/MRNet-Classification

The MRNet dataset consists of 1,370 knee MRI exams performed at Stanford University Medical Center. The dataset contains 1,104 (80.6%) abnormal exams, with 319 (23.3%) ACL tears and 508 (37.1%) meniscal tears; labels were obtained through manual extraction from clinical reports. this is an implementation of a CNN model to train the before mentioned data and see how accurately it predicted that the photo of the particular knee ( given 3 different views of it ) had any of the 3 labeled problems (Abnormality - ACL Tear - Meniscus Tear).

Primary LanguageJupyter Notebook

This repository is not active