Artificial Intelligence-Based Solution in Personalized Computer-Aided Arthroscopy of Shoulder Prostheses

• Published in: Journal of personalized medicine 2022-01, Vol.12 (1), p.109
• Main Authors: Sultan, Haseeb, Owais, Muhammad, Choi, Jiho, Mahmood, Tahir, Haider, Adnan, Ullah, Nadeem, Park, Kang Ryoung
• Format: Article
• Language: English
• Subjects: Accuracy; Arthroscopy; Artificial intelligence; Automation; Classification; Datasets; Decision making; Deep learning; Design; Joint replacement surgery; Joint surgery; Morbidity; Neural networks; Orthopedics; Pain; Patients; Precision medicine; Prostheses; Prosthetics; Shoulder; Surgeons; Surgery; Surgical outcomes; Transplants & implants
• ISSN: 2075-4426; 2075-4426
• DOI: 10.3390/jpm12010109

Early recognition of prostheses before reoperation can reduce perioperative morbidity and mortality. Because of the intricacy of the shoulder biomechanics, accurate classification of implant models before surgery is fundamental for planning the correct medical procedure and setting apparatus for personalized medicine. Expert surgeons usually use X-ray images of prostheses to set the patient-specific apparatus. However, this subjective method is time-consuming and prone to errors. As an alternative, artificial intelligence has played a vital role in orthopedic surgery and clinical decision-making for accurate prosthesis placement. In this study, three different deep learning-based frameworks are proposed to identify different types of shoulder implants in X-ray scans. We mainly propose an efficient ensemble network called the Inception Mobile Fully-Connected Convolutional Network (IMFC-Net), which is comprised of our two designed convolutional neural networks and a classifier. To evaluate the performance of the IMFC-Net and state-of-the-art models, experiments were performed with a public data set of 597 de-identified patients (597 shoulder implants). Moreover, to demonstrate the generalizability of IMFC-Net, experiments were performed with two augmentation techniques and without augmentation, in which our model ranked first, with a considerable difference from the comparison models. A gradient-weighted class activation map technique was also used to find distinct implant characteristics needed for IMFC-Net classification decisions. The results confirmed that the proposed IMFC-Net model yielded an average accuracy of 89.09%, a precision rate of 89.54%, a recall rate of 86.57%, and an F1.score of 87.94%, which were higher than those of the comparison models. The proposed model is efficient and can minimize the revision complexities of implants.