Shunsuke Kamba1, Naoto Tamai2, Iduru Saitoh2, Hiroaki Matsui2, Hideka Horiuchi2, Masakuni Kobayashi3, Taku Sakamoto4, Mai Ego4, Akihiro Fukuda5, Aya Tonouchi5, Yuki Shimahara5, Masako Nishikawa6, Haruo Nishino7, Yutaka Saito4, Kazuki Sumiyama2. 1. Department of Endoscopy, The Jikei University School of Medicine, 3-25-8 Nishi-Shimbashi, Minato-ku, Tokyo, 105-8461, Japan. kanba@jikei.ac.jp. 2. Department of Endoscopy, The Jikei University School of Medicine, 3-25-8 Nishi-Shimbashi, Minato-ku, Tokyo, 105-8461, Japan. 3. Department of Endoscopy, The Jikei University School of Medicine Third Hospital, 4-11-1 Izumihoncho, Komae-shi, Tokyo, 201-8601, Japan. 4. Endoscopy Division, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-ku, Tokyo, 104-0045, Japan. 5. LPIXEL Inc., 1-6-1 Otemachi, Chiyoda-ku, Tokyo, 100-0004, Japan. 6. Clinical Research Support Center, The Jikei University School of Medicine, 3-25-8 Nishi-Shimbashi, Minato-ku, Tokyo, 105-8461, Japan. 7. Coloproctology Center, Matsushima Hospital, 3-138 Isecho, Nishi-ku, Yokohama-shi, Kanagawa, 220-0045, Japan.
Abstract
BACKGROUND: We have developed the computer-aided detection (CADe) system using an original deep learning algorithm based on a convolutional neural network for assisting endoscopists in detecting colorectal lesions during colonoscopy. The aim of this study was to clarify whether adenoma miss rate (AMR) could be reduced with CADe assistance during screening and surveillance colonoscopy. METHODS: This study was a multicenter randomized controlled trial. Patients aged 40 to 80 years who were referred for colorectal screening or surveillance at four sites in Japan were randomly assigned at a 1:1 ratio to either the "standard colonoscopy (SC)-first group" or the "CADe-first group" to undergo a back-to-back tandem procedure. Tandem colonoscopies were performed on the same day for each participant by the same endoscopist in a preassigned order. All polyps detected in each pass were histopathologically diagnosed after biopsy or resection. RESULTS: A total of 358 patients were enrolled and 179 patients were assigned to the SC-first group or CADe-first group. The AMR of the CADe-first group was significantly lower than that of the SC-first group (13.8% vs. 36.7%, P < 0.0001). Similar results were observed for the polyp miss rate (14.2% vs. 40.6%, P < 0.0001) and sessile serrated lesion miss rate (13.0% vs. 38.5%, P = 0.03). The adenoma detection rate of CADe-assisted colonoscopy was 64.5%, which was significantly higher than that of standard colonoscopy (53.6%; P = 0.036). CONCLUSION: Our study results first showed a reduction in the AMR when assisting with CADe based on deep learning in a multicenter randomized controlled trial.
BACKGROUND: We have developed the computer-aided detection (CADe) system using an original deep learning algorithm based on a convolutional neural network for assisting endoscopists in detecting colorectal lesions during colonoscopy. The aim of this study was to clarify whether adenoma miss rate (AMR) could be reduced with CADe assistance during screening and surveillance colonoscopy. METHODS: This study was a multicenter randomized controlled trial. Patients aged 40 to 80 years who were referred for colorectal screening or surveillance at four sites in Japan were randomly assigned at a 1:1 ratio to either the "standard colonoscopy (SC)-first group" or the "CADe-first group" to undergo a back-to-back tandem procedure. Tandem colonoscopies were performed on the same day for each participant by the same endoscopist in a preassigned order. All polyps detected in each pass were histopathologically diagnosed after biopsy or resection. RESULTS: A total of 358 patients were enrolled and 179 patients were assigned to the SC-first group or CADe-first group. The AMR of the CADe-first group was significantly lower than that of the SC-first group (13.8% vs. 36.7%, P < 0.0001). Similar results were observed for the polyp miss rate (14.2% vs. 40.6%, P < 0.0001) and sessile serrated lesion miss rate (13.0% vs. 38.5%, P = 0.03). The adenoma detection rate of CADe-assisted colonoscopy was 64.5%, which was significantly higher than that of standard colonoscopy (53.6%; P = 0.036). CONCLUSION: Our study results first showed a reduction in the AMR when assisting with CADe based on deep learning in a multicenter randomized controlled trial.
Authors: Katharina Zimmermann-Fraedrich; Heiko Pohl; Thomas Rösch; Douglas K Rex; Cesare Hassan; Evelien Dekker; Michal Filip Kaminski; Michael Bretthauer; Jocelyn de Heer; Yuki Werner; Guido Schachschal; Stefan Groth Journal: Gut Date: 2020-05-14 Impact factor: 23.059
Authors: Thomas Y T Lam; Max F K Cheung; Yasmin L Munro; Kong Meng Lim; Dennis Shung; Joseph J Y Sung Journal: J Med Internet Res Date: 2022-08-25 Impact factor: 7.076