Diagnostic accuracy of ultrasound for rotator cuff tears

Okoroha, Kelechi R.; Fidai, Mohsin S.; Tramer, Joseph S.; Davis, Kayla D.; Kolowich, Patricia A.

doi:10.14366/usg.18058

Cited by 37 publications

(28 citation statements)

References 34 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The use of ultrasound recently has gained popularity in diagnosing and quantifying different types of shoulder pathology such as rotator cuff injury and Hill-Sachs lesions. 29,51,52 This is because of the relativity lower cost, less time, and zero radiation exposure to the patient. 53 This imaging modality is becoming more favorable, especially in patients who cannot undergo MRI because of medical implants (e.g., pacemaker).…”

Section: Discussionmentioning

confidence: 99%

Accuracy and Reliability of Imaging Modalities for the Diagnosis and Quantification of Hill-Sachs Lesions: A Systematic Review

Vopat

Peebles

McBride

et al. 2021

Arthroscopy: The Journal of Arthroscopic & Related Surgery

View full text Add to dashboard Cite

Purpose: To determine the reliability and accuracy of different imaging modalities in assessing Hill-Sachs lesions within the setting of anterior shoulder instability. Methods: A systematic review was performed according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines using the PubMed, Scopus, Embase, and Cochrane Library databases. The inclusion criteria were clinical trials or cadaveric studies that assessed the accuracy of humeral head bone loss imaging or reliability and English-language articles. The exclusion criteria were animal studies; imaging studies without measures of accuracy, reliability, or clinical predictive power; studies of shoulder injuries without humeral head bone loss; editorials; abstracts; reviews; case reports; and surveys. The search terms included "imaging" OR "radiographic" OR "CT" OR "MRI" AND "Hill-Sachs" OR "humeral head bone loss." Assessment of the methodologic quality of the included studies was performed using the original Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool. Results: Forty studies (2,560 shoulders) met the inclusion criteria and were assessed. For diagnosing the presence of Hill-Sachs lesions, computed tomography (CT) arthrography had the highest reported accuracy (median, 91%; range, 66%-100%). For the same assessment, CT arthrography also had the greatest reported sensitivity (median, 94%; range, 50%-100%). For the quantification of Hill-Sachs lesion parameters, reported intraobserver reliabilities were highest for 3-dimensional (3D) CT (intraclass correlation coefficient [ICC] range, 0.916-0.999), followed by 2-dimensional CT (ICC range, 0.858-0.861) and magnetic resonance imaging (MRI) (ICC range, 0.28-0.97). For the same quantification parameters, interobserver reliabilities were also reported for 3D CT (ICC range, 0.772-0.996), 2-dimensional CT (ICC range, 0.721-0.879), and MRI (k range, 0.444-0.700). Intraobserver reliabilities for determining glenoid tracking were only reported for 3D CT (k range, 0.730-1.00; ICC range, 0.803-0.901) and MRI (ICC range, 0.770-0.790). Conclusions: This study shows that the current literature supports a variety of different imaging modalities that provide clinically acceptable accuracy in diagnosing and quantifying Hill-Sachs lesions, as well as determining whether they will cause persistent anterior shoulder instability. Furthermore, this systematic review justifies that further research is needed to help develop a treatment algorithm on the proper imaging modalities needed to help treat patients with anterior shoulder instability that is both reliable and financially acceptable. Level of Evidence: Level IV, systematic review of Level I through IV studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Accuracy and Reliability of Imaging Modalities for the Diagnosis and Quantification of Hill-Sachs Lesions: A Systematic Review

Vopat

Peebles

McBride

et al. 2021

Arthroscopy: The Journal of Arthroscopic & Related Surgery

View full text Add to dashboard Cite

show abstract

“…Plain film has limited value but does suggest the diagnosis if the humeral head is found to be displaced [9]. In the hands of a skilled operator, ultrasound has been demonstrated to be accurate in the diagnosis of tears, but MRI appears to be more accurate in gauging the extent of a tear and degree of tendon retraction [16].…”

Section: And 5 Respectively)mentioning

confidence: 99%

Disorders of the Upper Extremity

Jensen¹

2020

Family Medicine

View full text Add to dashboard Cite

show abstract

“…Symptomatic RCTs can be treated either nonsurgically or surgically. The precise diagnosis of RCT is essential before surgical treatment [ 4 , 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

“…Among non-invasive imaging techniques, ultrasound imaging (UI) and magnetic resonance imaging (MRI) systems have been widely used for the diagnosing locations of RCT [ 3 , 6 ]. An MRI system has been a favorable imaging tool for localizing an RCT but it has a few limitations [ 7 , 8 ]; e.g., it is not easily accessible owing to its high cost, acoustic noise, and time consumption, and it cannot be applied to the diagnosis of locations of RCT dynamically.…”

Section: Introductionmentioning

confidence: 99%

Imbalanced Loss-Integrated Deep-Learning-Based Ultrasound Image Analysis for Diagnosis of Rotator-Cuff Tear

Lee

Kim

Lee

et al. 2021

Sensors

View full text Add to dashboard Cite

A rotator cuff tear (RCT) is an injury in adults that causes difficulty in moving, weakness, and pain. Only limited diagnostic tools such as magnetic resonance imaging (MRI) and ultrasound Imaging (UI) systems can be utilized for an RCT diagnosis. Although UI offers comparable performance at a lower cost to other diagnostic instruments such as MRI, speckle noise can occur the degradation of the image resolution. Conventional vision-based algorithms exhibit inferior performance for the segmentation of diseased regions in UI. In order to achieve a better segmentation for diseased regions in UI, deep-learning-based diagnostic algorithms have been developed. However, it has not yet reached an acceptable level of performance for application in orthopedic surgeries. In this study, we developed a novel end-to-end fully convolutional neural network, denoted as Segmentation Model Adopting a pRe-trained Classification Architecture (SMART-CA), with a novel integrated on positive loss function (IPLF) to accurately diagnose the locations of RCT during an orthopedic examination using UI. Using the pre-trained network, SMART-CA can extract remarkably distinct features that cannot be extracted with a normal encoder. Therefore, it can improve the accuracy of segmentation. In addition, unlike other conventional loss functions, which are not suited for the optimization of deep learning models with an imbalanced dataset such as the RCT dataset, IPLF can efficiently optimize the SMART-CA. Experimental results have shown that SMART-CA offers an improved precision, recall, and dice coefficient of 0.604% (+38.4%), 0.942% (+14.0%) and 0.736% (+38.6%) respectively. The RCT segmentation from a normal ultrasound image offers the improved precision, recall, and dice coefficient of 0.337% (+22.5%), 0.860% (+15.8%) and 0.484% (+28.5%), respectively, in the RCT segmentation from an ultrasound image with severe speckle noise. The experimental results demonstrated the IPLF outperforms other conventional loss functions, and the proposed SMART-CA optimized with the IPLF showed better performance than other state-of-the-art networks for the RCT segmentation with high robustness to speckle noise.

show abstract

Diagnostic accuracy of ultrasound for rotator cuff tears

Cited by 37 publications

References 34 publications

Accuracy and Reliability of Imaging Modalities for the Diagnosis and Quantification of Hill-Sachs Lesions: A Systematic Review

Accuracy and Reliability of Imaging Modalities for the Diagnosis and Quantification of Hill-Sachs Lesions: A Systematic Review

Disorders of the Upper Extremity

Imbalanced Loss-Integrated Deep-Learning-Based Ultrasound Image Analysis for Diagnosis of Rotator-Cuff Tear

Contact Info

Product

Resources

About