INTELKAMAT - Cervical Colposcopy Image Dataset

Overview INTELKAMAT is an anonymised cervical colposcopy image dataset comprising 934 RGB JPEG images at 1280×960 pixels from 30 women examined at the Medical University Hospital of Pleven, Bulgaria (2022-2024). Each patient is represented by 6-69 images (median 28). The dataset broadens the geographic representation of open cervical colposcopy data and supports the development of AI-assisted colposcopy methods. Clinical annotations All 30 patients (100 %) are annotated by the colposcopist co-author: Transformation zone: Type 1 (14), Type 2 (7), Type 3 (9) Findings: Ovula Nabothi (3), zona glandularia (3), Ectopia (2), Polyp (1), Vessels (1), Leukoplakia (1) View modifiers: Forceps, Mucus, IUD thread, After manipulation, After excision, Blood Contents images/ - 30 folders (MUP_001..MUP_030), 934 anonymised JPEGs annotated_references/ - 24 doctor-annotated reference photos patients.csv, images.csv, annotation_audit.csv - structured metadata abbreviations.txt - English clinical vocabular Acknowledgments The support of the project BG16RFPR002-1.014-0002-С001 “CENTRE OF COMPETENCE IN PERSONALIZED MEDICINE, 3D AND TELEMEDICINE, ROBOTIC ASSISTED AND MINIMALLY INVASIVE SURGERY” funded by the PRIDST 2021-2027, co-funded by thе EU is greatly acknowledged. This research was also funded by the Bulgarian National Science Fund (BNSF) through “COMPETITION FOR FINANCIAL SUPPORT FOR BASIC RESEARCH PROJECTS– 2022”, project КП-06-H63/5 from 13.12.2022 – “Application of AI Methods for Colposcopic Recognition and Categorization of Cervical Features”, with a contract No BG-175467353-2022-04-0257-C01.