{"ID":2891563,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16119","arxiv_id":"2507.16119","title":"Universal Wavelet Units in 3D Retinal Layer Segmentation","abstract":"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.","short_abstract":"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, i...","url_abs":"https://arxiv.org/abs/2507.16119","url_pdf":"https://arxiv.org/pdf/2507.16119v1","authors":"[\"An D. Le\",\"Hung Nguyen\",\"Melanie Tran\",\"Jesse Most\",\"Dirk-Uwe G. Bartsch\",\"William R Freeman\",\"Shyamanga Borooah\",\"Truong Q. Nguyen\",\"Cheolhong An\"]","published":"2025-07-22T00:11:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"eess.SP\"]","methods":"[]","has_code":false}