Background: Fatty infiltration of the rotator cuff muscles is highly related to poor outcomes after rotator cuff tears. Fat fraction (FF) based on traditional 2–dimensional measurements (2D-FF) from a single sagittal Y-view slice cannot determine intramuscular FF in the rotator cuff muscles; the newly developed 3–dimensional method (3D-FF) is supposed to precede 2D measurements for intramuscular FF evaluation in accuracy and reliability. Purpose: (1) To measure 3D-FF and (2) to compare 3D-FF and 2D-FF in terms of quantitative values and intra- and interobserver agreement. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: Six-point Dixon magnetic resonance imaging was performed in patients with full–thickness supraspinatus tears. 2D-FF was calculated on a single sagittal Y-view. Semiautomatic segmentation software (ITK-SNAP) was used to reconstruct 3D volumes of the supraspinatus muscle and fat. 3D-FF was obtained by dividing the fat volume by the total volume of the supraspinatus muscle. A paired t test was used to compare the individual differences between 2D-FF and 3D-FF results. Linear regression and Bland-Altman analyses were performed to determine the agreement between 2D-FF and 3D-FF. Intraclass correlation coefficients (ICCs) were calculated to determine intra- and interobserver agreement. Results: The 3D muscular and fatty models presented an inhomogeneous distribution of intramuscular fat in the supraspinatus, indicating the superiority of 3D-FF over 2D-FF in capturing all muscle morphologic information. 2D-FF was significantly higher than 3D-FF in the supraspinatus with large (19.5% ± 5.9% vs 16.2% ± 3.7%; P = .002) and massive (34.8% ± 13.3% vs 26.2% ± 9.4%; P < .001) rotator cuff tears. 2D-FF overestimated the FF compared with 3D-FF by >50% in 14.7% of all patients and by >15% in 67.6% of patients with large or massive RCTs. The discrepancy between 2D-FF and 3D-FF increased with increasing mean FF. The intra- and interobserver agreement of 3D-FF (ICCs, 0.89-0.99 and 0.89-0.95) was superior to that of 2D-FF (ICCs, 0.71-0.95 and 0.64-0.79). Conclusion: 3D-FF indicated an inhomogeneous distribution of intramuscular fat by capturing all muscle and fat morphologic information. In patients with large and massive rotator cuff tears, 2D-FF of the supraspinatus was significantly higher than 3D-FF. 3D-FF was more reliable than 2D-FF for estimating fatty infiltration in the supraspinatus, with better intra- and interobserver agreement.

No abstract

Background: Sports levels, baseline patient-reported outcome measures (PROMs), and surgical procedures are correlated with the outcomes of anterior cruciate ligament reconstruction (ACLR). Machine learning may be superior to conventional statistical methods in making repeatable and accurate predictions. Purpose: To identify the best-performing machine learning models for predicting the objective and subjective clinical outcomes of ACLR and to determine the most important predictors. Study Design: Case-control study; Level of evidence, 3. Methods: A total of 432 patients who underwent anatomic double-bundle ACLR with hamstring tendon autograft between January 2010 and February 2019 were included in the machine learning analysis. A total of 15 predictive variables and 6 outcome variables were selected to validate the logistic regression, Gaussian naïve Bayes machine, random forest, Extreme Gradient Boosting (XGBoost), isotonically calibrated XGBoost, and sigmoid calibrated XGBoost models. For each clinical outcome, the best-performing model was determined using the area under the receiver operating characteristic curve (AUC), whereas the importance and direction of each predictive variable were demonstrated in a Shapley Additive Explanations summary plot. Results: The AUC and accuracy of the best-performing model, respectively, were 0.944 (excellent) and 98.6% for graft failure; 0.920 (excellent) and 91.4% for residual laxity; 0.930 (excellent) and 91.0% for failure to achieve the minimal clinically important difference (MCID) of the Lysholm score; 0.942 (excellent) and 95.1% for failure to achieve the MCID of the International Knee Documentation Committee (IKDC) score; 0.773 (fair) and 70.5% for return to preinjury sports; and 0.777 (fair) and 69.2% for return to pivoting sports. Medial meniscal resection, participation in competitive sports, and steep posterior tibial slope were top predictors of graft failure, whereas high-grade preoperative knee laxity, long follow-up period, and participation in competitive sports were top predictors of residual laxity. High preoperative Lysholm and IKDC scores were highly predictive of not achieving the MCIDs of PROMs. Young age, male sex, high preoperative IKDC score, and large graft diameter were important predictors of return to preinjury or pivoting sports. Conclusion: Machine learning analysis can provide reliable predictions for the objective and subjective clinical outcomes (graft failure, residual laxity, PROMs, and return to sports) of ACLR. Patient-specific evaluation and decision making are recommended before and after surgery.