Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.20300 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908507589050368 |
|---|---|
| author | Sharifian, Peyman Azimi, Mohammad Saber Karimian, AliReza Arabi, Hossein |
| author_facet | Sharifian, Peyman Azimi, Mohammad Saber Karimian, AliReza Arabi, Hossein |
| contents | Deep learning models for medical image analysis often suffer from performance degradation when applied to data from different scanners or protocols, a phenomenon known as domain shift. This study investigates this challenge in the context of sex classification from 3D T1-weighted brain magnetic resonance imaging (MRI) scans using the IXI and OASIS3 datasets. While models achieved high within-domain accuracy (around 0.95) when trained and tested on a single dataset (IXI or OASIS3), we demonstrate a significant performance drop to chance level (about 0.50) when models trained on one dataset are tested on the other, highlighting the presence of a strong domain shift. To address this, we employed the ComBat harmonization technique to align the feature distributions of the two datasets. We evaluated three state-of-the-art 3D deep learning architectures (3D ResNet18, 3D DenseNet, and 3D EfficientNet) across multiple training strategies. Our results show that ComBat harmonization effectively reduces the domain shift, leading to a substantial improvement in cross-domain classification performance. For instance, the cross-domain balanced accuracy of our best model (ResNet18 3D with Attention) improved from approximately 0.50 (chance level) to 0.61 after harmonization. t-SNE visualization of extracted features provides clear qualitative evidence of the reduced domain discrepancy post-harmonization. This work underscores the critical importance of domain adaptation techniques for building robust and generalizable neuroimaging AI models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_20300 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mitigating MRI Domain Shift in Sex Classification: A Deep Learning Approach with ComBat Harmonization Sharifian, Peyman Azimi, Mohammad Saber Karimian, AliReza Arabi, Hossein Medical Physics Deep learning models for medical image analysis often suffer from performance degradation when applied to data from different scanners or protocols, a phenomenon known as domain shift. This study investigates this challenge in the context of sex classification from 3D T1-weighted brain magnetic resonance imaging (MRI) scans using the IXI and OASIS3 datasets. While models achieved high within-domain accuracy (around 0.95) when trained and tested on a single dataset (IXI or OASIS3), we demonstrate a significant performance drop to chance level (about 0.50) when models trained on one dataset are tested on the other, highlighting the presence of a strong domain shift. To address this, we employed the ComBat harmonization technique to align the feature distributions of the two datasets. We evaluated three state-of-the-art 3D deep learning architectures (3D ResNet18, 3D DenseNet, and 3D EfficientNet) across multiple training strategies. Our results show that ComBat harmonization effectively reduces the domain shift, leading to a substantial improvement in cross-domain classification performance. For instance, the cross-domain balanced accuracy of our best model (ResNet18 3D with Attention) improved from approximately 0.50 (chance level) to 0.61 after harmonization. t-SNE visualization of extracted features provides clear qualitative evidence of the reduced domain discrepancy post-harmonization. This work underscores the critical importance of domain adaptation techniques for building robust and generalizable neuroimaging AI models. |
| title | Mitigating MRI Domain Shift in Sex Classification: A Deep Learning Approach with ComBat Harmonization |
| topic | Medical Physics |
| url | https://arxiv.org/abs/2508.20300 |