Deep-learning framework and computer assisted fatty infiltration analysis for the supraspinatus muscle in MRI

Abstract

Occupation ratio and fatty infiltration are important parameters for evaluating patients with rotator cuff tears. We analyzed the occupation ratio using a deep-learning framework and studied the fatty infiltration of the supraspinatus muscle using an automated region-based Otsu thresholding technique. To calculate the amount of fatty infiltration of the supraspinatus muscle using an automated region-based Otsu thresholding technique. The mean Dice similarity coefficient, accuracy, sensitivity, specificity, and relative area difference for the segmented lesion, measuring the similarity of clinician assessment and that of a deep neural network, were 0.97, 99.84, 96.89, 99.92, and 0.07, respectively, for the supraspinatus fossa and 0.94, 99.89, 93.34, 99.95, and 2.03, respectively, for the supraspinatus muscle. The fatty infiltration measure using the Otsu thresholding method significantly differed among the Goutallier grades (Grade 0; 0.06, Grade 1; 4.68, Grade 2; 20.10, Grade 3; 42.86, Grade 4; 55.79, p < 0.0001). The occupation ratio and fatty infiltration using Otsu thresholding demonstrated a moderate negative correlation (ρ = − 0.75, p < 0.0001). This study included 240 randomly selected patients who underwent shoulder magnetic resonance imaging (MRI) from January 2015 to December 2016. We used a fully convolutional deep-learning algorithm to quantitatively detect the fossa and muscle regions by measuring the occupation ratio of the supraspinatus muscle. Fatty infiltration was objectively evaluated using the Otsu thresholding method. The proposed convolutional neural network exhibited fast and accurate segmentation of the supraspinatus muscle and fossa from shoulder MRI, allowing automatic calculation of the occupation ratio. Quantitative evaluation using a modified Otsu thresholding method can be used to calculate the proportion of fatty infiltration in the supraspinatus muscle. We expect that this will improve the efficiency and objectivity of diagnoses by quantifying the index used for shoulder MRI.

Three-Dimensional Software- and MR-Imaging-Based Muscle Volumetry Reveals Overestimation of Supraspinatus Muscle Atrophy Using Occupation Ratios in Full-Thickness Tendon Tears

“…Our data demonstrate that 3D muscle volumetry should be preferred in patients with full-thickness SSP tendon tears when the muscle volume needs to be quantified preoperatively in order to estimate the postoperative success rate after tendon repair procedures. This is in accordance with previous studies [ 17 ] and is important since various previous experimental and clinical studies have shown that significant SSP muscle atrophy is an important adverse prognostic factor affecting patients’ outcomes in addition to other conditions, e.g., fatty infiltration or severe tear size [ 8 , 18 , 19 , 20 , 21 , 22 , 23 , 24 ].…”

Artificial Intelligence in the Management of Rotator Cuff Tears

“…Just recently, another study analysed the use of deep-learning framework to study occupation ratio and fatty infiltration of the supraspinatus muscle [ 30 ]. Scapular sagittal Y-view MRI images (T1-weighted) were used as baseline for obtaining reliable indicators of the supraspinatus muscle status.…”

Agreement between intraoperative and magnetic resonance imaging assessments of rotator cuff pathology and 2 magnetic resonance imaging-based assessments of supraspinatus muscle atrophy

“… 13 , 25 However, in its current application, occupation ratio relies on manual tracing of a single muscle cross-section and is limited to the supraspinatus muscle with its well-defined fossa. Future development of automated muscle segmentation algorithms 17 applied to 3D muscle volumes, 8 using quantitative MRI such as Dixon to measure fat fraction 6 and acquisition of age and gender normative data on muscle volumes 25 and fat fractions, would greatly enhance accurate assessment of shoulder muscle pathology.…”