Democratising Pathology Co-Pilots: An Open Pipeline and Dataset for Whole-Slide Vision-Language Modelling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913034263330816 |
|---|---|
| author | Moonemans, Sander Ram, Sebastiaan Meeuwsen, Frédérique Lems, Carlijn van der Laak, Jeroen Litjens, Geert Ciompi, Francesco |
| author_facet | Moonemans, Sander Ram, Sebastiaan Meeuwsen, Frédérique Lems, Carlijn van der Laak, Jeroen Litjens, Geert Ciompi, Francesco |
| contents | Vision-language models (VLMs) have the potential to become co-pilots for pathologists. However, most VLMs either focus on small regions of interest within whole-slide images, provide only static slide-level outputs, or rely on data that is not publicly available, limiting reproducibility. Furthermore, training data containing WSIs paired with detailed clinical reports is scarce, restricting progress toward transparent and generalisable VLMs. We address these limitations with three main contributions. First, we introduce Polysome, a standardised tool for synthetic instruction generation. Second, we apply Polysome to the public HISTAI dataset, generating HISTAI-Instruct, a large whole-slide instruction tuning dataset spanning 24,259 slides and over 1.1 million instruction-response pairs. Finally, we use HISTAI-Instruct to train ANTONI-α, a VLM capable of visual-question answering (VQA). We show that ANTONI-α outperforms MedGemma on WSI-level VQA tasks of tissue identification, neoplasm detection, and differential diagnosis. We also compare the performance of multiple incarnations of ANTONI-α trained with different amounts of data. All methods, data, and code are publicly available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_17326 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Democratising Pathology Co-Pilots: An Open Pipeline and Dataset for Whole-Slide Vision-Language Modelling Moonemans, Sander Ram, Sebastiaan Meeuwsen, Frédérique Lems, Carlijn van der Laak, Jeroen Litjens, Geert Ciompi, Francesco Computer Vision and Pattern Recognition Vision-language models (VLMs) have the potential to become co-pilots for pathologists. However, most VLMs either focus on small regions of interest within whole-slide images, provide only static slide-level outputs, or rely on data that is not publicly available, limiting reproducibility. Furthermore, training data containing WSIs paired with detailed clinical reports is scarce, restricting progress toward transparent and generalisable VLMs. We address these limitations with three main contributions. First, we introduce Polysome, a standardised tool for synthetic instruction generation. Second, we apply Polysome to the public HISTAI dataset, generating HISTAI-Instruct, a large whole-slide instruction tuning dataset spanning 24,259 slides and over 1.1 million instruction-response pairs. Finally, we use HISTAI-Instruct to train ANTONI-α, a VLM capable of visual-question answering (VQA). We show that ANTONI-α outperforms MedGemma on WSI-level VQA tasks of tissue identification, neoplasm detection, and differential diagnosis. We also compare the performance of multiple incarnations of ANTONI-α trained with different amounts of data. All methods, data, and code are publicly available. |
| title | Democratising Pathology Co-Pilots: An Open Pipeline and Dataset for Whole-Slide Vision-Language Modelling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.17326 |