AI applied to MRI reliably detects the presence of meniscus tears

It is known that meniscus tears are difficult to diagnose on knee MRIs. Therefore, this study reviews and compares the accuracy of convolutional neural networks (CNNs). The authors assessed databases including PubMed, MEDLINE, EMBASE, and Cochrane, finding eleven articles to include in the final review, consisting of over 13,000 patients and over 57,000 images. They concluded that CNN is accurate in confirming meniscus tears; however, there is room for improvement when assessing the location of tears.

Key points:

• Artificial intelligence (AI) provides great potential in improving the diagnosis of meniscus tears.
• The pooled diagnostic performance for AI in identifying meniscus tears was better (sensitivity 87%, specificity 89%) than locating the tears (sensitivity 88%, specificity 84%).
• AI is good at confirming the diagnosis of meniscus tears, but future work is required to guide the management of the disease.

Article: Artificial intelligence applied to magnetic resonance imaging reliably detects the presence, but not the location, of meniscus tears: a systematic review and meta-analysis

Authors: Yi Zhao, Andrew Coppola, Urvi Karamchandani, Dimitri Amiras & Chinmay M. Gupte