# OmniRad: A Radiological Foundation Model for Multi-Task Medical Image Analysis

arXiv: https://arxiv.org/abs/2602.04547 · HTML: https://mlsanity.com/paper/2602.04547/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [YOLOv12: Attention-Centric Real-Time Object Detectors](https://mlsanity.com/paper/2502.12524/) (2025)
- [MedViT: A Robust Vision Transformer for Generalized Medical Image Classification](https://mlsanity.com/paper/2302.09462/) (2023)
- [Learning to Merge Tokens in Vision Transformers](https://mlsanity.com/paper/2202.12015/) (2022)
- [MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation](https://mlsanity.com/paper/2409.19483/) (2024)
- [DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology](https://mlsanity.com/paper/2404.05022/) (2024)
- [Real-Time Object Detection Meets DINOv3](https://mlsanity.com/paper/2509.20787/) (2025)
- [Residual-based Language Models are Free Boosters for Biomedical Imaging](https://mlsanity.com/paper/2403.17343/) (2024)
- [SegmentAnyBone: A Universal Model that Segments Any Bone at Any Location on MRI](https://mlsanity.com/paper/2401.12974/) (2024)
- [Abn-BLIP: Abnormality-aligned Bootstrapping Language-Image Pre-training for Pulmonary Embolism Diagnosis and Report Generation from CTPA](https://mlsanity.com/paper/2503.02034/) (2025)
- [Classification of lung cancer subtypes on CT images with synthetic pathological priors](https://mlsanity.com/paper/2308.04663/) (2023)

## Built on by (most cited first, 3 of 3)

- [Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models](https://mlsanity.com/paper/2607.04199/) (2026)
- [APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms](https://mlsanity.com/paper/2606.30577/) (2026)
- [Histopathological Spectrum-Guided Prostate Stratification via Segmentation-Assisted Diagnostic Transformer](https://mlsanity.com/paper/2607.22703/) (2026)

## Abstract (arXiv)

Radiological analysis increasingly benefits from pretrained visual representations that can support heterogeneous downstream tasks across imaging modalities. In this work, we introduce OmniRad, a self-supervised radiological foundation model pretrained on 1.2 million medical images, designed with radiology-inspired principles emphasizing representation reuse and cross-task transferability. We evaluate the pretrained encoder under multiple downstream adaptation regimes, including lightweight task-specific adapters with a frozen backbone as well as full end-to-end fine-tuning for classification, allowing us to assess both representation quality and task-specific performance. OmniRad is evaluated on a broad suite of public benchmarks spanning classification and segmentation across multiple modalities. On the MedMNISTv2 collection, OmniRad improves classification F1 by up to 2.05% over competing foundation models. For dense prediction, OmniRad attains mean Dice score improvements across six MedSegBench datasets when using frozen representations. Qualitative analyses and latent-space visualizations suggest improved feature clustering and modality-related separation.