Key result
Deep learning models achieved prediction accuracies ranging from 72.5% to 100% for the identification of knee injuries on MRI, demonstrating potential to perform on par with human experts.
Why the study?
Improved treatment of knee injuries relies on accurate and cost-effective detection, and deep-learning approaches have increasingly dominated knee injury detection in MRI studies.
Do deep learning-based approaches accurately detect knee injuries in MRI studies?
Systematic Review (n=22)
Do deep learning-based approaches accurately detect knee injuries in MRI studies?
Deep learning models demonstrate high prediction accuracy (72.5-100%) for detecting knee injuries on MRI, potentially matching human-level performance.
May aid knee MRI interpretation; extends diagnostic evidence but variable performance warrants prospective validation.
The improved treatment of knee injuries critically relies on having an accurate and cost-effective detection. In recent years, deep-learning-based approaches have monopolized knee injury detection in MRI studies. The aim of this paper is to present the findings of a systematic literature review of knee (anterior cruciate ligament, meniscus, and cartilage) injury detection papers using deep learning. The systematic review was carried out following the PRISMA guidelines on several databases, including PubMed, Cochrane Library, EMBASE, and Google Scholar. Appropriate metrics were chosen to interpret the results. The prediction accuracy of the deep-learning models for the identification of knee injuries ranged from 72.5-100%. Deep learning has the potential to act at par with human-level performance in decision-making tasks related to the MRI-based diagnosis of knee injuries. The limitations of the present deep-learning approaches include data imbalance, model generalizability across different centers, verification bias, lack of related classification studies with more than two classes, and ground-truth subjectivity. There are several possible avenues of further exploration of deep learning for improving MRI-based knee injury diagnosis. Explainability and lightweightness of the deployed deep-learning systems are expected to become crucial enablers for their widespread use in clinical practice.
No takes yet. Share an insight, caveat, or question.
Siouras et al. (2022) conducted a systematic review in Knee injuries (anterior cruciate ligament, meniscus, and cartilage) (n=22). Deep learning algorithms vs. Human clinical evaluation (radiologists/experts) was evaluated on Prediction accuracy for the identification of knee injuries. Deep learning models achieved prediction accuracies ranging from 72.5% to 100% for the identification of knee injuries on MRI, demonstrating potential to perform on par with human experts.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: