New PAR dataset released for prostate biopsy AI analysis

Researchers have released the PAR dataset, a collection of 1,017 whole slide images of prostate biopsy samples from 185 patients in Erbil, Iraq. This dataset aims to address the scarcity of histopathology data, particularly for underrepresented populations in the Middle East, to improve the generalizability of AI models in digital pathology. The images were scanned using Leica, Hamamatsu, and Grundium scanners and are associated with Gleason scores and International Society of Urological Pathology grades, enabling analyses of grading concordance, color normalization, and cross-scanner robustness. AI

IMPACT Enhances AI model development for pathology by including data from underrepresented populations.

RANK_REASON The cluster describes the release of a new dataset for AI research in digital pathology, detailed in an arXiv paper. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• BioImage Archive
• Erbil
• Grundium
• Hamamatsu
• Iraq
• Leica Camera
• Middle East
• Nita Mulliqi
• PAR dataset
• S-BIAD2323

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →