About me:
I am a PhD student interested in developing advanced medical image analysis systems for clinical applications, with a focus on surface-based neuroimaging. Before joining AI-Med, I completed the Master’s program Robotics, Cognition, Intelligence at TUM.
E-mail: fabi.bongratz@tum.de
Research interests:
- Medical Image Analysis
- Image Segmentation
- Geometric Deep Learning
- 3D Reconstruction
- Shape Analysis
Publications:
Riedel, Evamaria Olga; Bongratz, Fabian; Zebhauser, Paul Theo; Mühlau, Mark; Wachinger, Christian; Hedderich, Dennis Martin Febrile Infection-Related Epilepsy Syndrome (FIRES) in a Young Adult: A Case Report Highlighting Advanced Neuroimaging Journal Article In: Clinical Neuroradiology, 2025. @article{nokey, |
Madlindl, Patrick; Bongratz, Fabian; Wachinger, Christian Template-Based Cortical Surface Reconstruction with Minimal Energy Deformation Proceedings Article In: Shape in Medical Imaging. ShapeMI 2025. Lecture Notes in Computer Science, pp. 140-149, Springer, 2025. @inproceedings{nokey, |
Stoyanov, Ivan; Bongratz, Fabian; Wachinger, Christian Spherical Brownian Bridge Diffusion Models for Conditional Cortical Thickness Forecasting Proceedings Article In: Shape in Medical Imaging. ShapeMI 2025. Lecture Notes in Computer Science, pp. 150–162, Springer, 2025. @inproceedings{nokey, |
Bongratz, Fabian; Wolf, Tom Nuno; Ramon, Jaume Gual; Wachinger, Christian X-SiT: Inherently Interpretable Surface Vision Transformers for Dementia Diagnosis Proceedings Article In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 680-690, Springer Nature Switzerland, 2025. @inproceedings{nokey,Interpretable models are crucial for supporting clinical deci- sion-making, driving advances in their development and application for medical images. However, the nature of 3D volumetric data makes it inherently challenging to visualize and interpret intricate and complex structures like the cerebral cortex. Cortical surface renderings, on the other hand, provide a more accessible and understandable 3D represen- tation of brain anatomy, facilitating visualization and interactive explo- ration. Motivated by this advantage and the widespread use of surface data for studying neurological disorders, we present the eXplainable Sur- face Vision Transformer (X-SiT). This is the first inherently interpretable neural network that offers human-understandable predictions based on interpretable cortical features. As part of X-SiT, we introduce a proto- typical surface patch decoder for classifying surface patch embeddings, incorporating case-based reasoning with spatially corresponding corti- cal prototypes. The results demonstrate state-of-the-art performance in detecting Alzheimer’s disease and frontotemporal dementia while addi- tionally providing informative prototypes that align with known disease patterns and reveal classification errors. |
Wachinger, Christian; Hedderich, Dennis M; Thalhammer, Melissa; Bongratz, Fabian Individualized mapping of aberrant cortical thickness via stochastic cortical self-reconstruction Journal Article In: Medical Image Analysis, vol. 107, pp. 103788, 2025. @article{nokey,Understanding individual differences in cortical structure is key to advancing diagnostics in neurology and psychiatry. Reference models aid in detecting aberrant cortical thickness, yet site-specific biases limit their direct application to unseen data, and region-wise averages prevent the detection of localized cortical changes. To address these limitations, we developed the Stochastic Cortical Self-Reconstruction (SCSR), a novel method that leverages deep learning to reconstruct cortical thickness maps at the vertex level without needing additional subject information. Trained on over 25,000 healthy individuals, SCSR generates highly individualized cortical reconstructions that can detect subtle thickness deviations. Our evaluations on independent test sets demonstrated that SCSR achieved significantly lower reconstruction errors and identified atrophy patterns that enabled better disease discrimination than established methods. It also hints at cortical thinning in preterm infants that went undetected by existing models, showcasing its versatility. Finally, SCSR excelled in mapping highly resolved cortical deviations of dementia patients from clinical data, highlighting its potential for supporting diagnosis in clinical practice. |
Bongratz, Fabian; Li, Yitong; Elbaroudy, Sama; Wachinger, Christian 3D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces Conference Information Processing in Medical Imaging (IPMI) 2025, 2025. @conference{BongratzLi2025Cor2Vox, |
Rickmann, Anne-Marie; Bongratz, Fabian; Wachinger, Christian Vertex Correspondence and Self-Intersection Reduction in Cortical Surface Reconstruction Journal Article In: IEEE Transactions on Medical Imaging, 2025. @article{nokey, |
Bongratz, Fabian; Fecht, Jan; Rickmann, Anne-Marie; Wachinger, Christian V2C-Long: Longitudinal Cortex Reconstruction with Spatiotemporal Correspondence Journal Article In: Imaging Neuroscience, 2025, ISSN: 2837-6056. @article{Bongratz2025_V2CLong, |
Bongratz, Fabian; Karmann, Markus; Holz, Adrian; Bonhoeffer, Moritz; Neumaier, Viktor; Deli, Sarah; Schmitz-Koep, Benita; Zimmer, Claus; Sorg, Christian; Thalhammer, Melissa; Hedderich, Dennis M; Wachinger, Christian MLV^2-Net: Rater-Based Majority-Label Voting for Consistent Meningeal Lymphatic Vessel Segmentation Proceedings Article In: ML4H 2024, 2024. @inproceedings{bongratz2024_mlv, |
Wolf, Tom Nuno; Bongratz, Fabian; Rickmann, Anne-Marie; Pölsterl, Sebastian; Wachinger, Christian Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning Proceedings Article Forthcoming In: AAAI Conference on Artificial Intelligence, 2024, Forthcoming. @inproceedings{nokey,Explaining predictions of black-box neural networks is crucial when applied to decision-critical tasks. Thus, attribution maps are commonly used to identify important image regions, despite prior work showing that humans prefer explanations based on similar examples. To this end, ProtoPNet learns a set of class-representative feature vectors (prototypes) for case-based reasoning. During inference, similarities of latent features to prototypes are linearly classified to form predictions and attribution maps are provided to explain the similarity. In this work, we evaluate whether architectures for case-based reasoning fulfill established axioms required for faithful explanations using the example of ProtoPNet. We show that such architectures allow the extraction of faithful explanations. However, we prove that the attribution maps used to explain the similarities violate the axioms. We propose a new procedure to extract explanations for trained ProtoPNets, named ProtoPFaith. Conceptually, these explanations are Shapley values, calculated on the similarity scores of each prototype. They allow to faithfully answer which prototypes are present in an unseen image and quantify each pixel's contribution to that presence, thereby complying with all axioms. The theoretical violations of ProtoPNet manifest in our experiments on three datasets (CUB-200-2011, Stanford Dogs, RSNA) and five architectures (ConvNet, ResNet, ResNet50, WideResNet50, ResNeXt50). Our experiments show a qualitative difference between the explanations given by ProtoPNet and ProtoPFaith. Additionally, we quantify the explanations with the Area Over the Perturbation Curve, on which ProtoPFaith outperforms ProtoPNet on all experiments by a factor >10**3. |
Bongratz, Fabian; Rickmann, Anne-Marie; Wachinger, Christian Neural deformation fields for template-based reconstruction of cortical surfaces from MRI Journal Article In: Medical Image Analysis, vol. 93, pp. 103093, 2024, ISSN: 1361-8415. @article{BongratzV2CFlow2024,The reconstruction of cortical surfaces is a prerequisite for quantitative analyses of the cerebral cortex in magnetic resonance imaging (MRI). Existing segmentation-based methods separate the surface registration from the surface extraction, which is computationally inefficient and prone to distortions. We introduce Vox2Cortex-Flow (V2C-Flow), a deep mesh-deformation technique that learns a deformation field from a brain template to the cortical surfaces of an MRI scan. To this end, we present a geometric neural network that models the deformation-describing ordinary differential equation in a continuous manner. The network architecture comprises convolutional and graph-convolutional layers, which allows it to work with images and meshes at the same time. V2C-Flow is not only very fast, requiring less than two seconds to infer all four cortical surfaces, but also establishes vertex-wise correspondences to the template during reconstruction. In addition, V2C-Flow is the first approach for cortex reconstruction that models white matter and pial surfaces jointly, therefore avoiding intersections between them. Our comprehensive experiments on internal and external test data demonstrate that V2C-Flow results in cortical surfaces that are state-of-the-art in terms of accuracy. Moreover, we show that the established correspondences are more consistent than in FreeSurfer and that they can directly be utilized for cortex parcellation and group analyses of cortical thickness. |
Bongratz, Fabian; Rickmann, Anne-Marie; Wachinger, Christian Abdominal organ segmentation via deep diffeomorphic mesh deformations Journal Article In: Scientific Reports, vol. 13, no. 1, 2023. @article{BongratzAbdominal2023,Abdominal organ segmentation from CT and MRI is an essential prerequisite for surgical planning and computer-aided navigation systems. It is challenging due to the high variability in the shape, size, and position of abdominal organs. Three-dimensional numeric representations of abdominal shapes with point-wise correspondence to a template are further important for quantitative and statistical analyses thereof. Recently, template-based surface extraction methods have shown promising advances for direct mesh reconstruction from volumetric scans. However, the generalization of these deep learning-based approaches to different organs and datasets, a crucial property for deployment in clinical environments, has not yet been assessed. We close this gap and employ template-based mesh reconstruction methods for joint liver, kidney, pancreas, and spleen segmentation. Our experiments on manually annotated CT and MRI data reveal limited generalization capabilities of previous methods to organs of different geometry and weak performance on small datasets. We alleviate these issues with a novel deep diffeomorphic mesh-deformation architecture and an improved training scheme. The resulting method, UNetFlow, generalizes well to all four organs and can be easily fine-tuned on new data. Moreover, we propose a simple registration-based post-processing that aligns voxel and mesh outputs to boost segmentation accuracy. |
Rickmann, Anne-Marie; Bongratz, Fabian; Wachinger, Christian Vertex Correspondence in Cortical Surface Reconstruction Conference Medical Image Computing and Computer Assisted Intervention -- MICCAI 2023, vol. 14227, Springer Nature Switzerland, Cham, 2023, ISBN: 978-3-031-43993-3. @conference{rickmann_v2cc_2023,Mesh-based cortical surface reconstruction is a fundamental task in neuroimaging that enables highly accurate measurements of brain morphology. Vertex correspondence between a patient's cortical mesh and a group template is necessary for comparing cortical thickness and other measures at the vertex level. However, post-processing methods for generating vertex correspondence are time-consuming and involve registering and remeshing a patient's surfaces to an atlas. Recent deep learning methods for cortex reconstruction have neither been optimized for generating vertex correspondence nor have they analyzed the quality of such correspondence. In this work, we propose to learn vertex correspondence by optimizing an L1 loss on registered surfaces instead of the commonly used Chamfer loss. This results in improved inter- and intra-subject correspondence suitable for direct group comparison and atlas-based parcellation. We demonstrate that state-of-the-art methods provide insufficient correspondence for mapping parcellations, highlighting the importance of optimizing for accurate vertex correspondence. |
Rickmann, Anne-Marie; Bongratz, Fabian; P"olsterl, Sebastian; Sarasua, Ignacio; Wachinger, Christian Joint Reconstruction and Parcellation of Cortical Surfaces Proceedings Article In: International Workshop on Machine Learning in Clinical Neuroimaging, pp. 3–12, Springer, 2022. @inproceedings{rickmann2022joint, |
Bongratz, Fabian; Rickmann, Anne-Marie; Pölsterl, Sebastian; Wachinger, Christian Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks Proceedings Article In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. @inproceedings{Bongratz_2022_CVPR,The reconstruction of cortical surfaces from brain magnetic resonance imaging (MRI) scans is essential for quantitative analyses of cortical thickness and sulcal morphology. Although traditional and deep learning-based algorithmic pipelines exist for this purpose, they have two major drawbacks: lengthy runtimes of multiple hours (traditional) or intricate post-processing, such as mesh extraction and topology correction (deep learning-based). In this work, we address both of these issues and propose Vox2Cortex, a deep learning-based algorithm that directly yields topologically correct, three-dimensional meshes of the boundaries of the cortex. Vox2Cortex leverages convolutional and graph convolutional neural networks to deform an initial template to the densely folded geometry of the cortex represented by an input MRI scan. We show in extensive experiments on three brain MRI datasets that our meshes are as accurate as the ones reconstructed by state-of-the-art methods in the field, without the need for time- and resource-intensive post-processing. To accurately reconstruct the tightly folded cortex, we work with meshes containing about 168,000 vertices at test time, scaling deep explicit reconstruction methods to a new level. |
You must be logged in to post a comment.