PR-IHC-40X: Progesterone Receptor Immunohistochemistry Dataset for Breast Cancer Diagnosis

PR-IHC-40x dataset comprises a high-resolution collection of regions of interest (ROI) images and corresponding ground truth (GT) annotation for progesterone receptor (PR) immunohistochemistry (IHC) analysis in breast cancer pathology. We obtained 50 glass slides from University Malaya Medical Centre (UMMC) and digitized to whole slide images (WSIs) at 40\u00d7 magnification using a 3DHistech Pannoramic DESK scanner. Pathologists annotated ROIs on the collaborative Cytomine platform that formed the basis of dataset extraction. Ground truth masks were generated in a multi-stage process, binary nuclei masks for segmentations were first created with a StarDist deep learning model and refined by manual correction, while classification ground truth were first determined using a CNN-based approach and then modified by diaminobenzidine (DAB) intensity thresholding to four expression classes\u2014Strong (red), Moderate (yellow), Weak (green), and Negative (blue). The classification outputs were re-corrected in a loop against pathologists' feedback and manually checked results. There were approximately 32,000 nuclei within 250 ROI images that were manually checked and validated by senior pathologists individually. Each ROI comes with its binary segmentation mask and four-class color annotations, which are a reliable dataset for deep learning research on nuclei segmentation, PR expression classification, and Allred scoring.