RIVA: An Image Dataset of Conventional Pap Smear Cytology with Multiple Independent Annotations

Q: How does OCRA curate its research paper database?

OCRA indexes peer-reviewed papers from PubMed and CrossRef, enriched with MeSH terms, author profiles, and citation metrics. Papers are categorized by cancer type, research method, and clinical relevance.

Q: Can I search papers by MeSH term or author?

Yes. Use the search bar to filter papers by MeSH term, author name, journal, keyword, or cancer type. Each paper includes linked MeSH terms and author profiles for further exploration.

Q: How current is the paper database?

The database is updated regularly through automated ingestion from PubMed and CrossRef. Most papers appear within days of their PubMed indexing date.

doi:10.1038/s41597-025-06280-2

The Pap smear remains the primary screening test for cervical cancer in many low-resource regions, yet publicly available image datasets largely feature liquid-based preparations. We introduce RIVA, a high-resolution collection of 959 conventional-smear images (1024 × 1024 px) scanned at 40x magnification, sourced from 115 patients. To ensure label quality, each image was annotated by up to four independent medical professionals, with 42% of the images reviewed by all four, resulting in 26,158 annotations based on the Bethesda classification. Annotations provide coordinates of nuclei and classification labels by up to four annotators. The dataset includes 15,949 unique cells across five (pre)cancerous types (SCC, HSIL, ASCH, LSIL, ASCUS) and three non-lesion categories (NILM, ENDO, INFL). These four-expert annotations not only give RIVA a consensus-driven ground truth for robust AI training but also enable inter-annotator consistency analysis-agreement rates reach 94% for lesion vs. non-lesion and 74% across the full eight-category Bethesda scheme.

RIVA: An Image Dataset of Conventional Pap Smear Cytology with Multiple Independent Annotations

Links

Journal

Funding