TY - JOUR
T1 - Using Deep Learning-Based Methods for Automated Segmentation of Soft Tissues From Shoulder Ultrasound Images
AU - Lee, Ying Chun
AU - Lin, Chih Yang
AU - Hsiao, Chia Chun
AU - Mo, Pu Chun
AU - Guo, Jiaqi
AU - Jan, Yih Kuen
N1 - Publisher Copyright:
©2024 The Authors.
PY - 2024
Y1 - 2024
N2 - Shoulder pain and injuries present significant challenges to researchers and clinicians for diagnosing underlying structural changes due to the complexity of the shoulder joint. Ultrasonography has been used for diagnosing shoulder impairment and can non-invasively assess structures and mechanical properties of the shoulder. However, the complexity of the shoulder structures often results in diagnostic difficulties and misdiagnosis. Although deep learning of artificial intelligence has been applied in various biomedical imaging, the adoption of deep learning techniques in the segmentation of musculoskeletal ultrasound images, especially the shoulder, is limited. This study addresses this gap by assessing the effectiveness of 3 deep learning models, U-Net, Mask R-CNN, and DeepLab V3+, for the segmentation of soft tissues from shoulder ultrasound images. We collected 721 images from the shoulder area of 17 healthy adults, including the anterior deltoid, medial deltoid, posterior deltoid, and supraspinatus. We employed a combination of three augmentation methods (elastic transform, horizontal flip, and shift scale rotate) to enhance the dataset. The mixed augmentation strategy resulted in U-Net outperforming Mask R-CNN and DeepLab V3+ with a mean Average Precision (mAP) of 78-81%, a mean Intersection over Union (mIoU) of 81-87%, and Recall and Precision values between 91-94% and 87-91%, respectively. The effective use of deep learning methods could assist clinicians on assessing shoulder structures from ultrasound images.
AB - Shoulder pain and injuries present significant challenges to researchers and clinicians for diagnosing underlying structural changes due to the complexity of the shoulder joint. Ultrasonography has been used for diagnosing shoulder impairment and can non-invasively assess structures and mechanical properties of the shoulder. However, the complexity of the shoulder structures often results in diagnostic difficulties and misdiagnosis. Although deep learning of artificial intelligence has been applied in various biomedical imaging, the adoption of deep learning techniques in the segmentation of musculoskeletal ultrasound images, especially the shoulder, is limited. This study addresses this gap by assessing the effectiveness of 3 deep learning models, U-Net, Mask R-CNN, and DeepLab V3+, for the segmentation of soft tissues from shoulder ultrasound images. We collected 721 images from the shoulder area of 17 healthy adults, including the anterior deltoid, medial deltoid, posterior deltoid, and supraspinatus. We employed a combination of three augmentation methods (elastic transform, horizontal flip, and shift scale rotate) to enhance the dataset. The mixed augmentation strategy resulted in U-Net outperforming Mask R-CNN and DeepLab V3+ with a mean Average Precision (mAP) of 78-81%, a mean Intersection over Union (mIoU) of 81-87%, and Recall and Precision values between 91-94% and 87-91%, respectively. The effective use of deep learning methods could assist clinicians on assessing shoulder structures from ultrasound images.
KW - Artificial intelligence
KW - computer assisted diagnosis
KW - muscle
KW - ultrasonography
UR - http://www.scopus.com/inward/record.url?scp=85199564500&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2024.3432691
DO - 10.1109/ACCESS.2024.3432691
M3 - 期刊論文
AN - SCOPUS:85199564500
SN - 2169-3536
VL - 12
SP - 111481
EP - 111492
JO - IEEE Access
JF - IEEE Access
ER -