SyncAI.news, a Varaisys broadcasting
VoxForge: A Unified Foundation Model for Dense 3D Features Across MRI, CT and PET
RA

Rushil Anirudh, Jayaraman J. Thiagarajan

· 1 min read

ResearcharXiv cs.CV

VoxForge: A Unified Foundation Model for Dense 3D Features Across MRI, CT and PET

arXiv:2611.25309v1 Announce Type: new Abstract: A unified 3D medical foundation model promises reusable, frozen features that serve a wide variety of tasks such as segmentation, classification and registration on MRI, CT and PET as well as specialist models do. Generalist models still need separate backbones for localized and global tasks, specialist models are confined to a single modality, with the concern that spanning modalities under-emphasizes fine anatomy, and both typically rely on end-to-end fine-tuning to be competitive. We present VoxForge, a single encoder that integrates recent advances in 3D architecture, self-distillation and cross-modal curricula to learn transferable features from permissively licensed MRI and CT volumes. We evaluate it strictly frozen, the test a reusable foundation model must pass, against state-of-the-art generalist and specialist models on segmentation, classification and registration across MRI and CT, and on PET, which it never sees. VoxForge has the best or tied-best average rank in every task group, serves localized and global tasks across modalities at the level of state-of-the-art specialists, and is extremely label-efficient, matching top-performing models on TotalSegmentator CT with a tenth of the labels.

Original source

This story was published by arXiv cs.CV and written by Rushil Anirudh, Jayaraman J. Thiagarajan. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News