A Single-Shot Region-Adaptive Network for Myotendinous Junction Segmentation in Muscular Ultrasound Images

Tracking the myotendinous junction (MTJ) in consecutive ultrasound images is crucial for understanding the mechanics and pathological conditions of the muscle-tendon unit. However, the lack of reliable and efficient identification of MTJ due to poor image quality and boundary ambiguity restricts its application in motion analysis. In recent years, with the rapid development of deep learning, the region-based convolution neural network (RCNN) has shown great potential in the field of simultaneous objection detection and instance segmentation in medical images. This article proposes a region-adaptive network (RAN) to localize MTJ region and to segment it in a single shot. Our model learns about the salient information of MTJ with the help of a composite architecture. Herein, a region-based multitask learning network explores the region containing MTJ, while a parallel end-to-end U-shaped path extracts the MTJ structure from the adaptively selected region for combating data imbalance and boundary ambiguity. By demonstrating the ultrasound images of the gastrocnemius, we showed that the RAN achieves superior segmentation performance when compared with the state-of-the-art Mask RCNN method with an average Dice score of 80.1%. Our proposed method is robust and reliable for advanced muscle and tendon function examinations obtained by ultrasound imaging.

I. Introduction

MTU that consists of muscles and tendons plays a crucial role in force generation and kinetic energy mechanism during human movement [1]. In recent years, ultrasound imaging has become a prospective field of research in characterizing in vivo mechanics of MTU by identifying structural changes and anatomical landmarks within the muscle from the visual inspection of B-mode images during the muscle activation [2]–[14]. Structural parameters between frames, such as tendon length and MTJ, have been widely studied in both diagnosis and rehabilitation, such as comprehending the treatment outcomes for patients with motor problems [7] and monitoring rehabilitation plans for patients with surgical operations [8], [9].