ADPv2: A Hierarchical Histological Tissue Type-Annotated Dataset for Potential Biomarker Discovery of Colorectal Disease

TL;DR

ADPv2 is a new hierarchical histological tissue dataset for colorectal disease, enabling detailed tissue analysis and biomarker discovery, with a trained model achieving high classification accuracy.

Contribution

We introduce ADPv2, a detailed hierarchical histological dataset for gastrointestinal tissues, and demonstrate its utility with a multilabel classification model and disease pathway analysis.

Findings

Achieved a mean average precision of 0.88 in multilabel classification.

Enabled organ-specific tissue analysis for biomarker discovery.

Revealed statistical patterns supporting colon cancer pathways.

Abstract

Computational pathology (CoPath) leverages histopathology images to enhance diagnostic precision and reproducibility in clinical pathology. However, publicly available datasets for CoPath that are annotated with extensive histological tissue type (HTT) taxonomies at a granular level remain scarce due to the significant expertise and high annotation costs required. Existing datasets, such as the Atlas of Digital Pathology (ADP), address this by offering diverse HTT annotations generalized to multiple organs, but limit the capability for in-depth studies on specific organ diseases. Building upon this foundation, we introduce ADPv2, a novel dataset focused on gastrointestinal histopathology. Our dataset comprises 20,004 image patches derived from healthy colon biopsy slides, annotated according to a hierarchical taxonomy of 32 distinct HTTs of 3 levels. Furthermore, we train a multilabel representation learning model following a two-stage training procedure on our ADPv2 dataset. We leverage the VMamba architecture and achieving a mean average precision (mAP) of 0.88 in multilabel classification of colon HTTs. Finally, we show that our dataset is capable of an organ-specific in-depth study for potential biomarker discovery by analyzing the model's prediction behavior on tissues affected by different colon diseases, which reveals statistical patterns that confirm the two pathological pathways of colon cancer development. Our dataset is publicly available at https://zenodo.org/records/15307021