Human visual perception-inspired medical image segmentation network with multi-feature compression.
Authors
Affiliations (4)
Affiliations (4)
- School of Computer Science, Northwestern Polytechnical University, Xi'an 710129, China; School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an 710072, China. Electronic address: [email protected].
- School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi'an 710072, China. Electronic address: [email protected].
- Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, Ultrasomics Artificial Intelligence X-Lab, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou 510060, China. Electronic address: [email protected].
- Department of Ultrasound, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510060, China. Electronic address: [email protected].
Abstract
Medical image segmentation is crucial for computer-aided diagnosis and treatment planning, directly influencing clinical decision-making. To enhance segmentation accuracy, existing methods typically fuse local, global, and various other features. However, these methods often ignore the negative impact of noise on the results during the feature fusion process. In contrast, certain regions of the human visual system, such as the inferotemporal cortex and parietal cortex, effectively suppress irrelevant noise while integrating multiple features-a capability lacking in current methods. To address this gap, we propose MS-Net, a medical image segmentation network inspired by human visual perception. MS-Net incorporates a multi-feature compression (MFC) module that mimics the human visual system's processing of complex images, first learning various feature types and subsequently filtering out irrelevant ones. Additionally, MS-Net features a segmentation refinement (SR) module that emulates how physicians segment lesions. This module initially performs coarse segmentation to capture the lesion's approximate location and shape, followed by a refinement step to achieve precise boundary delineation. Experimental results demonstrate that MS-Net not only attains state-of-the-art segmentation performance across three public datasets but also significantly reduces the number of parameters compared to existing models. Code is available at https://github.com/guangguangLi/MS-Net.