1. Artificial intelligence to diagnose meniscus tears on MRI
- Author
-
Laure Fournier, C. Morillot, M. Bou Antoun, J. Zerbib, X. Chassin, Y. Giret, V. Roblot, A. Cotten, Université de Paris - UFR Médecine Paris Centre [Santé] (UP Médecine Paris Centre), Université de Paris (UP), Hôpital Européen Georges Pompidou [APHP] (HEGP), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Hôpitaux Universitaires Paris Ouest - Hôpitaux Universitaires Île de France Ouest (HUPO), Paris-Centre de Recherche Cardiovasculaire (PARCC (UMR_S 970/ U970)), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Hôpitaux Universitaires Paris Ouest - Hôpitaux Universitaires Île de France Ouest (HUPO)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Hôpitaux Universitaires Paris Ouest - Hôpitaux Universitaires Île de France Ouest (HUPO)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Paris (UP), and ANR-19-P3IA-0001,PRAIRIE,PaRis Artificial Intelligence Research InstitutE(2019)
- Subjects
Region convolutional neuronal networks (RCNN) ,Meniscal tears ,Datasets as Topic ,Meniscus (anatomy) ,Diagnostic tools ,Convolutional neural network ,Artificial intelligence (AI) ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,medicine ,[INFO.INFO-IM]Computer Science [cs]/Medical Imaging ,Humans ,Radiology, Nuclear Medicine and imaging ,Magnetic resonance imaging (MRI) ,Radiological and Ultrasound Technology ,medicine.diagnostic_test ,Orientation (computer vision) ,business.industry ,External validation ,Convolutional neuronal network (CNN) ,Pattern recognition ,Magnetic resonance imaging ,General Medicine ,Magnetic Resonance Imaging ,Tibial Meniscus Injuries ,medicine.anatomical_structure ,030220 oncology & carcinogenesis ,Meniscus tears ,Artificial intelligence ,Neural Networks, Computer ,Meniscus tear ,business ,Algorithms - Abstract
Purpose The purpose of this study was to build and evaluate a high-performance algorithm to detect and characterize the presence of a meniscus tear on magnetic resonance imaging examination (MRI) of the knee. Material and methods An algorithm was trained on a dataset of 1123 MR images of the knee. We separated the main task into three sub-tasks: first to detect the position of both horns, second to detect the presence of a tear, and last to determine the orientation of the tear. An algorithm based on fast-region convolutional neural network (CNN) and faster-region CNN, was developed to classify the tasks. The algorithm was thus used on a test dataset composed of 700 images for external validation. The performance metric was based on area under the curve (AUC) analysis for each task and a final weighted AUC encompassing the three tasks was calculated. Results The use of our algorithm yielded an AUC of 0.92 for the detection of the position of the two meniscal horns, of 0.94 for the presence of a meniscal tear and of 083 for determining the orientation of the tear, resulting in a final weighted AUC of 0.90. Conclusion We demonstrate that our algorithm based on fast-region CNN is able to detect meniscal tears and is a first step towards developing more end-to-end artificial intelligence-powered diagnostic tools.
- Published
- 2019