Computer-Aided Diagnosis Based on Convolutional Neural Network System for Colorectal Polyp Classification: Preliminary Experience

Abstract

Background and Aim: Computer-aided diagnosis (CAD) is becoming a next-generation tool for the diagnosis of human disease. CAD for colon polyps has been suggested as a particularly useful tool for trainee colonoscopists, as the use of a CAD system avoids the complications associated with endoscopic resections. In addition to conventional CAD, a convolutional neural network (CNN) system utilizing artificial intelligence (AI) has been developing rapidly over the past 5 years. We attempted to generate a unique CNN-CAD system with an AI function that studied endoscopic images extracted from movies obtained with colonoscopes used in routine examinations. Here, we report our preliminary results of this novel CNN-CAD system for the diagnosis of colon polyps. Methods: A total of 1,200 images from cases of colonoscopy performed between January 2010 and December 2016 at Kindai University Hospital were used. These images were extracted from the video of actual endoscopic examinations. Additional video images from 10 cases of unlearned processes were retrospectively assessed in a pilot study. They were simply diagnosed as either an adenomatous or nonadenomatous polyp. Results: The number of images used by AI to learn to distinguish adenomatous from nonadenomatous was 1,200:600. These images were extracted from the videos of actual endoscopic examinations. The size of each image was adjusted to 256 × 256 pixels. A 10-hold cross-validation was carried out. The accuracy of the 10-hold cross-validation is 0.751, where the accuracy is the ratio of the number of correct answers over the number of all the answers produced by the CNN. The decisions by the CNN were correct in 7 of 10 cases. Conclusion: A CNN-CAD system using routine colonoscopy might be useful for the rapid diagnosis of colorectal polyp classification. Further prospective studies in an in vivo setting are required to confirm the effectiveness of a CNN-CAD system in routine colonoscopy.

Endoscopic Diagnostic Support System for cT1b Colorectal Cancer Using Deep Learning

“…There have been reports on machine learning and image diagnostic support using deep learning methods as one type of CNN [17,[31][32][33]. In our study, while the accuracy rate of diagnosis was high, cT1b sensitivity was high and specificity was low.…”

“…Given the difficulties in obtaining clear images, careful observation is required [27]. In June 2014, in a diagnosis of colonic polyps by 3 selected expert endoscopists using a new NBI classification system proposed by the Japan NBI Expert Team, the accuracy of depth of invasion diagnosis was 87.4-98.5% for low-grade polyps, high-grade dysplasia, and cT1a and cT1b, which was very high [31]. This depth of invasion diagnosis by experts has a highly accurate diagnosis rate due to the combination of endoscopic diagnosis modalities.…”

Artificial intelligence and colonoscopy: Current status and future perspectives

“…More investigation is therefore required. This endeavor seems questionable, however, considering that an optical diagnosis using white light endoscopy is usually inferior to that using NBI or chromoendoscopy with or without magnification …”

“…This endeavor seems questionable, however, considering that an optical diagnosis using white light endoscopy is usually inferior to that using NBI or chromoendoscopy with or without magnification. 59 Prospective study with in vivo use of AI Although many retrospective/experimental studies were conducted in this field, only five prospective studies evaluated real-time use of AI during colonoscopy. 33,53,54,57,60 Kominami et al 33 prospectively evaluated the CAD model designed for magnifying NBI.…”

New Paradigm in Gastrointestinal Cancer Treatment

“…In addition to conventional CAD, a convolutional neural network (CNN) system utilizing artificial intelligence has been developing rapidly over the past 5 years. Komeda et al [5] attempted to generate a unique CNN-CAD system with an amoxicillin (AMPC) function that studied endoscopic images extracted from movies obtained with colonoscopes used in routine examinations. They found that the accuracy of the 10-fold cross-validation is 0.751, where the accuracy is the ratio of the number of correct answers over the number of all the answers produced by the CNN and the decisions by the CNN were correct in 7 of 10 cases.…”