Polyp characterization using deep learning and a publicly accessible polyp video database

Abstract

Objectives: Convolutional neural networks (CNN) for computer-aided diagnosis of polyps are often trained using high-quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) often excluded. This study developed a CNN from videos to classify polyps as adenomatous or nonadenomatous using standard narrow-band imaging (NBI) and NBI-near focus (NBI-NF) and created a publicly accessible polyp video database. Methods:We trained a CNN with 16,832 high and moderate quality frames from 229 polyp videos (56 SSLs). It was evaluated with 222 polyp videos (36 SSLs) across two test-sets. Test-set I consists of 14,320 frames (157 polyps, 111 diminutive). Test-set II, which is publicly accessible, 3317 video frames (65 polyps, 41 diminutive), which was benchmarked with three expert and three nonexpert endoscopists.Results: Sensitivity for adenoma characterization was 91.6% in test-set I and 89.7% in test-set II. Specificity was 91.9% and 88.5%.Sensitivity for diminutive polyps was 89.9% and 87.5%; specificity 90.5% and 88.2%. In NBI-NF, sensitivity was 89.4% and 89.5%, with a specificity of 94.7% and 83.3%. In NBI, sensitivity was 85.3% and 91.7%, with a specificity of 87.5% and 90.0%, respectively. The CNN achieved preservation and incorporation of valuable endoscopic innovations (PIVI)-1 and PIVI-2 thresholds for each test-set. In the benchmarking of test-set II, the CNN was significantly more accurate than nonexperts (13.8% difference [95% confidence interval 3.2-23.6], P = 0.01) with no significant difference with experts.Conclusions: A single CNN can differentiate adenomas from SSLs and hyperplastic polyps in both NBI and NBI-NF. A publicly accessible NBI polyp video database was created and benchmarked.

Impact of computer‐aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study

“…The results showed that referring to NBI-CAD results significantly improved the diagnostic sensitivity, NPV, and accuracy, regardless of the endoscopist's expertise. Several CADx systems for colorectal polyps have been used to date, [17][18][19][20][21] and their clinical diagnostic performances have been reported. 9,[22][23][24] Similar to our precedent study, some studies reported that PIVI-1 9,23 and PIVI-2 9,22 thresholds could be achieved, which could facilitate the widespread adoption of CADx in clinical practice.…”

Artificial Intelligence Applied to Colonoscopy: Is It Time to Take a Step Forward?

“…Hybrid AI systems may be especially relevant in contexts such as colonoscopies by nonexpert endoscopists with low ADR or in fecal occult blood test-based screening programs where the prevalence of neoplastic lesions is higher. However, there are concerns regarding the usefulness of certain endoscopic technological innovations in CRC screening programs since they do not always increase the ADR when patients undergo high-quality colonoscopy by endoscopists with a high ADR [ 51 , 52 , 59 , 61 , 62 , 63 , 64 ].…”

Artificial intelligence-based polyp size measurement in gastrointestinal endoscopy using the auxiliary waterjet as a reference

“…Artificial intelligence (AI) was introduced in clinical practice several years ago, with the main focus being polyp detection 12 13 ; however, AI-based diagnosis has been further explored for polyp characterization 14 and other gastroenterological diseases, such as eosinophilic esophagitis 15 and Crohn's disease 12 . AI has the potential to solve the issue of polyp sizing, and several AI-based concepts have recently been described 16 17 18 .…”