An automated framework for stroke and hemorrhage detection using decision tree classifier

Medical imaging plays an important role in the early detection and treatment of medical diagnosis. It provides physicians with information essential for efficient and effective diagnosis of various diseases. The objective of the research work included in this paper is to provide a robust technique for automatic segmentation of ischemic stroke, hemorrhage, hematoma and tumor lesions from brain MR and CT images. In this paper, the characteristics of Decision Tree classifier are discussed. The Decision Tree classification model is used for diagnosis of three brain diseases namely ischemic stroke, hemorrhage and hematoma and tumor. The performance of the decision tree model in diagnosing ischemic stroke, hemorrhage and hematoma and brain tumor is 91%, 93% and 95%, respectively. The proposed system can help the physicians to identify the type of ischemic stroke, the type of human brain hemorrhage and hematoma and the type of brain tumors for further treatment. It also focuses on using textural analysis in the classification process. With the aim of improving some of the existing methods and developing new techniques to facilitate accurate, fast and reliable computer based diagnosis of brain diseases. An automated method is developed for the classification of normal or ischemic stroke brain CT, the type of brain CT hemorrhage and hematomas and the type of the MR brain tumor images using the decision tree classifier.