# LUMOS: Latent Universal Medical Priors for Segmentation

arXiv: https://arxiv.org/abs/2603.01115 · HTML: https://mlsanity.com/paper/2603.01115/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation](https://mlsanity.com/paper/2406.02918/) (2024)
- [SAM2-UNet: Segment Anything 2 Makes Strong Encoder for Natural and Medical Image Segmentation](https://mlsanity.com/paper/2408.08870/) (2024)
- [MedDINOv3: How to adapt vision foundation models for medical image segmentation?](https://mlsanity.com/paper/2509.02379/) (2025)
- [Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy](https://mlsanity.com/paper/2105.07467/) (2021)
- [SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3](https://mlsanity.com/paper/2509.00833/) (2025)
- [Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation](https://mlsanity.com/paper/2508.20909/) (2025)
- [Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation](https://mlsanity.com/paper/2212.07585/) (2022)
- [Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures](https://mlsanity.com/paper/2407.14754/) (2024)
- [Adapting Vision Foundation Models for Real-time Ultrasound Image Segmentation](https://mlsanity.com/paper/2503.24368/) (2025)
- [Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration](https://mlsanity.com/paper/2509.06467/) (2025)
- [Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts](https://mlsanity.com/paper/2409.06821/) (2024)
- [MedicoSAM: Robust Improvement of SAM for Medical Imaging](https://mlsanity.com/paper/2501.11734/) (2025)
- [DINOv3 with Test-Time Training for Medical Image Registration](https://mlsanity.com/paper/2508.14809/) (2025)
- [Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View](https://mlsanity.com/paper/2407.12870/) (2024)
- [Exploiting DINOv3-Based Self-Supervised Features for Robust Few-Shot Medical Image Segmentation](https://mlsanity.com/paper/2601.08078/) (2026)
- [Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels](https://mlsanity.com/paper/2401.12535/) (2024)

## Abstract (arXiv)

General vision foundation models (VFMs) have been primarily developed on natural images, and their utility for medical image segmentation is therefore often considered to depend on costly adaptation or domain-specific fine-tuning. In this paper, we revisit this assumption from a different perspective: rather than requiring VFM segmentors to relearn visual regularities, we investigate whether the low-level visual priors necessary for anatomical delineation already lie dormant within general VFMs. We observe that frozen VFMs, despite lacking medical supervision, encode transferable visual regularities. These properties are not exclusive to natural images but are also fundamental to medical image understanding. Motivated by this observation, we propose Latent Universal Medical PriOrs for Segmentation (LUMOS), a novel framework that amplifies general VFM priors to conventional medical segmentors. LUMOS consists of two key components: (1) Pathfinder that distills visual cues from a frozen vision foundation model, and (2) Inspiror that sparks the conventional medical networks with spatial guidance from distilled visual regularities. In this way, the segmentor is relieved from learning complex visual regularities entirely from limited medical annotations and can instead focus on task-specific anatomical delineation. Across diverse medical datasets and token-based VFMs, LUMOS shows that general VFMs can serve as spatial prior generators when their frozen token spaces preserve patch-level pattern relevance. DINO provides stable matched-backbone gains, while SigLIP exposes VFM-specific sensitivity caused by its different token granularity and representation objective.