Citation

Rajasekaran, M. Pallikonda and Ramaraj, Kottaimalai and Thiyagarajan, Arunprasath and Hossen, Jakir and Wong, Wai Kit Precise segmentation of anterior cruciate ligament tear from clinical MR images using meta-heuristic optimization. In: Transforming Healthcare: Artificial Intelligence, Machine Learning, and 5G Innovations for Enhanced Patient Care. CRC Press, pp. 99-119. ISBN 978-104043889-3, 978-103288010-5

Text Precise segmentation of anterior cruciate ligament tear from clinical.pdf - Published Version Restricted to Repository staff only Download (108kB)

Abstract

One of the key components that stabilize the knee is the anterior cruciate ligament (ACL), and damage to this ligament increases the likelihood of osteoarthritis. ACL tears frequently occur in young athletes. It frequently happens as a result of excessive stretching and abrupt motion, and the patient experiences excruciating agony. ACL tears can be better analyzed and classified with precise segmentation at the very beginning. These kinds of injury evaluations have become commonly performed using magnetic resonance imaging, or MRI, because of recent advancements in healthcare imaging technology. Nevertheless, the visual evaluation carried out with these images frequently necessitates manually tracing the borders of particular structures using computer programs. Since it is dependent on the radiologist’s perception and previous expertise, this kind of analysis is frequently subjective and time-consuming. Several computer vision-based methods are used to detect ACL tears, but most of these systems’ performance is difficult due to the intricate structure of knee ligaments. An automatic ACL segmentation software that makes use of both active contour and morphological procedures is offered in this work by integrating Gray-Level Co-occurrence Matrix (GLCM) and AlexNet architecture. The research helps to segment the tear portion by incorporating the meta-heuristic optimization technique. Using deep learning, the present research effectively separated ACL tears from MRI scans. Accuracy, sensitivity, and specificity were assessed to validate the suggested segmentation technique’s efficacy. The outcomes exhibit that by employing a hybrid optimization method, ACL segmentation on MRI achieves a higher level of accuracy than manual segmentation. The technique shows promise for use in medical image analytics to segment knee ACL damage from MR images.

Item Type:	Book Section
Uncontrolled Keywords:	Image segmentation
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	22 Dec 2025 07:59
Last Modified:	26 Dec 2025 08:23
URII:	http://shdl.mmu.edu.my/id/eprint/15127

Downloads

Edit (login required)