Comprehensive deep learning-assisted multi-condition analysis of knee MRI studies improves resident radiologist performance

TL;DR

A deep-learning model for knee MRI analysis improves accuracy and efficiency of resident radiologists in detecting various knee conditions.

Contribution

A 3D slice transformer network for multi-tissue, multi-condition knee MRI analysis that enhances resident radiologists' diagnostic performance.

Findings

The model achieved an AUC of at least 0.85 for 8 conditions and 0.75 for 18 conditions.

Model assistance improved accuracy and sensitivity for inexperienced residents and increased inter-reader agreement.

Reading times for experienced residents were reduced by 10% with model assistance.

Abstract

Developing a deep-learning model for automated multi-tissue, multi-condition knee MRI analysis and assessing its clinical potential.

This retrospective dual-center study included 3121 MRI studies from 3018 adults, who underwent routine knee MRI examinations at a radiologic practice (2012–2019). Twenty-three conditions across cartilage, menisci, bone marrow, ligaments, and other soft tissues were manually labeled. A 3D slice transformer network was trained for binary classification and evaluated in terms of the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a five-fold cross-validation and an external test set of 448 MRI studies (429 adults) from a university hospital (2022–2023). To assess differences in diagnostic performance, two inexperienced and two experienced radiology residents read 50 external test studies with and without model assistance. Paired t-tests were used for statistical analysis.

Averaged over cross-validation tests, the model’s AUC was at least 0.85 for 8 conditions and at least 0.75 for 18 conditions. Generalization on the external test set was robust, with a mean absolute AUC difference of 0.05 ± 0.03 per condition. Model assistance improved accuracy and sensitivity for inexperienced residents, increased inter-reader agreement for both groups, and increased sensitivity and shortened reading times by 10% (p = 0.045) for experienced residents. Specificity decreased slightly when conditions with low model performance (AUC < 0.75) were included.

Our deep-learning model performed well across diverse knee conditions and effectively assisted radiology residents. Future work should focus on more fine-grained predictions for subtle or rare conditions to enable comprehensive joint assessment in clinical practice.

Question Increasing MRI utilization adds pressure on radiologists, necessitating comprehensive AI models for image analysis to manage this growing demand efficiently.

Findings Our AI model enhanced diagnostic performance and efficiency of resident radiologists when reading knee MRI studies, demonstrating robust results across diverse conditions and two datasets.

Clinical relevance Model assistance increases the sensitivity of radiologists, helping to identify pathologies that were overlooked without AI assistance. Reduced reading times suggest potential alleviation of radiologists’ workload.

Figures