# Comprehensive language-image pre-training for 3D medical image understanding

arXiv: https://arxiv.org/abs/2510.15042 · HTML: https://mlsanity.com/paper/2510.15042/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 51 of its 74 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 30 of 51)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)
- [PaLI: A Jointly-Scaled Multilingual Language-Image Model](https://mlsanity.com/paper/2209.06794/) (2022)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing](https://mlsanity.com/paper/2204.09817/) (2022)
- [Perception Encoder: The best visual embeddings are not at the output of the network](https://mlsanity.com/paper/2504.13181/) (2025)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing](https://mlsanity.com/paper/2301.04558/) (2023)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [Finetune like you pretrain: Improved finetuning of zero-shot vision models](https://mlsanity.com/paper/2212.00638/) (2022)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)

## Built on by (most cited first, 22 of 22)

- [Universal CT Representations from Anatomy to Disease Phenotype through Agglomerative Pretraining](https://mlsanity.com/paper/2605.21906/) (2026)
- [Jolia: Concept-Level Vision-Language Alignment for 3D CT Contrastive Learning](https://mlsanity.com/paper/2606.24570/) (2026)
- [Organ-Aware Attention Improves CT Triage and Classification](https://mlsanity.com/paper/2601.13385/) (2026)
- [GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations](https://mlsanity.com/paper/2606.03180/) (2026)
- [Learning Anatomy-Grounded CT Vision-Language Representations with Organ-Hierarchical Report Knowledge](https://mlsanity.com/paper/2607.10953/) (2026)
- [ORACLE-CT: Anatomy-Aware Support Pooling for CT Classification](https://mlsanity.com/paper/2606.05460/) (2026)
- [Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography](https://mlsanity.com/paper/2606.25546/) (2026)
- [CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs](https://mlsanity.com/paper/2606.27264/) (2026)
- [When Do Cheap Probes Predict Expensive Training? Probing 3D-CT Encoders for Text Generation](https://mlsanity.com/paper/2607.22771/) (2026)
- [ORCA: ORgan-Centroid Aggregation for Training-Free 3D CT Visual Token Compression](https://mlsanity.com/paper/2608.00345/) (2026)
- [Big, Bright, or Invisible: A Frozen-Feature Benchmark of 3D CT Foundation Models](https://mlsanity.com/paper/2608.05960/) (2026)
- [Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation](https://mlsanity.com/paper/2608.08713/) (2026)
- [Learning from Compressed CT: Feature Attention Style Transfer and Structured Factorized Projections for Resource-Efficient Medical Image Analysis](https://mlsanity.com/paper/2605.00448/) (2026)
- [DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT](https://mlsanity.com/paper/2606.07775/) (2026)
- [Fine-Grained Vision-Language Pretraining with Organ-Conditioned Pattern Tokens for CT Understanding](https://mlsanity.com/paper/2607.13892/) (2026)
- [Sparse Concept Channels in Frozen 3D CT Vision Encoders](https://mlsanity.com/paper/2607.20993/) (2026)
- [Learning How Much, Not Just What: Cross-Patient Burden Order for CT Vision-Language Pretraining](https://mlsanity.com/paper/2608.00231/) (2026)
- [Semantically Calibrated Evidence Composition for CT Vision-Language Learning](https://mlsanity.com/paper/2608.00239/) (2026)
- [NV-Reason-CT: 3D Visual Language Model for CT Analysis](https://mlsanity.com/paper/2609.27511/) (2026)
- [FD-AA: A Lightweight Focal-Diffuse And Attenuation-Aware Head for Incidental Abdominal Abnormality Detection in Chest CT](https://mlsanity.com/paper/2609.36189/) (2026)
- [The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging](https://mlsanity.com/paper/2610.13237/) (2026)
- [CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT](https://mlsanity.com/paper/2610.14226/) (2026)

## Abstract (arXiv)

In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports. While the methodology holds promise, three challenges limit the capabilities of current 3D VLEs: data scarcity due to privacy concerns, high computational costs resulting from the volumetric nature of the images, and a domain shift between the long reports used for training and the short prompts used during inference for, e.g., zero-shot classification. As a consequence, natural-image VLE recipes do not directly transfer to 3D medical imaging. In this paper, we overcome these challenges by injecting additional supervision via a report generation objective and combining vision-language with vision-only pre-training, allowing us to leverage both image-only and paired image-text 3D datasets. Further, we propose a novel loss that addresses the domain shift between long reports and short textual prompts. Through these additional objectives, paired with best practices of the 3D medical imaging domain, we develop the Comprehensive Language-Image Pre-training (COLIPRI) encoder family. Our COLIPRI encoders achieve state-of-the-art performance in report generation, semantic segmentation, classification probing, and zero-shot classification. The model weights and inference code are freely available at https://huggingface.co/microsoft/colipri.