Computer-aided detection of colorectal polyps using a newly generated deep convolutional neural network: from development to first clinical experience

Abstract

Aim The use of artificial intelligence represents an objective approach to increase endoscopist’s adenoma detection rate (ADR) and limit interoperator variability. In this study, we evaluated a newly developed deep convolutional neural network (DCNN) for automated detection of colorectal polyps ex vivo as well as in a first in-human trial. Methods For training of the DCNN, 116 529 colonoscopy images from 278 patients with 788 different polyps were collected. A subset of 10 467 images containing 504 different polyps were manually annotated and treated as the gold standard. An independent set of 45 videos consisting of 15 534 single frames was used for ex vivo performance testing. In vivo real-time detection of colorectal polyps during routine colonoscopy by the DCNN was tested in 42 patients in a back-to-back approach. Results When analyzing the test set of 15 534 single frames, the DCNN’s sensitivity and specificity for polyp detection and localization within the frame was 90% and 80%, respectively, with an area under the curve of 0.92. In vivo, baseline polyp detection rate and ADR were 38% and 26% and significantly increased to 50% (P = 0.023) and 36% (P = 0.044), respectively, with the use of the DCNN. Of the 13 additionally with the DCNN detected lesions, the majority were diminutive and flat, among them three sessile serrated adenomas. Conclusion This newly developed DCNN enables highly sensitive automated detection of colorectal polyps both ex vivo and during first in-human clinical testing and could potentially increase the detection of colorectal polyps during colonoscopy.

Pilot study of a new freely available computer-aided polyp detection system in clinical practice

“…Assessing the characteristics of the detected adenomas, we found a similar size distribution compared to previously published studies [ 4 – 7 ]. Other CAD systems report a false positive (FP) rate of 0.9 to 8% [ 12 – 14 ]. Assessment of false detections by EndoMind is located in the lower range with 2.2%.…”

Frame-by-Frame Analysis of a Commercially Available Artificial Intelligence Polyp Detection System in Full-Length Colonoscopies

“…Subsequently, several commercially available CADe systems have been developed for colonoscopy. In prospective RCTs, CADe systems showed a significantly higher ADR compared to expert colonoscopists [1-4, 7, 18-21]. Moreover, a recently published meta-analysis found a significant increase of ADR [6].…”

“…However, there are still many unanswered questions regarding CADe systems. For example, many false-positive (FP) activations of up to 8% of all frames occur during examination with CADe systems [7]. The number and duration of FP activations play an important role regarding the examiners comfort in using those systems, as these activations can affect the examiners attention leading to misinterpretation of normal mucosa [8].…”

Real-time colorectal polyp detection using a novel computer-aided detection system (CADe): a feasibility study

“…To reduce the number of false positives, a minimum of three consecutive frames are considered positive before a detection signal (acoustically and/or visually) is provided. This results in a delay between the initial detection of a polyp and it being marked of ± 100 ms. For more information, we refer to Pfeifer et al, who described in great detail how this CADe system was developed [20].…”