This thesis describes the design, implementation, and pre-clinical validation of two distinct biomedical technologies that address current challenges in orthopaedic shoulder surgery. The first is an intraoperative optical surface imaging system based on a hand-held structured light sensor for improving glenoid positioning in total shoulder arthroplasty. The second is a system for tracking adherence to shoulder physiotherapy using inertial sensors embedded in a smart watch and machine learning.

Glenoid implant positioning is an important and challenging step in total shoulder arthroplasty. Accurate glenoid positioning is essential for prosthesis longevity and functional outcomes. This thesis presents Bullseye, a novel method to ensure accurate glenoid guide pin placement using intra-operative structured light imaging combined and computer vision. Pre-clinical validation on sawbone and cadaveric scapulae demonstrates this system accurately and efficiently measures the glenoid guide pin position within a verification workflow that integrates well into routine surgical practice. Clinical validation is required to determine if use of the Bullseye technology improves component positioning outcomes and patient clinical outcomes in the context of a clinical trial.

Physical therapy is considered essential for the successful rehabilitation of common shoulder injuries and following shoulder surgery. Patients may receive some training and supervision for shoulder physiotherapy through private pay or private insurance, but they are typically responsible for performing most of their physiotherapy independently at home. It is unknown how often patients perform their home exercises and if these exercises are done correctly without supervision. There are no established tools for measuring this. It is therefore unclear if the full benefit of shoulder physiotherapy treatments are being realized. This thesis presents the Smart Physiotherapy Activity Recognition System (SPARS) for tracking home shoulder physiotherapy exercises using inertial sensors in a consumer smart watches and a machine learning approach. SPARS was successful in classifying shoulder exercises in healthy adults in the laboratory setting. Clinical validation to establish the performance of this technology with patients and investigate the potential individual and societal impacts of its use is ongoing.