Artificial intelligence and deep learning for small bowel capsule endoscopy

Abstract

Capsule endoscopy is ideally suited to artificial intelligencebased interpretation given its reliance on pattern recognition in still images. Time saving viewing modes and lesion detection features currently available rely on machine learning algorithms, a form of artificial intelligence. Current software necessitates close human supervision given poor sensitivity relative to an expert reader. However, with the advent of deep learning, artificial intelligence is becoming increasingly reliable and will be increasingly relied upon. We review the major advances in artificial intelligence for capsule endoscopy in recent publications and briefly review artificial intelligence development for historical understanding. Importantly, recent advancements in artificial intelligence have not yet been incorporated into practice and it is immature to judge the potential of this technology based on current platforms. Remaining regulatory and standardization hurdles are being overcome and artificial intelligence-based clinical applications are likely to proliferate rapidly.

Artificial intelligence for assisting cancer diagnosis and treatment in the era of precision medicine

“…The success of DL has also been consistently reported in the diagnosis of malignant diseases using CT, MRI, positron emission tomography-CT (PET-CT) scans [37][38][39][40][41], and endoscopy [42][43][44][45][46][47][48][49][50]. Most recently, Yuan et al [40] used CT scans to develop a classifier using a three-dimensional (3D) ResNet algorithm to predict occult peritoneal metastasis in colorectal cancer with an AUC of 0.922, which was substantially higher than that achieved via routine contrast-enhanced CT diagnosis (AUC = 0.791).…”

“…The success of DL has also been consistently reported in the diagnosis of malignant diseases using CT, MRI, positron emission tomography‐CT (PET‐CT) scans [37–41], and endoscopy [42–50]. Most recently, Yuan et al .…”

Convolution neural network for the diagnosis of wireless capsule endoscopy: a systematic review and meta-analysis

“…Due to the extension of film reading time, the readers' attention cannot be focused for a long time, further increasing the misdiagnosis rate [44]. With the development of CNN and the increasing accessibility of public databases, the application of AI in capsule endoscopy has been greatly developed, which reduces the burden of human readers [43]. AI algorithms, especially deep learning algorithms, have made significant progress in image recognition [45].…”

A New Dawn for the Use of Artificial Intelligence in Gastroenterology, Hepatology and Pancreatology

“…Time-saving approaches are needed [ 86 ]. AI is a promising tool for this, and several studies have been performed and summarized previously [ 87 ]. Small intestinal bleeds are the most frequent indication for the use of VCE.…”