Identification of patients with a high risk of gastric cancer during gastric cancer surveillance is highly important. Most gastric cancers develop in the background of chronic gastritis associated with Helicobacter pylori (H. pylori) infection. Pathological evaluation using biopsy specimen was proposed to stratify gastric cancer risk in the operative link for gastritis assessment and operative link for gastric intestinal metaplasia assessment staging systems from the West. However, biopsy specimens cannot represent the whole stomach, and endoscopic biopsy confers a risk of bleeding in certain patients. In the Kyoto classification of gastritis proposed by a Japanese study group, five endoscopically visible findings (atrophy, intestinal metaplasia, enlarged folds, nodularity, and diffuse redness) were selected, which are closely related to gastric cancer development due to H. pylori infection. Furthermore, the gastric cancer risk grading system based on the Kyoto classification of gastritis was suggested to identify patients with an increased risk of developing gastric cancer. Although this grading system needs validation to prove its efficacy, it is expected to be useful for most endoscopists who are involved in gastric cancer surveillance.

Background Fat fraction values obtained from magnetic resonance imaging (MRI) can be used to obtain an accurate diagnosis of fatty liver diseases. However, MRI is expensive and cannot be performed for everyone. Objective In this study, we aim to develop multi-view ultrasound image–based convolutional deep learning models to detect fatty liver disease and yield fat fraction values. Methods We extracted 90 ultrasound images of the right intercostal view and 90 ultrasound images of the right intercostal view containing the right renal cortex from 39 cases of fatty liver (MRI–proton density fat fraction [MRI–PDFF] ≥ 5%) and 51 normal subjects (MRI–PDFF < 5%), with MRI–PDFF values obtained from Good Gang-An Hospital. We obtained combined liver and kidney-liver (CLKL) images to train the deep learning models and developed classification and regression models based on the VGG19 model to classify fatty liver disease and yield fat fraction values. We employed the data augmentation techniques such as flip and rotation to prevent the deep learning model from overfitting. We determined the deep learning model with performance metrics such as accuracy, sensitivity, specificity, and coefficient of determination (R2). Results In demographic information, all metrics such as age and sex were similar between the two groups—fatty liver disease and normal subjects. In classification, the model trained on CLKL images achieved 80.1% accuracy, 86.2% precision, and 80.5% specificity to detect fatty liver disease. In regression, the predicted fat fraction values of the regression model trained on CLKL images correlated with MRI–PDFF values (R2=0.633), indicating that the predicted fat fraction values were moderately estimated. Conclusions With deep learning techniques and multi-view ultrasound images, it is potentially possible to replace MRI–PDFF values with deep learning predictions for detecting fatty liver disease and estimating fat fraction values.

BACKGROUND Fat fraction values obtained from magnetic resonance images (MRI) can be used to obtain an accurate diagnosis of fatty liver diseases. However, MRI is expensive and cannot be performed for everyone. OBJECTIVE In this study, we aim to develop multi-view ultrasound image-based convolutional deep learning models to detect fatty liver disease and yield fat fraction values. METHODS We extracted 90 (the right intercostal view) and 90 (the right intercostal view containing the right renal cortex) ultrasound images from 39 fatty liver subjects (MRI-PDFF ≥ 5%) and 51 normal subjects (MRI-PDFF < 5%) containing MRI-PDFF values from Good Gang-An Hospital. We combined liver and kidney-liver (CLKL) images to train the deep learning models, and developed classification and regression models based on VGG19 to classify fatty liver disease and yield fat fraction values. We employed the data augmentation techniques such as flip and rotation to prevent the deep learning model from overfitting. We determined the deep learning model with performance metrics such as accuracy, sensitivity, specificity, and coefficient of determination (R2). RESULTS In demographic information, all metrics such as age and sex were similar between the two groups, i.e., fatty liver disease and normal subjects. In classification, model trained on CLKL images achieved 80.1% accuracy, 86.2% precision, and 80.5% specificity to detect fatty liver disease. In regression, the predicted fat fraction values of the regression model trained on CLKL images correlated with MRI-proton density fat fraction (MRI-PDFF) values (R2, 0.633), indicating that the predicted fat fraction values were moderately estimated. CONCLUSIONS With deep learning techniques and multi-view ultrasound images, it is potentially possible to replace MRI-PDFF values with deep learning predictions for detecting fatty liver disease and estimating fat fraction values.