DPFA-UNet: Dual-Path Fusion Attention for Accurate Brain Tumor Segmentation

Abstract

Gliomas are the most common primary brain tumors within the central nervous system, typically observed through magnetic resonance imaging (MRI). Precise segmentation of brain tumor in MRI is highly significant for both clinical diagnosis and treatment. However, due to complexity of tumor structures, existing deep-learning-based methods for brain tumor segmentation still face challenges in accurately delineating tumor core (TC) and enhancing tumor (ET) regions, which are primary targets for actual treatment. To address this problem, this work proposes dual-path fusion attention-based UNet (DPFA-UNet) that leverages a dual-path attention block (DPA) and a concurrent attention fusion block (CAF) within a U-shaped architecture. Specifically, DPA enhances adaptability to lesions of varying sizes by using multi-scale branches that capture fine details and global features. CAF fuses high- and low-level semantic features using a parallel attention mechanism, effectively focusing on the focal regions. It also incorporates a mask generated by deep supervision mechanism to further guide feature fusion. Additionally, to reduce demand for hardware resources, we incorporate depthwise separable convolution into the model. Experiments are conducted on public BraTS 2021 and BraTS 2019 datasets. The results verify that DPFA-UNet outperforms existing brain tumor segmentation methods, particularly in segmenting TC and ET regions.