ABSTRACT
This paper presents a method for the automatic detection and location of lobar ischaemic stroke lesion from brain CT images. The proposed method consists of three main steps: image enhancement, detection of abnormal slices and location of ischaemic stroke. Image enhancement based on fuzzy logic and histogram features were used for the detection of abnormal slices. Subsequently, CT images were divided into 10 parts. The relative density of each part was compared with that of the other parts. The part with the maximum relative density value indicated the location of ischaemic stroke. The results were computed from the brain CT images of ischaemic stroke patients. The objective of this paper was to propose a method to assist clinicians or neurologists for the early detection of ischaemic stroke and its proper management, thus reducing mortality and morbidity.
