You, Suhang; Reyes, Mauricio (2022). Influence of contrast and texture based image modifications on the performance and attention shift of U-Net models for brain tissue segmentation. Frontiers in neuroimaging, 1(1012639), p. 1012639. Frontiers 10.3389/fnimg.2022.1012639
|
Text
fnimg-01-1012639.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (3MB) | Preview |
Contrast and texture modifications applied during training or test-time have recently shown promising results to enhance the generalization performance of deep learning segmentation methods in medical image analysis. However, a deeper understanding of this phenomenon has not been investigated. In this study, we investigated this phenomenon using a controlled experimental setting, using datasets from the Human Connectome Project and a large set of simulated MR protocols, in order to mitigate data confounders and investigate possible explanations as to why model performance changes when applying different levels of contrast and texture-based modifications. Our experiments confirm previous findings regarding the improved performance of models subjected to contrast and texture modifications employed during training and/or testing time, but further show the interplay when these operations are combined, as well as the regimes of model improvement/worsening across scanning parameters. Furthermore, our findings demonstrate a spatial attention shift phenomenon of trained models, occurring for different levels of model performance, and varying in relation to the type of applied image modification.
Item Type: |
Journal Article (Original Article) |
---|---|
Division/Institute: |
10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research > ARTORG Center - AI in Medical Imaging Laboratory 10 Strategic Research Centers > ARTORG Center for Biomedical Engineering Research |
UniBE Contributor: |
You, Suhang, Reyes, Mauricio |
Subjects: |
600 Technology > 610 Medicine & health 500 Science > 570 Life sciences; biology |
ISSN: |
2813-1193 |
Publisher: |
Frontiers |
Language: |
English |
Submitter: |
Pubmed Import |
Date Deposited: |
10 Aug 2023 10:32 |
Last Modified: |
20 Aug 2023 02:37 |
Publisher DOI: |
10.3389/fnimg.2022.1012639 |
PubMed ID: |
37555149 |
Uncontrolled Keywords: |
brain segmentation image augmentation network interpretability pixel attribution segmentation saliency maps |
BORIS DOI: |
10.48350/185329 |
URI: |
https://boris.unibe.ch/id/eprint/185329 |