Updates in narrow‐band imaging for colorectal polyps: Narrow‐band imaging generations, detection, diagnosis, and artificial intelligence

Abstract

Narrow‐band imaging (NBI) is an optical digital enhancement method that allows the observation of vascular and surface structures of colorectal lesions. Its usefulness in the detection and diagnosis of colorectal polyps has been demonstrated in several clinical trials and the diagnostic algorithms have been simplified after the establishment of endoscopic classifications such as the Japan NBI Expert Team classification. However, there were issues including lack of brightness in the earlier models, poor visibility under insufficient bowel preparation, and the incompatibility of magnifying endoscopes in certain endoscopic platforms, which had impeded NBI from becoming standardized globally. Nonetheless, NBI continued its evolution and the newest endoscopic platform launched in 2020 offers significantly brighter and detailed images. Enhanced visualization is expected to improve the detection of polyps while universal compatibility across all scopes including magnifying endoscopy will promote the global standardization of magnifying diagnosis. Therefore, knowledge related to magnifying colonoscopy will become essential as magnification becomes standardly equipped in future models, although the advent of computer‐aided diagnosis and detection may greatly assist endoscopists to ensure quality of practice. Given that most endoscopic departments will be using both old and new models, it is important to understand how each generation of endoscopic platforms differ from each other. We reviewed the advances in the endoscopic platforms, artificial intelligence, and evidence related to NBI essential for the next generation of endoscopic practice.

A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart

“…In contrast, our model can achieve good results with simple white-light colonoscopy alone. This outcome limits the convenience and widespread applicability of their models [ 9 ]. One of the contributions of our study is that our AI model works better for white light than NBI images.…”

“…For example, Azam et al [ 8 ] built an AI model with both wight-light and NBI images to improve the accuracy of their model. However, the NBI or other enhanced method has their weaknesses [ 9 ]. The efficiency of NBI is highly dependent on bowel preparation, and the image of NBI is darker than the white-light images.…”

Image enhanced colonoscopy: updates and prospects—a review

“…First generation NBI was launched in 2006 as a part of two endoscopic systems, EVIS LUCERA SPECTRUM (in Japan and UK) and EXERA II (elsewhere) ( 31 ). Images generated by first-generation NBI were not ideal due to low brightness, and studies indicated that the adenoma detection rate (ADR) was comparable between NBI and WLE ( 32 , 33 ).…”

“…These models used a stronger xenon lamp and a new signal processor which worked by elimination of filter mechanism as well as reduction of image noise, thereby producing brighter sharp images. It also allowed an optical magnification of ×45 power with a simple press of a button ( 27 , 31 ). A recent meta-analysis of 11 RCTs involving 4,491 patients found that ADR for second-generation NBI was better compared to HD-WLE (OR: 1.28; 95% CI: 1.05–1.56; P=0.02) ( 34 ).…”

The Utility of Narrow-Band Imaging International Colorectal Endoscopic Classification in Predicting the Histologies of Diminutive Colorectal Polyps Using I-Scan Optical Enhancement: A Prospective Study

“…NBI is an optical digital imaging technique wherein two selected wavelengths (415 + −30 nm and 540 + −30 nm) enhance the structural aspects of the surface of the mucosa and existing blood vessels [ 12 ]. Numerous studies have shown that NBI is capable of accurate tissue characterization [ 8 , 13 , 14 , 15 ]. This strong evidence led to the development of the NBI International Colorectal Endoscopic (NICE) classification, which allows for an accurate differentiation between adenomatous and hyperplastic polyps in vivo by analyzing the color, surface pattern, and vascular pattern of DCPs with NBI [ 16 , 17 , 18 ].…”