Computed tomography images are widely used in the diagnosis of ischemic stroke because of its faster acquisition and compatibility with most life support devices. This chapter presents a new approach to automated detection of ischemic stroke using k-means clustering technique which separates the lesion region from healthy tissues and classification of ischemic stroke using texture features. The proposed method has five stages, pre-processing, tracing midline of the brain, extraction of texture features and feature selection, classification and segmentation. In the first stage noise is suppressed using a median filtering and skull bone components of the images are removed. In the second stage, midline shift of the brain is calculated. In the third stage, fourteen texture features are extracted and optimal features are selected using genetic algorithm. In the fourth stage, support vector machine, artificial neural network and decision tree classifiers have been used. Finally, the ischemic stroke region is extracted by using k-means clustering technique.
TopBackground
Stroke or cerebrovascular accident is a disease, which affects the vessels that supply blood to the brain. The stroke occurs when a blood vessel either bursts or there is a blockage of the blood vessel. Due to loss of oxygen, nerve cells in the affected brain area are not able to perform basic functions which lead to death of the brain tissue. Stroke leads to serious long term disability or death. This can be due to ischemia (lack of blood flow) caused by blockage (thrombosis, arterial embolism), or a hemorrhage (leakage of blood). In an ischemic stroke, blood supply to part of the brain is decreased leading to death of the brain tissue in that region (Adam et al., 2005).
According to the World Health Organization (WHO), 15 million people are affected by stroke; of these 5 million die and another 5 million (2002 estimates) are permanently disabled. As the average human life span has increased, stroke has become the third leading cause of death worldwide after heart disease and cancer. Between these, ischemic stroke accounts for about 80 percent of all strokes (Thom et al., 2006). A lacunar stroke, a subtype of ischemic stroke, is relatively difficult to identify, as it manifests as a small hypodense area of less than 15 mm in diameter on CT (Toni et al., 2000). There are various classification systems for acute ischemic stroke. The Oxford Community Stroke Project (OCSP) classification relies primarily on the initial symptoms; the stroke episode is classified as Total Anterior Circulation Infarct (TACI), Partial Anterior Circulation Infarct (PACI), Lacunar Infarct (LACI) or Posterior Circulation Infarct (POCI).
Clinical diagnosis of ischemic stroke is difficult within the first few hours after the onset of stroke. Therefore, early detection of ischemic stroke is crucial. Early detection solely relies on some important early abnormal signs, including Loss of Insular Ribbon (LIR), loss of gray-white matter Attenuation of the Lentiform Nucleus (ALN), Hemispherical Sulcus Effacement (HSE) and the Hyperdense Middle Cerebral Artery Sign (HMCAS) (Tomura et al., 1988). Hypo dense changes are found to be the most frequent sign of early ischemia. However, its detection is difficult, since the early infarct sign is subtle hypo attenuation. An early and rapid diagnosis of stroke is critical for proper treatment of the patients. Definitive therapy is aimed to remove the blockage by breaking the clot (thrombolysis) or by removing it mechanically (thrombectomy), where immediately the blood flow is restored to the affected tissue.
MRI is the most sensitive diagnostic method in detecting ischemic stroke, especially in very early stages and to determine whether thrombolysis is needed or not. In most instances, CT provides information required to make decisions during emergency. Compared to MRI, brain imaging with CT is more accessible, less expensive and quicker especially in severely ill patients. Non-enhanced CT is often the first radiologic examination performed in case of suspicion of stroke (Von Kumar, 2005).