{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:31:23Z","timestamp":1790573483395,"version":"4.1.0"},"reference-count":49,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T00:00:00Z","timestamp":1764201600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: 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\u2013eosin (H&amp;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. Methods: 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 second gynecologic pathologist (P2, microscope and digital), EagleEye alone (EE), and an AI-assisted read (EE + P2) served as diagnostic conditions. Outcomes were dichotomized as &lt;CIN2 vs. CIN2+. Agreement was evaluated using Cohen\u2019s \u03ba and sensitivity\/specificity (95% CI) under pre-specified internal reference standards. In 30 cases with prior p16 staining, visual correspondence between AI heatmaps\/tiles and p16-positive epithelial domains was recorded. Results: Agreement between P1 and EagleEye was moderate (\u03ba = 0.67), while P2 showed high internal consistency (\u03ba = 0.86) and good agreement with P1 (\u03ba = 0.78). Using P1 as reference, EagleEye detected CIN2+ with 93.3% sensitivity and 71.8% specificity. When the AI-assisted consensus (EE + P2) was used as an augmented internal comparator, P1 showed 83.8% sensitivity and 100% specificity, indicating that the human-in-the-loop workflow identified additional CIN2+ cases that had been signed out as &lt;CIN2 by P1, particularly near the CIN1\/CIN2 boundary. In a subset of cases originally classified as CIN3 by P1, EagleEye flagged squamous cell carcinoma (SCC); several of these were confirmed as SCC by expert review (EE + P2). In ACIS, EagleEye under-called relative to pathologists but improved after adjudication. p16-to-AI spatial correspondence \u226570% was observed in 73.3% of evaluated cases. Conclusions: In this single-centre, spectrum-balanced cohort, EagleEye achieved high CIN2+ sensitivity and substantial agreement with expert readers in a human-in-the-loop workflow. The main added value was internal case-finding of treatment-relevant lesions when AI assistance was available, while final diagnoses remained with the pathologist.<\/jats:p>","DOI":"10.3390\/cancers17233808","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T16:31:52Z","timestamp":1764261112000},"page":"3808","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Digital Pathology with AI for Cervical Biopsies: Diagnostic Accuracy at the CIN2+ Threshold"],"prefix":"10.3390","volume":"17","author":[{"given":"Anja Kristin","family":"Andreassen","sequence":"first","affiliation":[{"name":"Department of Clinical Medicine, Faculty of Health Sciences, UiT The Arctic University of Norway, 9019 Troms\u00f8, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elin","family":"Mortensen","sequence":"additional","affiliation":[{"name":"Department of Medical Biology, Faculty of Health Sciences, UiT The Arctic University of Norway, 9019 Troms\u00f8, Norway"},{"name":"Department of Clinical Pathology, University Hospital of North Norway, 9019 Troms\u00f8, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roy","family":"Stenbro","sequence":"additional","affiliation":[{"name":"EagleEye, 0655 Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00d8istein","family":"S\u00f8rensen","sequence":"additional","affiliation":[{"name":"EagleEye, 0655 Oslo, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8250-3992","authenticated-orcid":false,"given":"Sveinung Wergeland","family":"S\u00f8rbye","sequence":"additional","affiliation":[{"name":"Department of Clinical Pathology, University Hospital of North Norway, 9019 Troms\u00f8, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1002\/(SICI)1096-9896(199909)189:1<12::AID-PATH431>3.0.CO;2-F","article-title":"Human papillomavirus is a necessary cause of invasive cervical cancer worldwide","volume":"189","author":"Walboomers","year":"1999","journal-title":"J. Pathol."},{"key":"ref_2","unstructured":"IARC Working Group on the Evaluation of Carcinogenic Risks to Humans (2025, November 01). Biological Agents. Volume 100B: Human Papillomaviruses, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK304347\/."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1136\/jcp.55.4.244","article-title":"The causal relation between human papillomavirus and cervical cancer","volume":"55","author":"Bosch","year":"2002","journal-title":"J. Clin. Pathol."},{"key":"ref_4","unstructured":"World Health Organization (2025, November 01). WHO Guidelines for Treatment of Cervical Intraepithelial Neoplasia 2\u20133 and Adenocarcinoma In Situ, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK206777\/."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1097\/LGT.0000000000000525","article-title":"2019 ASCCP risk-based management consensus guidelines for abnormal cervical cancer screening tests and cancer precursors","volume":"24","author":"Perkins","year":"2020","journal-title":"J. Low. Genit. Tract Dis."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"e077341","DOI":"10.1136\/bmj-2023-077341","article-title":"Effect of the HPV vaccination programme on incidence of cervical cancer and grade 3 cervical intraepithelial neoplasia by socioeconomic deprivation in England","volume":"385","author":"Falcaro","year":"2024","journal-title":"BMJ"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1056\/NEJMoa1917338","article-title":"HPV vaccination and the risk of invasive cervical cancer","volume":"383","author":"Lei","year":"2020","journal-title":"N. Engl. J. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/S0140-6736(13)62218-7","article-title":"Efficacy of HPV-based screening for prevention of invasive cervical cancer: Follow-up of four European randomised controlled trials","volume":"383","author":"Ronco","year":"2014","journal-title":"Lancet"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e96","DOI":"10.1016\/S2468-2667(17)30007-5","article-title":"Primary HPV testing versus cytology-based cervical screening in vaccinated and unvaccinated women in Australia","volume":"2","author":"Lew","year":"2017","journal-title":"Lancet Public Health"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"611","DOI":"10.3109\/0284186X.2011.555779","article-title":"European guidelines for quality assurance in cervical histopathology","volume":"50","author":"Bulten","year":"2011","journal-title":"Acta Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1500","DOI":"10.1001\/jama.285.11.1500","article-title":"Interobserver reproducibility of cervical cytologic and histologic interpretations","volume":"285","author":"Stoler","year":"2001","journal-title":"JAMA"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1097\/LGT.0b013e31825c31dd","article-title":"The Lower Anogenital Squamous Terminology (LAST) Standardization Project","volume":"16","author":"Darragh","year":"2012","journal-title":"J. Low. Genit. Tract Dis."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1309\/AJCPSD3ZXJXP7NNB","article-title":"Cervical histopathology variability among laboratories","volume":"139","author":"Gage","year":"2013","journal-title":"Am. J. Clin. Pathol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1097\/PAS.0000000000000381","article-title":"Interpretive variability of cervical biopsies and its relationship to HPV status","volume":"39","author":"Stoler","year":"2015","journal-title":"Am. J. Surg. Pathol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1097\/LGT.0000000000000721","article-title":"Provider- and facility-level variation in precancerous cervical biopsy diagnoses","volume":"27","author":"Beaber","year":"2023","journal-title":"J. Low. Genit. Tract Dis."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1097\/PAS.0000000000001072","article-title":"Routine use of adjunctive p16 immunohistochemistry improves diagnostic agreement of cervical biopsy interpretation: The CERTAIN Study","volume":"42","author":"Stoler","year":"2018","journal-title":"Am. J. Surg. Pathol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1038\/s41416-024-02681-z","article-title":"Predictable changes in the accuracy of HPV tests after vaccination","volume":"130","author":"Rebolj","year":"2024","journal-title":"Br. J. Cancer"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Luki\u0107, A., De Vincenzo, R., Ciavattini, A., Ricci, C., Senatori, R., Ruscito, I., and Frega, A. (2021). Are we facing a new colposcopic practice in the HPV vaccination era?. Vaccines, 9.","DOI":"10.3390\/vaccines9101081"},{"key":"ref_19","unstructured":"U.S. Food and Drug Administration. (2025, November 01). FDA Allows Marketing of First Whole Slide Imaging System for Digital Pathology. 12 April 2017, Available online: https:\/\/www.fda.gov\/news-events\/press-announcements\/fda-allows-marketing-first-whole-slide-imaging-system-digital-pathology."},{"key":"ref_20","unstructured":"College of American Pathologists (2025, November 01). Validating Whole Slide Imaging for Diagnostic Purposes in Pathology: Guideline Update; April 2022. Available online: https:\/\/www.cap.org\/protocols-and-guidelines\/cap-guidelines\/current-cap-guidelines\/validating-whole-slide-imaging-for-diagnostic-purposes-in-pathology."},{"key":"ref_21","first-page":"411","article-title":"Mitosis detection in breast cancer histology images with deep neural networks","volume":"16","author":"Giusti","year":"2013","journal-title":"Med. Image Comput. Comput. Assist. Interv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.csbj.2024.12.033","article-title":"Machine learning methods for histopathological image analysis: Updates in 2024","volume":"27","author":"Komura","year":"2024","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1016\/S1470-2045(19)30154-8","article-title":"Digital pathology and artificial intelligence","volume":"20","author":"Niazi","year":"2019","journal-title":"Lancet Oncol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105819","DOI":"10.1016\/j.humpath.2025.105819","article-title":"Artificial intelligence in breast pathology: Overview and recent updates","volume":"162","author":"Datwani","year":"2025","journal-title":"Hum. Pathol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","article-title":"Clinical-grade computational pathology using weakly supervised deep learning on whole-slide images","volume":"25","author":"Campanella","year":"2019","journal-title":"Nat. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","article-title":"Data-efficient and weakly supervised computational pathology on whole-slide images","volume":"5","author":"Lu","year":"2021","journal-title":"Nat. Biomed. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Veta","year":"2017","journal-title":"JAMA"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/S1470-2045(19)30738-7","article-title":"Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: A population-based, diagnostic study","volume":"21","author":"Kartasalo","year":"2020","journal-title":"Lancet Oncol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/S1470-2045(19)30739-9","article-title":"Automated deep-learning system for Gleason grading of prostate cancer using biopsies: A diagnostic study","volume":"21","author":"Bulten","year":"2020","journal-title":"Lancet Oncol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.1097\/PAS.0000000000001151","article-title":"Impact of deep learning assistance on the histopathologic review of lymph nodes for metastatic breast cancer","volume":"42","author":"Steiner","year":"2018","journal-title":"Am. J. Surg. Pathol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"26","DOI":"10.4103\/jpi.jpi_52_20","article-title":"Automated cervical digitized histology whole-slide image analysis toolbox","volume":"12","author":"Sornapudi","year":"2021","journal-title":"J. Pathol. Inform."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1038\/s41698-024-00652-4","article-title":"Learning generalizable AI models for multi-center histopathology image classification","volume":"8","author":"Darbandsari","year":"2024","journal-title":"NPJ Precis. Oncol."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"108041","DOI":"10.1016\/j.isci.2023.108041","article-title":"A multi-center performance assessment for automated histopathological classification and grading of glioma using whole-slide images","volume":"26","author":"Jin","year":"2023","journal-title":"iScience"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"40","DOI":"10.4103\/jpi.jpi_50_20","article-title":"DeepCIN: Attention-based cervical histology image classification with sequential feature modeling for pathologist-level accuracy","volume":"11","author":"Sornapudi","year":"2020","journal-title":"J. Pathol. Inform."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"An, H., Ding, L., Ma, M., Huang, A., Gan, Y., Sheng, D., Jiang, Z., and Zhang, X. (2023). Deep learning-based recognition of cervical squamous intraepithelial lesions. Diagnostics, 13.","DOI":"10.3390\/diagnostics13101720"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Cho, B.J., Kim, J.W., Park, J., Kwon, G.Y., Hong, M., Jang, S.H., Bang, H., Kim, G., and Park, S.T. (2022). Automated diagnosis of cervical intraepithelial neoplasia in histology images via deep learning. Diagnostics, 12.","DOI":"10.3390\/diagnostics12020548"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"110141","DOI":"10.1016\/j.dib.2024.110141","article-title":"CAISHI: A benchmark histopathological H&E image dataset for cervical adenocarcinoma in situ identification, retrieval and few-shot learning evaluation","volume":"53","author":"Yang","year":"2024","journal-title":"Data Brief"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1016\/j.ajpath.2024.01.016","article-title":"A histopathologic image analysis for the classification of endocervical adenocarcinoma Silva patterns using weakly supervised deep learning","volume":"194","author":"Liu","year":"2024","journal-title":"Am. J. Pathol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1038\/s43856-024-00502-1","article-title":"A comprehensive AI model development framework for consistent Gleason grading","volume":"4","author":"Huo","year":"2024","journal-title":"Commun. Med."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1055\/a-1545-4279","article-title":"2020 WHO classification of female genital tumors","volume":"81","author":"Brambs","year":"2021","journal-title":"Geburtshilfe Frauenheilkd."},{"key":"ref_41","unstructured":"3DHISTECH Ltd (2025, November 01). Pannoramic Digital Slide Scanners. Budapest, Hungary. Available online: https:\/\/www.3dhistech.com."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Mohammadi, M., Fell, C., Morrison, D., Syed, S., Konanahalli, P., Bell, S., Bryson, G., Arandjelovi\u0107, O., Harrison, D.J., and Harris-Birtill, D. (2024). Automated reporting of cervical biopsies using artificial intelligence. PLoS Digit. Health, 3.","DOI":"10.1371\/journal.pdig.0000381"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"4369","DOI":"10.1038\/s41467-024-48705-3","article-title":"Artificial intelligence enables precision diagnosis of cervical cytology grades and cervical cancer","volume":"15","author":"Wang","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"S\u00f8rbye, S.W., Suhrke, P., Rev\u00e5, B.W., Berland, J., Maurseth, R.J., and Al-Shibli, K. (2017). Accuracy of cervical cytology: Comparison of diagnoses of 100 Pap smears read by four pathologists at three hospitals in Norway. BMC Clin. Pathol., 17.","DOI":"10.1186\/s12907-017-0058-8"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"100166","DOI":"10.1016\/j.acpath.2025.100166","article-title":"Pathology in the artificial intelligence era: Guiding innovation and implementation to preserve human insight","volume":"12","author":"Gaffney","year":"2025","journal-title":"Acad. Pathol."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Joshua, A., Allen, K.E., and Orsi, N.M. (2025). An overview of artificial intelligence in gynaecological pathology diagnostics. Cancers, 17.","DOI":"10.3390\/cancers17081343"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1186\/s13000-024-01590-2","article-title":"The current troubled state of the global pathology workforce: A concise review","volume":"19","author":"Walsh","year":"2024","journal-title":"Diagn. Pathol."},{"key":"ref_48","unstructured":"Leh, S. (2025, June 10). Implementering av KI-verkt\u00f8y i Patologidiagnostikk: Prosjektmandat\/Plan; NorPreM. Available online: https:\/\/norprem.no\/wp-content\/uploads\/2024\/12\/Prosjektmandat-NorPreM-KI-patologi-v1.1.pdf."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2984","DOI":"10.3390\/ai5040144","article-title":"Artificial intelligence in cervical cancer screening: Opportunities and challenges","volume":"5","author":"Dellino","year":"2024","journal-title":"AI"}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/23\/3808\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T16:39:31Z","timestamp":1764261571000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/23\/3808"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,27]]},"references-count":49,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["cancers17233808"],"URL":"https:\/\/doi.org\/10.3390\/cancers17233808","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,27]]}}}