@inproceedings{GoeppelFrikelHaltmeier, author = {G{\"o}ppel, Simon and Frikel, J{\"u}rgen and Haltmeier, Markus}, title = {Data-proximal Neural Networks for Limited-view CT}, series = {Bildverarbeitung f{\"u}r die Medizin 2025 : Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2025 : Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, editor = {Palm, Christoph and Breininger, Katharina and Deserno, Thomas M. and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Tolxdorff, Thomas M.}, publisher = {Springer Fachmedien Wiesbaden}, address = {Wiesbaden}, isbn = {978-3-658-47421-8}, doi = {10.1007/978-3-658-47422-5_41}, pages = {185 -- 190}, abstract = {Limited-angle computed tomography (CT) requires solving an inverse problem that is both ill-conditioned and underdetermined. In recent years, learned reconstruction methods have proven highly effective in addressing this challenge. Most of these methods follow a two-step process: first, an initial reconstruction method is applied to the data to generate an auxiliary reconstruction; second, a neural network is used to map the auxiliary reconstruction closer to the ground truth images. However, when applied to unseen data, there are no guarantees that the network's output will remain consistent with the available measurement data. To address this, we recently introduced a data-proximal network architecture. In this paper, we implement this approach for limited-angle CT and compare its performance with a standard residual network and a null space network.}, language = {en} } @inproceedings{SeligBauerFrikeletal., author = {Selig, Tim and Bauer, Patrick and Frikel, J{\"u}rgen and M{\"a}rz, Thomas and Storath, Martin and Weinmann, Andreas}, title = {Two-stage Approach for Low-dose and Sparse-angle CT Reconstruction using Backprojection}, series = {Bildverarbeitung f{\"u}r die Medizin 2025 (BVM 2025): Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, booktitle = {Bildverarbeitung f{\"u}r die Medizin 2025 (BVM 2025): Proceedings, German Conference on Medical Image Computing, Regensburg March 09-11, 2025}, editor = {Palm, Christoph and Breininger, Katharina and Deserno, Thomas M. and Handels, Heinz and Maier, Andreas and Maier-Hein, Klaus H. and Tolxdorff, Thomas M.}, publisher = {Springer VS}, address = {Wiesbaden}, isbn = {978-3-658-47421-8}, doi = {10.1007/978-3-658-47422-5_67}, pages = {286 -- 291}, abstract = {This paper presents a novel two-stage approach for computed tomography (CT) reconstruction, focusing on sparse-angle and low-dose setups to minimize radiation exposure while maintaining high image quality. Two-stage approaches consist of an initial reconstruction followed by a neural network for image refinement. In the initial reconstruction, we apply the backprojection (BP) instead of the traditional filtered backprojection (FBP). This enhances computational speed and offers potential advantages for more complex geometries, such as fan-beam and cone-beam CT. Additionally, BP addresses noise and artifacts in sparse-angle CT by leveraging its inherent noise-smoothing effect, which reduces streaking artifacts common in FBP reconstructions. For the second stage, we fine-tune the DRUNet proposed by Zhang et al. to further improve reconstruction quality. We call our method BP-DRUNet and evaluate its performance on a synthetically generated ellipsoid dataset alongside thewell-established LoDoPaBCT dataset. Our results show that BP-DRUNet produces competetive results in terms of PSNR and SSIM metrics compared to the FBP-based counterpart, FBPDRUNet, and delivers visually competitive results across all tested angular setups.}, language = {en} } @inproceedings{KlausmannRueckertRauberetal., author = {Klausmann, Leonard and Rueckert, Tobias and Rauber, David and Maerkl, Raphaela and Yildiran, Suemeyye R. and Gutbrod, Max and Palm, Christoph}, title = {DIY challenge blueprint: from organization to technical realization in biomedical image analysis}, series = {Medical Image Computing and Computer Assisted Intervention - MICCAI 2025 ; Proceedings Part XI}, booktitle = {Medical Image Computing and Computer Assisted Intervention - MICCAI 2025 ; Proceedings Part XI}, publisher = {Springer}, address = {Cham}, isbn = {978-3-032-05141-7}, doi = {10.1007/978-3-032-05141-7_9}, pages = {85 -- 95}, abstract = {Biomedical image analysis challenges have become the de facto standard for publishing new datasets and benchmarking different state-of-the-art algorithms. Most challenges use commercial cloud-based platforms, which can limit custom options and involve disadvantages such as reduced data control and increased costs for extended functionalities. In contrast, Do-It-Yourself (DIY) approaches have the capability to emphasize reliability, compliance, and custom features, providing a solid basis for low-cost, custom designs in self-hosted systems. Our approach emphasizes cost efficiency, improved data sovereignty, and strong compliance with regulatory frameworks, such as the GDPR. This paper presents a blueprint for DIY biomedical imaging challenges, designed to provide institutions with greater autonomy over their challenge infrastructure. Our approach comprehensively addresses both organizational and technical dimensions, including key user roles, data management strategies, and secure, efficient workflows. Key technical contributions include a modular, containerized infrastructure based on Docker, integration of open-source identity management, and automated solution evaluation workflows. Practical deployment guidelines are provided to facilitate implementation and operational stability. The feasibility and adaptability of the proposed framework are demonstrated through the MICCAI 2024 PhaKIR challenge with multiple international teams submitting and validating their solutions through our self-hosted platform. This work can be used as a baseline for future self-hosted DIY implementations and our results encourage further studies in the area of biomedical image analysis challenges.}, language = {en} } @inproceedings{BauerFrikel, author = {Bauer, Patrick and Frikel, J{\"u}rgen}, title = {BPConvNet: a deep learning based ρ-Filtered layergram reconstruction method for computed tomography}, series = {AIP Conference Proceedings}, volume = {3315}, booktitle = {AIP Conference Proceedings}, number = {1}, publisher = {AIP Publishing}, issn = {0094-243X}, doi = {10.1063/5.0286063}, abstract = {In this article, we address the reconstruction problem in computed tomography (CT) when dealing with sparse view data. Traditional approaches like filtered backprojection (FBP) often fail under these conditions, leading to streaking artifacts. We propose BPConvNet, a deep learning based version of the ρ-filtered layergram or backprojection filtration (BPF) technique (cf. [1]). Unlike FBP, the BPF method applies filtering (F) after backprojection (BP), hence the name. The proposed BPConvNet adapts the BPF workflow by substituting the filtering step with a residual convolutional neural network. Our numerical experiments demonstrate that BPConvNet is competitive to similar deep learning methods. Moreover, we explain that BPConvNet can be easily adapted to to different CT acquisition geometries, such as fan beam and 3D configurations}, language = {en} } @inproceedings{GutbrodRauberWeberNunesetal., author = {Gutbrod, Max and Rauber, David and Weber Nunes, Danilo and Palm, Christoph}, title = {OpenMIBOOD: Open Medical Imaging Benchmarks for Out-Of-Distribution Detection}, series = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10.-17. June 2025, Nashville}, booktitle = {2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10.-17. June 2025, Nashville}, publisher = {IEEE}, isbn = {979-8-3315-4364-8}, doi = {10.1109/CVPR52734.2025.02410}, pages = {25874 -- 25886}, abstract = {The growing reliance on Artificial Intelligence (AI) in critical domains such as healthcare demands robust mechanisms to ensure the trustworthiness of these systems, especially when faced with unexpected or anomalous inputs. This paper introduces the Open Medical Imaging Benchmarks for Out-Of-Distribution Detection (OpenMIBOOD), a comprehensive framework for evaluating out-of-distribution (OOD) detection methods specifically in medical imaging contexts. OpenMIBOOD includes three benchmarks from diverse medical domains, encompassing 14 datasets divided into covariate-shifted in-distribution, nearOOD, and far-OOD categories. We evaluate 24 post-hoc methods across these benchmarks, providing a standardized reference to advance the development and fair comparison of OODdetection methods. Results reveal that findings from broad-scale OOD benchmarks in natural image domains do not translate to medical applications, underscoring the critical need for such benchmarks in the medical field. By mitigating the risk of exposing AI models to inputs outside their training distribution, OpenMIBOOD aims to support the advancement of reliable and trustworthy AI systems in healthcare. The repository is available at https://github.com/remic-othr/OpenMIBOOD.}, language = {en} }