Automated Classification of Stroke Lesion Using Bagged Tree Classifier


Ali, Nur Hasanah and Saad, N. M. and Muda, A. S. and Noor, N. S. M. and Abdullah, A. R. and Syafeeza, A. R. (2020) Automated Classification of Stroke Lesion Using Bagged Tree Classifier. IOP Conference Series: Materials Science and Engineering, 884 (1). pp. 1-10. ISSN 1757-8981

[img] Text
28.pdf - Published Version
Restricted to Repository staff only

Download (667kB)


Stroke is a "brain attack" that often causes paralysis, resulted from either bleeding in the brain (hemorrhagic) or the blockage of blood flow to the brain (ischemic). It posed a big challenge to Malaysian healthcare services with at least 32 deaths per day, while survivors were burdened with multiple problems. Conventionally, the diagnosis is performed manually by neuroradiologists during a highly subjective and time consuming tasks. Therefore, this paper intends to diagnose and classify stroke by investigating diffusion- weighted imaging (DWI) of brain stroke images using Bagged Tree classification. Stroke is classified into three main types which are acute stroke, chronic stroke and hemorrhage stroke. The performance of the proposed method is then verified using accuracy and Area Under the Curve (AUC). Based on the results, the overall accuracy for the classification is 96.7%. The AUC of each type of stroke for acute stroke, chronic stroke and hemorrhage stroke is 97%, 100% and 99%, respectively. This outcome could serve as an insight to improve the healthcare of the community by providing better solutions using such intelligent system.

Item Type: Article
Uncontrolled Keywords: Brain diseases
Subjects: R Medicine > RC Internal medicine
Divisions: Faculty of Engineering and Technology (FET)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 14 Oct 2021 04:26
Last Modified: 14 Oct 2021 04:26


Downloads per month over past year

View ItemEdit (login required)