Background: Estimating skeletal muscle force output and structure requires measurement of morphological parameters including muscle thickness, pennation angle, and fascicle length. The identification of aponeurosis and muscle fascicles from medical images is required to measure these parameters accurately.
Methods: This paper introduces a multi-stage fusion and segmentation model (named MSF-Net), to precisely extract muscle aponeurosis and fascicles from ultrasound images. The segmentation process is divided into three stages of feature fusion modules. A prior feature fusion module (PFFM) is designed in the first stage to fuse prior features, thus enabling the network to focus on the region of interest and eliminate image noise. The second stage involves the addition of multi-scale feature fusion module (MS-FFM) for effective fusion of elemental information gathered from different scales. This process enables the precise extraction of muscle fascicles of varied sizes. Finally, the high-low-level feature fusion attention module (H-LFFAM) is created in the third stage to selectively reinforce features containing useful information.
Results: Our proposed MSF-Net outperforms other methods and achieves the highest evaluation metrics. In addition, MSF-Net can obtain similar results to manual measurements by clinical experts. The mean deviation of muscle thickness and fascicle length was 0.18 mm and 1.71 mm, and the mean deviation of pennation angle was 0.31°.
Conclusions: MSF-Net can accurately extract muscle morphological parameters, which enables medical experts to evaluate muscle morphology and function, and guide rehabilitation training. Therefore, MSF-Net provides a complementary imaging tool for clinical assessment of muscle structure and function.
Keywords: Attention gate; B-mode ultrasound; Deep learning; Medical image segmentation; Muscle morphological parameters.
Copyright © 2023 Elsevier B.V. All rights reserved.