diagnostics Article Efficient Detection of Knee Anterior Cruciate Ligament from Magnetic Resonance Imaging Using Deep Learning Approach Mazhar Javed Awan 1,2, * , Mohd Shafry Mohd Rahim 1 , Naomie Salim 1 , Mazin Abed Mohammed 3 , Begonya Garcia-Zapirain 4, * and Karrar Hameed Abdulkareem 5   Citation: Javed Awan, M.; Mohd Rahim, M.S.; Salim, N.; Mohammed, M.A.; Garcia-Zapirain, B.; Abdulkareem, K.H. Efficient Detection of Knee Anterior Cruciate Ligament from Magnetic Resonance Imaging Using Deep Learning Approach. Diagnostics 2021, 11, 105. https://doi.org/10.3390/diagnostics 11010105 Received: 16 December 2020 Accepted: 8 January 2021 Published: 11 January 2021 Publisher’s Note: MDPI stays neu- tral with regard to jurisdictional clai- ms in published maps and institutio- nal affiliations. Copyright: © 2021 by the authors. Li- censee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and con- ditions of the Creative Commons At- tribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). 1 School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM), Johor 81310, Malaysia; shafry@utm.my (M.S.M.R.); naomie@utm.my (N.S.) 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; mazinalshujeary@uoanbar.edu.iq 4 eVIDA Lab, University of Deusto, 48007 Bilbao, Spain 5 College of Agriculture, Al-Muthanna University, Samawah 66001, Iraq; khak9784@mu.edu.iq * Correspondence: awan1982@graduate.utm.my (M.J.A.); mbgarciazapi@deusto.es (B.G.-Z.) 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: anterior cruciate ligament; healthcare; knee injury; artificial intelligence; convolutional neural network; MRI; detection; classification; residual network; augmentation 1. Introduction The anterior cruciate ligament (ACL) is an important stabilizing ligament of the knee that connects the femur to the tibia [1]. In the knee, there are four primary ligaments: two ligaments inside the knee are anterior cruciate ligament, posterior cruciate ligament while two outside ligaments are lateral collateral ligament, medial collateral ligament. Figure 1 shows the anatomy of knee ligament tears [2]. The ACL is the most common injured knee ligament in athletes. It provides the stability as the knee moves. This movement can produce increased friction on the meniscus and cartilage in the joint. The symptoms of ACL include pain, swelling and deformation of the knee, making walking difficult [3,4]. A radiologist’s work is to detect various injuries, such as torn ACLs from radiological scans. It is a time-consuming process to interpret knee ACL injuries, tears in meniscus, knee cartilages abnormalities which causes knee osteoarthritis, osteoporosis and knee joint replacement from radiology images manually [5]. There are many methods to diagnose an ACL tear in the knee: physical tests, and biomarkers [6], X-ray, computed tomography (CT), mammography, ultrasound imaging and magnetic resonance imaging (MRI) [7]. MRI is the best choice for diagnosing ACL tears as ACL is not visible as a plain file X-ray [8–10]. Diagnostics 2021, 11, 105. https://doi.org/10.3390/diagnostics11010105 https://www.mdpi.com/journal/diagnostics