Universal Wavelet Units in 3D Retinal Layer Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912496421437440 |
|---|---|
| author | Le, An D. Nguyen, Hung Tran, Melanie Most, Jesse Bartsch, Dirk-Uwe G. Freeman, William R Borooah, Shyamanga Nguyen, Truong Q. An, Cheolhong |
| author_facet | Le, An D. Nguyen, Hung Tran, Melanie Most, Jesse Bartsch, Dirk-Uwe G. Freeman, William R Borooah, Shyamanga Nguyen, Truong Q. An, Cheolhong |
| contents | This paper presents the first study to apply tunable wavelet units (UwUs) for 3D retinal layer segmentation from Optical Coherence Tomography (OCT) volumes. To overcome the limitations of conventional max-pooling, we integrate three wavelet-based downsampling modules, OrthLattUwU, BiorthLattUwU, and LS-BiorthLattUwU, into a motion-corrected MGU-Net architecture. These modules use learnable lattice filter banks to preserve both low- and high-frequency features, enhancing spatial detail and structural consistency. Evaluated on the Jacobs Retina Center (JRC) OCT dataset, our framework shows significant improvement in accuracy and Dice score, particularly with LS-BiorthLattUwU, highlighting the benefits of tunable wavelet filters in volumetric medical image segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16119 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Universal Wavelet Units in 3D Retinal Layer Segmentation Le, An D. Nguyen, Hung Tran, Melanie Most, Jesse Bartsch, Dirk-Uwe G. Freeman, William R Borooah, Shyamanga Nguyen, Truong Q. An, Cheolhong Computer Vision and Pattern Recognition Signal Processing This paper presents the first study to apply tunable wavelet units (UwUs) for 3D retinal layer segmentation from Optical Coherence Tomography (OCT) volumes. To overcome the limitations of conventional max-pooling, we integrate three wavelet-based downsampling modules, OrthLattUwU, BiorthLattUwU, and LS-BiorthLattUwU, into a motion-corrected MGU-Net architecture. These modules use learnable lattice filter banks to preserve both low- and high-frequency features, enhancing spatial detail and structural consistency. Evaluated on the Jacobs Retina Center (JRC) OCT dataset, our framework shows significant improvement in accuracy and Dice score, particularly with LS-BiorthLattUwU, highlighting the benefits of tunable wavelet filters in volumetric medical image segmentation. |
| title | Universal Wavelet Units in 3D Retinal Layer Segmentation |
| topic | Computer Vision and Pattern Recognition Signal Processing |
| url | https://arxiv.org/abs/2507.16119 |