The promise and limitations of artificial intelligence in musculoskeletal imaging

Abstract

With the recent developments in deep learning and the rapid growth of convolutional neural networks, artificial intelligence has shown promise as a tool that can transform several aspects of the musculoskeletal imaging cycle. Its applications can involve both interpretive and non-interpretive tasks such as the ordering of imaging, scheduling, protocoling, image acquisition, report generation and communication of findings. However, artificial intelligence tools still face a number of challenges that can hinder effective implementation into clinical practice. The purpose of this review is to explore both the successes and limitations of artificial intelligence applications throughout the muscuskeletal imaging cycle and to highlight how these applications can help enhance the service radiologists deliver to their patients, resulting in increased efficiency as well as improved patient and provider satisfaction.

Artificial intelligence in diagnosing upper limb musculoskeletal disorders: a systematic review and meta-analysis of diagnostic tests

“…Therefore, to promote ongoing research effectively; a comprehensive plan should emphasize the development of specific models to address new pathologies or enhance existing ones. This approach will drive sustained innovation at the intersection of AI and the musculoskeletal field ( 40 ).…”

Implementation of artificial intelligence models in magnetic resonance imaging with focus on diagnosis of rheumatoid arthritis and axial spondyloarthritis: narrative review

“…While recent studies on AI applications have shown promising results, specific constraints and challenges still hinder their seamless integration into clinical practice ( 18 ). AI methods require a diverse and extensive set of training data for both testing and validation.…”

“…A significant concern arises when an AI model contains a system error, as this could lead to severe consequences for a broad population if the model manages to proliferate ( 18 ).…”

Evaluating feasibility of lower extremity joint moments predicted by an artificial intelligence model during walking in patients with cerebral palsy

“…Given that the AI model, employed in this study, is thoroughly detailed in reference [10], a concise overview of the model is provided in this section. The implemented machine learning architecture is based on a one-dimensional convolutional neural network, which had ve convolutional layers with an increasing number of lters [128, 128, 512, 1024, 2048] and decreasing one-dimensional kernel sizes [30, 15,10,5,3]. This architecture aimed to extract features for varying time intervals.…”

“…Today, the use of arti cial intelligence (AI) has grown signi cantly and rapidly in various branches of science, and motion analysis science has not been left untouched in this regard 1,2 . AI models have provided the capability to look deeper into the musculoskeletal system and movement disorders, which were not achievable by conventional models [3][4][5] . Shin et al discussed the bene ts of AI in facilitating and increasing the e ciency of musculoskeletal imaging work ow in clinical applications in a review study 6 .…”