Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912930861154304 |
|---|---|
| author | Usman, Annayah Khan, Behraj Syed, Tahir Qasim |
| author_facet | Usman, Annayah Khan, Behraj Syed, Tahir Qasim |
| contents | Precise volumetric delineation of hippocampal structures is essential for quantifying neurodevelopmental trajectories in pre-term and term infants, where subtle morphological variations may carry prognostic significance. While foundation encoders trained on large-scale visual data offer discriminative representations, their 2D formulation is a limitation with respect to the $3$D organization of brain anatomy. We propose a volumetric segmentation strategy that reconciles this tension through a structured window-based disassembly-reassembly mechanism: the global MRI volume is decomposed into non-overlapping 3D windows or sub-cubes, each processed via a separate decoding arm built upon frozen high-fidelity features, and subsequently reassembled prior to a ground-truth correspendence using a dense-prediction head. This architecture preserves constant a decoder memory footprint while forcing predictions to lie within an anatomically consistent geometry. Evaluated on the ALBERT dataset for hippocampal segmentation, the proposed approach achieves a Dice score of 0.65 for a single 3D window. The method demonstrates that volumetric anatomical structure could be recovered from frozen 2D foundation representations through structured compositional decoding, and offers a principled and generalizable extension for foundation models for 3D medical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23962 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images Usman, Annayah Khan, Behraj Syed, Tahir Qasim Image and Video Processing Computer Vision and Pattern Recognition Precise volumetric delineation of hippocampal structures is essential for quantifying neurodevelopmental trajectories in pre-term and term infants, where subtle morphological variations may carry prognostic significance. While foundation encoders trained on large-scale visual data offer discriminative representations, their 2D formulation is a limitation with respect to the $3$D organization of brain anatomy. We propose a volumetric segmentation strategy that reconciles this tension through a structured window-based disassembly-reassembly mechanism: the global MRI volume is decomposed into non-overlapping 3D windows or sub-cubes, each processed via a separate decoding arm built upon frozen high-fidelity features, and subsequently reassembled prior to a ground-truth correspendence using a dense-prediction head. This architecture preserves constant a decoder memory footprint while forcing predictions to lie within an anatomically consistent geometry. Evaluated on the ALBERT dataset for hippocampal segmentation, the proposed approach achieves a Dice score of 0.65 for a single 3D window. The method demonstrates that volumetric anatomical structure could be recovered from frozen 2D foundation representations through structured compositional decoding, and offers a principled and generalizable extension for foundation models for 3D medical applications. |
| title | Extending 2D foundational DINOv3 representations to 3D segmentation of neonatal brain MR images |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.23962 |