Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.20256 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915467678973952 |
|---|---|
| author | Low, Zhen Xuen Brandon Zhang, Rory Min, Hang Pham, William Vivash, Lucy Moses, Jasmine Lynch, Miranda Dorfman, Karina Marotta, Cassandra Koh, Shaun Bunyamin, Jacob Rowsthorn, Ella Jarema, Alex Peiris, Himashi Chen, Zhaolin Shultz, Sandy R. Wright, David K. Kong, Dexiao Naismith, Sharon L. O'Brien, Terence J. Xia, Ying Law, Meng Sinclair, Benjamin |
| author_facet | Low, Zhen Xuen Brandon Zhang, Rory Min, Hang Pham, William Vivash, Lucy Moses, Jasmine Lynch, Miranda Dorfman, Karina Marotta, Cassandra Koh, Shaun Bunyamin, Jacob Rowsthorn, Ella Jarema, Alex Peiris, Himashi Chen, Zhaolin Shultz, Sandy R. Wright, David K. Kong, Dexiao Naismith, Sharon L. O'Brien, Terence J. Xia, Ying Law, Meng Sinclair, Benjamin |
| contents | Enlarged perivascular spaces (PVS) are increasingly recognized as biomarkers of cerebral small vessel disease, Alzheimer's disease, stroke, and aging-related neurodegeneration. However, manual segmentation of PVS is time-consuming and subject to moderate inter-rater reliability, while existing automated deep learning models have moderate performance and typically fail to generalize across diverse clinical and research MRI datasets. We adapted MedNeXt-L-k5, a Transformer-inspired 3D encoder-decoder convolutional network, for automated PVS segmentation. Two models were trained: one using a homogeneous dataset of 200 T2-weighted (T2w) MRI scans from the Human Connectome Project-Aging (HCP-Aging) dataset and another using 40 heterogeneous T1-weighted (T1w) MRI volumes from seven studies across six scanners. Model performance was evaluated using internal 5-fold cross validation (5FCV) and leave-one-site-out cross validation (LOSOCV). MedNeXt-L-k5 models trained on the T2w images of the HCP-Aging dataset achieved voxel-level Dice scores of 0.88+/-0.06 (white matter, WM), comparable to the reported inter-rater reliability of that dataset, and the highest yet reported in the literature. The same models trained on the T1w images of the HCP-Aging dataset achieved a substantially lower Dice score of 0.58+/-0.09 (WM). Under LOSOCV, the model had voxel-level Dice scores of 0.38+/-0.16 (WM) and 0.35+/-0.12 (BG), and cluster-level Dice scores of 0.61+/-0.19 (WM) and 0.62+/-0.21 (BG). MedNeXt-L-k5 provides an efficient solution for automated PVS segmentation across diverse T1w and T2w MRI datasets. MedNeXt-L-k5 did not outperform the nnU-Net, indicating that the attention-based mechanisms present in transformer-inspired models to provide global context are not required for high accuracy in PVS segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_20256 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MedNet-PVS: A MedNeXt-Based Deep Learning Model for Automated Segmentation of Perivascular Spaces Low, Zhen Xuen Brandon Zhang, Rory Min, Hang Pham, William Vivash, Lucy Moses, Jasmine Lynch, Miranda Dorfman, Karina Marotta, Cassandra Koh, Shaun Bunyamin, Jacob Rowsthorn, Ella Jarema, Alex Peiris, Himashi Chen, Zhaolin Shultz, Sandy R. Wright, David K. Kong, Dexiao Naismith, Sharon L. O'Brien, Terence J. Xia, Ying Law, Meng Sinclair, Benjamin Computer Vision and Pattern Recognition Artificial Intelligence Enlarged perivascular spaces (PVS) are increasingly recognized as biomarkers of cerebral small vessel disease, Alzheimer's disease, stroke, and aging-related neurodegeneration. However, manual segmentation of PVS is time-consuming and subject to moderate inter-rater reliability, while existing automated deep learning models have moderate performance and typically fail to generalize across diverse clinical and research MRI datasets. We adapted MedNeXt-L-k5, a Transformer-inspired 3D encoder-decoder convolutional network, for automated PVS segmentation. Two models were trained: one using a homogeneous dataset of 200 T2-weighted (T2w) MRI scans from the Human Connectome Project-Aging (HCP-Aging) dataset and another using 40 heterogeneous T1-weighted (T1w) MRI volumes from seven studies across six scanners. Model performance was evaluated using internal 5-fold cross validation (5FCV) and leave-one-site-out cross validation (LOSOCV). MedNeXt-L-k5 models trained on the T2w images of the HCP-Aging dataset achieved voxel-level Dice scores of 0.88+/-0.06 (white matter, WM), comparable to the reported inter-rater reliability of that dataset, and the highest yet reported in the literature. The same models trained on the T1w images of the HCP-Aging dataset achieved a substantially lower Dice score of 0.58+/-0.09 (WM). Under LOSOCV, the model had voxel-level Dice scores of 0.38+/-0.16 (WM) and 0.35+/-0.12 (BG), and cluster-level Dice scores of 0.61+/-0.19 (WM) and 0.62+/-0.21 (BG). MedNeXt-L-k5 provides an efficient solution for automated PVS segmentation across diverse T1w and T2w MRI datasets. MedNeXt-L-k5 did not outperform the nnU-Net, indicating that the attention-based mechanisms present in transformer-inspired models to provide global context are not required for high accuracy in PVS segmentation. |
| title | MedNet-PVS: A MedNeXt-Based Deep Learning Model for Automated Segmentation of Perivascular Spaces |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.20256 |