Multi-Task Cascaded Attention Network for Brain Tumor Segmentation and Classification

Abstract

The segmentation and classification of brain tumors are important yet highly challenging tasks in the field of medical image processing. In this paper, we proposed a multi-task cascaded attention network (MTCAN) for brain tumor segmentation and classification. Specifically, the MTCAN uses a multi-scale residual attention mechanism to fuse and re-calibrate tumor features at different scales, which enhances the network’s focus on brain tumors. Additionally, a cross-stage feature fusion module is proposed to enable information transmission and guide training between the cascaded networks. Experimental results demonstrate that the proposed MTCAN outperforms other state-of-the-art methods in segmenting and classifying brain tumors, holding significant clinical application value.