# A report-grounded vision-language foundation model for colonoscopy from 280000 routine reports

arXiv: https://arxiv.org/abs/2607.28466 · HTML: https://mlsanity.com/paper/2607.28466/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 46 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Placed in

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

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images](https://mlsanity.com/paper/1612.00799/) (2016)
- [PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents](https://mlsanity.com/paper/2303.07240/) (2023)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train](https://mlsanity.com/paper/2306.16741/) (2023)
- [A multi-centre polyp detection and segmentation dataset for generalisability assessment](https://mlsanity.com/paper/2106.04463/) (2021)
- [Robust Polyp Detection and Diagnosis through Compositional Prompt-Guided Diffusion Models](https://mlsanity.com/paper/2502.17951/) (2025)
- [EndoFinder: Online Image Retrieval for Explainable Colorectal Polyp Diagnosis](https://mlsanity.com/paper/2407.11401/) (2024)
- [GI-Bench: A Panoramic Benchmark Revealing the Knowledge-Experience Dissociation of Multimodal Large Language Models in Gastrointestinal Endoscopy Against Clinical Standards](https://mlsanity.com/paper/2601.08183/) (2026)

## Abstract (arXiv)

Vision-language models remain underused in colonoscopy despite the rich expert descriptions recorded in routine reports. These reports document lesion appearance, size and location but summarise entire procedures rather than caption individual frames, leaving clinical findings only weakly linked to the corresponding images. Here we develop EndoCLIP, a colonoscopy vision-language foundation model trained on 125,756 lesion-level image-text pairs progressively recovered from 280,476 routine colonoscopy records. Across lesion-level image-text retrieval, structured report generation and six multi-centre clinical classification tasks, EndoCLIP outperforms general-purpose and biomedical vision-language encoders in both zero-shot and linear-probe settings. On benign-versus-malignant classification, its linear probe approaches the performance of expert readers in a blinded study involving 12 endoscopists. These results suggest that recovering finding-to-frame correspondence can transform routine documentation into scalable supervision, enabling clinical targets to be specified in language rather than separately annotated for each task.