# Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models

arXiv: https://arxiv.org/abs/2604.01987 · HTML: https://mlsanity.com/paper/2604.01987/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 2 Apr 2026.

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

- [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)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge](https://mlsanity.com/paper/1612.08012/) (2016)
- [TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRI](https://mlsanity.com/paper/2405.19492/) (2024)
- [MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging](https://mlsanity.com/paper/2410.06542/) (2024)
- [Domain-adversarial neural networks to address the appearance variability of histopathology images](https://mlsanity.com/paper/1707.06183/) (2017)
- [COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 from Chest CT Images Through Bigger, More Diverse Learning](https://mlsanity.com/paper/2101.07433/) (2021)
- [Pillar-0: A New Frontier for Radiology Foundation Models](https://mlsanity.com/paper/2511.17803/) (2025)
- [Curia: A Multi-Modal Foundation Model for Radiology](https://mlsanity.com/paper/2509.06830/) (2025)

## Built on by (most cited first, 6 of 6)

- [Jolia: Concept-Level Vision-Language Alignment for 3D CT Contrastive Learning](https://mlsanity.com/paper/2606.24570/) (2026)
- [Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices](https://mlsanity.com/paper/2607.01001/) (2026)
- [Big, Bright, or Invisible: A Frozen-Feature Benchmark of 3D CT Foundation Models](https://mlsanity.com/paper/2608.05960/) (2026)
- [Lesion Detection in CT with Frozen Self-Distilled Features: SALT, a Spatially Adaptive Label-Guided Temperature](https://mlsanity.com/paper/2608.05100/) (2026)
- [Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation](https://mlsanity.com/paper/2608.05844/) (2026)
- [Volumetric Radiology AI in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2608.20549/) (2026)

## Abstract (arXiv)

The rapid growth of medical imaging has fueled the development of Foundation Models (FMs) to reduce the growing, unsustainable workload on radiologists. While recent FMs have shown the power of large-scale pre-training to CT and MRI analysis, there remains significant room to optimize how these models learn from complex radiological volumes. Building upon the Curia framework, this work introduces Curia-2, which significantly improves the original pre-training strategy and representation quality to better capture the specificities of radiological data. The proposed methodology enables scaling the architecture up to billion-parameter Vision Transformers, marking a first for multi-modal CT and MRI FMs. Furthermore, we formalize the evaluation of these models by extending and restructuring CuriaBench into two distinct tracks: a 2D track tailored for slice-based vision models and a 3D track for volumetric benchmarking. Our results demonstrate that Curia-2 outperforms all FMs on vision-focused tasks and fairs competitively to vision-language models on clinically complex tasks such as finding detection. Weights will be made publicly available to foster further research.