Jang, Sung Ill; Kim, Young Jae; Kim, Eui Joo; Kang, Huapyong; Shon, Seung Jin; Seol, Yu Jin; Lee, Dong Ki; Kim, Kwang Gi; Cho, Jae Hee
Journal of gastroenterology and hepatology
2021Aug ; 12 ( 4 ) :.
PMID : 34431545
ÀúÀÚ »ó¼¼Á¤º¸
Jang, Sung Ill - Department of Internal Medicine, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea.
Kim, Young Jae - Department of Biomedical Engineering, Gachon University College of Health Science,
Kim, Eui Joo - Department of Internal Medicine, Gil Medical Center, Gachon University College of
Kang, Huapyong - Department of Internal Medicine, Gil Medical Center, Gachon University College of
Shon, Seung Jin - Department of Internal Medicine, Gangnam Severance Hospital, Yonsei University
Seol, Yu Jin - Department of Biomedical Engineering, Gachon University College of Health Science,
Lee, Dong Ki - Department of Internal Medicine, Gangnam Severance Hospital, Yonsei University
Kim, Kwang Gi - Department of Biomedical Engineering, Gachon University College of Health Science,
Cho, Jae Hee - Department of Internal Medicine, Gangnam Severance Hospital, Yonsei University
ABSTRACT
BACKGROUND AND AIM: Endoscopic ultrasound (EUS) is the most accurate diagnostic modality for polypoid lesions of the gallbladder (GB), but is limited by subjective interpretation. Deep learning-based artificial intelligence (AI) algorithms are under development. We evaluated the diagnostic performance of AI in differentiating polypoid lesions using EUS images.
METHODS: The diagnostic performance of the EUS-AI system with ResNet50 architecture was evaluated via three processes: training, internal validation, and testing using an AI development cohort of 1039 EUS images (836 GB polyps and 203 gallstones). The diagnostic performance was verified using an external validation cohort of 83 patients and compared with the performance of EUS endoscopists.
RESULTS: In the AI development cohort, we developed an EUS-AI algorithm and evaluated the diagnostic performance of the EUS-AI including sensitivity, specificity, positive predictive value, negative predictive value, and accuracy. For the differential diagnosis of neoplastic and non-neoplastic GB polyps, these values for EUS-AI were 57.9%, 96.5%, 77.8%, 91.6%, and 89.8%, respectively. In the external validation cohort, we compared diagnostic performances between EUS-AI and endoscopists. For the differential diagnosis of neoplastic and non-neoplastic GB polyps, the sensitivity and specificity were 33.3% and 96.1% for EUS-AI; they were 74.2% and 44.9%, respectively, for the endoscopists. Besides, the accuracy of the EUS-AI was between the accuracies of mid-level (66.7%) and expert EUS endoscopists (77.5%).
CONCLUSIONS: This newly developed EUS-AI system showed favorable performance for the diagnosis of neoplastic GB polyps, with a performance comparable to that of EUS endoscopists. CI - ??2021 Journal of Gastroenterology and Hepatology Foundation and John Wiley & Sons Australia, Ltd.
keyword
Artificial intelligence; Deep learning; Endosonography; Gallbladder disease; Polyps
¸µÅ©