{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["17(23)"],"submitter":["Andreassen AK"],"pubmed_abstract":["<b>Background/Objectives</b>: Histopathologic grading of cervical biopsies is subject to interobserver variability, particularly at the CIN2+ treatment threshold. We evaluated a deep learning system (EagleEye) for detecting CIN2+ (CIN2, CIN3, ACIS, invasive carcinoma) on hematoxylin-eosin (H&E) whole-slide images (WSIs) and compared its performance with independent pathologists, including an AI-assisted workflow. Spatial correspondence with p16 staining was preliminarily assessed. <b>Methods</b>: Ninety-nine archived cervical punch biopsies from a single university hospital, originally diagnosed as Normal (n = 19), CIN1 (n = 20), CIN2 (n = 20), CIN3 (n = 20), or adenocarcinoma in situ (ACIS; n = 20), were digitized in a deliberately spectrum-balanced design. The original sign-out (P1), a s"],"journal":["Cancers"],"pagination":["3808"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12691344"],"repository":["biostudies-literature"],"pubmed_title":["Digital Pathology with AI for Cervical Biopsies: Diagnostic Accuracy at the CIN2+ Threshold."],"pmcid":["PMC12691344"],"pubmed_authors":["Mortensen E","Sorbye SW","Stenbro R","Andreassen AK","Sorensen O"],"additional_accession":[]},"is_claimable":false,"name":"Digital Pathology with AI for Cervical Biopsies: Diagnostic Accuracy at the CIN2+ Threshold.","description":"<b>Background/Objectives</b>: Histopathologic grading of cervical biopsies is subject to interobserver variability, particularly at the CIN2+ treatment threshold. We evaluated a deep learning system (EagleEye) for detecting CIN2+ (CIN2, CIN3, ACIS, invasive carcinoma) on hematoxylin-eosin (H&E) whole-slide images (WSIs) and compared its performance with independent pathologists, including an AI-assisted workflow. Spatial correspondence with p16 staining was preliminarily assessed. <b>Methods</b>: Ninety-nine archived cervical punch biopsies from a single university hospital, originally diagnosed as Normal (n = 19), CIN1 (n = 20), CIN2 (n = 20), CIN3 (n = 20), or adenocarcinoma in situ (ACIS; n = 20), were digitized in a deliberately spectrum-balanced design. The original sign-out (P1), a s","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Nov","modification":"2026-05-26T14:03:03.974Z","creation":"2026-05-24T03:11:52.559Z"},"accession":"S-EPMC12691344","cross_references":{"pubmed":["41375009"],"doi":["10.3390/cancers17233808"]}}