A Torn ACL Mapping in Knee MRI Images Using Deep Convolution Neural Network with Inception-v3. (8th February 2022)

• Record Type: Journal Article
• Authors: Sridhar, S.; Amutharaj, J.; Valsalan, Prajoona; Arthi, B.; Ramkumar, S.; Mathupriya, S.; Rajendran, T.; Waji, Yosef Asrat
• Other Names: Abdulhay Enas Academic Editor.
• Is Part Of: Journal of healthcare engineering. Volume 2022(2022)
• Publication Date: 2022-02-08
• Subjects: Hospital buildings -- Environmental engineering -- Periodicals; Medical technology -- Periodicals; Medical informatics -- Periodicals; 610.28
• DOI: 10.1155/2022/7872500
• Languages: English
• ISSNs: 2040-2295

Abstract

Abstract : The anterior cruciate ligaments (ACL) are the fundamental structures in preserving the common biomechanics of the knees and most frequently damaged knee ligaments. An ACL injury is a tear or sprain of the ACL, one of the fundamental ligaments in the knee. ACL damage most generally happens during sports, for example, soccer, ball, football, and downhill skiing, which include sudden stops or changes in direction, jumping, and landings. Magnetic resonance imaging (MRI) has a major role in the field of diagnosis these days. Specifically, it is effective for diagnosing the cruciate ligaments and any related meniscal tears. The primary objective of this research is to detect the ACL tear from MRI knee images, which can be useful to determine the knee abnormality. In this research, a Deep Convolution Neural Network (DCNN) based Inception-v3 deep transfer learning (DTL) model was proposed for classifying the ACL tear MRI images. Preprocessing, feature extraction, and classification are the main processes performed in this research. The dataset utilized in this work was collected from the MRNet database. A total of 1, 370 knee MRI images are used for evaluation. 70% of data (959 images) are used for training and testing, and 30% of data (411 images) are used in this model for performance analysis. The proposed DCNN with the Inception-v3 DTL model is evaluated and compared with existing deep learning models like VGG16, VGG19, Xception, and Inception ResNet-v28. The performance metrics like accuracy, precision, recall, specificity, and F-measure are evaluated to estimate the performance analysis of the model. The model has obtained 99.04% training accuracy and 95.42% testing accuracy in performance analysis.