Deep Learning for Automated 3D Assessment of Rotator Cuff Muscle Atrophy and Fat Infiltration prior to Total Shoulder Arthroplasty.
Authors
Affiliations (9)
Affiliations (9)
- Department of Orthopaedic Surgery, Duke University, Durham, NC, USA; Rothman Orthopaedic Institute, Philadelphia, PA, USA. Electronic address: [email protected].
- ARTORG Center for Biomedical Engineering, University of Bern, Bern, Switzerland.
- Department of Orthopaedic Surgery, Duke University, Durham, NC, USA.
- Rothman Orthopaedic Institute, Philadelphia, PA, USA.
- Department of Diagnostic and Interventional Radiology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
- Laboratory of Biomechanical Orthopedics, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland; Department of Orthopedics and Traumatology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
- Laboratory of Biomechanical Orthopedics, Ecole Polytechnique Fédérale de Lausanne, Lausanne, Switzerland.
- Department of Orthopedics and Traumatology, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
- Tampa General Hospital, Department of Orthopaedic Surgery, Tampa, FL, USA; Florida Orthopaedic Institute, Shoulder & Elbow Department, Tampa, FL, USA.
Abstract
Rotator cuff muscle pathology affects outcomes following total shoulder arthroplasty, yet current assessment methods lack reliability in quantifying muscle atrophy and fat infiltration. We developed a deep learning-based model for automated segmentation of rotator cuff muscles on computed tomography (CT) and propose a T-score classification of volumetric muscle atrophy. We further characterized distinct atrophy phenotypes, 3D fat infiltration percentage (3DFI%), and anterior-posterior (AP) balance, which were compared between healthy controls, anatomic total shoulder arthroplasty (aTSA), and reverse total shoulder arthroplasty (rTSA) patients. 952 shoulder CT scans were included (762 controls, 103 undergoing aTSA for glenohumeral osteoarthritis, and 87 undergoing rTSA for cuff tear arthropathy. A deep learning model was developed to allow automated segmentation of supraspinatus (SS), subscapularis (SC), infraspinatus (IS) and teres minor (TM). Muscle volumes were normalized to scapula volume, and control muscle volumes were referenced to calculate T-scores for each muscle. T-scores were classified as no atrophy (>-1.0), moderate atrophy (-1 to -2.5), and severe atrophy (<-2.5). 3DFI% was quantified as the proportion of fat within each muscle using Hounsfield unit thresholds. The T-scores, 3DFI%, and AP balance were compared between the three cohorts. The aTSA cohort had significantly greater atrophy in all muscles compared to control (p<0.001), whereas the rTSA cohort had significantly greater atrophy in SS, SC, and IS than aTSA (p<0.001). In the aTSA cohort, the most common phenotype was SS<sub>severe</sub>/SC<sub>moderate</sub>/IS+TM<sub>moderate</sub>, while in the rTSA cohort it was SS<sub>severe</sub>/SC<sub>moderate</sub>/IS+TM<sub>severe</sub>. The aTSA group had significantly higher 3DFI% compared to controls for all muscles (p<0.001), while the rTSA cohort had significantly higher 3DFI% than aTSA and control cohorts for all muscles (p<0.001). Additionally, the aTSA cohort had a significantly lower AP muscle volume ratio (1.06 vs. 1.14, p<0.001), whereas the rTSA group had a significantly higher AP muscle volume ratio than the control cohort (1.31 vs. 1.14, p<0.001). Our study demonstrates successful development of a deep learning model for automated volumetric assessment of rotator cuff muscle atrophy, 3DFI% and AP balance on shoulder CT scans. We found that aTSA patients had significantly greater muscle atrophy and 3DFI% than controls, while the rTSA patients had the most severe muscle atrophy and 3DFI%. Additionally, distinct phenotypes of muscle atrophy and AP muscle balance exist in aTSA and rTSA that warrant further investigation with regards to shoulder arthroplasty outcomes.