🎉 Latest News: Our paper on "Vision-Language Transformers in 3D MRI Synthesis" has been accepted at MICCAI 2026!
Home > Publications > OmniVision-3D: Self-Supervised 3D V...
MICCAI 2026 (Oral) (Conference Paper)
Year: 2026 DOI / Link: https://doi.org/10.1007/s11548-026-001

OmniVision-3D: Self-Supervised 3D Vision Transformers for Zero-Shot Volumetric Tumor Detection

Authors & Research Affiliations

Dr. Sarah Chen, Alex Rivera, Prof. Michael Zhang, Dr. Elena Rostova
MedVis AI Research Laboratory, Department of Computer Science & Medical Imaging

Abstract / Summary

We propose OmniVision-3D, a self-supervised foundation model trained on over 50,000 unannotated 3D CT/MRI scans for zero-shot volumetric tumor detection.

Citation (BibTeX)

@article{pub7, title={ OmniVision-3D: Self-Supervised 3D Vision Transformers for Zero-Shot Volumetric Tumor Detection }, author={ Dr. Sarah Chen, Alex Rivera, Prof. Michael Zhang, Dr. Elena Rostova }, journal={ MICCAI 2026 (Oral) }, year={ 2026 }, doi={ https://doi.org/10.1007/s11548-026-001 } }

Related Lab Publications