Classification of Stroke using Texture Analysis on CT images
Pramod Bhat1, Mandeep Singh2
1Pramod Bhat,Research Scholer, Electrical & Instrumentation Engg. Dept, Thapar University,Patiala, India.
2Mandeep Singh, Assistant Professor, Electrical & Instrumentation Engg. Dept.Thaper University,Patiala,India
Manuscript received on April 04, 2013. | Revised Manuscript received on April 28, 2013. | Manuscript published on May 05, 2013. | PP: 527-530 | Volume-3, Issue-2, May 2013. | Retrieval Number: C0838062312 /2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Correct diagnosis of the stroke type is very important for proper medication as any delay or wrong diagnosis may become fatal to the patient. Many methods have been developed to diagnose stroke using MRI images. In this work we have used unenhanced CT images for diagnosis stroke using texture features and classifiers. Five different classifiers have been used and they are combined to get better diagnosis accuracy. The accuracy of classifier ensemble output was 85.39% and the area under ROC (AUC) was found to be about 93 % for every classes. The method proves very effective for diagnosis of stroke with good accuracy and able to differentiate acute, chronic and hemorrhage successfully.
Keywords: Texture features, Classifier ensemble, CT scan