A Hybrid Attention-Based Fuzzy Pooling Network Model for Locating Polyp Positions in Gastroscopic Image in Internet of Medical Things

Using deep-learning techniques, such as convolutional neural networks to locate polyps in gastroscopic images automatically is of great significance for preventing gastric cancer. However, polyps are typically irregular in shape and inconsistent in size, posing challenges to the predictive performance of previous models. Previous localization models typically treat all parts of the gastroscopic image equally with multiple convolution and pooling operations without considering the importance of different positions. As polyps may occupy only a tiny portion of the gastroscopic image, the model should prioritize attention to different positions in the image differently. Moreover, in previous models, pooling operations generally employ max-pooling or average-pooling, which are less effective in information retention and positional awareness. Therefore, inspired by attention mechanisms and fuzzy algorithms, in this work, we propose a Hybrid Attention Fuzzy Pooling Network (HAFPN) for locating polyps in gastroscopic images in Internet of Medical Things. The advantages of the HAFPN model lie in the following. First, valuable local information in the image is preserved using a hybrid attention mechanism. Specifically, the HAFPN model inputs gastroscopic images into a convolutional neural network augmented with channel attention and spatial attention mechanisms to calculate the coordinates of gastric polyps. The combination of channel attention and spatial attention mechanisms helps the HAFPN model dynamically capture channel and spatial information from the original image. Second, fuzzy pooling operations preserve positional information in the feature maps. We conducted extensive experiments on a real gastroscopic dataset to validate the effectiveness of the HAFPN model.