CB‐HRNet: A Class‐Balanced High‐Resolution Network for the evaluation of endoscopic activity in patients with ulcerative colitis

Abstract

Endoscopic evaluation is the key to the management of ulcerative colitis (UC). However, there is interobserver variability in interpreting endoscopic images among gastroenterologists. Furthermore, it is time‐consuming. Convolutional neural networks (CNNs) can help overcome these obstacles and has yielded preliminary positive results. We aimed to develop a new CNN‐based algorithm to improve the performance for evaluation tasks of endoscopic images in patients with UC. A total of 12,163 endoscopic images from 308 patients with UC were collected from January 2014 to December 2021. The training set and test set images were randomly divided into 37,515 and 3191 after excluding possible interference and data augmentation. Mayo Endoscopic Subscores (MES) were predicted by different CNN‐based models with different loss functions. Their performances were evaluated by several metrics. After comparing the results of different CNN‐based models with different loss functions, High‐Resolution Network with Class‐Balanced Loss achieved the best performances in all MES classification subtasks. It was especially great at determining endoscopic remission in UC, which achieved a high accuracy of 95.07% and good performances in other evaluation metrics with sensitivity 92.87%, specificity 95.41%, kappa coefficient 0.8836, positive predictive value 93.44%, negative predictive value 95.00% and area value under the receiver operating characteristic curve 0.9834, respectively. In conclusion, we proposed a new CNN‐based algorithm, Class‐Balanced High‐Resolution Network (CB‐HRNet), to evaluate endoscopic activity of UC with excellent performance. Besides, we made an open‐source dataset and it can be a new benchmark in the task of MES classification.

A systematic review and meta-analysis of artificial intelligence-diagnosed endoscopic remission in ulcerative colitis

“…The remaining 53 articles were read in detail, of which 18 were included. 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 The literature screening process is illustrated in Figure 1 . Details of the included studies are presented in Table 1 .…”

“…Twelve studies were retrospective and six were prospective 28 , 30 , 31 , 34 , 35 , 40 ; fourteen studies were single-center and four were multicenter 30 , 31 , 33 , 40 ; and nine studies were from Europe and America and nine were from Asia. 26 , 28 , 29 , 33 , 35 , 38 , 39 , 42 , 43 All the studies used images obtained from common white-light imaging and used DL algorithms. It should be noted that of the six prospective studies, only Takenaka 2020 28 explicitly stated that the AI model was involved in the actual diagnostic process of the patient, and the other five studies only prospectively collected data for AI testing.…”

“…Wang et al. 43 created an open-source dataset of UC endoscopic images comprising 7,978 images from 308 patients (excluding augmented images). Additionally, the authors proposed a new DL network named CB-HRNet.…”

“…The public dataset LIMUC 38 comprises 11,276 endoscopic images from 564 patients with UC. The public dataset TMC-UCM 43 comprises 7,978 images from 308 patients with UC. Several studies have used these datasets for AI model training and testing.…”