HISTAI: An Open-Source, Large-Scale Whole Slide Image Dataset for Computational Pathology

TL;DR

Public WSI datasets are often limited in scale, tissue diversity, and clinical metadata, hindering AI generalization in digital pathology. HISTAI introduces a large open-access multimodal WSI collection with over 60,000 slides and rich clinical metadata, organized into tissue-specific subsets and hosted on Hugging Face. The dataset includes detailed diagnostic information, demographics, ICD-10 codes, and pathological annotations, enabling robust benchmarking and multimodal analyses. By promoting openness, reproducibility, and cross-tissue applicability, HISTAI aims to accelerate clinically relevant AI solutions in pathology and facilitate domain adaptation and transfer learning across institutions.

Abstract

Recent advancements in Digital Pathology (DP), particularly through artificial intelligence and Foundation Models, have underscored the importance of large-scale, diverse, and richly annotated datasets. Despite their critical role, publicly available Whole Slide Image (WSI) datasets often lack sufficient scale, tissue diversity, and comprehensive clinical metadata, limiting the robustness and generalizability of AI models. In response, we introduce the HISTAI dataset, a large, multimodal, open-access WSI collection comprising over 60,000 slides from various tissue types. Each case in the HISTAI dataset is accompanied by extensive clinical metadata, including diagnosis, demographic information, detailed pathological annotations, and standardized diagnostic coding. The dataset aims to fill gaps identified in existing resources, promoting innovation, reproducibility, and the development of clinically relevant computational pathology solutions. The dataset can be accessed at https://github.com/HistAI/HISTAI.