Efficient Detection of Knee Anterior Cruciate Ligament from Magnetic Resonance Imaging Using Deep Learning Approach

Mazhar Javed Awan; Mohd Shafry Mohd Rahim; Naomie Salim; Mazin Abed Mohammed; Begonya Garcia-Zapirain; Karrar Hameed Abdulkareem

doi:10.3390/diagnostics11010105

Efficient Detection of Knee Anterior Cruciate Ligament from Magnetic Resonance Imaging Using Deep Learning Approach

Diagnostics (Basel). 2021 Jan 11;11(1):105. doi: 10.3390/diagnostics11010105.

Authors

Mazhar Javed Awan^{1

2}, Mohd Shafry Mohd Rahim¹, Naomie Salim¹, Mazin Abed Mohammed³, Begonya Garcia-Zapirain⁴, Karrar Hameed Abdulkareem⁵

Affiliations

¹ School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM), Johor 81310, Malaysia.
² Department of Software Engineering, University of Management and Technology, Lahore 54770, Pakistan.
³ College of Computer Science and Information Technology, University of Anbar, 11, Ramadi, Anbar 31001, Iraq.
⁴ eVIDA Lab, University of Deusto, 48007 Bilbao, Spain.
⁵ College of Agriculture, Al-Muthanna University, Samawah 66001, Iraq.

Abstract

The most commonly injured ligament in the human body is an anterior cruciate ligament (ACL). ACL injury is standard among the football, basketball and soccer players. The study aims to detect anterior cruciate ligament injury in an early stage via efficient and thorough automatic magnetic resonance imaging without involving radiologists, through a deep learning method. The proposed approach in this paper used a customized 14 layers ResNet-14 architecture of convolutional neural network (CNN) with six different directions by using class balancing and data augmentation. The performance was evaluated using accuracy, sensitivity, specificity, precision and F1 score of our customized ResNet-14 deep learning architecture with hybrid class balancing and real-time data augmentation after 5-fold cross-validation, with results of 0.920%, 0.916%, 0.946%, 0.916% and 0.923%, respectively. For our proposed ResNet-14 CNN the average area under curves (AUCs) for healthy tear, partial tear and fully ruptured tear had results of 0.980%, 0.970%, and 0.999%, respectively. The proposing diagnostic results indicated that our model could be used to detect automatically and evaluate ACL injuries in athletes using the proposed deep-learning approach.

Keywords: MRI; anterior cruciate ligament; artificial intelligence; augmentation; classification; convolutional neural network; detection; healthcare; knee injury; residual network.