TY - JOUR A1 - Kofler, Andreas A1 - Wald, Christian A1 - Kolbitsch, Christoph A1 - von Tycowicz, Christoph A1 - Ambellan, Felix T1 - Joint Reconstruction and Segmentation in Undersampled 3D Knee MRI combining Shape Knowledge and Deep Learning JF - Physics in Medicine and Biology N2 - Task-adapted image reconstruction methods using end-to-end trainable neural networks (NNs) have been proposed to optimize reconstruction for subsequent processing tasks, such as segmentation. However, their training typically requires considerable hardware resources and thus, only relatively simple building blocks, e.g. U-Nets, are typically used, which, albeit powerful, do not integrate model-specific knowledge. In this work, we extend an end-to-end trainable task-adapted image reconstruction method for a clinically realistic reconstruction and segmentation problem of bone and cartilage in 3D knee MRI by incorporating statistical shape models (SSMs). The SSMs model the prior information and help to regularize the segmentation maps as a final post-processing step. We compare the proposed method to a state-of-the-art (SOTA) simultaneous multitask learning approach for image reconstruction and segmentation (MTL) and to a complex SSMs-informed segmentation pipeline (SIS). Our experiments show that the combination of joint end-to-end training and SSMs to further regularize the segmentation maps obtained by MTL highly improves the results, especially in terms of mean and maximal surface errors. In particular, we achieve the segmentation quality of SIS and, at the same time, a substantial model reduction that yields a five-fold decimation in model parameters and a computational speedup of an order of magnitude. Remarkably, even for undersampling factors of up to R=8, the obtained segmentation maps are of comparable quality to those obtained by SIS from ground-truth images. Y1 - 2024 U6 - https://doi.org/10.1088/1361-6560/ad3797 VL - 69 IS - 9 ER - TY - JOUR A1 - Caputo, Ariel A1 - Emporio, Marco A1 - Giachetti, Andrea A1 - Cristani, Marco A1 - Borghi, Guido A1 - D'Eusanio, Andrea A1 - Le, Minh-Quan A1 - Nguyen, Hai-Dang A1 - Tran, Minh-Triet A1 - Ambellan, Felix A1 - Hanik, Martin A1 - Navayazdani, Esfandiar A1 - Tycowicz, Christoph von T1 - SHREC 2022 Track on Online Detection of Heterogeneous Gestures JF - Computers and Graphics N2 - This paper presents the outcomes of a contest organized to evaluate methods for the online recognition of heterogeneous gestures from sequences of 3D hand poses. The task is the detection of gestures belonging to a dictionary of 16 classes characterized by different pose and motion features. The dataset features continuous sequences of hand tracking data where the gestures are interleaved with non-significant motions. The data have been captured using the Hololens 2 finger tracking system in a realistic use-case of mixed reality interaction. The evaluation is based not only on the detection performances but also on the latency and the false positives, making it possible to understand the feasibility of practical interaction tools based on the algorithms proposed. The outcomes of the contest's evaluation demonstrate the necessity of further research to reduce recognition errors, while the computational cost of the algorithms proposed is sufficiently low. Y1 - 2022 U6 - https://doi.org/10.1016/j.cag.2022.07.015 VL - 107 SP - 241 EP - 251 ER - TY - GEN A1 - Nava-Yazdani, Esfandiar A1 - Hanik, Martin A1 - Ambellan, Felix A1 - von Tycowicz, Christoph T1 - On Gradient Formulas in an Algorithm for the Logarithm of the Sasaki Metric N2 - The Sasaki metric is the canonical metric on the tangent bundle TM of a Riemannian manifold M. It is highly useful for data analysis in TM (e.g., when one is interested in the statistics of a set of geodesics in M). To this end, computing the Riemannian logarithm is often necessary, and an iterative algorithm was proposed by Muralidharan and Fletcher. In this note, we derive approximation formulas of the energy gradients in their algorithm that we use with success. T3 - ZIB-Report - 22-12 Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:0297-zib-87174 SN - 1438-0064 ER - TY - CHAP A1 - Myers, Adele A1 - Utpala, Saiteja A1 - Talbar, Shubham A1 - Sanborn, Sophia A1 - Shewmake, Christian A1 - Donnat, Claire A1 - Mathe, Johan A1 - Lupo, Umberto A1 - Sonthalia, Rishi A1 - Cui, Xinyue A1 - Szwagier, Tom A1 - Pignet, Arthur A1 - Bergsson, Andri A1 - Hauberg, Søren A1 - Nielsen, Dmitriy A1 - Sommer, Stefan A1 - Klindt, David A1 - Hermansen, Erik A1 - Vaupel, Melvin A1 - Dunn, Benjamin A1 - Xiong, Jeffrey A1 - Aharony, Noga A1 - Pe’er, Itsik A1 - Ambellan, Felix A1 - Hanik, Martin A1 - Navayazdani, Esfandiar A1 - Tycowicz, Christoph von A1 - Miolane, Nina T1 - ICLR 2022 Challenge for Computational Geomerty & Topology: Design and Results T2 - Proceedings of Topology, Algebra, and Geometry in Learning Y1 - 2022 VL - 196 SP - 269 EP - 276 PB - PMLR ER - TY - CHAP A1 - Lüdke, David A1 - Amiranashvili, Tamaz A1 - Ambellan, Felix A1 - Ezhov, Ivan A1 - Menze, Bjoern A1 - Zachow, Stefan T1 - Landmark-free Statistical Shape Modeling via Neural Flow Deformations T2 - Medical Image Computing and Computer Assisted Intervention - MICCAI 2022 N2 - Statistical shape modeling aims at capturing shape variations of an anatomical structure that occur within a given population. Shape models are employed in many tasks, such as shape reconstruction and image segmentation, but also shape generation and classification. Existing shape priors either require dense correspondence between training examples or lack robustness and topological guarantees. We present FlowSSM, a novel shape modeling approach that learns shape variability without requiring dense correspondence between training instances. It relies on a hierarchy of continuous deformation flows, which are parametrized by a neural network. Our model outperforms state-of-the-art methods in providing an expressive and robust shape prior for distal femur and liver. We show that the emerging latent representation is discriminative by separating healthy from pathological shapes. Ultimately, we demonstrate its effectiveness on two shape reconstruction tasks from partial data. Our source code is publicly available (https://github.com/davecasp/flowssm). Y1 - 2022 U6 - https://doi.org/10.1007/978-3-031-16434-7_44 VL - 13432 PB - Springer, Cham ER -