- Keywords: Knee Disorder Diagnosis, MRI, Pyramidal Detail Pooling, Feature Pyramid Network, ACL tear detection, Meniscus tear detection
- TL;DR: We propose MRPyrNet, a CNN strategy to improve the capabilities of state-of-the-art solutions in the ACL and meniscal tear detection.
- Abstract: Convolutional neural networks (CNNs) applied on magnetic resonance imaging (MRI) have demonstrated their ability in the diagnosis of knee injuries. Despite the promising results, the currently available solutions do not take into account the particular anatomy of knee disorders. Existing works have shown that anomalies are localized in small-sized knee regions that appear near the center of MRI scans. Based on such facts, we propose MRPyrNet, a CNN architecture capable of extracting more relevant features from these regions. Our solution is composed of a Feature Pyramid Network with Pyramidal Detail Pooling, and can be plugged into any existing CNN-based diagnostic pipeline. Experimental results on two publicly available datasets demonstrate that MRPyrNet improves the ACL tear and meniscal tear diagnosis capabilities of baseline methodologies. Code is available at https://git.io/JtMPH.
- Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
- Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
- Paper Type: methodological development
- Primary Subject Area: Detection and Diagnosis
- Secondary Subject Area: Unsupervised Learning and Representation Learning