The Sensitivity of Magnetic Resonance Imaging and Ultrasonography in Detecting Rotator Cuff Tears

Detection of the rotator cuff tears using a novel convolutional neural network from magnetic resonance image (MRI)

The rotator cuff tear is a common situation for basketballers, handballers, or other athletes that strongly use their shoulders. This injury can be diagnosed precisely from a magnetic resonance (MR) image. In this paper, a novel deep learning-based framework is proposed to diagnose rotator cuff tear from MRI images of patients suspected of the rotator cuff tear. First, we collected 150 shoulders MRI images from two classes of rotator cuff tear patients and healthy ones with the same numbers. These images were observed by an orthopedic specialist and then tagged and used as input in the various configurations of the Convolutional Neural Network (CNN). At this stage, five different configurations of convolutional networks have been examined. Then, in the next step, the selected network with the highest accuracy is used to extract the deep features and classify the two classes of rotator cuff tear and healthy. Also, MRI images are feed to two quick pre-trained CNNs (MobileNetv2 and SqueezeNet) to compare with the proposed CNN. Finally, the evaluation is performed using the 5-fold cross-validation method. Also, a specific Graphical User Interface (GUI) was designed in the MATLAB environment for simplicity, which allows for testing by detecting the image class. The proposed CNN achieved higher accuracy than the two mentioned pre-trained CNNs. The average accuracy, precision, sensitivity, and specificity achieved by the best selected CNN configuration are equal to 92.67%, 91.13%, 91.75%, and 92.22%, respectively. The deep learning algorithm could accurately rule out significant rotator cuff tear based on shoulder MRI.

Diagnostic Accuracy of Ultrasonography for Rotator Cuff Tears: A Systematic Review and Meta-analysis

Background

With recent improvements in transducer strength, image resolution, and operator training, ultrasound (US) provides an excellent alternative imaging modality for the diagnosis of rotator cuff tears.

Purpose

To evaluate the diagnostic accuracy of US for partial- and full-thickness rotator cuff tears and biceps tendon tears, compare diagnostic values with those of magnetic resonance imaging (MRI) using arthroscopy as the reference standard, assess longitudinal improvements in accuracy, and compare diagnostic values from operators with different training backgrounds.

Study Design

Systematic review; Level of evidence, 3.

Methods

The PubMed and Cochrane Library databases were systematically searched for full-text journal articles published between January 1, 2010, and April 1, 2020. The inclusion criteria were studies that evaluated the diagnostic accuracy of US for rotator cuff tears or biceps tendon tears utilizing arthroscopy as the reference standard. The exclusion criteria were studies with <10 patients, studies including massive tears without reporting diagnostic data for specific tendons, and studies lacking diagnostic outcome data. Extracted outcomes included diagnostic accuracy, sensitivity, specificity, negative predictive value, and positive predictive value. The mean difference and 95% confidence interval were calculated for both US and MRI diagnostic values, and meta-analysis was conducted using the Mantel-Haenszel random-effects model.

Results

In total, 23 eligible studies involving 2054 shoulders were included. US demonstrated a higher median diagnostic accuracy for supraspinatus tendon tears (0.83) and biceps tendon tears (0.93) as compared with subscapularis tendon tears (0.76). US was found to have a higher median accuracy (0.93) for full-thickness supraspinatus tears than partial-thickness tears (0.81). US had superior median sensitivity for partial-thickness supraspinatus tears when performed by radiologists as opposed to surgeons (0.86 vs 0.57). Meta-analysis of the 5 studies comparing US and MRI demonstrated no statistically significant difference in diagnostic sensitivity, specificity, or accuracy for any thickness supraspinatus tears (P = .31-.55), full-thickness tears (P = .63-.97), or partial-thickness tears (P = .13-.81).

Conclusion

For experienced operators, US is a highly sensitive and specific diagnostic modality for the diagnosis of supraspinatus tears and demonstrates statistically equivalent capability to MRI in the diagnosis of both full- and partial-thickness rotator cuff tears.