Wide-Field 3D Ultrasound Imaging Platform With a Semi-Automatic 3D Segmentation Algorithm for Quantitative Analysis of Rotator Cuff Tears

Moon Hwan Lee,Chang-Hyuk Choi,Kyungsu Lee,Jae Youn Hwang,Jun-Young Kim

doi:10.1109/access.2020.2985858

Abstract

Rotator cuff tear (RCT) is a common injury that causes pain and disability in adults. The quantitative diagnosis of the RCT can be crucial in determining a treatment plan or monitoring treatment efficacy. Currently, only a few diagnosis tools, such as magnetic resonance imaging (MRI) and ultrasound imaging (US), are utilized for the diagnosis. Specifically, US exhibited comparable performance with MRI while offering a readily available diagnosis of RCTs at a lower cost. However, three-dimensional(3D) US and analysis of the regions are necessary to enable a better diagnosis of RCTs. Therefore, we developed a wide-field 3D US platform with a semi-automatic 3D image segmentation algorithm for 3D quantitative diagnosis of RCTs. The 3D US platform is built based on a conventional 2D US system and obtains 3D US images via linear scanning. With respect to 3D segmentation algorithm based on active contour model, frequency compounding and anisotropic diffusion methods were applied, and their effects on segmentation were discussed. The platform was used for clinical examination after evaluating the platform via the RCT-mimicking phantoms. As verified by the Dice coefficient(average DC: 0.663, volume DC: 0.723), which was approximately up to 50% higher than that obtained with conventional algorithms, the RCT regions segmented by the developed algorithm significantly matched the ground truth. The results indicated that the wide-field 3D US platform with the 3D segmentation algorithm can constitute a useful tool for improving the accuracy in the diagnosis of RCTs, and can eventually lead to better determination of treatment plans and surgical planning.

Highlights

Rotator cuff tear (RCT) is a common disease in the shoulder joint, which causes pain and a limited range of motion resulting in functional disability
B. 3D SEGMENTATION ALGORITHM FOR ROTATOR CUFF TEAR REGIONS For the precise 3D segmentation of rotator cuff tear regions on a 3D ultrasound image, we developed a semi-automatic segmentation algorithm based on frequency compounding (FC), speckle reducing anisotropic diffusion(SRAD), and Chan-Vese active contour techniques
The field of view of the 3D image is 38 mm×50 mm×56 mm, and this is suitable for the imaging of rotator cuff tear regions in the shoulder

Summary

Introduction

Rotator cuff tear (RCT) is a common disease in the shoulder joint, which causes pain and a limited range of motion resulting in functional disability. The aging population is currently growing globally, and the number of patients with RCTs are increasing. Non-invasive imaging techniques, such as ultrasound sonography (US) and Magnetic Resonance Imaging (MRI), increase the diagnostic accuracy of RCT due to a variety of technological advances [3]. MRI is considered as the favored imaging tool for diagnosis and surgical planning. This imaging modality is not clinically readily available due to its high cost, time consumption, and acoustic noise [4]. US is widely used for diagnosis and surgical planning for RCTs due to its real-time dynamic capture, low-cost, time-saving, and readily-availability when compared to MRI [5]–[7]. Roy et al [9] reported that US exhibits high sensitivity and specificity for the diagnosis of RCT, and several studies described that US exhibited

Methods

Results

Discussion

Conclusion