Multi-Level Medical Image Segmentation Network Based on Multi-Scale and Context Information Fusion Strategy

Accurate segmentation of human tissue structure from medical images is one of the critical links in medical image diagnosis. However, due to the medical image scale of different tissues varying significantly and being structurally complex, the low contrast between tissues and background in some medical imaging makes it challenging to identify. The existing models are difficult to extract representative multi-scale features of medical images that cannot accurately segment the organizational structure from the background in low-contrast medical images. To solve these problems, this study presents a scale and context information fusion network structure based on multi-type medical image segmentation (SCIF-Net), which contains three modules: feature pyramid encoder (FPE), multi-scale feature dynamic aggregation (MFDA), and adaptive spatial information fusion (ASIF). We build the FPE module to further enhance the representational ability of the network encoder output feature map at each stage. The MFDA module is used to effectively extract multi-scale information from the encoder output feature map and aggregate multi-scale features. The constructed ASIF module enables the network to selectively concentrate on the vital spatial information in the encoder feature map and merge the decoder feature map semantic information, minimizing background noise influence. Extensive experiments on the retinal segmentation task, gland segmentation task, and femur segmentation task, show that the SCIF-Net network outperforms other advanced methods.