Beschreibung
Anterior Cruciate Ligament (ACL) knee injury is a common injury among active athlete; wrong interpretation could jeopardize athlete future. This research aims to develop an automated diagnostic system on ACL knee injury. Specifically, this work explores an ensemble algorithm of screening and classifying system to diagnose ACL knee injuries using MRI image. The development of the system involves several technical processes; digital image processing, feature reduction, injury screening and injury classification. Screening is done through support vector machine (SVM) and classifying process used artificial neural network (ANN). The outcome is categorized into three types of injuries; normal, partial and crucial. Results of this automated system improved the current analysis system performance by an average accuracy of 86.2% and it is proven by receiver operating characteristic (ROC) curve that shows sensitivity at 81.7%. This system has been verified by medical specialists (orthopedic and radiologist) to ensure the result achieved medical operating standard.
Autorenporträt
Doctor of Philosophy Electrical and Electronics, Master of Science Electronics System Design, Bachelor of Hons. Mechatronic Engineering, Diploma Mechatronic Engineering
Herstellerkennzeichnung:
OmniScriptum SRL
Str. Armeneasca 28/1, office 1
2012 Chisinau
MD
E-Mail: info@omniscriptum.com
