Journal of the American Society of Cytopathology · 2026
Evaluation of the Hologic Genius Digital Diagnostics System for clinical use in Papanicolaou test interpretation: a validation study of 1748 cases.
СтатьяВалидационное исследованиеНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
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.
Underwood Dawn L, Chaari Rema Rao, Webb Sydnee, Booth Christine N, Doxtader Erika E
Аннотация
INTRODUCTION: The integration of digital whole slide imaging and artificial intelligence is poised to transform cytopathology practice. Our aim was to validate the Hologic Genius Digital Diagnostics System (GDDS) for clinical use in Papanicolaou (Pap) test interpretation by comparing digital interpretations using the GDDS to computer-assisted interpretations using the ThinPrep Imaging System (TIS).
MATERIALS AND METHODS: The study set consisted of 1748 Pap tests, including 53 unsatisfactory for evaluation cases, 1450 negative for intraepithelial lesion or malignancy (NILM) cases, and 245 atypical squamous cells of undetermined significance or worse cases. Each Pap test was reviewed either retrospectively or prospectively by one of 29 cytologists, and results of review on the GDDS were compared to review on the TIS for concordance. Cases requiring hierarchical review were reviewed by one of 23 pathologists. Concordance was calculated between each method. Diagnostic concordance of 95% was required for validation.
RESULTS: The GDDS interpretation was concordant with the TIS interpretation in 1722/1748 cases (98.5%). Of the 26 discordant cases, most (20) were discordances between unsatisfactory and NILM, while 5 were attributed to interpretation error, and one was a low-cellularity low-grade squamous intraepithelial lesion containing rare diagnostic cells in the GDDS tiles that was originally interpreted as NILM on the TIS.
CONCLUSIONS: Pap test interpretation using the GDDS showed high concordance with interpretations using the TIS, achieving the 95% threshold for clinical validation. Discordances were mainly attributable to the ability of the GDDS to quantify cellularity in low/borderline cellularity cases, or rarely to identify significant abnormalities missed by the TIS.
MATERIALS AND METHODS: The study set consisted of 1748 Pap tests, including 53 unsatisfactory for evaluation cases, 1450 negative for intraepithelial lesion or malignancy (NILM) cases, and 245 atypical squamous cells of undetermined significance or worse cases. Each Pap test was reviewed either retrospectively or prospectively by one of 29 cytologists, and results of review on the GDDS were compared to review on the TIS for concordance. Cases requiring hierarchical review were reviewed by one of 23 pathologists. Concordance was calculated between each method. Diagnostic concordance of 95% was required for validation.
RESULTS: The GDDS interpretation was concordant with the TIS interpretation in 1722/1748 cases (98.5%). Of the 26 discordant cases, most (20) were discordances between unsatisfactory and NILM, while 5 were attributed to interpretation error, and one was a low-cellularity low-grade squamous intraepithelial lesion containing rare diagnostic cells in the GDDS tiles that was originally interpreted as NILM on the TIS.
CONCLUSIONS: Pap test interpretation using the GDDS showed high concordance with interpretations using the TIS, achieving the 95% threshold for clinical validation. Discordances were mainly attributable to the ability of the GDDS to quantify cellularity in low/borderline cellularity cases, or rarely to identify significant abnormalities missed by the TIS.