Generative Style Transfer for MRI Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909452160991232 |
|---|---|
| author | Chepchirchir, Rancy Sunday, Jill Confidence, Raymond Zhang, Dong Chaudhry, Talha Anazodo, Udunna C. Muchungi, Kendi Zou, Yujing |
| author_facet | Chepchirchir, Rancy Sunday, Jill Confidence, Raymond Zhang, Dong Chaudhry, Talha Anazodo, Udunna C. Muchungi, Kendi Zou, Yujing |
| contents | In Sub-Saharan Africa (SSA), the utilization of lower-quality Magnetic Resonance Imaging (MRI) technology raises questions about the applicability of machine learning methods for clinical tasks. This study aims to provide a robust deep learning-based brain tumor segmentation (BraTS) method tailored for the SSA population using a threefold approach. Firstly, the impact of domain shift from the SSA training data on model efficacy was examined, revealing no significant effect. Secondly, a comparative analysis of 3D and 2D full-resolution models using the nnU-Net framework indicates similar performance of both the models trained for 300 epochs achieving a five-fold cross-validation score of 0.93. Lastly, addressing the performance gap observed in SSA validation as opposed to the relatively larger BraTS glioma (GLI) validation set, two strategies are proposed: fine-tuning SSA cases using the GLI+SSA best-pretrained 2D fullres model at 300 epochs, and introducing a novel neural style transfer-based data augmentation technique for the SSA cases. This investigation underscores the potential of enhancing brain tumor prediction within SSA's unique healthcare landscape. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generative Style Transfer for MRI Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa Chepchirchir, Rancy Sunday, Jill Confidence, Raymond Zhang, Dong Chaudhry, Talha Anazodo, Udunna C. Muchungi, Kendi Zou, Yujing Image and Video Processing Artificial Intelligence Machine Learning Medical Physics In Sub-Saharan Africa (SSA), the utilization of lower-quality Magnetic Resonance Imaging (MRI) technology raises questions about the applicability of machine learning methods for clinical tasks. This study aims to provide a robust deep learning-based brain tumor segmentation (BraTS) method tailored for the SSA population using a threefold approach. Firstly, the impact of domain shift from the SSA training data on model efficacy was examined, revealing no significant effect. Secondly, a comparative analysis of 3D and 2D full-resolution models using the nnU-Net framework indicates similar performance of both the models trained for 300 epochs achieving a five-fold cross-validation score of 0.93. Lastly, addressing the performance gap observed in SSA validation as opposed to the relatively larger BraTS glioma (GLI) validation set, two strategies are proposed: fine-tuning SSA cases using the GLI+SSA best-pretrained 2D fullres model at 300 epochs, and introducing a novel neural style transfer-based data augmentation technique for the SSA cases. This investigation underscores the potential of enhancing brain tumor prediction within SSA's unique healthcare landscape. |
| title | Generative Style Transfer for MRI Image Segmentation: A Case of Glioma Segmentation in Sub-Saharan Africa |
| topic | Image and Video Processing Artificial Intelligence Machine Learning Medical Physics |
| url | https://arxiv.org/abs/2501.04734 |