A deep learning network based on multi-scale and attention for the diagnosis of chronic atrophic gastritis

Chronic atrophic gastritis plays an important role in the process of gastric cancer. Deep learning is gradually introduced in the medical field, and how to better apply a convolutional neural network (CNN) to the diagnosis of chronic atrophic gastritis remains a research hotspot. This study was designed to improve the performance of CNN on diagnosing chronic atrophic gastritis by constructing and evaluating a network structure based on the characteristics of gastroscopic images.

Three endoscopists reviewed the endoscopic images of the gastric antrum from the Gastroscopy Image Database of Zhongnan Hospital and labelled available images according to pathological results. Two novel modules proposed recently were introduced to construct the Multi-scale with Attention net (MWA-net) considering the characters of similar medical images. After training the network using images of training sets, the diagnostic ability of the MWA-net was evaluated by comparing it with those of other deep learning models and endoscopists with varying degrees of expertise.

As a result, 5,159 images of the gastric antrum from 2,240 patients were used to train and test the MWA-net. Compared with the direct application of famous networks, the MWA-net achieved the best performance (accuracy, 92.13%) with an increase of 1.80% compared to that of ResNet. The suspicious lesions indicated by the network are consistent with the conclusion of experts. The sensitivity and specificity of the convolutional network for gastric atrophy diagnosis are 90.19% and 94.51%, respectively, which are higher than those of experts.

Highly similar images of chronic atrophic gastritis can be identified by the proposed MWA-net, which has a better performance than other well-known networks. This work can further reduce the workload of gastroscopists, simplify the diagnostic process and provide medical assistance to more residents.