Deep learning-assisted detection of meniscus and anterior cruciate ligament combined tears in adult knee magnetic resonance imaging: a crossover study with arthroscopy correlation.
Authors
Affiliations (8)
Affiliations (8)
- Nantes Université, CHU Nantes, Clinique Chirurgicale Orthopédique et Traumatologique, Nantes, France.
- Université Versailles Saint-Quentin-en-Yvelines, Centre hospitalier de Versailles - Hôpital Mignot, Service de Chirurgie Orthopédique et Traumatologique, Versailles, France.
- Nantes Université, CHU Nantes, Clinique Chirurgicale Orthopédique et Traumatologique, Nantes, France. [email protected].
- Nantes Université, INSERM, UMRS 1229, Regenerative Medicine and Skeleton (RMeS), ONIRIS, Nantes, France. [email protected].
- Incepto Medical, Paris, France.
- Groupe Hospitalier du Havre, Service de Radiologie, Le Havre, France.
- Université Versailles Saint-Quentin-en-Yvelines, Centre hospitalier de Versailles - Hôpital Mignot, Service de Radiologie, Versailles, France.
- LAbCom I3M DACTIM-MIS, CNRS 7348, Poitiers, France.
Abstract
We aimed to compare the diagnostic performance of physicians in the detection of arthroscopically confirmed meniscus and anterior cruciate ligament (ACL) tears on knee magnetic resonance imaging (MRI), with and without assistance from a deep learning (DL) model. We obtained preoperative MR images from 88 knees of patients who underwent arthroscopic meniscal repair, with or without ACL reconstruction. Ninety-eight MR images of knees without signs of meniscus or ACL tears were obtained from a publicly available database after matching on age and ACL status (normal or torn), resulting in a global dataset of 186 MRI examinations. The Keros<sup>®</sup> (Incepto, Paris) DL algorithm, previously trained for the detection and characterization of meniscus and ACL tears, was used for MRI assessment. Magnetic resonance images were individually, and blindly annotated by three physicians and the DL algorithm. After three weeks, the three human raters repeated image assessment with model assistance, performed in a different order. The Keros<sup>®</sup> algorithm achieved an area under the curve (AUC) of 0.96 (95% CI 0.93, 0.99), 0.91 (95% CI 0.85, 0.96), and 0.99 (95% CI 0.98, 0.997) in the detection of medial meniscus, lateral meniscus and ACL tears, respectively. With model assistance, physicians achieved higher sensitivity (91% vs. 83%, p = 0.04) and similar specificity (91% vs. 87%, p = 0.09) in the detection of medial meniscus tears. Regarding lateral meniscus tears, sensitivity and specificity were similar with/without model assistance. Regarding ACL tears, physicians achieved higher specificity when assisted by the algorithm (70% vs. 51%, p = 0.01) but similar sensitivity with/without model assistance (93% vs. 96%, p = 0.13). The current model consistently helped physicians in the detection of medial meniscus and ACL tears, notably when they were combined. Diagnostic study, Level III.