Wolfgang Block
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wolfgang Block has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Alois Martin Sprinkart
Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Bonn, Germany
6 shared publications - Julian Alexander Luetkens
Department of Diagnostic and Interventional Radiology, University Hospital Bonn , Venusberg-Campus 1, 53127 Bonn
5 shared publications - Sebastian Nowak
Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Bonn, Germany
5 shared publications - Ulrike Attenberger
Department of Radiology and Nuclear Medicine, Medical University of Vienna, Vienna, Austria
5 shared publications - Alexander Isaak
Department of Diagnostic and Interventional Radiology, University Hospital Bonn , Venusberg-Campus 1, 53127 Bonn
3 shared publications - Claus Christian Pieper
Department of Diagnostic and Interventional Radiology, University Hospital Bonn, Venusberg-Campus 1, 53127 Bonn, Germany
3 shared publications
Latest Publications
- Open Access
- 16 June 2026
- Published by Springer Nature in Langenbeck's Archives of Surgery
- Vol. 411 (1) , 165
Towards clinically interpretable machine learning in emergency surgery: feature importance and insights across clinical time points in abdominal pain cases
Purpose: Machine learning (ML) may support decision-making for acute abdominal pain (AAP), but limited interpretability hinders adoption. We evaluated a random-forest classifier for predicting urgent abdominal surgery and examined how predictive value and feature importance evolve across clinical timepoints. Methods: In this retrospective single-center study, we included adults presenting with AAP to the emergency department. The outcome was urgent abdominal surgery within 24 h. Features were grouped into stepwise sets. For each feature set, models were trained in 20 random 80/20 train–test splits with randomized hyperparameter search. Performance was summarized by AUC ROC and AUC PR, and interpretability by permutation importance and SHapley Additive exPlanations (SHAP). Results: Among 1,350 patients (median age 43 years, 682 (50.5%) females), 276 (20.4%) underwent urgent surgery. The final model achieved a median AUC ROC of 0.83. Discrimination increased stepwise from basic data (0.53), symptoms (0.61), pain history (0.66), vital signs (0.68), laboratory values (0.76), and physical examination (0.83). Computed tomography added only marginal improvement (0.83). Feature importance shifted from symptoms to vital signs and subsequently laboratory markers, particularly c-reactive Protein, white blood cell count, and prothrombin time, complemented by guarding. SHAP analyses confirmed these trends by consistently linking abnormal laboratory or clinical values to operative outcomes. Conclusion: Interpretable ML enables pre-imaging risk stratification for urgent surgery in AAP. Near-final discrimination is achieved after laboratory testing and physical examination, while computed tomography adds limited value at population level. Timepoint-specific feature contribution may facilitate integration of ML into surgical decision-making.
- 16 June 2026
- Published by Springer Nature in Langenbeck's Archives of Surgery
- Vol. 411 (1) , 165
Open AccessTowards clinically interpretable machine learning in emergency surgery: feature importance and insights across clinical time points in abdominal pain cases
Purpose: Machine learning (ML) may support decision-making for acute abdominal pain (AAP), but limited interpretability hinders adoption. We evaluated a random-forest classifier for predicting urgent abdominal surgery and examined how predictive value and feature importance evolve across clinical timepoints. Methods: In this retrospective single-center study, we included adults presenting with AAP to the emergency department. The outcome was urgent abdominal surgery within 24 h. Features were grouped into stepwise sets. For each feature set, models were trained in 20 random 80/20 train–test splits with randomized hyperparameter search. Performance was summarized by AUC ROC and AUC PR, and interpretability by permutation importance and SHapley Additive exPlanations (SHAP). Results: Among 1,350 patients (median age 43 years, 682 (50.5%) females), 276 (20.4%) underwent urgent surgery. The final model achieved a median AUC ROC of 0.83. Discrimination increased stepwise from basic data (0.53), symptoms (0.61), pain history (0.66), vital signs (0.68), laboratory values (0.76), and physical examination (0.83). Computed tomography added only marginal improvement (0.83). Feature importance shifted from symptoms to vital signs and subsequently laboratory markers, particularly c-reactive Protein, white blood cell count, and prothrombin time, complemented by guarding. SHAP analyses confirmed these trends by consistently linking abnormal laboratory or clinical values to operative outcomes. Conclusion: Interpretable ML enables pre-imaging risk stratification for urgent surgery in AAP. Near-final discrimination is achieved after laboratory testing and physical examination, while computed tomography adds limited value at population level. Timepoint-specific feature contribution may facilitate integration of ML into surgical decision-making.
- Top Cited Papers
- 1 January 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 314 (1) , e240895
Privacy-ensuring Open-weights Large Language Models Are Competitive with Closed-weights GPT-4o in Extracting Chest Radiography Findings from Free-Text Reports
Privacy-ensuring, open-weights large language models showed great potential in the extraction of structured content from free-text radiology reports, facilitating the secondary use of clinical databases for applications in data-driven medicine.
- 1 January 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 314 (1) , e240895
Top Cited PapersPrivacy-ensuring Open-weights Large Language Models Are Competitive with Closed-weights GPT-4o in Extracting Chest Radiography Findings from Free-Text Reports
Privacy-ensuring, open-weights large language models showed great potential in the extraction of structured content from free-text radiology reports, facilitating the secondary use of clinical databases for applications in data-driven medicine.
- Open Access
- 1 October 2024
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 13 (19) , e035599
Deep Learning Virtual Contrast‐Enhanced T1 Mapping for Contrast‐Free Myocardial Extracellular Volume Assessment
Background: The acquisition of contrast‐enhanced T1 maps to calculate extracellular volume (ECV) requires contrast agent administration and is time consuming. This study investigates generative adversarial networks for contrast‐free, virtual extracellular volume (vECV) by generating virtual contrast‐enhanced T1 maps. Methods and Results: This retrospective study includes 2518 registered native and contrast‐enhanced T1 maps from 1000 patients who underwent cardiovascular magnetic resonance at 1.5 Tesla. Recent hematocrit values of 123 patients (hold‐out test) and 96 patients from a different institution (external evaluation) allowed for calculation of conventional ECV. A generative adversarial network was trained to generate virtual contrast‐enhanced T1 maps from native T1 maps for vECV creation. Mean and SD of the difference per patient (ΔECV) were calculated and compared by permutation of the 2‐sided t test with 10 000 resamples. For ECV and vECV, differences in area under the receiver operating characteristic curve (AUC) for discriminating hold‐out test patients with normal cardiovascular magnetic resonance versus myocarditis or amyloidosis were tested with Delong's test. ECV and vECV showed a high agreement in patients with myocarditis (ΔECV: hold‐out test, 2.0%±1.5%; external evaluation, 1.9%±1.7%) and normal cardiovascular magnetic resonance (ΔECV: hold‐out test, 1.9%±1.4%; external evaluation, 1.5%±1.2%), but variations in amyloidosis were higher (ΔECV: hold‐out test, 6.2%±6.0%; external evaluation, 15.5%±6.4%). In the hold‐out test, ECV and vECV had a comparable AUC for the diagnosis of myocarditis (ECV AUC, 0.77 versus vECV AUC, 0.76; P =0.76) and amyloidosis (ECV AUC, 0.99 versus vECV AUC, 0.96; P =0.52). Conclusions: Generation of vECV on the basis of native T1 maps is feasible. Multicenter training data are required to further enhance generalizability of vECV in amyloidosis.
- 1 October 2024
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 13 (19) , e035599
Open AccessDeep Learning Virtual Contrast‐Enhanced T1 Mapping for Contrast‐Free Myocardial Extracellular Volume Assessment
Background: The acquisition of contrast‐enhanced T1 maps to calculate extracellular volume (ECV) requires contrast agent administration and is time consuming. This study investigates generative adversarial networks for contrast‐free, virtual extracellular volume (vECV) by generating virtual contrast‐enhanced T1 maps. Methods and Results: This retrospective study includes 2518 registered native and contrast‐enhanced T1 maps from 1000 patients who underwent cardiovascular magnetic resonance at 1.5 Tesla. Recent hematocrit values of 123 patients (hold‐out test) and 96 patients from a different institution (external evaluation) allowed for calculation of conventional ECV. A generative adversarial network was trained to generate virtual contrast‐enhanced T1 maps from native T1 maps for vECV creation. Mean and SD of the difference per patient (ΔECV) were calculated and compared by permutation of the 2‐sided t test with 10 000 resamples. For ECV and vECV, differences in area under the receiver operating characteristic curve (AUC) for discriminating hold‐out test patients with normal cardiovascular magnetic resonance versus myocarditis or amyloidosis were tested with Delong's test. ECV and vECV showed a high agreement in patients with myocarditis (ΔECV: hold‐out test, 2.0%±1.5%; external evaluation, 1.9%±1.7%) and normal cardiovascular magnetic resonance (ΔECV: hold‐out test, 1.9%±1.4%; external evaluation, 1.5%±1.2%), but variations in amyloidosis were higher (ΔECV: hold‐out test, 6.2%±6.0%; external evaluation, 15.5%±6.4%). In the hold‐out test, ECV and vECV had a comparable AUC for the diagnosis of myocarditis (ECV AUC, 0.77 versus vECV AUC, 0.76; P =0.76) and amyloidosis (ECV AUC, 0.99 versus vECV AUC, 0.96; P =0.52). Conclusions: Generation of vECV on the basis of native T1 maps is feasible. Multicenter training data are required to further enhance generalizability of vECV in amyloidosis.
- 19 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (3) , 940-953
Optical Flow-Guided Cine MRI Segmentation With Learned Corrections
In cardiac cine magnetic resonance imaging (MRI), the heart is repeatedly imaged at numerous time points during the cardiac cycle. Frequently, the temporal evolution of a certain region of interest such as the ventricles or the atria is highly relevant for clinical diagnosis. In this paper, we devise a novel approach that allows for an automatized propagation of an arbitrary region of interest (ROI) along the cardiac cycle from respective annotated ROIs provided by medical experts at two different points in time, most frequently at the end-systolic (ES) and the end-diastolic (ED) cardiac phases. At its core, a 3D TV-L1-based optical flow algorithm computes the apparent motion of consecutive MRI images in forward and backward directions. Subsequently, the given terminal annotated masks are propagated by this bidirectional optical flow in 3D, which results, however, in improper initial estimates of the segmentation masks due to numerical inaccuracies. These initially propagated segmentation masks are then refined by a 3D U-Net-based convolutional neural network (CNN), which was trained to enforce consistency with the forward and backward warped masks using a novel loss function. Moreover, a penalization term in the loss function controls large deviations from the initial segmentation masks. This method is benchmarked both on a new dataset with annotated single ventricles containing patients with severe heart diseases and on a publicly available dataset with different annotated ROIs. We emphasize that our novel loss function enables fine-tuning the CNN on a single patient, thereby yielding state-of-the-art results along the complete cardiac cycle.
- 19 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (3) , 940-953
Optical Flow-Guided Cine MRI Segmentation With Learned Corrections
In cardiac cine magnetic resonance imaging (MRI), the heart is repeatedly imaged at numerous time points during the cardiac cycle. Frequently, the temporal evolution of a certain region of interest such as the ventricles or the atria is highly relevant for clinical diagnosis. In this paper, we devise a novel approach that allows for an automatized propagation of an arbitrary region of interest (ROI) along the cardiac cycle from respective annotated ROIs provided by medical experts at two different points in time, most frequently at the end-systolic (ES) and the end-diastolic (ED) cardiac phases. At its core, a 3D TV-L1-based optical flow algorithm computes the apparent motion of consecutive MRI images in forward and backward directions. Subsequently, the given terminal annotated masks are propagated by this bidirectional optical flow in 3D, which results, however, in improper initial estimates of the segmentation masks due to numerical inaccuracies. These initially propagated segmentation masks are then refined by a 3D U-Net-based convolutional neural network (CNN), which was trained to enforce consistency with the forward and backward warped masks using a novel loss function. Moreover, a penalization term in the loss function controls large deviations from the initial segmentation masks. This method is benchmarked both on a new dataset with annotated single ventricles containing patients with severe heart diseases and on a publicly available dataset with different annotated ROIs. We emphasize that our novel loss function enables fine-tuning the CNN on a single patient, thereby yielding state-of-the-art results along the complete cardiac cycle.
- 11 October 2023
- Published by Elsevier in European Journal of Radiology
- Vol. 168, 111150
Direct deep learning-based survival prediction from pre-interventional CT prior to transcatheter aortic valve replacement
- 11 October 2023
- Published by Elsevier in European Journal of Radiology
- Vol. 168, 111150
Direct deep learning-based survival prediction from pre-interventional CT prior to transcatheter aortic valve replacement
- Open Access
- 9 August 2021
- Published by Springer Nature in European Radiology Experimental
- Vol. 5 (1) , 1-11
Simplified intravoxel incoherent motion diffusion-weighted MRI of liver lesions: feasibility of combined two-colour index maps
Background: To evaluate the feasibility of two-colour index maps containing combined diffusion and perfusion information from simplified intravoxel incoherent motion (IVIM) for liver lesion malignancy assessment. Methods: Diffusion-weighted data from a respiratory-gated 1.5-T magnetic resonance sequence were analysed in 109 patients with liver lesions. With three b values (0, 50, 800 s/mm2) estimated diffusion coefficient D′, perfusion fraction f′, and apparent diffusion coefficient (ADC) maps were calculated and analysed for regions of interest (ROIs). D′ and f′ cutoff values were determined by differentiating haemangiomas from other lesions and focal nodular hyperplasias from other lesions, respectively. Combined IDf index maps were generated with a voxel value set to 100, if both D′ and f′ voxel values were lower than their cutoff values (1,529.4 × 10-6 mm2/s and 114.4 × 10-3, respectively), otherwise to 0. Moreover, IADC index maps were generated from ADC cutoff value (1,338.5 × 10-6 mm2/s) obtained by differentiating benign from malignant lesions. Discriminatory power was assessed for both IDf and IADC. Index maps were displayed as two-colour overlays to b-800 images and visually assessed within the translucent hyperintense areas. Results: For IDf, the same diagnostic accuracy was achieved as for the combined use of parameters D′ and f′ (93.6%). Compared to IADC, IDf showed a higher diagnostic accuracy. Visual judgment of IDf yielded an accuracy (95.4%) similar to that of quantitative analysis (93.6%). Conclusion: Voxel-wise combined two-colour index maps IDf provide similar diagnostic accuracy as ROI-based combination of estimated IVIM parameters D′ and f′ and are suitable for visual assessment of liver lesion malignancy.
- 9 August 2021
- Published by Springer Nature in European Radiology Experimental
- Vol. 5 (1) , 1-11
Open AccessSimplified intravoxel incoherent motion diffusion-weighted MRI of liver lesions: feasibility of combined two-colour index maps
Background: To evaluate the feasibility of two-colour index maps containing combined diffusion and perfusion information from simplified intravoxel incoherent motion (IVIM) for liver lesion malignancy assessment. Methods: Diffusion-weighted data from a respiratory-gated 1.5-T magnetic resonance sequence were analysed in 109 patients with liver lesions. With three b values (0, 50, 800 s/mm2) estimated diffusion coefficient D′, perfusion fraction f′, and apparent diffusion coefficient (ADC) maps were calculated and analysed for regions of interest (ROIs). D′ and f′ cutoff values were determined by differentiating haemangiomas from other lesions and focal nodular hyperplasias from other lesions, respectively. Combined IDf index maps were generated with a voxel value set to 100, if both D′ and f′ voxel values were lower than their cutoff values (1,529.4 × 10-6 mm2/s and 114.4 × 10-3, respectively), otherwise to 0. Moreover, IADC index maps were generated from ADC cutoff value (1,338.5 × 10-6 mm2/s) obtained by differentiating benign from malignant lesions. Discriminatory power was assessed for both IDf and IADC. Index maps were displayed as two-colour overlays to b-800 images and visually assessed within the translucent hyperintense areas. Results: For IDf, the same diagnostic accuracy was achieved as for the combined use of parameters D′ and f′ (93.6%). Compared to IADC, IDf showed a higher diagnostic accuracy. Visual judgment of IDf yielded an accuracy (95.4%) similar to that of quantitative analysis (93.6%). Conclusion: Voxel-wise combined two-colour index maps IDf provide similar diagnostic accuracy as ROI-based combination of estimated IVIM parameters D′ and f′ and are suitable for visual assessment of liver lesion malignancy.
- 1 March 2019
- Published by Elsevier in Seizure: European Journal of Epilepsy
- Vol. 66, 1-3
Retinoencephalopathy with occipital lobe epilepsy in an OPA-1 mutation carrier
- 1 March 2019
- Published by Elsevier in Seizure: European Journal of Epilepsy
- Vol. 66, 1-3
Retinoencephalopathy with occipital lobe epilepsy in an OPA-1 mutation carrier
- Open Access
- 20 September 2018
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 39 (10) , 1839-1847
Cerebrovascular Reactivity during Prolonged Breath-Hold in Experienced Freedivers
BACKGROUND AND PURPOSE: Experienced freedivers can endure prolonged breath-holds despite severe hypoxemia and are therefore ideal subjects to study apnea-induced cerebrovascular reactivity. This multiparametric study investigated CBF, the spatial coefficient of variation as a correlate of arterial transit time and brain metabolism, dynamics during prolonged apnea. MATERIALS AND METHODS: Fifteen male freedivers (age range, 20–64 years; cumulative previous prolonged breath-holds >2 minutes and 30 seconds: 4–79,200) underwent repetitive 3T pseudocontinuous arterial spin-labeling and 31P-/1H-MR spectroscopy before, during, and after a 5-minute breath-hold (split into early and late phases) and gave temporally matching venous blood gas samples. Correlation of temporal and regional cerebrovascular reactivity to blood gases and cumulative previous breath-holds of >2 minutes and 30 seconds in a lifetime was assessed. RESULTS: The spatial coefficient of variation of CBF (by arterial spin-labeling) decreased during the early breath-hold phase (−30.0%, P = .002), whereas CBF remained almost stable during this phase and increased in the late phase (+51.8%, P = .001). CBF differed between the anterior and the posterior circulation during all phases (eg, during late breath-hold: MCA, 57.3 ± 14.2 versus posterior cerebral artery, 42.7 ± 10.8 mL/100 g/min; P = .001). There was an association between breath-hold experience and lower CBF (1000 previous breath-holds reduced WM CBF by 0.6 mL/100 g/min; 95% CI, 0.15–1.1 mL/100 g/min; P = .01). While breath-hold caused peripheral lactate rise (+18.5%) and hypoxemia (oxygen saturation, −24.0%), cerebral lactate and adenosine diphosphate remained within physiologic ranges despite early signs of oxidative stress [−6.4% phosphocreatine / (adenosine triphosphate + adenosine diphosphate); P = .02]. CONCLUSIONS: This study revealed that the cerebral energy metabolism of trained freedivers withstands severe hypoxic hypercarbia in prolonged breath-hold due to a complex cerebrovascular hemodynamic response.
- 20 September 2018
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 39 (10) , 1839-1847
Open AccessCerebrovascular Reactivity during Prolonged Breath-Hold in Experienced Freedivers
BACKGROUND AND PURPOSE: Experienced freedivers can endure prolonged breath-holds despite severe hypoxemia and are therefore ideal subjects to study apnea-induced cerebrovascular reactivity. This multiparametric study investigated CBF, the spatial coefficient of variation as a correlate of arterial transit time and brain metabolism, dynamics during prolonged apnea. MATERIALS AND METHODS: Fifteen male freedivers (age range, 20–64 years; cumulative previous prolonged breath-holds >2 minutes and 30 seconds: 4–79,200) underwent repetitive 3T pseudocontinuous arterial spin-labeling and 31P-/1H-MR spectroscopy before, during, and after a 5-minute breath-hold (split into early and late phases) and gave temporally matching venous blood gas samples. Correlation of temporal and regional cerebrovascular reactivity to blood gases and cumulative previous breath-holds of >2 minutes and 30 seconds in a lifetime was assessed. RESULTS: The spatial coefficient of variation of CBF (by arterial spin-labeling) decreased during the early breath-hold phase (−30.0%, P = .002), whereas CBF remained almost stable during this phase and increased in the late phase (+51.8%, P = .001). CBF differed between the anterior and the posterior circulation during all phases (eg, during late breath-hold: MCA, 57.3 ± 14.2 versus posterior cerebral artery, 42.7 ± 10.8 mL/100 g/min; P = .001). There was an association between breath-hold experience and lower CBF (1000 previous breath-holds reduced WM CBF by 0.6 mL/100 g/min; 95% CI, 0.15–1.1 mL/100 g/min; P = .01). While breath-hold caused peripheral lactate rise (+18.5%) and hypoxemia (oxygen saturation, −24.0%), cerebral lactate and adenosine diphosphate remained within physiologic ranges despite early signs of oxidative stress [−6.4% phosphocreatine / (adenosine triphosphate + adenosine diphosphate); P = .02]. CONCLUSIONS: This study revealed that the cerebral energy metabolism of trained freedivers withstands severe hypoxic hypercarbia in prolonged breath-hold due to a complex cerebrovascular hemodynamic response.