weighted images with respect to lesion conspicuity and diagnostic performance of the ADC. Materials and Methods: This institutional review board–approved prospective monocentric study included n = 55 (mean age 69 ± 9 years) patients undergoing clinically indicated prostate MRI on two 3 T MRI scanners with high-performance gradients. Diffusion-weighted imaging (DWI) was performed with an echo-planar sequence at 2 different TEs, 41 ms and 70 ms, with b-values of 50 s/mm2 and 800 s/mm2. Computed DWI was generated for a b-value of 1400 s/mm2. The lesion conspicuity and image quality were rated by 3 independent readers with a 5-point Likert scale and tested with the Wilcoxon rank sum test. Lesion ADCs were recorded, and their ability to detect significant lesions (Gleason score >6) was assessed with a receiver operator curve analysis. Results: Among the participants, n = 24 had clinically significant prostate cancer. The image quality at b = 1400 s/mm2 was rated significantly higher at TE = 41 ms than at TE = 70 ms (mean Likert score ± standard deviation for TE = 41 ms vs TE = 70 ms: R1: 4.06 ± 0.68 vs 3.02 ± 0.59; R2: 4.09 ± 0.82 vs 3.26 ± 0.67; R3: 4.16 ± 0.71 vs 3.18 ± 0.70; for all P’s < 0.001). The lesion conspicuity at b = 1400 s/mm2 was rated higher at TE = 41 ms than at TE = 70 ms (mean Likert score ± standard deviation for TE = 41 ms vs TE = 70 ms: R1: 4.55 ± 0.66 vs 4.46 ± 0.72, P = 0.17; R2: 4.64 ± 0.59 vs 4.53 ± 0.63, P = 0.03; R3: 4.53 ± 0.66 vs 4.28 ± 0.80, P = 0.01). However, the ADC-based area under the curve for lesion characterization decreased from 0.80 at TE = 70 ms to 0.70 at TE = 41 ms (P = 0.07). Conclusions: Shortening TE to 41 ms in prostate DWI increases lesion conspicuity on high b-value images; however, it negatively impacts the diagnostic performance of the ADC.
- 28 February 2025
- Published by Wolters Kluwer Health in Investigative Radiology
Pros and Cons of High-Performance Gradient Enabled Short-TE Prostate DWI
Objectives: Recent advances in high-performance gradient technology have enabled shorter echo times (TEs) for diffusion-weighted prostate MRI. Short TE may improve the conspicuity of the usually T2 hypointense lesions but may also influence the diagnostic performance of the apparent diffusion coefficient (ADC) due to a changed weighting of subcompartments, including prostate fluid and tissues. The purpose of this study was to evaluate the influence of TE on prostate diffusion-weighted images with respect to lesion conspicuity and diagnostic performance of the ADC. Materials and Methods: This institutional review board–approved prospective monocentric study included n = 55 (mean age 69 ± 9 years) patients undergoing clinically indicated prostate MRI on two 3 T MRI scanners with high-performance gradients. Diffusion-weighted imaging (DWI) was performed with an echo-planar sequence at 2 different TEs, 41 ms and 70 ms, with b-values of 50 s/mm2 and 800 s/mm2. Computed DWI was generated for a b-value of 1400 s/mm2. The lesion conspicuity and image quality were rated by 3 independent readers with a 5-point Likert scale and tested with the Wilcoxon rank sum test. Lesion ADCs were recorded, and their ability to detect significant lesions (Gleason score >6) was assessed with a receiver operator curve analysis. Results: Among the participants, n = 24 had clinically significant prostate cancer. The image quality at b = 1400 s/mm2 was rated significantly higher at TE = 41 ms than at TE = 70 ms (mean Likert score ± standard deviation for TE = 41 ms vs TE = 70 ms: R1: 4.06 ± 0.68 vs 3.02 ± 0.59; R2: 4.09 ± 0.82 vs 3.26 ± 0.67; R3: 4.16 ± 0.71 vs 3.18 ± 0.70; for all P’s < 0.001). The lesion conspicuity at b = 1400 s/mm2 was rated higher at TE = 41 ms than at TE = 70 ms (mean Likert score ± standard deviation for TE = 41 ms vs TE = 70 ms: R1: 4.55 ± 0.66 vs 4.46 ± 0.72, P = 0.17; R2: 4.64 ± 0.59 vs 4.53 ± 0.63, P = 0.03; R3: 4.53 ± 0.66 vs 4.28 ± 0.80, P = 0.01). However, the ADC-based area under the curve for lesion characterization decreased from 0.80 at TE = 70 ms to 0.70 at TE = 41 ms (P = 0.07). Conclusions: Shortening TE to 41 ms in prostate DWI increases lesion conspicuity on high b-value images; however, it negatively impacts the diagnostic performance of the ADC.
- 24 December 2024
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 60 (6) , 357-368
Relevance of Prostatic Fluid on the Apparent Diffusion Coefficient
Objectives: Diffusion-weighted imaging (DWI) is pivotal for prostate magnetic resonance imaging. This is rooted in the generally reduced apparent diffusion coefficient (ADC) observed in prostate cancer in comparison to healthy prostate tissue. This difference originates from microstructural tissue composition changes, including a potentially decreased fluid-containing lumen volume. This study explored the nature of the observed ADC contrast in prostate tissue through inversion recovery–prepared DWI examinations that generated varying levels of fluid suppression. Materials and Methods: This institutional review board–approved, single-center, prospective study was conducted from 2023 to 2024; all participants underwent magnetic resonance imaging including DWI with b-values of 50 and 800 s/mm2 at 16 inversion times (TI; 60–4000 milliseconds). The measured ADC was interpreted with a 2-compartment model (compartments: tissue and fluid). Descriptive statistics were computed for all analyzed parameters. Results: Twelve healthy male volunteers (45 ± 17 years) and 1 patient with prostate adenocarcinoma (66 years) were evaluated. The ADC map appearance depended heavily on the TI, and we observed a feature-rich ADC(TI) curve. The ADC in the transition zone (TZ) of healthy volunteers increased between TI = 60 milliseconds and approximately 1100 milliseconds, then dropped drastically before increasing again, stabilizing at a very high TI. This effect was greatly reduced in the patient's prostate cancer lesion. The 2-compartment model described this behavior well. After the inversion, tissue magnetization recovers faster, decreasing its signal contribution in absolute terms and resulting in an increase in the ADC. At the tipping point, the total magnetization is zero at b = 0, when the positive tissue magnetization and still-inverted fluid magnetization cancel out. A small diffusion encoding leads to a positive signal, thus generating an infinite ADC. After the tipping point, the fluid magnetization remains negative and thereby reduces the ADC. Conclusions: Prostate fluid appears to contribute significantly to prostate ADCs. Its contribution could be adjusted by choosing an appropriate inversion recovery preparation, potentially enhancing contrast for prostate cancer lesions.
- 24 December 2024
- Published by Wolters Kluwer Health in Investigative Radiology
- Vol. 60 (6) , 357-368
Relevance of Prostatic Fluid on the Apparent Diffusion Coefficient
Objectives: Diffusion-weighted imaging (DWI) is pivotal for prostate magnetic resonance imaging. This is rooted in the generally reduced apparent diffusion coefficient (ADC) observed in prostate cancer in comparison to healthy prostate tissue. This difference originates from microstructural tissue composition changes, including a potentially decreased fluid-containing lumen volume. This study explored the nature of the observed ADC contrast in prostate tissue through inversion recovery–prepared DWI examinations that generated varying levels of fluid suppression. Materials and Methods: This institutional review board–approved, single-center, prospective study was conducted from 2023 to 2024; all participants underwent magnetic resonance imaging including DWI with b-values of 50 and 800 s/mm2 at 16 inversion times (TI; 60–4000 milliseconds). The measured ADC was interpreted with a 2-compartment model (compartments: tissue and fluid). Descriptive statistics were computed for all analyzed parameters. Results: Twelve healthy male volunteers (45 ± 17 years) and 1 patient with prostate adenocarcinoma (66 years) were evaluated. The ADC map appearance depended heavily on the TI, and we observed a feature-rich ADC(TI) curve. The ADC in the transition zone (TZ) of healthy volunteers increased between TI = 60 milliseconds and approximately 1100 milliseconds, then dropped drastically before increasing again, stabilizing at a very high TI. This effect was greatly reduced in the patient's prostate cancer lesion. The 2-compartment model described this behavior well. After the inversion, tissue magnetization recovers faster, decreasing its signal contribution in absolute terms and resulting in an increase in the ADC. At the tipping point, the total magnetization is zero at b = 0, when the positive tissue magnetization and still-inverted fluid magnetization cancel out. A small diffusion encoding leads to a positive signal, thus generating an infinite ADC. After the tipping point, the fluid magnetization remains negative and thereby reduces the ADC. Conclusions: Prostate fluid appears to contribute significantly to prostate ADCs. Its contribution could be adjusted by choosing an appropriate inversion recovery preparation, potentially enhancing contrast for prostate cancer lesions.
- Open Access
- 29 April 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (9) , 934
Diffusion-Weighted Imaging for Skin Pathologies of the Breast—A Feasibility Study
Several breast pathologies can affect the skin, and clinical pathways might differ significantly depending on the underlying diagnosis. This study investigates the feasibility of using diffusion-weighted imaging (DWI) to differentiate skin pathologies in breast MRIs. This retrospective study included 88 female patients who underwent diagnostic breast MRI (1.5 or 3T), including DWI. Skin areas were manually segmented, and the apparent diffusion coefficients (ADCs) were compared between different pathologies: inflammatory breast cancer (IBC; n = 5), benign skin inflammation (BSI; n = 11), Paget’s disease (PD; n = 3), and skin-involved breast cancer (SIBC; n = 11). Fifty-eight women had healthy skin (H; n = 58). The SIBC group had a significantly lower mean ADC than the BSI and IBC groups. These differences persisted for the first-order features of the ADC (mean, median, maximum, and minimum) only between the SIBC and BSI groups. The mean ADC did not differ significantly between the BSI and IBC groups. Quantitative DWI assessments demonstrated differences between various skin-affecting pathologies, but did not distinguish clearly between all of them. More extensive studies are needed to assess the utility of quantitative DWI in supplementing the diagnostic assessment of skin pathologies in breast imaging.
- 29 April 2024
- Published by MDPI AG in Diagnostics
- Vol. 14 (9) , 934
Open AccessDiffusion-Weighted Imaging for Skin Pathologies of the Breast—A Feasibility Study
Several breast pathologies can affect the skin, and clinical pathways might differ significantly depending on the underlying diagnosis. This study investigates the feasibility of using diffusion-weighted imaging (DWI) to differentiate skin pathologies in breast MRIs. This retrospective study included 88 female patients who underwent diagnostic breast MRI (1.5 or 3T), including DWI. Skin areas were manually segmented, and the apparent diffusion coefficients (ADCs) were compared between different pathologies: inflammatory breast cancer (IBC; n = 5), benign skin inflammation (BSI; n = 11), Paget’s disease (PD; n = 3), and skin-involved breast cancer (SIBC; n = 11). Fifty-eight women had healthy skin (H; n = 58). The SIBC group had a significantly lower mean ADC than the BSI and IBC groups. These differences persisted for the first-order features of the ADC (mean, median, maximum, and minimum) only between the SIBC and BSI groups. The mean ADC did not differ significantly between the BSI and IBC groups. Quantitative DWI assessments demonstrated differences between various skin-affecting pathologies, but did not distinguish clearly between all of them. More extensive studies are needed to assess the utility of quantitative DWI in supplementing the diagnostic assessment of skin pathologies in breast imaging.
- Open Access
Clinical Viability of Boron Neutron Capture Therapy for Personalized Radiation Treatment
Boron Neutron Capture Therapy (BNCT) is a promising binary disease-targeted therapy, as neutrons preferentially kill cells labeled with boron (10B), which makes it a precision medicine treatment modality that provides a therapeutic effect exclusively on patient-specific tumor spread. Contrary to what is usual in radiotherapy, BNCT proposes cell-tailored treatment planning rather than to the tumor mass. The success of BNCT depends mainly on the sufficient spatial biodistribution of 10B located around or within neoplastic cells to produce a high-dose gradient between the tumor and healthy tissue. However, it is not yet possible to precisely determine the concentration of 10B in a specific tissue in real-time using non-invasive methods. Critical issues remain to be resolved if BNCT is to become a valuable, minimally invasive, and efficient treatment. In addition, functional imaging technologies, such as PET, can be applied to determine biological information that can be used for the combined-modality radiotherapy protocol for each specific patient. Regardless, not only imaging methods but also proteomics and gene expression methods will facilitate BNCT becoming a modality of personalized medicine. This work provides an overview of the fundamental principles, recent advances, and future directions of BNCT as cell-targeted cancer therapy for personalized radiation treatment.
Open AccessClinical Viability of Boron Neutron Capture Therapy for Personalized Radiation Treatment
Boron Neutron Capture Therapy (BNCT) is a promising binary disease-targeted therapy, as neutrons preferentially kill cells labeled with boron (10B), which makes it a precision medicine treatment modality that provides a therapeutic effect exclusively on patient-specific tumor spread. Contrary to what is usual in radiotherapy, BNCT proposes cell-tailored treatment planning rather than to the tumor mass. The success of BNCT depends mainly on the sufficient spatial biodistribution of 10B located around or within neoplastic cells to produce a high-dose gradient between the tumor and healthy tissue. However, it is not yet possible to precisely determine the concentration of 10B in a specific tissue in real-time using non-invasive methods. Critical issues remain to be resolved if BNCT is to become a valuable, minimally invasive, and efficient treatment. In addition, functional imaging technologies, such as PET, can be applied to determine biological information that can be used for the combined-modality radiotherapy protocol for each specific patient. Regardless, not only imaging methods but also proteomics and gene expression methods will facilitate BNCT becoming a modality of personalized medicine. This work provides an overview of the fundamental principles, recent advances, and future directions of BNCT as cell-targeted cancer therapy for personalized radiation treatment.