Detection Accuracy and Latency of Colorectal Lesions with Computer-Aided Detection System Based on Low-Bias Evaluation

Diagnostics

Masako Nishikawa¹  Sho Takahashi¹  Hiroaki Matsui²  Shunsuke Kamba²  Kazuki Sumiyama²  Hideka Horiuchi²  Naoto Tamai²  Yuki Shimahara³  Aya Tonouchi³  Natsumaro Kutsuna³  Akihiro Fukuda³ 

[1] Clinical Research Support Center, The Jikei University School of Medicine, 3-25-8 Nishishimbashi, Minato-ku, Tokyo 105-8461, Japan;Department of Endoscopy, The Jikei University School of Medicine, 3-25-8 Nishishimbashi, Minato-ku, Tokyo 105-8461, Japan;LPixel Inc., 1-6-1 Otemachi, Chiyoda-ku, Tokyo 100-0004, Japan;

关键词: artificial intelligence;    computer-aided detection;    colonoscopy;    colorectal lesions;    deep learning;   

DOI  :  10.3390/diagnostics11101922

来源: DOAJ

【 摘 要 】

We developed a computer-aided detection (CADe) system to detect and localize colorectal lesions by modifying You-Only-Look-Once version 3 (YOLO v3) and evaluated its performance in two different settings. The test dataset was obtained from 20 randomly selected patients who underwent endoscopic resection for 69 colorectal lesions at the Jikei University Hospital between June 2017 and February 2018. First, we evaluated the diagnostic performances using still images randomly and automatically extracted from video recordings of the entire endoscopic procedure at intervals of 5 s, without eliminating poor quality images. Second, the latency of lesion detection by the CADe system from the initial appearance of lesions was investigated by reviewing the videos. A total of 6531 images, including 662 images with a lesion, were studied in the image-based analysis. The AUC, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.983, 94.6%, 95.2%, 68.8%, 99.4%, and 95.1%, respectively. The median time for detecting colorectal lesions measured in the lesion-based analysis was 0.67 s. In conclusion, we proved that the originally developed CADe system based on YOLO v3 could accurately and instantaneously detect colorectal lesions using the test dataset obtained from videos, mitigating operator selection biases.

【 授权许可】

Unknown