Non-same-scale feature attention network based on BPD for medical image segmentation

Abstract

The accuracy of diagnosis in medical systems requires automatic image segmentation techniques to provide accurate segmented images of lesions. Segmented images need to be more accurate not only in terms of shape size but also in terms of position. In recent years, a large number of deep learning algorithms have worked tirelessly on this goal. In the field of medical image segmentation, although the prediction images generated by traditional algorithms may not exhibit ideal performance, it is important to note that these methods still provide valuable information regarding edge features. Thus, our goal is to develop a combined approach that integrates traditional algorithms with deep learning techniques. By harnessing the rich edge feature information offered by traditional algorithms, we can enhance the accuracy of image segmentation achieved through deep learning. We propose the Non-same-scale feature attention network based on BPD for medical image segmentation (BPD-NSSFA). First, the network acquires a feature map with rich edge information through Boundary-to-Pixel Direction (BPD) and sends the feature map together with the original image into the backbone network to complete feature extraction and feature fusion. At the bottleneck layer, we use ASPP to expand the receptive field to focus on the associations between more feature information. Finally, we create a Non-same-Scale Feature Attention Block for feature fusion and supervise the fusion process using a deep supervision mechanism. To validate the effectiveness of our network, we select seven different datasets of varying sizes to test the performance of the network. From the experimental results, our network demonstrates superior performance compared to current state-of-the-art methods in lesion localization, edge processing, and noise robustness. Additionally, ablative experiments confirm the rationality of the network structure.