Fabian Isensee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Recognitions
Fabian Isensee has a total of 562 co-authors. Here are the top co-authors by number of shared publications:
- Lena Maier-Hein
German Cancer Research Center
28 shared publications - Maximilian Rokuss
Deutsches Krebsforschungszentrum
10 shared publications - Yannick Kirchhoff
Division of Medical Image Computing, German Cancer Research Center, Heidelberg, Germany
9 shared publications - Balint Kovacs
Deutsches Krebsforschungszentrum
8 shared publications - Constantin Ulrich
German Cancer Research Center (DKFZ)
7 shared publications Klaus H. Maier-Hein
DKFZ
7 shared publications
Latest Publications
- Open Access
- 18 October 2026
- Published by Springer Nature in Research Square
Interactive Lesion Segmentation in Whole-Body PET/CT and Longitudinal CT: The autoPET/CT-IV Challenge
Deep learning enables automated tumour segmentation in whole-body positron emission tomography and computed tomography, but robustness remains limited by heterogeneous tracer uptake, anatomical variability, and inter-center differences. We report the fourth autoPET challenge, which evaluated interactive lesion segmentation using incremental simulated user prompts and longitudinal lesion segmentation from paired baseline and follow-up scans. In the interactive task (Task 1, ~ 30,000 training and ~ 3,000 test lesions), submitted methods improved with additional user input and achieved a mean Dice similarity coefficient of 0.74 at the final interaction step, with performance remaining robust across tracers and centers. Longitudinal segmentation (Task 2, ~ 7,500 training and ~ 4,500 test lesions) was substantially more challenging, with a best mean Dice similarity coefficient of 0.38. Here, we show that interactive segmentation can combine automated inference with iterative expert input while maintaining performance across heterogeneous imaging domains, whereas longitudinal lesion prediction remains limited by temporal and anatomical variability.
- 18 October 2026
- Published by Springer Nature in Research Square
Open AccessInteractive Lesion Segmentation in Whole-Body PET/CT and Longitudinal CT: The autoPET/CT-IV Challenge
Deep learning enables automated tumour segmentation in whole-body positron emission tomography and computed tomography, but robustness remains limited by heterogeneous tracer uptake, anatomical variability, and inter-center differences. We report the fourth autoPET challenge, which evaluated interactive lesion segmentation using incremental simulated user prompts and longitudinal lesion segmentation from paired baseline and follow-up scans. In the interactive task (Task 1, ~ 30,000 training and ~ 3,000 test lesions), submitted methods improved with additional user input and achieved a mean Dice similarity coefficient of 0.74 at the final interaction step, with performance remaining robust across tracers and centers. Longitudinal segmentation (Task 2, ~ 7,500 training and ~ 4,500 test lesions) was substantially more challenging, with a best mean Dice similarity coefficient of 0.38. Here, we show that interactive segmentation can combine automated inference with iterative expert input while maintaining performance across heterogeneous imaging domains, whereas longitudinal lesion prediction remains limited by temporal and anatomical variability.
- 26 September 2026
- Published by Springer Nature
- p. 358-368
Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation
- 26 September 2026
- Published by Springer Nature
- p. 358-368
Lost in the Folds: When Cross-Validation Is Not a Deep Ensemble for Uncertainty Estimation
- Open Access
- 8 September 2026
- Published by Springer Nature in Nature Methods
- p. 1-10
MemBrain v2: an end-to-end tool for the analysis of membranes in cryo-electron tomography
Cryo-electron tomography provides unique insights into macromolecular complexes in their native environments, yet membrane analysis remains a major bottleneck due to low signal-to-noise ratios, missing wedge artifacts and the complexity of membrane-associated particles. Existing tools often require extensive manual annotation, struggle with generalization across datasets and lack integrated solutions for segmentation, particle localization and quantitative analysis. We introduce MemBrain v2, a deep-learning-enabled framework that unifies these tasks into a streamlined pipeline. MemBrain-seg leverages a diverse, collaboratively generated training dataset and specialized model training strategies to achieve generalizable membrane segmentation across variable tomographic conditions. MemBrain-pick enables data-efficient localization of membrane-bound particles by integrating geometric constraints with deep learning, reducing the need for extensive manual annotation. MemBrain-stats provides quantitative insights into particle distributions, computing spatial metrics to analyze intramembrane particle organization. MemBrain v2 integrates seamlessly into cryo-electron tomography workflows, providing an accessible and structured approach to membrane analysis.
- 8 September 2026
- Published by Springer Nature in Nature Methods
- p. 1-10
Open AccessMemBrain v2: an end-to-end tool for the analysis of membranes in cryo-electron tomography
Cryo-electron tomography provides unique insights into macromolecular complexes in their native environments, yet membrane analysis remains a major bottleneck due to low signal-to-noise ratios, missing wedge artifacts and the complexity of membrane-associated particles. Existing tools often require extensive manual annotation, struggle with generalization across datasets and lack integrated solutions for segmentation, particle localization and quantitative analysis. We introduce MemBrain v2, a deep-learning-enabled framework that unifies these tasks into a streamlined pipeline. MemBrain-seg leverages a diverse, collaboratively generated training dataset and specialized model training strategies to achieve generalizable membrane segmentation across variable tomographic conditions. MemBrain-pick enables data-efficient localization of membrane-bound particles by integrating geometric constraints with deep learning, reducing the need for extensive manual annotation. MemBrain-stats provides quantitative insights into particle distributions, computing spatial metrics to analyze intramembrane particle organization. MemBrain v2 integrates seamlessly into cryo-electron tomography workflows, providing an accessible and structured approach to membrane analysis.
- 23 July 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (8)
The TopCoW Challenge — Topology-Aware Circle of Willis Segmentation for CT and MR Angiography
- 23 July 2026
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 3 (8)
The TopCoW Challenge — Topology-Aware Circle of Willis Segmentation for CT and MR Angiography
- Open Access
- 9 February 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Explainable AI-based analysis of human pancreas sections identifies traits of type 2 diabetes
Type 2 diabetes (T2D) is a chronic disease currently affecting around 500 million people worldwide with often severe health consequences. Yet, histopathological analyses are still inadequate to infer the glycaemic state of a person based on morphological alterations linked to impaired insulin secretion and β -cell failure in T2D. Giga-pixel microscopy can capture subtle morphological changes, but data complexity exceeds human analysis capabilities. In response, we generate a dataset of pancreas whole-slide images from living donors with multiple chromogenic and multiplex immunofluorescence stainings and train deep learning models to predict the T2D status. Using explainable AI, we make the learned relationships interpretable, quantify them as biomarkers, and assess their association with T2D. Remarkably, the highest prediction performance is achieved by simultaneously focusing on islet α - and δ -cells and neuronal axons, alongside subtle pancreatic alterations in T2D donors such as larger adipocyte clusters, altered islet-adipocyte proximity and smaller islets. This data-driven approach provides a foundation for future research into relevant diagnostic and therapeutic targets, refining several hypotheses regarding tissue alterations associated with T2D.
- 9 February 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessExplainable AI-based analysis of human pancreas sections identifies traits of type 2 diabetes
Type 2 diabetes (T2D) is a chronic disease currently affecting around 500 million people worldwide with often severe health consequences. Yet, histopathological analyses are still inadequate to infer the glycaemic state of a person based on morphological alterations linked to impaired insulin secretion and β -cell failure in T2D. Giga-pixel microscopy can capture subtle morphological changes, but data complexity exceeds human analysis capabilities. In response, we generate a dataset of pancreas whole-slide images from living donors with multiple chromogenic and multiplex immunofluorescence stainings and train deep learning models to predict the T2D status. Using explainable AI, we make the learned relationships interpretable, quantify them as biomarkers, and assess their association with T2D. Remarkably, the highest prediction performance is achieved by simultaneously focusing on islet α - and δ -cells and neuronal axons, alongside subtle pancreatic alterations in T2D donors such as larger adipocyte clusters, altered islet-adipocyte proximity and smaller islets. This data-driven approach provides a foundation for future research into relevant diagnostic and therapeutic targets, refining several hypotheses regarding tissue alterations associated with T2D.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (5) , 2212-2228
Benchmark of Segmentation Techniques for Pelvic Fracture in CT and X-Ray: Summary of the PENGWIN 2024 Challenge
The segmentation of pelvic fracture fragments in CT and X-ray images is crucial for trauma diagnosis, surgical planning, and intraoperative guidance. However, accurately and efficiently delineating the bone fragments remains a significant challenge due to complex anatomy and imaging limitations. The PENGWIN challenge, organized as a MICCAI 2024 satellite event, aimed to advance automated fracture segmentation by benchmarking state-of-the-art algorithms on these complex tasks. A diverse dataset of 150 CT scans was collected from multiple clinical centers, and a large set of simulated X-ray images was generated using the DeepDRR method. Final submissions from 16 teams worldwide were evaluated under a rigorous multi-metric testing scheme. The top-performing CT algorithm achieved an average fragment-wise intersection over union (IoU) of 0.930, demonstrating satisfactory accuracy. However, in the X-ray task, the best algorithm achieved an IoU of 0.774, which is promising but not yet sufficient for intra-operative decision-making, reflecting the inherent challenges of fragment overlap in projection imaging. Beyond the quantitative evaluation, the challenge revealed methodological diversity in algorithm design. Variations in instance representation, such as primary-secondary classification versus boundary-core separation, led to differing segmentation strategies. Despite promising results, the challenge also exposed inherent uncertainties in fragment definition, particularly in cases of incomplete fractures. These findings suggest that interactive segmentation approaches, integrating human decision-making with task-relevant information, may be essential for improving model reliability and clinical applicability.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (5) , 2212-2228
Benchmark of Segmentation Techniques for Pelvic Fracture in CT and X-Ray: Summary of the PENGWIN 2024 Challenge
The segmentation of pelvic fracture fragments in CT and X-ray images is crucial for trauma diagnosis, surgical planning, and intraoperative guidance. However, accurately and efficiently delineating the bone fragments remains a significant challenge due to complex anatomy and imaging limitations. The PENGWIN challenge, organized as a MICCAI 2024 satellite event, aimed to advance automated fracture segmentation by benchmarking state-of-the-art algorithms on these complex tasks. A diverse dataset of 150 CT scans was collected from multiple clinical centers, and a large set of simulated X-ray images was generated using the DeepDRR method. Final submissions from 16 teams worldwide were evaluated under a rigorous multi-metric testing scheme. The top-performing CT algorithm achieved an average fragment-wise intersection over union (IoU) of 0.930, demonstrating satisfactory accuracy. However, in the X-ray task, the best algorithm achieved an IoU of 0.774, which is promising but not yet sufficient for intra-operative decision-making, reflecting the inherent challenges of fragment overlap in projection imaging. Beyond the quantitative evaluation, the challenge revealed methodological diversity in algorithm design. Variations in instance representation, such as primary-secondary classification versus boundary-core separation, led to differing segmentation strategies. Despite promising results, the challenge also exposed inherent uncertainties in fragment definition, particularly in cases of incomplete fractures. These findings suggest that interactive segmentation approaches, integrating human decision-making with task-relevant information, may be essential for improving model reliability and clinical applicability.
- Top Cited Papers
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
ToothSeg: Robust Tooth Instance Segmentation and Numbering in CBCT using Deep Learning and Self-Correction
Accurate interpretation of cone-beam computed tomography (CBCT) scans is critical for oral diagnosis and treatment planning. Existing methods for automated tooth segmentation in CBCT face challenges, such as difficulties in generalizing across imaging artifacts and anatomical variations, as well as requiring manual revisions in many cases. To address these limitations, this study introduces ToothSeg, a fully automated approach for tooth instance segmentation and numbering in CBCT using deep learning and self-correction. ToothSeg combines semantic and instance segmentation into a unified method where their respective strengths are complemented. In particular, self-correction is employed when combining the segmentations, resolving merged or split teeth and determining the optimal sequence of tooth numbers for each dental arch. We conducted a comprehensive evaluation using a diverse in-house dataset (n = 1282, 25+ devices) and the publicly available ToothFairy2 challenge dataset (n = 480, 1 device), including an ablation study, a comparison to state-of-the-art methods, and an analysis of challenging cases. Compared to an optimized semantic segmentation model, including instance segmentation and self-correction consistently improved tooth segmentation (True Positive Dice: 93.6% to 94.3%) and tooth detection and numbering (multiclass instance F1: 94.2% to 95.5%). Furthermore, ToothSeg outperformed the other methods on both datasets (True Positive Dice: $\boldsymbol{\ge }$ +0.4%, multiclass instance F1: $\boldsymbol{\ge }$ +1.8%), particularly for challenging cases. This study provides a promising approach for automated tooth segmentation and numbering in CBCT, which is significant for reducing manual workload and supporting scalable, data-driven research in oral and craniofacial health. Code and models are publicly available at https://github.com/MIC-DKFZ/ToothSeg.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-12
Top Cited PapersToothSeg: Robust Tooth Instance Segmentation and Numbering in CBCT using Deep Learning and Self-Correction
Accurate interpretation of cone-beam computed tomography (CBCT) scans is critical for oral diagnosis and treatment planning. Existing methods for automated tooth segmentation in CBCT face challenges, such as difficulties in generalizing across imaging artifacts and anatomical variations, as well as requiring manual revisions in many cases. To address these limitations, this study introduces ToothSeg, a fully automated approach for tooth instance segmentation and numbering in CBCT using deep learning and self-correction. ToothSeg combines semantic and instance segmentation into a unified method where their respective strengths are complemented. In particular, self-correction is employed when combining the segmentations, resolving merged or split teeth and determining the optimal sequence of tooth numbers for each dental arch. We conducted a comprehensive evaluation using a diverse in-house dataset (n = 1282, 25+ devices) and the publicly available ToothFairy2 challenge dataset (n = 480, 1 device), including an ablation study, a comparison to state-of-the-art methods, and an analysis of challenging cases. Compared to an optimized semantic segmentation model, including instance segmentation and self-correction consistently improved tooth segmentation (True Positive Dice: 93.6% to 94.3%) and tooth detection and numbering (multiclass instance F1: 94.2% to 95.5%). Furthermore, ToothSeg outperformed the other methods on both datasets (True Positive Dice: $\boldsymbol{\ge }$ +0.4%, multiclass instance F1: $\boldsymbol{\ge }$ +1.8%), particularly for challenging cases. This study provides a promising approach for automated tooth segmentation and numbering in CBCT, which is significant for reducing manual workload and supporting scalable, data-driven research in oral and craniofacial health. Code and models are publicly available at https://github.com/MIC-DKFZ/ToothSeg.
- Open Access
- 29 December 2025
- Published by Academy of Digital Humanities - Georgia in Digital Kartvelology
- Vol. 4, 73-82
Non-Destructive Investigation of a Georgian Codex Binding Using a Portable Computed Tomography Scanner
This study demonstrates a non-destructive approach to investigating the structure of bookbindings in historical manuscripts using high-resolution X-ray computed tomography (CT). We applied the portable CT scanner ENCI to a Georgian codex from the Graz University Library, MS 2058/1, the famous Sinai Lectionary. Three-dimensional reconstructions reveal the complex arrangement of the spine, cords, threads, and gatherings of folios. Individual characters written in vermilion and iron gall ink can be digitally segmented and distinguished. These results highlight the potential of X-ray tomography as a powerful, non-invasive tool for the structural and textual analysis of delicate manuscripts, offering new opportunities to study fragile or partially damaged books while preserving their physical integrity.
- 29 December 2025
- Published by Academy of Digital Humanities - Georgia in Digital Kartvelology
- Vol. 4, 73-82
Open AccessNon-Destructive Investigation of a Georgian Codex Binding Using a Portable Computed Tomography Scanner
This study demonstrates a non-destructive approach to investigating the structure of bookbindings in historical manuscripts using high-resolution X-ray computed tomography (CT). We applied the portable CT scanner ENCI to a Georgian codex from the Graz University Library, MS 2058/1, the famous Sinai Lectionary. Three-dimensional reconstructions reveal the complex arrangement of the spine, cords, threads, and gatherings of folios. Individual characters written in vermilion and iron gall ink can be digitally segmented and distinguished. These results highlight the potential of X-ray tomography as a powerful, non-invasive tool for the structural and textual analysis of delicate manuscripts, offering new opportunities to study fragile or partially damaged books while preserving their physical integrity.
- 20 September 2025
- Published by Springer Nature
- p. 436-446
Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentation
- 20 September 2025
- Published by Springer Nature
- p. 436-446
Revisiting 3D Medical Scribble Supervision: Benchmarking Beyond Cardiac Segmentation
- Open Access
Promptable Longitudinal Lesion Segmentation in Whole-Body CT
Accurate segmentation of lesions in longitudinal whole-body CT is essential for monitoring disease progression and treatment response. While automated methods benefit from incorporating longitudinal information, they remain limited in their ability to consistently track individual lesions across time. Task 2 of the autoPET/CT IV Challenge addresses this by providing lesion localizations and baseline delineations, framing the problem as longitudinal promptable segmentation. In this work, we extend the recently proposed LongiSeg framework with promptable capabilities, enabling lesion-specific tracking through point and mask interactions. To address the limited size of the provided training set, we leverage large-scale pretraining on a synthetic longitudinal CT dataset. Our experiments show that pretraining substantially improves the ability to exploit longitudinal context, yielding an improvement of up to 6 Dice points compared to models trained from scratch. These findings demonstrate the effectiveness of combining longitudinal context with interactive prompting for robust lesion tracking. Code is publicly available at https://github.com/MIC-DKFZ/LongiSeg/tree/autoPET.
Open AccessPromptable Longitudinal Lesion Segmentation in Whole-Body CT
Accurate segmentation of lesions in longitudinal whole-body CT is essential for monitoring disease progression and treatment response. While automated methods benefit from incorporating longitudinal information, they remain limited in their ability to consistently track individual lesions across time. Task 2 of the autoPET/CT IV Challenge addresses this by providing lesion localizations and baseline delineations, framing the problem as longitudinal promptable segmentation. In this work, we extend the recently proposed LongiSeg framework with promptable capabilities, enabling lesion-specific tracking through point and mask interactions. To address the limited size of the provided training set, we leverage large-scale pretraining on a synthetic longitudinal CT dataset. Our experiments show that pretraining substantially improves the ability to exploit longitudinal context, yielding an improvement of up to 6 Dice points compared to models trained from scratch. These findings demonstrate the effectiveness of combining longitudinal context with interactive prompting for robust lesion tracking. Code is publicly available at https://github.com/MIC-DKFZ/LongiSeg/tree/autoPET.