Dual-feature Fusion Attention Network for Small Object Segmentation

• Published in: Computers in biology and medicine Vol. 160; p. 106985
• Main Authors: Fei, Xin, Li, Xiaojie, Shi, Canghong, Ren, Hongping, Mumtaz, Imran, Guo, Jun, Wu, Yu, luo, Yong, Lv, Jiancheng, Wu, Xi
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2023; Elsevier Limited
• Subjects: Accuracy; Artificial neural networks; Boundaries; Complementarity; Dual-branch feature fusion; Humans; Image enhancement; Image processing; Image Processing, Computer-Assisted; Image segmentation; Internal Medicine; Medical imaging; Modules; Multi-resolution features; Neural networks; Neural Networks, Computer; Other; Polyps; Radiation therapy; Radiologists; Reverse attention; Small object segmentation; Small object segmentation; Dual-branch feature fusion; Multi-resolution features; Reverse attention
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106985

Accurate segmentation of medical images is an important step during radiotherapy planning and clinical diagnosis. However, manually marking organ or lesion boundaries is tedious, time-consuming, and prone to error due to subjective variability of radiologist. Automatic segmentation remains a challenging task owing to the variation (in shape and size) across subjects. Moreover, existing convolutional neural networks based methods perform poorly in small medical objects segmentation due to class imbalance and boundary ambiguity. In this paper, we propose a dual feature fusion attention network (DFF-Net) to improve the segmentation accuracy of small objects. It mainly includes two core modules: the dual-branch feature fusion module (DFFM) and the reverse attention context module (RACM). We first extract multi-resolution features by multi-scale feature extractor, then construct DFFM to aggregate the global and local contextual information to achieve information complementarity among features, which provides sufficient guidance for accurate small objects segmentation. Moreover, to alleviate the degradation of segmentation accuracy caused by blurred medical image boundaries, we propose RACM to enhance the edge texture of features. Experimental results on datasets NPC, ACDC, and Polyp demonstrate that our proposed method has fewer parameters, faster inference, and lower model complexity, and achieves better accuracy than more state-of-the-art methods. [Display omitted] •We propose an efficient segmentation DFF-Net network for small medical objects.•DFF-Net achieves better results with fewer parameters than other SOTA methods.•Our RACM and DFFM module guide segmentation and enhance the edge texture of features.