Multi-Class Gastroesophageal Reflux Disease Classification System Using Deep Learning Techniques

Gastroesophageal reflux disease (GERD) has been a ubiquitous health problem for centuries. Its symptoms are hard to distinguish and endoscopists with less experience usually find it difficult to diagnose the severity of GERD, and this disease might progress to more severe diseases like Barrett’s esophagus without adequate treatment. Therefore, we proposed a multi-class classification system, which comprised a deep learning (DL) model and graphical user interface (GUI), to classify GERD grading from endoscopic images so as to provide finer predictions on erosive esophagus and easier assessment to the system. The Los Angeles Classification system (LACS) was selected as the standard for severity grading. We collected 3,654 white light (WL) esophagoscopic images from the database engine of Xiangyang Centre Hospital. We built the DL model using pre-trained convolutional neural network (CNN) model as the backbone, and different pre-trained models were used and compared. We also evaluated the effectiveness of applying data resampling and attention map to the DL model for optimizing model performance. Besides, data augmentation was also employed. After the best model was selected, we built the GUI using HuggingFace. Experimental results showed that DenseNet121 with oversampling and attention map achieved the best results with an accuracy of 0.7469, recall of 0.7057 and Cohen’s kappa of 0.7757. It was also discovered that the experimental groups using both techniques outperformed the others, while using DenseNet121 obtained better results considering all experimental groups. The model outputs were displayed in terms of the predicted label, probabilities for each grade and a heatmap containing highlighted attention. In conclusion, a multi-class DL classification system was developed for GERD grading classification, and it exhibited its potentially acceptable efficacy for GERD diagnosis based on the LACS.