Papanicolaou test interpretation utilizing the Hologic Genius Digital Diagnostics System vs manual glass slide review: A retrospective study of 596 cases.
Erika E Doxtader, Kaitlyn Ooms, Jennifer A Brainard, Maria Luisa C Policarpio-Nicolas, Gloria Lewis, Olaronke Oshilaja, Sarah Kirschling, Dawn L Underwood, Sarah Harrington, Kasey Johnson, Christine N Booth
{"title":"Papanicolaou test interpretation utilizing the Hologic Genius Digital Diagnostics System vs manual glass slide review: A retrospective study of 596 cases.","authors":"Erika E Doxtader, Kaitlyn Ooms, Jennifer A Brainard, Maria Luisa C Policarpio-Nicolas, Gloria Lewis, Olaronke Oshilaja, Sarah Kirschling, Dawn L Underwood, Sarah Harrington, Kasey Johnson, Christine N Booth","doi":"10.1093/ajcp/aqaf080","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Advances in digital pathology and artificial intelligence have the potential to enhance cytopathology practice. The objective of this study was to compare the performance of the Hologic Genius Digital Diagnostics System with manual glass slide review for Papanicolaou test interpretation.</p><p><strong>Methods: </strong>Three cytologists retrospectively reviewed 596 Papanicolaou tests using both the Genius Digital Diagnostics System and manual review, with a 4-week washout period between reviews. The study set consisted of 299 Papanicolaou tests originally interpreted as negative for intraepithelial lesion or malignancy and 297 tests originally interpreted as atypical squamous cells of undetermined significance or above (ASC-US+). Cases interpreted as ASC-US+, reactive/repair, or endometrial cells in a woman older than 45 years of age were additionally reviewed by 1 of 5 cytopathologists. Concordance was calculated between each method and the original cytologic interpretation (reference standard). Sensitivity and specificity for detection of high-grade disease were determined for each method. Cytologist review time per case was recorded.</p><p><strong>Results: </strong>Digital interpretation was concordant with the original interpretation in 578 of 596 (97%) cases, while manual interpretation was concordant with the original interpretation in 577 of 596 (97%) cases. Digital review had higher sensitivity for detection of high-grade disease than manual review did (100% vs 86%) but was less specific (93% vs 98%). The average digital review time per case was statistically significantly shorter than manual review time (194.5 seconds vs 485.0 seconds, P < .001).</p><p><strong>Conclusions: </strong>Papanicolaou test interpretation using the Genius Digital Diagnostics System is noninferior to manual review. Digital review had higher sensitivity for detection of high-grade disease and statistically significantly reduced screening time.</p>","PeriodicalId":7506,"journal":{"name":"American journal of clinical pathology","volume":" ","pages":"513-521"},"PeriodicalIF":1.9000,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of clinical pathology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/ajcp/aqaf080","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PATHOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: Advances in digital pathology and artificial intelligence have the potential to enhance cytopathology practice. The objective of this study was to compare the performance of the Hologic Genius Digital Diagnostics System with manual glass slide review for Papanicolaou test interpretation.
Methods: Three cytologists retrospectively reviewed 596 Papanicolaou tests using both the Genius Digital Diagnostics System and manual review, with a 4-week washout period between reviews. The study set consisted of 299 Papanicolaou tests originally interpreted as negative for intraepithelial lesion or malignancy and 297 tests originally interpreted as atypical squamous cells of undetermined significance or above (ASC-US+). Cases interpreted as ASC-US+, reactive/repair, or endometrial cells in a woman older than 45 years of age were additionally reviewed by 1 of 5 cytopathologists. Concordance was calculated between each method and the original cytologic interpretation (reference standard). Sensitivity and specificity for detection of high-grade disease were determined for each method. Cytologist review time per case was recorded.
Results: Digital interpretation was concordant with the original interpretation in 578 of 596 (97%) cases, while manual interpretation was concordant with the original interpretation in 577 of 596 (97%) cases. Digital review had higher sensitivity for detection of high-grade disease than manual review did (100% vs 86%) but was less specific (93% vs 98%). The average digital review time per case was statistically significantly shorter than manual review time (194.5 seconds vs 485.0 seconds, P < .001).
Conclusions: Papanicolaou test interpretation using the Genius Digital Diagnostics System is noninferior to manual review. Digital review had higher sensitivity for detection of high-grade disease and statistically significantly reduced screening time.
目的：数字病理学和人工智能的进步有可能加强细胞病理学的实践。本研究的目的是比较Hologic Genius数字诊断系统与手动玻片检查在Papanicolaou测试解释中的性能。方法：三名细胞学家使用Genius数字诊断系统和人工复习对596例Papanicolaou试验进行回顾性复习，复习之间有4周的洗脱期。研究集包括299项Papanicolaou试验，最初解释为上皮内病变或恶性肿瘤阴性，297项试验最初解释为意义不明或以上的非典型鳞状细胞（ASC-US+）。在年龄大于45岁的女性中，被解释为ASC-US+、反应性/修复性或子宫内膜细胞的病例由5名细胞病理学家中的1名进行额外检查。计算每种方法与原始细胞学解释（参考标准）之间的一致性。测定每种方法检测高级别疾病的敏感性和特异性。记录每个病例的细胞学检查时间。结果：596例中有578例（97%）数字口译与原口译一致，596例中有577例（97%）人工口译与原口译一致。数字复查对检测高级别疾病的敏感性高于人工复查（100% vs 86%），但特异性较低（93% vs 98%）。每个病例的平均数字复核时间在统计学上显著短于人工复核时间（194.5秒vs 485.0秒），P结论：使用Genius数字诊断系统的Papanicolaou测试解释不逊于人工复核。数字评价对高级别疾病的检测具有更高的敏感性，统计学上显著减少了筛查时间。
期刊介绍：
The American Journal of Clinical Pathology (AJCP) is the official journal of the American Society for Clinical Pathology and the Academy of Clinical Laboratory Physicians and Scientists. It is a leading international journal for publication of articles concerning novel anatomic pathology and laboratory medicine observations on human disease. AJCP emphasizes articles that focus on the application of evolving technologies for the diagnosis and characterization of diseases and conditions, as well as those that have a direct link toward improving patient care.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
