Real-time detection of colon polyps during colonoscopy using deep learning: systematic validation with four independent datasets

Abstract

We developed and validated a deep-learning algorithm for polyp detection. We used a YOLOv2 to develop the algorithm for automatic polyp detection on 8,075 images (503 polyps). We validated the algorithm using three datasets: A: 1,338 images with 1,349 polyps; B: an open, public CVC-clinic database with 612 polyp images; and C: 7 colonoscopy videos with 26 polyps. To reduce the number of false positives in the video analysis, median filtering was applied. We tested the algorithm performance using 15 unaltered colonoscopy videos (dataset D). For datasets A and B, the per-image polyp detection sensitivity was 96.7% and 90.2%, respectively. For video study (dataset C), the per-image polyp detection sensitivity was 87.7%. False positive rates were 12.5% without a median filter and 6.3% with a median filter with a window size of 13. For dataset D, the sensitivity and false positive rate were 89.3% and 8.3%, respectively. The algorithm detected all 38 polyps that the endoscopists detected and 7 additional polyps. The operation speed was 67.16 frames per second. The automatic polyp detection algorithm exhibited good performance, as evidenced by the high detection sensitivity and rapid processing. Our algorithm may help endoscopists improve polyp detection.

Figure 1

Examples of polyp detection in still-image analysis (dataset A). (a) Polypoid polyps, (b,c) isochromatic flat polyps, and (d) distant, diminutive polyp.

Figure 2

Examples of polyp detection in video-image analysis (dataset D). Green boxes show polyps detected by algorithm. (a,b) Polyps detected under various light conditions. (c) Partially appearing polyp detected by the algorithm. (d) Diminutive polyp detected under suboptimal bowel preparation.

Figure 3

Examples of additional polyps detected by the algorithm (shown in green boxes).