Masayoshi Yamada1,2, Ryosaku Shino3, Hiroko Kondo4,5, Shigemi Yamada4,5, Hiroyuki Takamaru6, Taku Sakamoto6, Pradeep Bhandari7, Hitoshi Imaoka3, Aya Kuchiba8, Taro Shibata8, Yutaka Saito6, Ryuji Hamamoto4,5. 1. Endoscopy Division, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo, Japan. masyamad@ncc.go.jp. 2. Division of Medical AI Research and Development, National Cancer Center Research Institute, Tokyo, Japan. masyamad@ncc.go.jp. 3. Biometrics Research Laboratories, NEC Corporation, Kawasaki, Kanagawa, Japan. 4. Division of Medical AI Research and Development, National Cancer Center Research Institute, Tokyo, Japan. 5. RIKEN Center for Advanced Intelligence Project, Cancer Translational Research Team, Tokyo, Japan. 6. Endoscopy Division, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo, Japan. 7. Department of Gastroenterology, Portsmouth Hospitals University NHS Trust, Portsmouth, UK. 8. Biostatistics Division, National Cancer Center, Tokyo, Japan.
Abstract
BACKGROUND: Improved optical diagnostic technology is needed that can be used by also outside expert centers. Hence, we developed an artificial intelligence (AI) system that automatically and robustly predicts the pathological diagnosis based on the revised Vienna Classification using standard colonoscopy images. METHODS: We prepared deep learning algorithms and colonoscopy images containing pathologically proven lesions (56,872 images, 6775 lesions). Four classifications were adopted: revised Vienna Classification category 1, 3, and 4/5 and normal images. The best algorithm-ResNet152-in the independent internal validation (14,048 images, 1718 lesions) was used for external validation (255 images, 128 lesions) based on neoplastic and non-neoplastic classification. Diagnostic performance of endoscopists was compared using a computer-assisted interpreting test. RESULTS: In the internal validation, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy for adenoma (category 3) of 84.6% (95% CI 83.5-85.6%), 99.7% (99.5-99.8%), 90.8% (89.9-91.7%), 89.2% (88.5-99.0%), and 89.8% (89.3-90.4%), respectively. In the external validation, ResNet152's sensitivity, specificity, PPV, NPV, and accuracy for neoplastic lesions were 88.3% (82.6-94.1%), 90.3% (83.0-97.7%), 94.6% (90.5-98.8%), 80.0% (70.6-89.4%), and 89.0% (84.5-93.6%), respectively. This diagnostic performance was superior to that of expert endoscopists. Area under the receiver-operating characteristic curve was 0.903 (0.860-0.946). CONCLUSIONS: The developed AI system can help non-expert endoscopists make differential diagnoses of colorectal neoplasia on par with expert endoscopists during colonoscopy. (229/250 words).
BACKGROUND: Improved optical diagnostic technology is needed that can be used by also outside expert centers. Hence, we developed an artificial intelligence (AI) system that automatically and robustly predicts the pathological diagnosis based on the revised Vienna Classification using standard colonoscopy images. METHODS: We prepared deep learning algorithms and colonoscopy images containing pathologically proven lesions (56,872 images, 6775 lesions). Four classifications were adopted: revised Vienna Classification category 1, 3, and 4/5 and normal images. The best algorithm-ResNet152-in the independent internal validation (14,048 images, 1718 lesions) was used for external validation (255 images, 128 lesions) based on neoplastic and non-neoplastic classification. Diagnostic performance of endoscopists was compared using a computer-assisted interpreting test. RESULTS: In the internal validation, the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy for adenoma (category 3) of 84.6% (95% CI 83.5-85.6%), 99.7% (99.5-99.8%), 90.8% (89.9-91.7%), 89.2% (88.5-99.0%), and 89.8% (89.3-90.4%), respectively. In the external validation, ResNet152's sensitivity, specificity, PPV, NPV, and accuracy for neoplastic lesions were 88.3% (82.6-94.1%), 90.3% (83.0-97.7%), 94.6% (90.5-98.8%), 80.0% (70.6-89.4%), and 89.0% (84.5-93.6%), respectively. This diagnostic performance was superior to that of expert endoscopists. Area under the receiver-operating characteristic curve was 0.903 (0.860-0.946). CONCLUSIONS: The developed AI system can help non-expert endoscopists make differential diagnoses of colorectal neoplasia on par with expert endoscopists during colonoscopy. (229/250 words).