Researchers in Japan have developed an artificial intelligence (AI)-based diagnostic tool for colposcopy examinations that may accurately identify cervical intraepithelial neoplasia (CIN) and subsequently suggest appropriate biopsy sites. The research will be presented by Ueda et al at the 2023 ASCO Breakthrough meeting (Abstract 82), taking place August 3 to 5 in Yokohama, Japan.
“Currently, there is no certification system for performing colposcopies in Japan, and the quality and interpretation of these examinations varies. Our study aimed to develop an AI-based tool that reproduced colposcopy examination techniques of specialists to be used as a diagnostic aid by accurately identifying CIN lesions and guiding tissue sampling locations,” said lead study author Akihiko Ueda, MD, a physician in the Department of Gynecology and Obstetrics at Kyoto University.
About the Study
To validate the accuracy of this technology, the researchers performed a retrospective analysis of 8,341 patients who underwent a colposcopy examination for secondary screening of abnormal cervical cytology or follow-up for CIN between 2013 and 2019. The median age of patients in the study was 41 years, and in the group, there were 7 early-stage cervical cancer cases, 203 CIN3 cases, 276 CIN2 cases, and 456 CIN1 cases.
Key Findings
Researchers constructed the AI-based tool to detect lesions by annotating abnormal colposcopy findings after acetic acid processing in cervical cancer and CIN3 cases for which diagnoses were confirmed by biopsies. The resulting detection model was applied to cervical intraepithelial neoplasia 1 and 2 cases, and the diagnostic accuracies of these lesions were evaluated by sensitivity, specificity, and area under the curve, as well as the number of lesions identified.
The model identified severe lesions in CIN3 cases with a sensitivity of 85%, a specificity of 73%, an area under the curve of 0.89 for lesion area, and an accuracy of 95% for the number of lesions identified.
The model predicted abnormal colposcopy findings in CIN1 cases with a sensitivity of 87%, a specificity of 70%, an area under the curve of 0.81 for lesion area, and an accuracy of 97% for the number of lesions identified.
The model predicted abnormal colposcopy findings in CIN2 cases with a sensitivity of 86%, a specificity of 67%, an area under the curve of 0.81 for lesion area, and an accuracy of 93% for the number of lesions identified.
According to the authors, there is room for improvement in the application’s ability to accurately predict histopathologic diagnosis, and the relationship between chronological changes in abnormal colposcopy findings and histopathologic diagnosis needs to be investigated.
ASCO Perspective
“Colposcopy plays an important role in cervical cancer screening. This study showed that harnessing the power of AI in cancer screening could pave the way for a potentially more effective and improved diagnostic performance in cervical cancer care,” said Roselle B. De Guzman, MD, ASCO Expert.
Disclosure: For full disclosures of the study authors, visit coi.asco.org.
