Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network

Abstract

Background Visual inspection, lesion detection, and differentiation between malignant and benign features are key aspects of an endoscopist’s role. The use of machine learning for the recognition and differentiation of images has been increasingly adopted in clinical practice. This study aimed to establish convolutional neural network (CNN) models to automatically classify gastric neoplasms based on endoscopic images. Methods Endoscopic white-light images of pathologically confirmed gastric lesions were collected and classified into five categories: advanced gastric cancer, early gastric cancer, high grade dysplasia, low grade dysplasia, and non-neoplasm. Three pretrained CNN models were fine-tuned using a training dataset. The classifying performance of the models was evaluated using a test dataset and a prospective validation dataset. Results A total of 5017 images were collected from 1269 patients, among which 812 images from 212 patients were used as the test dataset. An additional 200 images from 200 patients were collected and used for prospective validation. For the five-category classification, the weighted average accuracy of the Inception-Resnet-v2 model reached 84.6 %. The mean area under the curve (AUC) of the model for differentiating gastric cancer and neoplasm was 0.877 and 0.927, respectively. In prospective validation, the Inception-Resnet-v2 model showed lower performance compared with the endoscopist with the best performance (five-category accuracy 76.4 % vs. 87.6 %; cancer 76.0 % vs. 97.5 %; neoplasm 73.5 % vs. 96.5 %; P < 0.001). However, there was no statistical difference between the Inception-Resnet-v2 model and the endoscopist with the worst performance in the differentiation of gastric cancer (accuracy 76.0 % vs. 82.0 %) and neoplasm (AUC 0.776 vs. 0.865). Conclusion The evaluated deep-learning models have the potential for clinical application in classifying gastric cancer or neoplasm on endoscopic white-light images.

Prediction of Submucosal Invasion for Gastric Neoplasms in Endoscopic Images Using Deep-Learning

“…Consecutive patients who were found to have any type of gastric neoplasm during upper gastrointestinal endoscopy between 2010 and 2017 at Chuncheon Sacred Heart Hospital were enrolled. The aim of endoscopic examinations and detailed procedures are described in our previous report [19]. All the neoplasm-suspected lesions that were resected using either the endoscopic resection (endoscopic mucosal resection or endoscopic submucosal dissection technique (ESD)) or surgical resection were included.…”

“…Pathological assessment of each lesion was carried out by two pathologists. Samples defined as tumors were cross-checked by yet another pathologist in the Chuncheon Sacred Heart hospital [19].…”

“…Images with poor quality or low resolution disabling their proper classification (defocusing, artifacts, shadowing, etc.) were excluded, as previously described [19]. Eventually, a total of 2899 images from 846 patients were included in the study.…”

Deep learning in gastric tissue diseases: a systematic review

“…Tumour heterogeneity between individuals and the difficulty of finding large databases of annotated medical images is a challenge for researchers. However, most studies addressed progress analysis of developing gastric cancer, such as classification and detection of gastritis, [34][35][36][37] Helicobacter pylori, [38][39][40] gastric neoplasms 41 and gastric ulcers 42 43 Two of the papers were restricted reviews regarding only images of endoscopy and addressed the effects of artificial intelligence on gastroenterology, and both were not included in the final database. Also, both reviews addressed challenges in the development of computeraided diagnostic systems.…”

The Future of Capsule Endoscopy: The Role of Artificial Intelligence and Other Technical Advancements

“…and colonoscopy images have become a vigorous research field, and these systems have demonstrated promising performance in the field of gastroenteroloy. [7][8][9] Typically, a CE video includes an average number of 50,000-60,000 frames in a single examination, requiring an average of 30-120 min of reading time by physicians, depending on the experience level of the reader. 5,10 Because physicians passively read numerous images with intense focus and attention, CE reading is a time-consuming and tedious process.…”