Multiscale fused network with additive channel–spatial attention for image segmentation

• Published in: Knowledge-based systems Vol. 214; p. 106754
• Main Authors: Gao, Chengling, Ye, Hailiang, Cao, Feilong, Wen, Chenglin, Zhang, Qinghua, Zhang, Feng
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 28.02.2021; Elsevier Science Ltd
• Subjects: Attention mechanism; Class imbalance; Deep learning; Feature extraction; Feature maps; Image segmentation; Medical imaging; Modules; Multiscale fusion; Semantic segmentation; Semantics; Deep learning; Attention mechanism; Semantic segmentation; Class imbalance; Multiscale fusion
• ISSN: 0950-7051; 1872-7409
• DOI: 10.1016/j.knosys.2021.106754

Class imbalance is a challenge in image segmentation. Deep learning has demonstrated potential advantages as a promising approach in solving such challenging problems because of its powerful ability to extract features. To treat class imbalance in medical image segmentation effectively, in this study, deep learning technology is employed. Further, a new approach, referred to as multiscale fused network with additive channel–spatial attention (MSF-ACSA), is developed. In particular, using the U-shape convolutional network as the structure of the main body network, an additive channel–spatial attention (ACSA) module, which exploits high-level features to guide low-level features for optimal responses, is designed. Therefore, the proposed MSF-ACSA can availably focus on regions of interest while adaptively recalibrating the channel significance of feature maps. Simultaneously, a multiscale fusion with deep supervision module is introduced to incorporate fine-grained details with coarse-grained semantics from diverse scale features. Furthermore, a focal weighted Tversky loss function is proposed to mitigate class imbalance issues. Numerous experimental results indicate that the proposed MSF-ACSA achieves the best performance when compared with state-of-the-art approaches for medical image segmentation.