ABOUT

India Pathology dataset (IPD) is a digital whole slide image library of histopathology and cytology to drive innovation in pathology research, education, and technology development. It is a joint venture between academia, hospitals, industry, and the government to digitalize retrospective and prospective patient data to create the largest pathology dataset of various diseases in India. IPD will be an invaluable resource for researchers to develop AI-based solutions for improving patient diagnosis, prognosis, and treatment. IPD is hosted at the IIIT Hyderabad data foundation, which provides various services centered around the data.

Overview

A large-scale coordinated effort is required to create an India-centric imaging biobank. IIIT Hyderabad established a Technology Innovation Hub for Data Banks, Data Services, and Data Analytics (TIH-Data), which hosts and offers data services for IPD. Whole Slide Image (WSI) scanners for digitalizing pathological data are set up at IIIT Hyderabad and NIMS Hyderabad. WSIs of existing and prospective biopsy samples from various hospitals are digitized. The scanned pathology images have multiple resolutions (10x, 20x, 40x). Along with WSI, IHC data and patient clinical information are also collected. We have digitalized over 2000 WSIs and are looking into expanding the existing dataset by working with different stakeholders at the national level. This is crucial to overcome the class imbalance in collected datasets and build larger datasets like The Cancer Genome Atlas Program (TCGA) to drive India-centric research and development.

Dataset


Access IPD dataset

Oncology Datasets

Brain

Lungs

Colorectal

Oral

Cervical

Breast

Other Datasets

Kidney - Lupus Nephritis
Get Access

Collaborators

Supported

This project is supported by the Technology Innovation Hub for Data Banks, Data Services, and Data Analytics (TIH-Data) under the National Mission on Interdisciplinary Cyber-Physical Systems (NM-ICPS) scheme.