I am heading the laboratory for Artificial Intelligence in Medical Imaging. I have previously completed post-doctoral training at the Medical Vision Group in the Computer Science and Artificial Intelligence Lab at MIT and the Lab for Computational Neuroimaging, Department of Neurology at Harvard medical school. I received my PhD and Diploma from the Computer Science Department at TU München.
Tel: 089 4400 56900
Email: christian at ai-med dot de
Networks: Research Gate | LinkedIn | ORCID
Publications: Google Scholar | DBLP | arXiv
Code: GitHub
Demo: QuickNAT
Old websites: MIT | TUM
Publications
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. |
Ghahremani, Morteza; Wachinger, Christian RegBN: Batch Normalization of Multimodal Data with Regularization Journal Article In: Advances in Neural Information Processing Systems (NeurIPS 2023), 2023. @article{ghahremani2023regbn, |
Gaus, Richard; Pölsterl, Sebastian; Greimel, Ellen; Schulte-Körne, Gerd; Wachinger, Christian In: JCPP Adv, vol. 3, no. 4, pp. e12184, 2023, ISSN: 2692-9384. @article{pmid38054056, BACKGROUND: Prediction of mental disorders based on neuroimaging is an emerging area of research with promising first results in adults. However, research on the unique demographic of children is underrepresented and it is doubtful whether findings obtained on adults can be transferred to children. METHODS: Using data from 6916 children aged 9-10 in the multicenter Adolescent Brain Cognitive Development study, we extracted 136 regional volume and thickness measures from structural magnetic resonance images to rigorously evaluate the capabilities of machine learning to predict 10 different psychiatric disorders: major depressive disorder, bipolar disorder (BD), psychotic symptoms, attention deficit hyperactivity disorder (ADHD), oppositional defiant disorder, conduct disorder, post-traumatic stress disorder, obsessive-compulsive disorder, generalized anxiety disorder, and social anxiety disorder. For each disorder, we performed cross-validation and assessed whether models discovered a true pattern in the data via permutation testing. RESULTS: Two of 10 disorders can be detected with statistical significance when using advanced models that (i) allow for non-linear relationships between neuroanatomy and disorder, (ii) model interdependencies between disorders, and (iii) avoid confounding due to sociodemographic factors: ADHD (AUROC = 0.567, = 0.002) and BD (AUROC = 0.551, = 0.002). In contrast, traditional models perform consistently worse and predict only ADHD with statistical significance (AUROC = 0.529, = 0.002). CONCLUSION: While the modest absolute classification performance does not warrant application in the clinic, our results provide empirical evidence that embracing and explicitly accounting for the complexities of mental disorders via advanced machine learning models can discover patterns that would remain hidden with traditional models. |
Wachinger, Christian; Wolf, Tom Nuno; Pölsterl, Sebastian Deep learning for the prediction of type 2 diabetes mellitus from neck-to-knee Dixon MRI in the UK biobank Journal Article In: Heliyon, vol. 9, no. 11, 2023. @article{nokey, |
Wachinger, Christian; Wolf, Tom Nuno; Pölsterl, Sebastian Deep learning for the prediction of type 2 diabetes mellitus from neck-to-knee Dixon MRI in the UK biobank Journal Article In: Heliyon, vol. 9, no. 11, pp. e22239, 2023, ISSN: 2405-8440. @article{pmid38034698, RATIONALE AND OBJECTIVES: We evaluate the automatic identification of type 2 diabetes from neck-to-knee, two-point Dixon MRI scans with 3D convolutional neural networks on a large, population-based dataset. To this end, we assess the best combination of MRI contrasts and stations for diabetes prediction, and the benefit of integrating risk factors. MATERIALS AND METHODS: Subjects with type 2 diabetes mellitus have been identified in the prospective UK Biobank Imaging study, and a matched control sample has been created to avoid confounding bias. Five-fold cross-validation is used for the evaluation. All scans from the two-point Dixon neck-to-knee sequence have been standardized. A neural network that considers multi-channel MRI input was developed and integrates clinical information in tabular format. An ensemble strategy is used to combine multi-station MRI predictions. A subset with quantitative fat measurements is identified for comparison to prior approaches. RESULTS: MRI scans from 3406 subjects (mean age, 66.2 years ± 7.1 [standard deviation]; 1128 women) were analyzed with 1703 diabetics. A balanced accuracy of 78.7 %, AUC ROC of 0.872, and an average precision of 0.878 was obtained for the classification of diabetes. The ensemble over multiple Dixon MRI stations yields better performance than selecting the individually best station. Moreover, combining fat and water scans as multi-channel inputs to the networks improves upon just using single contrasts as input. Integrating clinical information about known risk factors of diabetes in the network boosts the performance across all stations and the ensemble. The neural network achieved superior results compared to the prediction based on quantitative MRI measurements. CONCLUSIONS: The developed deep learning model accurately predicted type 2 diabetes from neck-to-knee two-point Dixon MRI scans. |
Feldmann, Lisa; Zsigo, Carolin; Mörtl, Isabelle; Bartling, Jürgen; Wachinger, Christian; Oort, Frans; Schulte-Körne, Gerd; Greimel, Ellen Emotion regulation in adolescents with major depression - Evidence from a combined EEG and eye-tracking study Journal Article In: J Affect Disord, vol. 340, pp. 899–906, 2023, ISSN: 1573-2517. @article{pmid37591354, BACKGROUND: Adolescent major depression (MD) is characterized by deficits in emotion regulation (ER). Little is known about the neurophysiological correlates that are associated with these deficits. Moreover, the additional examination of visual attention during ER would allow a more in-depth understanding of ER deficits but has not yet been applied simultaneously. METHODS: N = 33 adolescents with MD and n = 35 healthy controls (HCs) aged 12-18 years performed an ER task during which they either a) down-regulated their negative affective response to negative images via cognitive reappraisal or b) attended the images without changing their affective response. During the task, the Late Positive Potential (LPP), gaze fixations on emotional image aspects, and self-reported affective responses were collected simultaneously. RESULTS: Compared to HCs, adolescents with MD demonstrated reduced ER success based on self-report but did not differ in LPP amplitudes. Participants in both groups showed increased amplitudes in the middle LPP window when they reappraised negative pictures compared to when they attended them. Only in the HC group, increased LPP amplitudes during reappraisal were paralleled by more positive affective responses. LIMITATION: The applied stimuli were part of picture databases and might therefore have limited self-relevance. CONCLUSIONS: Increased LPP amplitude during ER in both groups might be specific to adolescence and might suggest that ER at this age is challenging and requires a high amount of cognitive resources. These findings provide an important starting point for future interventional studies in youth MD. |
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. |
Wolf, Tom Nuno; Pölsterl, Sebastian; Wachinger, Christian Don't PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer's Disease Proceedings Article In: Information Processing in Medical Imaging (IPMI), 2023. @inproceedings{nokey, Alzheimer's disease (AD) has a complex and multifactorial etiology, which requires integrating information about neuroanatomy, genetics, and cerebrospinal fluid biomarkers for accurate diagnosis. Hence, recent deep learning approaches combined image and tabular information to improve diagnostic performance. However, the black-box nature of such neural networks is still a barrier for clinical applications, in which understanding the decision of a heterogeneous model is integral. We propose PANIC, a prototypical additive neural network for interpretable AD classification that integrates 3D image and tabular data. It is interpretable by design and, thus, avoids the need for post-hoc explanations that try to approximate the decision of a network. Our results demonstrate that PANIC achieves state-of-the-art performance in AD classification, while directly providing local and global explanations. Finally, we show that PANIC extracts biologically meaningful signatures of AD, and satisfies a set of desirable desiderata for trustworthy machine learning. Our implementation is available at https://github.com/ai-med/PANIC. |
Zsigo, Carolin; Feldmann, Lisa; Oort, Frans; Piechaczek, Charlotte; Bartling, Jürgen; Schulte-Rüther, Martin; Wachinger, Christian; Schulte-Körne, Gerd; Greimel, Ellen Emotion regulation training for adolescents with major depression: Results from a randomized controlled trial Journal Article In: Emotion, 2023, ISSN: 1931-1516. @article{pmid38060020, Difficulties in emotion regulation (ER) are thought to contribute to the development and maintenance of major depression (MD) in adolescents. In healthy adults, a task-based training of ER has previously proven effective to reduce stress, but no such studies are available for MD. It is also unclear whether findings can be generalized onto adolescent populations. The final sample consisted of = 70 adolescents with MD, who were randomized to a task-based ER training ( = 36) or a control training ( = 34). Across four sessions, the ER group was trained to downregulate negative affect to negative images via reappraisal, while the control group was instructed to attend the images. Rumination, stress-, and affect-related measures were assessed as primary outcomes, behavioral and neurophysiological responses (late positive potential, LPP), as secondary outcomes. The trial was preregistered at clinicaltrials.gov (NCT03957850). While there was no significant differential effect of the ER training on primary outcomes, we found small to moderate effects on rumination in the ER group, but not the control group. During reappraisal (compared to attend), the ER group showed an unexpected increase of the LPP during the first, but not during later training sessions. Although replication in large, multicenter trials is needed, our findings on effect sizes suggest that ER training might be promising to decrease rumination in adolescent MD. The LPP increase at the first session may represent cognitive effort, which was successfully reduced over the sessions. Future studies should research whether training effects transfer to daily life and are durable over a longer time period. (PsycInfo Database Record (c) 2023 APA, all rights reserved). |
Bilic, Patrick; Christ, Patrick; Li, Hongwei Bran; Sarasua, Ignacio; Wachinger, Christian; others, The Liver Tumor Segmentation Benchmark (LiTS) Journal Article In: Med Image Anal, vol. 84, pp. 102680, 2023, ISSN: 1361-8423. @article{pmid36481607, In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094. |
Schmitz-Koep, Benita; Menegaux, Aurore; Zimmermann, Juliana; Thalhammer, Melissa; Neubauer, Antonia; Wendt, Jil; Schinz, David; Wachinger, Christian; Daamen, Marcel; Boecker, Henning; Zimmer, Claus; Priller, Josef; Wolke, Dieter; Bartmann, Peter; Sorg, Christian; Hedderich, Dennis M Aberrant allometric scaling of cortical folding in preterm-born adults Journal Article In: Brain Commun, vol. 5, no. 1, pp. fcac341, 2023, ISSN: 2632-1297. @article{pmid36632185, A universal allometric scaling law has been proposed to describe cortical folding of the mammalian brain as a function of the product of cortical surface area and the square root of cortical thickness across different mammalian species, including humans. Since these cortical properties are vulnerable to developmental disturbances caused by preterm birth in humans and since these alterations are related to cognitive impairments, we tested (i) whether cortical folding in preterm-born adults follows this cortical scaling law and (ii) the functional relevance of potential scaling aberrances. We analysed the cortical scaling relationship in a large and prospectively collected cohort of 91 very premature-born adults (<32 weeks of gestation and/or birthweight <1500 g, very preterm and/or very low birth weight) and 105 full-term controls at 26 years of age based on the total surface area, exposed surface area and average cortical thickness measured with structural magnetic resonance imaging and surface-based morphometry. We found that the slope of the log-transformed cortical scaling relationship was significantly altered in adults (very preterm and/or very low birth weight: 1.24, full-term: 1.14, = 0.018). More specifically, the slope was significantly altered in male adults (very preterm and/or very low birth weight: 1.24, full-term: 1.00, = 0.031), while there was no significant difference in the slope of female adults (very preterm and/or very low birth weight: 1.27, full-term: 1.12, = 0.225). Furthermore, offset was significantly lower compared with full-term controls in both male (very preterm and/or very low birth weight: -0.546, full-term: -0.538, = 0.001) and female adults (very preterm and/or very low birth weight: -0.545, full-term: -0.538, = 0.023), indicating a systematic shift of the regression line after preterm birth. Gestational age had a significant effect on the slope in very preterm and/or very low birth weight adults and more specifically in male very preterm and/or very low birth weight adults, indicating that the difference in slope is specifically related to preterm birth. The shape or tension term of the scaling law had no significant effect on cognitive performance, while the size of the cortex did. Results demonstrate altered scaling of cortical surface and cortical thickness in very premature-born adults. Data suggest altered mechanical forces acting on the cortex after preterm birth. |
Roy, Abhijit Guha; Siddiqui, Shayan; Pölsterl, Sebastian; Farshad, Azade; Navab, Nassir; Wachinger, Christian Few-shot segmentation of 3D medical images Book Section In: Nguyen, Hien Van; Summers, Ronald; Chellappa, Rama (Ed.): Meta Learning With Medical Imaging and Health Informatics Applications, pp. 161-183, Academic Press, 2023, ISBN: 978-0-323-99851-2. @incollection{GUHAROY2023161, Deep neural networks enable highly accurate image segmentation but require large amounts of manually annotated data for supervised training. Few-shot learning aims to overcome this weakness by learning a new class from a few annotated support samples. This chapter introduces our novel few-shot segmentation framework for volumetric medical images with only a few annotated slices. Compared to other related works in computer vision, the main challenges are the absence of pretrained networks and the volumetric nature of medical scans. We address these challenges by proposing a new architecture for few-shot segmentation that incorporates ‘squeeze & excite’ blocks. Our two-armed architecture consists of a conditioner arm, which processes the annotated support input and generates a task-specific representation. This representation is passed on to the segmenter arm that uses this information to segment the new query image. To facilitate efficient interaction between the conditioner and the segmenter arm, we propose to use ‘channel squeeze & spatial excitation’ blocks – a lightweight computational module – that enables heavy interaction between both the arms with negligible increase in model complexity. This contribution allows us to perform image segmentation without relying on a pretrained model, which generally is unavailable for medical scans. Furthermore, we propose an efficient strategy for volumetric segmentation by optimally pairing a few slices of the support volume to all the slices of the query volume. We perform experiments for organ segmentation on whole-body contrast-enhanced CT scans from the Visceral Dataset. Our proposed model outperforms multiple baselines and existing approaches in segmentation accuracy by a significant margin. The source code is available at https://github.com/abhi4ssj/few-shot-segmentation. |
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, |
Wolf, Tom Nuno; Pölsterl, Sebastian; Wachinger, Christian DAFT: A Universal Module to Interweave Tabular Data and 3D Images in CNNs Journal Article In: NeuroImage, pp. 119505, 2022. @article{WOLF2022119505, Prior work on Alzheimer’s Disease (AD) has demonstrated that convolutional neural networks (CNNs) can leverage the high-dimensional image information for diagnosing patients. Beside such data-driven approaches, many established biomarkers exist and are typically represented as tabular data, such as demographics, genetic alterations, or laboratory measurements from cerebrospinal fluid. However, little research has focused on the effective integration of tabular data into existing CNN architectures to improve patient diagnosis. We introduce the Dynamic Affine Feature Map Transform (DAFT), a general-purpose module for CNNs that incites or represses high-level concepts learned from a 3D image by conditioning feature maps of a convolutional layer on both a patient’s image and tabular clinical information. This is achieved by using an auxiliary neural network that outputs a scaling factor and offset to dynamically apply an affine transformation to the feature maps of a convolutional layer. In our experiments on AD diagnosis and time-to-dementia prediction, we show that the DAFT is highly effective in combining 3D image and tabular information by achieving a mean balanced accuracy of 0.622 for diagnosis, and mean c-index of 0.748 for time-to-dementia prediction, thus outperforming all baseline methods. Finally, our extensive ablation study and empirical experiments reveal that the performance improvement due to the DAFT is robust with respect to many design choices. |
Antonelli, Michela; Reinke, Annika; Sarasua, Ignacio; Wachinger, Christian; others, The Medical Segmentation Decathlon Journal Article In: Nat Commun, vol. 13, no. 1, pp. 4128, 2022, ISSN: 2041-1723. @article{pmid35840566, International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)-a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training. |
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. |
Ignacio Sarasua, Sebastian Pölsterl; Wachinger, Christian Hippocampal Representations for Deep Learning on Alzheimer's Disease Journal Article In: Scientific reports, vol. 12, no. 1, pp. 1-13, 2022, ISSN: 2045-2322. @article{sarasua2022hippocampal, Deep learning offers a powerful approach for analyzing hippocampal changes in Alzheimer's disease (AD) without relying on handcrafted features. Nevertheless, an input format needs to be selected to pass the image information to the neural network, which has wide ramifications for the analysis, but has not been evaluated yet. We compare five hippocampal representations (and their respective tailored network architectures) that span from raw images to geometric representations like meshes and point clouds. We performed a thorough evaluation for the prediction of AD diagnosis and time-to-dementia prediction with experiments on an independent test dataset. In addition, we evaluated the ease of interpretability for each representation-network pair. |
Ronge, Raphael; Nho, Kwangsik; Wachinger, Christian; Pölsterl, Sebastian Alzheimer's Disease Diagnosis via Deep Factorization Machine Models Conference Machine Learning in Medical Imaging (MLMI), 2021. @conference{Ronge2021, The current state-of-the-art deep neural networks (DNNs) for Alzheimer's Disease diagnosis use different biomarker combinations to classify patients, but do not allow extracting knowledge about the interactions of biomarkers. However, to improve our understanding of the disease, it is paramount to extract such knowledge from the learned model. In this paper, we propose a Deep Factorization Machine model that combines the ability of DNNs to learn complex relationships and the ease of interpretability of a linear model. The proposed model has three parts: (i) an embedding layer to deal with sparse categorical data, (ii) a Factorization Machine to efficiently learn pairwise interactions, and (iii) a DNN to implicitly model higher order interactions. In our experiments on data from the Alzheimer's Disease Neuroimaging Initiative, we demonstrate that our proposed model classifies cognitive normal, mild cognitive impaired, and demented patients more accurately than competing models. In addition, we show that valuable knowledge about the interactions among biomarkers can be obtained. |
Gröger, Fabian; Rickmann, Anne-Marie; Wachinger, Christian STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains Conference Machine Learning in Medical Imaging (MLMI), 2021. @conference{Gröger2021, We propose an unsupervised domain adaptation (UDA) approach for white matter hyperintensity (WMH) segmentation, which uses Self-TRaining with Uncertainty DEpendent Label refinement (STRUDEL). Self-training has recently been introduced as a highly effective method for UDA, which is based on self-generated pseudo labels. However, pseudo labels can be very noisy and therefore deteriorate model performance. We propose to predict the uncertainty of pseudo labels and integrate it in the training process with an uncertainty-guided loss function to high- light labels with high certainty. STRUDEL is further improved by incorporating the segmentation output of an existing method in the pseudo label generation that showed high robustness for WMH segmentation. In our experiments, we evaluate STRUDEL with a standard U-Net and a modified network with a higher receptive field. Our results on WMH segmentation across datasets demonstrate the significant improvement of STRUDEL with respect to standard self-training. |
Sarasua, Ignacio; Pölsterl, Sebastian; Wachinger, Christian TransforMesh: A Transformer Network for Longitudinal modeling of Anatomical Meshes Conference Machine Learning in Medical Imaging (MLMI), 2021. @conference{sarasua2021transformesh, The longitudinal modeling of neuroanatomical changes related to Alzheimer's disease (AD) is crucial for studying the progression of the disease. To this end, we introduce TransforMesh, a spatio-temporal network based on transformers that models longitudinal shape changes on 3D anatomical meshes. While transformer and mesh networks have recently shown impressive performances in natural language processing and computer vision, their application to medical image analysis has been very limited. To the best of our knowledge, this is the first work that combines transformer and mesh networks. Our results show that TransforMesh can model shape trajectories better than other baseline architectures that do not capture temporal dependencies. Moreover, we also explore the capabilities of TransforMesh in detecting structural anomalies of the hippocampus in patients developing AD. |
Pölsterl, Sebastian; Aigner, Christina; Wachinger, Christian Scalable, Axiomatic Explanations of Deep Alzheimer's Diagnosis from Heterogeneous Data Conference Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021. @conference{Poelsterl2021-svehnn, Deep Neural Networks (DNNs) have an enormous potential to learn from complex biomedical data. In particular, DNNs have been used to seamlessly fuse heterogeneous information from neuroanatomy, genetics, biomarkers, and neuropsychological tests for highly accurate Alzheimer’s disease diagnosis. On the other hand, their black-box nature is still a barrier for the adoption of such a system in the clinic, where interpretability is absolutely essential. We propose Shapley Value Explanation of Heterogeneous Neural Networks (SVEHNN) for explaining the Alzheimer’s diagnosis made by a DNN from the 3D point cloud of the neuroanatomy and tabular biomarkers. Our explanations are based on the Shapley value, which is the unique method that satisfies all fundamental axioms for local explanations previously established in the literature. Thus, SVEHNN has many desirable characteristics that previous work on interpretability for medical decision making is lacking. To avoid the exponential time complexity of the Shapley value, we propose to transform a given DNN into a Lightweight Probabilistic Deep Network without re-training, thus achieving a complexity only quadratic in the number of features. In our experiments on synthetic and real data, we show that we can closely approximate the exact Shapley value with a dramatically reduced runtime and can reveal the hidden knowledge the network has learned from the data. |
Pölsterl, Sebastian; Wolf, Tom Nuno; Wachinger, Christian Combining 3D Image and Tabular Data via the Dynamic Affine Feature Map Transform Conference Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021. @conference{Poelsterl2021-daft, Prior work on diagnosing Alzheimer’s disease from magnetic resonance images of the brain established that convolutional neural networks (CNNs) can leverage the high-dimensional image information for classifying patients. However, little research focused on how these models can utilize the usually low-dimensional tabular information, such as patient demographics or laboratory measurements. We introduce the Dynamic Affine Feature Map Transform (DAFT), a general-purpose module for CNNs that dynamically rescales and shifts the feature maps of a convolutional layer, conditional on a patient’s tabular clinical information. We show that DAFT is highly effective in combining 3D image and tabular information for diagnosis and time-to-dementia prediction, where it outperforms competing CNNs with a mean balanced accuracy of 0.622 and mean c-index of 0.748, respectively. Our extensive ablation study provides valuable insights into the architectural properties of DAFT. Our implementation is available at https://github.com/ai-med/DAFT. |
Sarasua, Ignacio; Lee, Jonwong; Wachinger, Christian Geometric Deep Learning on Anatomical Meshes for the Prediction of Alzheimer's Disease Conference ISBI: International Symposium on Biomedical Imaging 2021, 2021. @conference{sarasua2021geometric, Geometric deep learning can find representations that are optimal for a given task and therefore improve the performance over pre-defined representations. While current work has mainly focused on point representations, meshes also contain connectivity information and are therefore a more comprehensive characterization of the underlying anatomical surface. In this work, we evaluate four recent geometric deep learning approaches that operate on mesh representations. These approaches can be grouped into template-free and template-based approaches, where the template-based methods need a more elaborate pre-processing step with the definition of a common reference template and correspondences. We compare the different networks for the prediction of Alzheimer's disease based on the meshes of the hippocampus. Our results show advantages for template-based methods in terms of accuracy, number of learnable parameters, and training speed. While the template creation may be limiting for some applications, neuroimaging has a long history of building templates with automated tools readily available. Overall, working with meshes is more involved than working with simplistic point clouds, but they also offer new avenues for designing geometric deep learning architectures. |
Pölsterl, Sebastian; Wachinger, Christian Estimation of Causal Effects in the Presence of Unobserved Confounding in the Alzheimer's Continuum Conference IPMI: International Conference on Information Processing in Medical Imaging 2021, 2021. @conference{Poelsterl2021-causal-effects-in-ad, Studying the relationship between neuroanatomy and cognitive decline due to Alzheimer's has been a major research focus in the last decade. However, to infer cause-effect relationships rather than simple associations from observational data, we need to (i) express the causal relationships leading to cognitive decline in a graphical model, and (ii) ensure the causal effect of interest is identifiable from the collected data. We derive a causal graph from the current clinical knowledge on cause and effect in the Alzheimer's disease continuum, and show that identifiability of the causal effect requires all confounders to be known and measured. However, in complex neuroimaging studies, we neither know all potential confounders nor do we have data on them. To alleviate this requirement, we leverage the dependencies among multiple causes by deriving a substitute confounder via a probabilistic latent factor model. In our theoretical analysis, we prove that using the substitute confounder enables identifiability of the causal effect of neuroanatomy on cognition. We quantitatively evaluate the effectiveness of our approach on semi-synthetic data, where we know the true causal effects, and illustrate its use on real data on the Alzheimer's disease continuum, where it reveals important causes that otherwise would have been missed. |
Wachinger, Christian; Rieckmann, Anna; Pölsterl, Sebastian Detect and correct bias in multi-site neuroimaging datasets Journal Article In: Medical Image Analysis, vol. 67, pp. 101879, 2020. @article{wachinger2020detect, The desire to train complex machine learning algorithms and to increase the statistical power in association studies drives neuroimaging research to use ever-larger datasets. The most obvious way to increase sample size is by pooling scans from independent studies. However, simple pooling is often ill-advised as selection, measurement, and confounding biases may creep in and yield spurious correlations. In this work, we combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging. In the first experiment, Name That Dataset, we provide empirical evidence for the presence of bias by showing that scans can be correctly assigned to their respective dataset with 71.5% accuracy. Given such evidence, we take a closer look at confounding bias, which is often viewed as the main shortcoming in observational studies. In practice, we neither know all potential confounders nor do we have data on them. Hence, we model confounders as unknown, latent variables. Kolmogorov complexity is then used to decide whether the confounded or the causal model provides the simplest factorization of the graphical model. Finally, we present methods for dataset harmonization and study their ability to remove bias in imaging features. In particular, we propose an extension of the recently introduced ComBat algorithm to control for global variation across image features, inspired by adjusting for unknown population stratification in genetics. Our results demonstrate that harmonization can reduce dataset-specific information in image features. Further, confounding bias can be reduced and even turned into a causal relationship. However, harmonization also requires caution as it can easily remove relevant subject-specific information. Code is available at https://github.com/ai-med/Dataset-Bias. |
Pölsterl, Sebastian; Wachinger, Christian Adversarial Learned Molecular Graph Inference and Generation Proceedings Article In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2020. @inproceedings{Poelsterl2020-almgig, Recent methods for generating novel molecules use graph representations of molecules and employ various forms of graph convolutional neural networks for inference. However, training requires solving an expensive graph isomorphism problem, which previous approaches do not address or solve only approximately. In this work, we propose ALMGIG, a likelihood-free adversarial learning framework for inference and de novo molecule generation that avoids explicitly computing a reconstruction loss. Our approach extends generative adversarial networks by including an adversarial cycle-consistency loss to implicitly enforce the reconstruction property. To capture properties unique to molecules, such as valence, we extend the Graph Isomorphism Network to multi-graphs. To quantify the performance of models, we propose to compute the distance between distributions of physicochemical properties with the 1-Wasserstein distance. We demonstrate that ALMGIG more accurately learns the distribution over the space of molecules than all baselines. Moreover, it can be utilized for drug discovery by efficiently searching the space of molecules using molecules' continuous latent representation. Our code is available at https://github.com/ai-med/almgig |
Richards, Rose; Greimel, Ellen; Kliemann, Dorit; Koerte, Inga K; Schulte-Körne, Gerd; Reuter, Martin; Wachinger, Christian Increased Hippocampal Shape Asymmetry and Volumetric Ventricular Asymmetry in Autism Journal Article In: NeuroImage: Clinical, pp. 102207, 2020. @article{richards2020increased, |
Rickmann, Anne-Marie; Roy, Abhijit Guha; Sarasua, Ignacio; Wachinger, Christian Recalibrating 3D ConvNets with Project & Excite Journal Article In: IEEE Transactions on Medical Imaging, 2020. @article{rickmann2020recalibrating, |
Gutmann, Daniel AP; Rospleszcz, Susanne; Rathmann, Wolfgang; Schlett, Christopher L; Peters, Annette; Wachinger, Christian; Gatidis, Sergios; Bamberg, Fabian MRI-Derived Radiomics Features of Hepatic Fat Predict Metabolic States in Individuals without Cardiovascular Disease Journal Article In: Academic Radiology, 2020. @article{gutmann2020mri, |
Reuter, Martin; Wachinger, Christian; Lombaert, Hervé; Paniagua, Beatriz; Goksel, Orcun; Rekik, Islem Shape in Medical Imaging Miscellaneous 2020. @misc{reutershape, |
Özgün, Sinan; Rickmann, Anne-Marie; Roy, Abhijit Guha; Wachinger, Christian Importance Driven Continual Learning for Segmentation Across Domains Proceedings Article In: Liu, Mingxia; Yan, Pingkun; Lian, Chunfeng; Cao, Xiaohuan (Ed.): Machine Learning in Medical Imaging, pp. 423–433, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-59861-7. @inproceedings{10.1007/978-3-030-59861-7_43, The ability of neural networks to continuously learn and adapt to new tasks while retaining prior knowledge is crucial for many applications. However, current neural networks tend to forget previously learned tasks when trained on new ones, i.e., they suffer from Catastrophic Forgetting (CF). The objective of Continual Learning (CL) is to alleviate this problem, which is particularly relevant for medical applications, where it may not be feasible to store and access previously used sensitive patient data. In this work, we propose a Continual Learning approach for brain segmentation, where a single network is consecutively trained on samples from different domains. We build upon an importance driven approach and adapt it for medical image segmentation. Particularly, we introduce a learning rate regularization to prevent the loss of the network's knowledge. Our results demonstrate that directly restricting the adaptation of important network parameters clearly reduces Catastrophic Forgetting for segmentation across domains. Our code is publicly available on https://github.com/ai-med/MAS-LR. |
Senapati, Jyotirmay; Roy, Abhijit Guha; Pölsterl, Sebastian; Gutmann, Daniel; Gatidis, Sergios; Schlett, Christopher; Peters, Anette; Bamberg, Fabian; Wachinger, Christian Bayesian Neural Networks for Uncertainty Estimation of Imaging Biomarkers Proceedings Article In: Liu, Mingxia; Yan, Pingkun; Lian, Chunfeng; Cao, Xiaohuan (Ed.): Machine Learning in Medical Imaging, pp. 270–280, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-59861-7. @inproceedings{10.1007/978-3-030-59861-7_28, Image segmentation enables to extract quantitative measures from scans that can serve as imaging biomarkers for diseases. However, segmentation quality can vary substantially across scans, and therefore yield unfaithful estimates in the follow-up statistical analysis of biomarkers. The core problem is that segmentation and biomarker analysis are performed independently. We propose to propagate segmentation uncertainty to the statistical analysis to account for variations in segmentation confidence. To this end, we evaluate four Bayesian neural networks to sample from the posterior distribution and estimate the uncertainty. We then assign confidence measures to the biomarker and propose statistical models for its integration in group analysis and disease classification. Our results for segmenting the liver in patients with diabetes mellitus clearly demonstrate the improvement of integrating biomarker uncertainty in the statistical inference. |
Sarasua, Ignacio; Poelsterl, Sebastian; Wachinger, Christian Recalibration of Neural Networks for Point Cloud Analysis Proceedings Article In: 3DV, 2020. @inproceedings{sarasua2020recalibration, Spatial and channel re-calibration have become powerful concepts in computer vision. Their ability to capture long-range dependencies is especially useful for those networks that extract local features, such as CNNs. While re-calibration has been widely studied for image analysis, it has not yet been used on shape representations. In this work, we introduce re-calibration modules on deep neural networks for 3D point clouds. We propose a set of re-calibration blocks that extend Squeeze and Excitation blocks and that can be added to any network for 3D point cloud analysis that builds a global descriptor by hierarchically combining features from multiple local neighborhoods. We run two sets of experiments to validate our approach. First, we demonstrate the benefit and versatility of our proposed modules by incorporating them into three state-of-the-art networks for 3D point cloud analysis: PointNet++, DGCNN, and RSCNN. We evaluate each network on two tasks: object classification on ModelNet40, and object part segmentation on ShapeNet. Our results show an improvement of up to 1% in accuracy for ModelNet40 compared to the baseline method. In the second set of experiments, we investigate the benefits of re-calibration blocks on Alzheimer's Disease (AD) diagnosis. Our results demonstrate that our proposed methods yield a 2% increase in accuracy for diagnosing AD and a 2.3% increase in concordance index for predicting AD onset with time-to-event analysis. Concluding, re-calibration improves the accuracy of point cloud architectures, while only minimally increasing the number of parameters. |
Benjamin ; Sarasua Ignacio ; Wachinger Gutierrez-Becker, Christian Discriminative and generative models for anatomical shape analysis on point clouds with deep neural networks Journal Article In: Medical Image Analysis, vol. 67, pp. 101852, 2020. @article{gutierrez2020discriminative, We introduce deep neural networks for the analysis of anatomical shapes that learn a low-dimensional shape representation from the given task, instead of relying on hand-engineered representations. Our framework is modular and consists of several computing blocks that perform fundamental shape processing tasks. The networks operate on unordered point clouds and provide invariance to similarity transformations, avoiding the need to identify point correspondences between shapes. Based on the framework, we assemble a discriminative model for disease classification and age regression, as well as a generative model for the accruate reconstruction of shapes. In particular, we propose a conditional generative model, where the condition vector provides a mechanism to control the generative process. For instance, it enables to assess shape variations specific to a particular diagnosis, when passing it as side information. Next to working on single shapes, we introduce an extension for the joint analysis of multiple anatomical structures, where the simultaneous modeling of multiple structures can lead to a more compact encoding and a better understanding of disorders. We demonstrate the advantages of our framework in comprehensive experiments on real and synthetic data. The key insights are that (i) learning a shape representation specific to the given task yields higher performance than alternative shape descriptors, (ii) multi-structure analysis is both more efficient and more accurate than single-structure analysis, and (iii) point clouds generated by our model capture morphological differences associated to Alzheimer’s disease, to the point that they can be used to train a discriminative model for disease classification. Our framework naturally scales to the analysis of large datasets, giving it the potential to learn characteristic variations in large populations. |
Chauvin, L.; Kumar, K.; Wachinger, C.; Vangel, M.; de Guise, J.; Desrosiers, C.; Wells, W.; Toews, M. Neuroimage signature from salient keypoints is highly specific to individuals and shared by close relatives Journal Article In: NeuroImage, 2019. @article{Chauvin2019, |
Roy, Abhijit Guha; Siddiqui, Shayan; Pölsterl, Sebastian; Navab, Nassir; Wachinger, Christian 'Squeeze & Excite' Guided Few-Shot Segmentation of Volumetric Images Journal Article In: Medical Image Analysis, 2019. @article{few_shot_agr_2019, |
Pölsterl, Sebastian; Gutiérrez-Becker, Benjamı́n; Sarasua, Ignacio; Roy, Abhijit Guha; Wachinger, Christian An AutoML Approach for the Prediction of Fluid Intelligence from MRI-Derived Features Proceedings Article In: Adolescent Brain Cognitive Development Neurocognitive Prediction Challenge (ABCD-NP-Challenge), 2019. @inproceedings{Poelsterl2019-ABCDb, We propose an AutoML approach for the prediction of fluid intelligence from T1-weighted magnetic resonance images. We extracted 122 features from MRI scans and employed Sequential Model-based Algorithm Configuration to search for the best prediction pipeline, including the best data pre-processing and regression model. In total, we evaluated over 2600 prediction pipelines. We studied our final model by employing results from game theory in the form of Shapley values. Results indicate that predicting fluid intelligence from volume measurements is a challenging task with many challenges. We found that our final ensemble of 50 prediction pipelines associated larger parahippocampal gyrus volumes with lower fluid intelligence, and higher pons white matter volume with higher fluid intelligence. |
Pölsterl, Sebastian; Gutiérrez-Becker, Benjamı́n; Sarasua, Ignacio; Roy, Abhijit Guha; Wachinger, Christian Prediction of Fluid Intelligence from T1-Weighted Magnetic Resonance Images Proceedings Article In: Adolescent Brain Cognitive Development Neurocognitive Prediction Challenge (ABCD-NP-Challenge), 2019. @inproceedings{Poelsterl2019-ABCDa, We study predicting fluid intelligence of 9–10 year old children from T1-weighted magnetic resonance images. We extract volume and thickness measurements from MRI scans using FreeSurfer and the SRI24 atlas. We empirically compare two predictive models: (i) an ensemble of gradient boosted trees and (ii) a linear ridge regression model. For both, a Bayesian black-box optimizer for finding the best suitable prediction model is used. To systematically analyze feature importance our model, we employ results from game theory in the form of Shapley values. Our model with gradient boosting and FreeSurfer measures ranked third place among 24 submissions to the ABCD Neurocognitive Prediction Challenge. Our results on feature importance could be used to guide future research on the neurobiological mechanisms behind fluid intelligence in children. |
Pölsterl, Sebastian; Sarasua, Ignacio; Gutiérrez-Becker, Benjamín; Wachinger, Christian A Wide and Deep Neural Network for Survival Analysis from Anatomical Shape and Tabular Clinical Data Proceedings Article In: Data and Machine Learning Advances with Multiple Views Workshop, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2019. @inproceedings{Poelsterl2019-WideAndDeep, We introduce a wide and deep neural network for prediction of progression from patients with mild cognitive impairment to Alzheimer's disease. Information from anatomical shape and tabular clinical data (demographics, biomarkers) are fused in a single neural network. The network is invariant to shape transformations and avoids the need to identify point correspondences between shapes. To account for right censored time-to-event data, i.e., when it is only known that a patient did not develop Alzheimer's disease up to a particular time point, we employ a loss commonly used in survival analysis. Our network is trained end-to-end to combine information from a patient's hippocampus shape and clinical biomarkers. Our experiments on data from the Alzheimer's Disease Neuroimaging Initiative demonstrate that our proposed model is able to learn a shape descriptor that augments clinical biomarkers and outperforms a deep neural network on shape alone and a linear model on common clinical biomarkers. |
Rickmann, Anne-Marie; Roy, Abhijit Guha; Sarasua, Ignacio; Navab, Nassir; Wachinger, Christian 'Project & Excite' Modules for Segmentation of Volumetric Medical Scans Proceedings Article In: Medical Image Computing and Computer Aided Intervention, Springer, 2019. @inproceedings{rickmann2019, Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for image segmentation in medical imaging. Recently, squeeze and excitation (SE) modules and variations thereof have been introduced to recalibrate feature maps channel- and spatial-wise, which can boost performance while only minimally increasing model complexity. So far, the development of SE has focused on 2D images. In this paper, we propose 'Project & Excite' (PE) modules that base upon the ideas of SE and extend them to operating on 3D volumetric images. 'Project & Excite' does not perform global average pooling, but squeezes feature maps along different slices of a tensor separately to retain more spatial information that is subsequently used in the excitation step. We demonstrate that PE modules can be easily integrated in 3D U-Net, boosting performance by 5% Dice points, while only increasing the model complexity by 2%. We evaluate the PE module on two challenging tasks, whole-brain segmentation of MRI scans and whole-body segmentation of CT scans. |
Wachinger, Christian; Becker, Benjamin Gutierrez; Rieckmann, Anna; Pölsterl, Sebastian Quantifying Confounding Bias in Neuroimaging Datasets with Causal Inference Book Section In: Medical Image Computing and Computer Aided Intervention, 2019. @incollection{wachinger2019causal, Neuroimaging datasets keep growing in size to address increasingly complex medical questions. However, even the largest datasets today alone are too small for training complex machine learning models. A potential solution is to increase sample size by pooling scans from several datasets. In this work, we combine 12,207 MRI scans from 15 studies and show that simple pooling is often ill-advised due to introducing various types of biases in the training data. First, we systematically define these biases. Second, we detect bias by experimentally showing that scans can be correctly assigned to their respective dataset with 73.3% accuracy. Finally, we propose to tell causal from confounding factors by quantifying the extent of confounding and causality in a single dataset using causal inference. We achieve this by finding the simplest graphical model in terms of Kolmogorov complexity. As Kolmogorov complexity is not directly computable, we employ the minimum description length to approximate it. We empirically show that our approach is able to estimate plausible causal relationships from real neuroimaging data. |
Gutiérrez-Becker, Benjamin; Wachinger, Christian Learning a Conditional Generative Model for Anatomical Shape Analysis Proceedings Article In: International Conference on Information Processing in Medical Imaging (IPMI), pp. 505–516, Springer 2019. @inproceedings{gutierrez2019learning, |
Paschali, Magdalini; Simson, Walter; Roy, Abhijit Guha; Naeem, Muhammad Ferjad; Göbl, Rüdiger; Wachinger, Christian; Navab, Nassir Manifold Exploring Data Augmentation with Geometric Transformations for Increased Performance and Robustness Journal Article In: International Conference on Information Processing in Medical Imaging (IPMI), 2019. @article{paschali2019data, |
Sailesh Conjeti Abhijit Guha Roy, Nassir Navab Bayesian QuickNAT: Model uncertainty in deep whole-brain segmentation for structure-wise quality control Journal Article In: NeuroImage, vol. 195, 2019. @article{bayquicknat2019, We introduce Bayesian QuickNAT for the automated quality control of whole-brain segmentation on MRI T1 scans. Next to the Bayesian fully convolutional neural network, we also present inherent measures of segmentation uncertainty that allow for quality control per brain structure. For estimating model uncertainty, we follow a Bayesian approach, wherein, Monte Carlo (MC) samples from the posterior distribution are generated by keeping the dropout layers active at test time. Entropy over the MC samples provides a voxel-wise model uncertainty map, whereas expectation over the MC predictions provides the final segmentation. Next to voxel-wise uncertainty, we introduce four metrics to quantify structure-wise uncertainty in segmentation for quality control. We report experiments on four out-of-sample datasets comprising of diverse age range, pathology and imaging artifacts. The proposed structure-wise uncertainty metrics are highly correlated with the Dice score estimated with manual annotation and therefore present an inherent measure of segmentation quality. In particular, the intersection over union over all the MC samples is a suitable proxy for the Dice score. In addition to quality control at scan-level, we propose to incorporate the structure-wise uncertainty as a measure of confidence to do reliable group analysis on large data repositories. We envisage that the introduced uncertainty metrics would help assess the fidelity of automated deep learning based segmentation methods for large-scale population studies, as they enable automated quality control and group analyses in processing large data repositories. |
Roy, Abhijit Guha; Siddiqui, Shayan; Pölsterl, Sebastian; Navab, Nassir; Wachinger, Christian Braintorrent: A peer-to-peer environment for decentralized federated learning Journal Article In: arXiv preprint arXiv:1905.06731, 2019. @article{roy2019braintorrent, |
Roy, Abhijit Guha; Conjeti, Sailesh; Navab, Nassir; Wachinger, Christian QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy Journal Article In: NeuroImage, 2018. @article{quicknat_neuroimage_agr, |
Reuter, Martin; Wachinger, Christian; Lombaert, Hervé; Paniagua, Beatriz; Lüthi, Marcel; Egger, Bernhard Shape in Medical Imaging: International Workshop, ShapeMI 2018 Book Granada, Spain, Springer, 2018. @book{reuter2018shape, |
Wachinger, C.; Toews, M.; Langs, G.; Wells, W.; Golland, P. Keypoint Transfer for Fast Whole-Body Segmentation Journal Article In: IEEE Transactions on Medical Imaging, 2018. @article{wachinger_2018_tmi, |
You must be logged in to post a comment.