Ischemic stroke lesion detection, characterization and classification in CT images with optimal features selection
- PDF / 1,622,245 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 35 Downloads / 207 Views
ORIGINAL ARTICLE
Ischemic stroke lesion detection, characterization and classification in CT images with optimal features selection R. Kanchana1 · R. Menaka1 Received: 3 December 2019 / Revised: 5 May 2020 / Accepted: 13 May 2020 © Korean Society of Medical and Biological Engineering 2020
Abstract Ischemic stroke is the dominant disorder for mortality and morbidity. For immediate diagnosis and treatment plan of ischemic stroke, computed tomography (CT) images are used. This paper proposes a histogram bin based novel algorithm to segment the ischemic stroke lesion using CT and optimal feature group selection to classify normal and abnormal regions. Steps followed are pre-processing, segmentation, extracting texture features, feature ranking, feature grouping, classification and optimal feature group (FG) selection. The first order features, gray level run length matrix features, gray level co-occurrence matrix features and Hu’s moment features are extracted. Classification is done using logistic regression (LR), support vector machine classifier (SVMC), random forest classifier (RFC) and neural network classifier (NNC). This proposed approach effectively detects ischemic stroke lesion with a classification accuracy of 88.77%, 97.86%, 99.79% and 99.79% obtained by the LR, SVMC, RFC and NNC when FG12 is opted, which is validated by fourfold cross validation. Keywords Ischemic stroke · CT images · Histogram · CAD · Features · Classification
1 Introduction When the brain cells are not provided with enough oxygen or sufficient nutrients, it may lead to malfunctioning. Whenever the blood supply to the blood vessels in the brain is blocked or ruptured, stroke occurs [1]. As per American heart association and world health organization (WHO), stroke is one of the important causes of disability and ranks three in causing death [2–7]. The worldwide, fatality rate due to stroke is almost 9% of overall death [8]. Notable risk factors for stroke are hypertension, diabetes, hyper cholesterolotemia, smoking, atrial fibrillation and dyslipidemia [9]. Optimal antithrombotic therapy can be recommended for stroke prevention. Three main types of strokes are ischemic stroke, hemorrhagic stroke and transient ischemic stroke (TIA). Ischemic stroke is the very widely happening and the most deadly disorder resulting in 85% of the cases when compared with other types of stroke [10]. It is the blocking of blood vessels by thrombus in the artery, which supplies blood to the brain * R. Menaka [email protected] 1
School of Electronics Engineering, Vellore Institute of Technology, Chennai, India
[11]. Survival of ischemic stroke disorder patients is highly economical. Enhanced efforts and researches are under field to improve the life quality of such patients to reduce family burden considerably [12]. When comparing the gray matter density of ischemic stroke patients with healthy participants, a significant difference is noted. Hence, left inferior occipital gyrus, right anterior cingulum, left precentralgyrus, right cerebellum, right m
Data Loading...
