RT Journal Article SR Electronic T1 #873 Development of an artificial intelligence-based diagnostic system for the detection of abnormal colposcopic findings JF International Journal of Gynecologic Cancer JO Int J Gynecol Cancer FD BMJ Publishing Group Ltd SP A6 OP A6 DO 10.1136/ijgc-2023-ESGO.10 VO 33 IS Suppl 3 A1 Ueda, Akihiko A1 Yamaguchi, Ken A1 Kitamura, Sachiko A1 Taki, Mana A1 Yamanoi, Koji A1 Murakami, Ryusuke A1 Hamanishi, Junzo A1 Ueda, Masatsugu A1 Mandai, Masaki YR 2023 UL http://ijgc.bmj.com/content/33/Suppl_3/A6.1.abstract AB Introduction/Background Colposcopic examination requires sufficient training to detect cervical intraepithelial neoplasia (CIN) with (1) high diagnostic accuracy and (2) minimizing time and reducing tissue biopsies. The aim of this study was to develop an artificial intelligence (AI)-based system that replicates expert colposcopic examination techniques, independent of examiner skill.Methodology A retrospective analysis was performed using 8341 colposcopic videos from 2013 to 2019, consisting of seven early-stage cervical cancer cases, 203 CIN3 cases, 276 CIN2 cases, and 456 CIN1 cases. An AI-based lesion detection model was developed to identify major abnormal colposcopic findings. The model was trained using the annotated abnormal findings with the highest acetic acid intensity in cervical cancer and CIN3 cases whose histological diagnoses were confirmed. The developed AI model was then applied to CIN1 and CIN2 cases to evaluate the diagnostic accuracy of the lesions.Results The AI-based model was trained on 60 cases of cervical cancer and CIN3 and validated on 150 cases. The model was able to identify severe lesions with high accuracy, with a sensitivity of 85%, a specificity of 73%, an area under the curve (AUC) of 0.89 for lesion area, and an accuracy of 95% for the number of lesions identified. The model also predicted abnormal colposcopic findings in CIN1 and CIN2 cases with high accuracy for detection of lesion area (sensitivity: 87% and 86%, specificity: 70% and 67%, AUC: 0.81 and 0.81, respectively) and identification of the number of lesions (97% and 93%, respectively). Furthermore, a heat map display based on the prediction results allowed visualization of the area of highest acetic acid intensity corresponding to the actual biopsy locations.Conclusion We have newly developed an AI-based diagnostic system for colposcopy that can identify CIN lesions with high accuracy and suggest appropriate biopsy sites.