Optimising Knee Injury Detection with Spatial Attention and Validating Localisation Ability

TL;DR

This paper introduces MPFuseNet, a multi-plane CNN with spatial attention for knee injury detection in MRI, achieving state-of-the-art AUC scores and validating localisation with a new metric and explainability features.

Contribution

The study presents MPFuseNet, a novel multi-plane fusion network with spatial attention, and introduces PLA, a new metric for validating localisation accuracy in MRI knee injury detection.

Findings

Achieved AUC scores of 0.977 for ACL tears and 0.957 for abnormal MRIs.

Developed the novel PLA metric for localisation validation.

Extracted clinically relevant explainability features verified by radiologists.

Abstract

This work employs a pre-trained, multi-view Convolutional Neural Network (CNN) with a spatial attention block to optimise knee injury detection. An open-source Magnetic Resonance Imaging (MRI) data set with image-level labels was leveraged for this analysis. As MRI data is acquired from three planes, we compare our technique using data from a single-plane and multiple planes (multi-plane). For multi-plane, we investigate various methods of fusing the planes in the network. This analysis resulted in the novel 'MPFuseNet' network and state-of-the-art Area Under the Curve (AUC) scores for detecting Anterior Cruciate Ligament (ACL) tears and Abnormal MRIs, achieving AUC scores of 0.977 and 0.957 respectively. We then developed an objective metric, Penalised Localisation Accuracy (PLA), to validate the model's localisation ability. This metric compares binary masks generated from Grad-Cam output and the radiologist's annotations on a sample of MRIs. We also extracted explainability features in a model-agnostic approach that were then verified as clinically relevant by the radiologist.