# MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis

arXiv: https://arxiv.org/abs/2509.06617 · HTML: https://mlsanity.com/paper/2509.06617/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Metrics reloaded: Recommendations for image analysis validation](https://mlsanity.com/paper/2206.01653/) (2022)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models](https://mlsanity.com/paper/2310.08825/) (2023)
- [The University of California San Francisco Preoperative Diffuse Glioma MRI (UCSF-PDGM) Dataset](https://mlsanity.com/paper/2109.00356/) (2021)
- [Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks](https://mlsanity.com/paper/2312.02366/) (2023)
- [Semi-supervised learning made simple with self-supervised clustering](https://mlsanity.com/paper/2306.07483/) (2023)
- [Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classification](https://mlsanity.com/paper/2402.07595/) (2024)
- [Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2](https://mlsanity.com/paper/2411.15802/) (2024)
- [General Purpose Image Encoder DINOv2 for Medical Image Registration](https://mlsanity.com/paper/2402.15687/) (2024)

## Built on by (most cited first, 7 of 7)

- [Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans](https://mlsanity.com/paper/2510.10779/) (2025)
- [Pan-FM: A Pan-Organ Foundation Model with Saliency-Guided Masking for Missing Robustness](https://mlsanity.com/paper/2605.07055/) (2026)
- [Improving Medical Image Generative Models with Fr'echet Distance Loss](https://mlsanity.com/paper/2607.13300/) (2026)
- [DINO-Med3D: Bridging Dimension and Domain Gaps in Volumetric Segmentation via Progressive Adaptation](https://mlsanity.com/paper/2606.18886/) (2026)
- [LoRCA: LoRA Cycle Adaptation for Histology to HiP-CT Translation with DINOv3](https://mlsanity.com/paper/2608.10002/) (2026)
- [Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening](https://mlsanity.com/paper/2608.14763/) (2026)
- [Confidence-Gated Cloud-Edge Cascade Triage via Variational Risk Minimization for Medical Imaging](https://mlsanity.com/paper/2610.02269/) (2026)

## Abstract (arXiv)

Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness for multi-modal imaging tasks that are common in many medical fields, such as neurology and oncology. While supervised models perform well in this setting, they fail to leverage unlabeled datasets and struggle with missing modalities, a frequent challenge in clinical settings. To bridge these gaps, we introduce MM-DINOv2, a novel and efficient framework that adapts the pre-trained vision foundation model DINOv2 for multi-modal medical imaging. Our approach incorporates multi-modal patch embeddings, enabling vision foundation models to effectively process multi-modal imaging data. To address missing modalities, we employ full-modality masking, which encourages the model to learn robust cross-modality relationships. Furthermore, we leverage semi-supervised learning to harness large unlabeled datasets, enhancing both the accuracy and reliability of medical predictions. Applied to glioma subtype classification from multi-sequence brain MRI, our method achieves a Matthews Correlation Coefficient (MCC) of 0.6 on an external test set, surpassing state-of-the-art supervised approaches by +11.1%. Our work establishes a scalable and robust solution for multi-modal medical imaging tasks, leveraging powerful vision foundation models pre-trained on natural images while addressing real-world clinical challenges such as missing data and limited annotations.