Peng Xue1,2, Chao Tang3, Qing Li4, Yuexiang Li5, Yu Shen6, Yuqian Zhao7, Jiawei Chen5, Jianrong Wu8, Longyu Li9, Wei Wang10, Yucong Li11, Xiaoli Cui12, Shaokai Zhang13, Wenhua Zhang2, Xun Zhang14, Kai Ma5, Yefeng Zheng5, Tianyi Qian8, Man Tat Alexander Ng8, Zhihua Liu15, Youlin Qiao1,2, Yu Jiang16, Fanghui Zhao17. 1. Department of Epidemiology and Biostatistics, School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China. 2. Department of Cancer Epidemiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China. 3. School of Public Health, Dalian Medical University, Dalian, China. 4. Diagnosis and Treatment for Cervical Lesions Center, Shenzhen Maternity & Child Healthcare Hospital, Shenzhen, China. 5. Tencent Jarvis Lab, Shenzhen, China. 6. Zonsun Healthcare, Shenzhen, China. 7. Center for Cancer Prevention Research, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China. 8. Tencent Healthcare, Shenzhen, China. 9. Jiangxi Maternal and Child Health Hospital, Nanchang, China. 10. Chengdu Women's and Children's Central Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China. 11. Chongqing University Cancer Hospital, Chongqing, China. 12. Cancer Hospital of China Medical University, Liaoning Cancer Hospital & Institute, Shenyang, China. 13. Affiliated Cancer Hospital of Zhengzhou University/Henan Cancer Hospital, Zhengzhou, China. 14. Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China. 15. Department of Gynecology, Shenzhen Maternity & Child Healthcare Hospital, Shenzhen, China. 16. Department of Epidemiology and Biostatistics, School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100730, China. jiangyu@pumc.edu.cn. 17. Department of Cancer Epidemiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, 100021, China. zhaofangh@cicams.ac.cn.
Abstract
BACKGROUND: Colposcopy diagnosis and directed biopsy are the key components in cervical cancer screening programs. However, their performance is limited by the requirement for experienced colposcopists. This study aimed to develop and validate a Colposcopic Artificial Intelligence Auxiliary Diagnostic System (CAIADS) for grading colposcopic impressions and guiding biopsies. METHODS: Anonymized digital records of 19,435 patients were obtained from six hospitals across China. These records included colposcopic images, clinical information, and pathological results (gold standard). The data were randomly assigned (7:1:2) to a training and a tuning set for developing CAIADS and to a validation set for evaluating performance. RESULTS: The agreement between CAIADS-graded colposcopic impressions and pathology findings was higher than that of colposcopies interpreted by colposcopists (82.2% versus 65.9%, kappa 0.750 versus 0.516, p < 0.001). For detecting pathological high-grade squamous intraepithelial lesion or worse (HSIL+), CAIADS showed higher sensitivity than the use of colposcopies interpreted by colposcopists at either biopsy threshold (low-grade or worse 90.5%, 95% CI 88.9-91.4% versus 83.5%, 81.5-85.3%; high-grade or worse 71.9%, 69.5-74.2% versus 60.4%, 57.9-62.9%; all p < 0.001), whereas the specificities were similar (low-grade or worse 51.8%, 49.8-53.8% versus 52.0%, 50.0-54.1%; high-grade or worse 93.9%, 92.9-94.9% versus 94.9%, 93.9-95.7%; all p > 0.05). The CAIADS also demonstrated a superior ability in predicting biopsy sites, with a median mean-intersection-over-union (mIoU) of 0.758. CONCLUSIONS: The CAIADS has potential in assisting beginners and for improving the diagnostic quality of colposcopy and biopsy in the detection of cervical precancer/cancer.
RCT Entities:
BACKGROUND: Colposcopy diagnosis and directed biopsy are the key components in cervical cancer screening programs. However, their performance is limited by the requirement for experienced colposcopists. This study aimed to develop and validate a Colposcopic Artificial Intelligence Auxiliary Diagnostic System (CAIADS) for grading colposcopic impressions and guiding biopsies. METHODS: Anonymized digital records of 19,435 patients were obtained from six hospitals across China. These records included colposcopic images, clinical information, and pathological results (gold standard). The data were randomly assigned (7:1:2) to a training and a tuning set for developing CAIADS and to a validation set for evaluating performance. RESULTS: The agreement between CAIADS-graded colposcopic impressions and pathology findings was higher than that of colposcopies interpreted by colposcopists (82.2% versus 65.9%, kappa 0.750 versus 0.516, p < 0.001). For detecting pathological high-grade squamous intraepithelial lesion or worse (HSIL+), CAIADS showed higher sensitivity than the use of colposcopies interpreted by colposcopists at either biopsy threshold (low-grade or worse 90.5%, 95% CI 88.9-91.4% versus 83.5%, 81.5-85.3%; high-grade or worse 71.9%, 69.5-74.2% versus 60.4%, 57.9-62.9%; all p < 0.001), whereas the specificities were similar (low-grade or worse 51.8%, 49.8-53.8% versus 52.0%, 50.0-54.1%; high-grade or worse 93.9%, 92.9-94.9% versus 94.9%, 93.9-95.7%; all p > 0.05). The CAIADS also demonstrated a superior ability in predicting biopsy sites, with a median mean-intersection-over-union (mIoU) of 0.758. CONCLUSIONS: The CAIADS has potential in assisting beginners and for improving the diagnostic quality of colposcopy and biopsy in the detection of cervical precancer/cancer.
Entities:
Keywords:
Artificial intelligence; Cervical cancer prevention; Colposcopy diagnosis and biopsy; Global elimination of cervical cancer
Authors: Marina Treskova; Francisco Pozo-Martin; Stefan Scholz; Viktoria Schönfeld; Ole Wichmann; Thomas Harder Journal: Pharmacoeconomics Date: 2021-01-19 Impact factor: 4.981
Authors: Aleksandra Zimmer-Stelmach; Jan Zak; Agata Pawlosek; Anna Rosner-Tenerowicz; Joanna Budny-Winska; Michal Pomorski; Tomasz Fuchs; Mariusz Zimmer Journal: Diagnostics (Basel) Date: 2022-01-04