Automated and real-time validation of gastroesophageal varices under esophagogastroduodenoscopy using a deep convolutional neural network: a multicenter retrospective study (with video)

Chen, Ming-Kai; Wang, Jing; Xiao, Yong; Wu, Lianlian; Hu, Shan; Chen, Shi; Yi, Guo-Dong; Hu, Wei; Xie, Xianmu; Zhu, Yi; Chen, Yiyun; Yang, Yanning; Yu, Honggang

doi:10.1016/j.gie.2020.06.058

Cited by 14 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of 6034 images from 1156 GEV patients were used to train the models for EV segmentation (model 1), RC segmentation (for both EV and GV, model 2), RC and grade classification (for EV, model 3 and model 4), and GV segmentation (model 5). The size classification model for GV (model 6) has been published 10 . If models segment suspicious varices (or RC) area on an image, the image is classified as varices (RC) positive.…”

Section: Methodsmentioning

confidence: 99%

“…However, the endoscopic description of risk factors is subject to operator dependence. There is a low consistency among endoscopists on the grade, RC, and size of GEV 10,11 . Incorrect diagnoses by endoscopists come at the expense of the patients' security and medical costs.…”

Section: Introductionmentioning

confidence: 99%

“…More accurate methods, and larger multicenter validations are still needed. Deep convolutional neural networks (DCNN) were also used in endoscopy to detect EV and gastric varices (GV) 10 , 19 . These systems conclude whether varices appear in an image or video, but don’t point out where the lesion is.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

Wang

Chen

et al. 2022

npj Digit. Med.

Self Cite

View full text Add to dashboard Cite

Bleeding risk factors for gastroesophageal varices (GEV) detected by endoscopy in cirrhotic patients determine the prophylactical treatment patients will undergo in the following 2 years. We propose a methodology for measuring the risk factors. We create an artificial intelligence system (ENDOANGEL-GEV) containing six models to segment GEV and to classify the grades (grades 1–3) and red color signs (RC, RC0-RC3) of varices. It also summarizes changes in the above results with region in real time. ENDOANGEL-GEV is trained using 6034 images from 1156 cirrhotic patients across three hospitals (dataset 1) and validated on multicenter datasets with 11009 images from 141 videos (dataset 2) and in a prospective study recruiting 161 cirrhotic patients from Renmin Hospital of Wuhan University (dataset 3). In dataset 1, ENDOANGEL-GEV achieves intersection over union values of 0.8087 for segmenting esophageal varices and 0.8141 for gastric varices. In dataset 2, the system maintains fairly accuracy across images from three hospitals. In dataset 3, ENDOANGEL-GEV surpasses attended endoscopists in detecting RC of GEV and classifying grades (p < 0.001). When ranking the risk of patients combined with the Child‒Pugh score, ENDOANGEL-GEV outperforms endoscopists for esophageal varices (p < 0.001) and shows comparable performance for gastric varices (p = 0.152). Compared with endoscopists, ENDOANGEL-GEV may help 12.31% (16/130) more patients receive the right intervention. We establish an interpretable system for the endoscopic diagnosis and risk stratification of GEV. It will assist in detecting the first bleeding risk factors accurately and expanding the scope of quantitative measurement of diseases.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

Wang

Chen

et al. 2022

npj Digit. Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Previous studies have reported the application of AI in identifying esophageal cancer ( 9 , 10 ) and intestinal polyps ( 11 ), and AI has also demonstrated to be of effectively assistance in the field of endoscopic systems. At present, the object detection algorithms based on deep learning are commonly used in lesion detection in endoscopy ( 12 , 13 ). These algorithms have limitations, such as large calculation and low expression accuracy ( 14 , 15 ).…”

Section: Introductionmentioning

confidence: 99%

Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video)

et al. 2022

View full text Add to dashboard Cite

The artificial intelligence (AI)-assisted endoscopic detection of early gastric cancer (EGC) has been preliminarily developed. The currently used algorithms still exhibit limitations of large calculation and low-precision expression. The present study aimed to develop an endoscopic automatic detection system in EGC based on a mask region-based convolutional neural network (Mask R-CNN) and to evaluate the performance in controlled trials. For this purpose, a total of 4,471 white light images (WLIs) and 2,662 narrow band images (NBIs) of EGC were obtained for training and testing. In total, 10 of the WLIs (videos) were obtained prospectively to examine the performance of the RCNN system. Furthermore, 400 WLIs were randomly selected for comparison between the Mask R-CNN system and doctors. The evaluation criteria included accuracy, sensitivity, specificity, positive predictive value and negative predictive value. The results revealed that there were no significant differences between the pathological diagnosis with the Mask R-CNN system in the WLI test (χ2 = 0.189, P=0.664; accuracy, 90.25%; sensitivity, 91.06%; specificity, 89.01%) and in the NBI test (χ2 = 0.063, P=0.802; accuracy, 95.12%; sensitivity, 97.59%). Among 10 WLI real-time videos, the speed of the test videos was up to 35 frames/sec, with an accuracy of 90.27%. In a controlled experiment of 400 WLIs, the sensitivity of the Mask R-CNN system was significantly higher than that of experts (χ2 = 7.059, P=0.000; 93.00% VS 80.20%), and the specificity was higher than that of the juniors (χ2 = 9.955, P=0.000, 82.67% VS 71.87%), and the overall accuracy rate was higher than that of the seniors (χ2 = 7.009, P=0.000, 85.25% VS 78.00%). On the whole, the present study demonstrates that the Mask R-CNN system exhibited an excellent performance status for the detection of EGC, particularly for the real-time analysis of WLIs. It may thus be effectively applied to clinical settings.

show abstract

“…In recent years, the development of convolutional neural networks (CNNs) in medical practice has increased significantly. In particular, CNNs have been employed to asses a variety of gastrointestinal mucosal lesions from EGD, colonoscopy, and capsule endoscopy 17–22 . However, compared to other endoscopic procedures, EUS‐based CNNs are rare.…”

Section: Introductionmentioning

confidence: 99%

Convolutional neural network‐based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images

Kim

Cho

et al. 2021

J of Gastro and Hepatol

View full text Add to dashboard Cite

Background and Aim We aimed to develop a convolutional neural network (CNN)‐based object detection model for the discrimination of gastric subepithelial tumors, such as gastrointestinal stromal tumors (GISTs), and leiomyomas, in endoscopic ultrasound (EUS) images. Methods We used 376 images from 114 patients with histologically confirmed gastric GIST or leiomyoma to train the EUS‐CNN. We constructed the EUS‐CNN using an EfficientNet CNN model for feature extraction and a weighted bi‐directional feature pyramid network for object detection. We assessed the performance of our EUS‐CNN by calculating its accuracy, sensitivity, specificity, and area under receiver operating characteristic curve (AUC) using a validation set of 170 images from 54 patients. Four EUS experts and 15 EUS trainees were asked to judge the same validation dataset, and the diagnostic yields were compared between the EUS‐CNN and human assessments. Results In the per‐image analysis, the sensitivity, specificity, accuracy, and AUC of our EUS‐CNN were 95.6%, 82.1%, 91.2%, and 0.9234, respectively. In the per‐patient analysis, the sensitivity, specificity, accuracy, and AUC for our object detection model were 100.0%, 85.7%, 96.3%, and 0.9929, respectively. The EUS‐CNN outperformed human assessment in terms of accuracy, sensitivity, and negative predictive value. Conclusions We developed the EUS‐CNN system, which demonstrated high diagnostic ability for gastric GIST prediction. This EUS‐CNN system can be helpful not only for less‐experienced endoscopists but also for experienced ones. Additional EUS image accumulation and prospective studies are required alongside validation in a large multicenter trial.

show abstract

Automated and real-time validation of gastroesophageal varices under esophagogastroduodenoscopy using a deep convolutional neural network: a multicenter retrospective study (with video)

Cited by 14 publications

References 31 publications

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

Automatic detection of early gastric cancer in endoscopy based on Mask region-based convolutional neural networks (Mask R-CNN)(with video)

Convolutional neural network‐based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images

Contact Info

Product

Resources

About