Democratizing Pathology Co-Pilots: An Open Pipeline and Dataset for Whole-Slide Vision-Language Modelling

Sander Moonemans, Sebastiaan Ram, Frédérique Meeuwsen, Carlijn Lems, Jeroen van der Laak, Geert Litjens, Francesco Ciompi

Keywords: Instruction-tuning, visual question-answering, whole-slide images, digital assistant

Abstract: 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-$\alpha$_, a VLM capable of visual-question answering (VQA). We show that ANTONI-$\alpha$ 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-$\alpha$ trained with different amounts of data. All methods, data, and code are publicly available

Primary Subject Area: Generative Models

Secondary Subject Area: Application: Histopathology

Registration Requirement: Yes

Reproducibility: https://github.com/computationalpathologygroup/ANTONI-Alpha

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 305