Frequency Disentangled Learning for Segmentation of Midbrain Structures from Quantitative Susceptibility Mapping Data
| العنوان: | Frequency Disentangled Learning for Segmentation of Midbrain Structures from Quantitative Susceptibility Mapping Data |
|---|---|
| المؤلفون: | Fu, Guanghui, Jimenez, Gabriel, Loizillon, Sophie, Chougar, Lydia, Dormont, Didier, Valabregue, Romain, Burgos, Ninon, Lehéricy, Stéphane, Racoceanu, Daniel, Colliot, Olivier, Group, the ICEBERG Study |
| سنة النشر: | 2023 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Image and Video Processing (eess.IV), FOS: Electrical engineering, electronic engineering, information engineering, Computer Science - Computer Vision and Pattern Recognition, Electrical Engineering and Systems Science - Image and Video Processing |
| الوصف: | One often lacks sufficient annotated samples for training deep segmentation models. This is in particular the case for less common imaging modalities such as Quantitative Susceptibility Mapping (QSM). It has been shown that deep models tend to fit the target function from low to high frequencies. One may hypothesize that such property can be leveraged for better training of deep learning models. In this paper, we exploit this property to propose a new training method based on frequency-domain disentanglement. It consists of two main steps: i) disentangling the image into high- and low-frequency parts and feature learning; ii) frequency-domain fusion to complete the task. The approach can be used with any backbone segmentation network. We apply the approach to the segmentation of the red and dentate nuclei from QSM data which is particularly relevant for the study of parkinsonian syndromes. We demonstrate that the proposed method provides considerable performance improvements for these tasks. We further applied it to three public datasets from the Medical Segmentation Decathlon (MSD) challenge. For two MSD tasks, it provided smaller but still substantial improvements (up to 7 points of Dice), especially under small training set situations. 10 pages |
| اللغة: | English |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7104e4443f51b83ffce42d4e16bef20dTest http://arxiv.org/abs/2302.12980Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....7104e4443f51b83ffce42d4e16bef20d |
| قاعدة البيانات: | OpenAIRE |
| الوصف غير متاح. |