A workflow for automated generation of patient-specific finite element models in total shoulder arthroplasty
Year: 2026
Type: article
Abstract: This article presents a workflow for fully automated, patient-specific finite element analysis of total shoulder arthroplasty using preoperative data. A deep learning segmentation model was implemented to obtain the scapular bone surface and assess rotator cuff muscle degeneration from CT scans. The preoperative planning file was used to position the shoulder prosthesis and ream the bone accordingly. Loading conditions were determined using a deep learning musculoskeletal model. The finite element input file was generated, and the analysis was performed and postprocessed. The algorithm was developped in Python and is freely available. The workflow is illustrated using data from five patients with an anatomic prosthesis and five with a reverse prosthesis. This fully automated framework allows analyses to be replicated across large patient cohorts, and alternative surgical interventions to be evaluated, enabling further statistical analyses.
Language: English
Subfield: Surgery
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,801
OpenAlex ID: W4404956499
