Papanicolaou test interpretation utilizing the Hologic Genius Digital Diagnostics System vs manual glass slide review: A retrospective study of 596 cases.
Аннотация
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.
Предметные рубрики MeSH
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.