Multi-scale long-range interactive and regional attention network for stroke lesion segmentation. (October 2022)

• Record Type: Journal Article
• Authors: Wu, Zelin; Zhang, Xueying; Li, Fenglian; Wang, Suzhe; Huang, Lixia
• Is Part Of: Computers & electrical engineering. Volume 103(2022)
• Publication Date: 2022-10
• Subjects: Multi-scale -- Vision transformer -- Medical image segmentation -- Stroke lesion segmentation -- Interactive attention; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108345
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: High-performance segmentation can help physicians complete clinical diagnosis in a timely manner, thereby determining critical treatment periods and improving the efficiency of stroke diagnosis. However, such a lesion segmentation suffers from severe deviation and time-consuming due to small discrepancies between the lesions and healthy tissues. In order to segment stroke lesions with high performance, we intend to capture several scales of local–global semantic information in this study. Here, we propose the multi-scale long-range interactive and regional attention network (MLiRA-Net), which not only employs convolutional layers to build local features by patch partition block, but also adopts transformers to extract global information at multi-scale by encoding tokenized image patches. The MLiRA-Net establishes local–global spatial features of different scales, and achieves the re-direction of shallow features for upsampling recovery through skip-connections. To evaluate MLiRA-Net, we conduct extensive experiments on the anatomical tracings of lesions after stroke (ATLAS) dataset, and select dice similarity coefficient (DSC) and hausdorff distance (HD) as the major evaluation metrics. Experimental results show that the proposed method has the segmentation performance of 61.19% DSC and 13.49 mm HD. Compared with the existing TransUNet benchmark method, DSC and HD are improved by 4.96% and 5.95 mm, respectively. Graphical abstract: Highlights: To introduce multi-scale information, we design a new self-attention mechanism. We design a MLiRA-Net for stroke lesion segmentation. MLiRA-Net achieves best DSC and HD on the ATLAS dataset.