A Patch-based Student-Teacher Pyramid Matching Approach to Anomaly Detection in 3D Magnetic Resonance Imaging

Johannes Schwarz, Lena Will, Jörg Wellmer, Axel Mosig
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1357-1370, 2024.

Abstract

Anomaly detection on 3D magnet resonance images (MRI) is of high medical relevance in the context of detecting lesions associated with different diseases. Yet, reliable anomaly detection in MRI images involves major challenges, specifically taking into account information in 3D, and the need to localize relatively small and subtle abnormalities within the context of whole organ MRIs. In this paper, a top-down approach, which uses student-teacher feature pyramid matching (STFPM) for detecting anomalies at image and voxel level, is applied to 3D brain MRI inputs. The combination of a 3D patch based self-supervised pre-training and axial-coronal-sagittal (ACS) convolutions pushes the performance above that of f-AnoGAN (bottom-up). The evaluation is based on a tumor dataset.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-schwarz24a, title = {A Patch-based Student-Teacher Pyramid Matching Approach to Anomaly Detection in 3D Magnetic Resonance Imaging}, author = {Schwarz, Johannes and Will, Lena and Wellmer, J\"org and Mosig, Axel}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1357--1370}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/schwarz24a/schwarz24a.pdf}, url = {https://proceedings.mlr.press/v250/schwarz24a.html}, abstract = {Anomaly detection on 3D magnet resonance images (MRI) is of high medical relevance in the context of detecting lesions associated with different diseases. Yet, reliable anomaly detection in MRI images involves major challenges, specifically taking into account information in 3D, and the need to localize relatively small and subtle abnormalities within the context of whole organ MRIs. In this paper, a top-down approach, which uses student-teacher feature pyramid matching (STFPM) for detecting anomalies at image and voxel level, is applied to 3D brain MRI inputs. The combination of a 3D patch based self-supervised pre-training and axial-coronal-sagittal (ACS) convolutions pushes the performance above that of f-AnoGAN (bottom-up). The evaluation is based on a tumor dataset.} }
Endnote
%0 Conference Paper %T A Patch-based Student-Teacher Pyramid Matching Approach to Anomaly Detection in 3D Magnetic Resonance Imaging %A Johannes Schwarz %A Lena Will %A Jörg Wellmer %A Axel Mosig %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-schwarz24a %I PMLR %P 1357--1370 %U https://proceedings.mlr.press/v250/schwarz24a.html %V 250 %X Anomaly detection on 3D magnet resonance images (MRI) is of high medical relevance in the context of detecting lesions associated with different diseases. Yet, reliable anomaly detection in MRI images involves major challenges, specifically taking into account information in 3D, and the need to localize relatively small and subtle abnormalities within the context of whole organ MRIs. In this paper, a top-down approach, which uses student-teacher feature pyramid matching (STFPM) for detecting anomalies at image and voxel level, is applied to 3D brain MRI inputs. The combination of a 3D patch based self-supervised pre-training and axial-coronal-sagittal (ACS) convolutions pushes the performance above that of f-AnoGAN (bottom-up). The evaluation is based on a tumor dataset.
APA
Schwarz, J., Will, L., Wellmer, J. & Mosig, A.. (2024). A Patch-based Student-Teacher Pyramid Matching Approach to Anomaly Detection in 3D Magnetic Resonance Imaging. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1357-1370 Available from https://proceedings.mlr.press/v250/schwarz24a.html.

Related Material