Automatic Detection of Tumor and Bleed in Magnetic Resonance Brain Images

Automatic Detection of Tumor and Bleed in Magnetic Resonance Brain Images

Jayanthi V. E., Jagannath Mohan, Adalarasu K.
DOI: 10.4018/978-1-5225-5152-2.ch015
(Individual Chapters)
No Current Special Offers


Brain tumor and intracerebral hemorrhage are major causes for death among the people. Brain tumor is the growth of abnormal cells multiplied in an uncontrolled manner in brain. Magnetic resonance imaging (MRI) technique plays a major role for analysis, diagnosis, and treatment planning of abnormalities in the brain. Bleed is detected manually by radiologists, but it is laborious, time-consuming, and error prone. The automatic detection method was performed to detect the tumor as well as bleed in brain under a single system. The proposed method includes image acquisition, pre-processing, patch extraction, feature extraction, convolutional neural network (CNN) classification, and fuzzy inference system (FIS) to detect the abnormality with reduced classification loss percentage. This chapter is compared with the existing system of tumor detection using convolution neural network based on certain features such as skewness, kurtosis, homogeneity, smoothness, and correlation.
Chapter Preview


Many of the researchers proposed many methods to find brain tumour, stroke and other kinds of abnormalities in human brain using MR imaging (Isin, Direkoglu, & Sah, 2016). T2 weighted MR images were used for detection of tumour (Nidhi, & Pritee, 2017). The MR image segmentation utilizing pattern recognition method has been analysed (Bezdek, Hall, & Clarke, 1993). Method like Artificial Neural Network (ANN) can be used for brain segmentation and pattern recognition in order to detect the brain tumour (Parra, Iftekharuddin, & Kozma, 2003; Sayed, Zaghloul, & Nassef, 2016). Tissue probability mapping is used to measure the similarity to detect the brain tumour is proposed (Schwarz, Kasparek, Provaznik, & Jarkovsky, 2007) and it gives the best result in case of large initial miss-registration.Atlas based fuzzy connectedness segmentation technique used for automatic segmentation of brain MRI image is explained (Zhou & Bai, 2007). The result gives important data by measuring the difference between abnormal and normal brain. In atlas registration, PABLIC correction and Re-FC segmentation are applied to detect the brain tumour automatically in MRI scanned image. To remove the overall position and scale differences between the atlas and MRI, atlas registration concept is used. This is based on four concepts, i.e., normalized mutual information as the similarity measure, nearest neighbour interpolation, similarity transform and power optimization. HSOM based segmentation and wavelet packet features are used to detect and characterize the brain tumour is discussed (Gladis Pushpa Rathi & Palani, 2010).

Key Terms in this Chapter

Convolutional Neural Network (CNN): In machine learning, a convolutional neural network is a class of deep, feed-forward artificial neural networks that has successfully been applied to analyzing visual imagery. CNNs use a variation of multilayer perceptrons designed to require minimal preprocessing. They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics.

Brain: The human brain is the central organ of the human nervous system and with the spinal cord makes up the central nervous system. The brain consists of the cerebrum, the brainstem, and the cerebellum. It controls most of the activities of the body, processing, integrating, and coordinating the information it receives from the sense organs, and making decisions as to the instructions sent to the rest of the body. The brain is contained in, and protected by, the skull bones of the head. The cerebrum is the largest part of the human brain.

Magnetic Resonance Imaging (MRI): Clinical magnetic resonance imaging is an imaging technique used in radiology to form pictures of the anatomy and the physiological processes of the body in both health and disease. MRI scanners use strong magnetic fields, radio waves, and field gradients to generate images of the organs in the body. MRI does not involve x-rays, which distinguishes it from computed tomography.

Fuzzy Inference System (FIS): Fuzzy inference systems have been successfully applied in fields such as automatic control, data classification, decision analysis, expert systems, and computer vision. Because of its multidisciplinary nature, the fuzzy inference system is known by a number of names, such as fuzzy rule-based system.

Brain Tumor: The brain is the body organ composed of nerve cells and supportive tissues like glial cells and meninges. There are three major parts; they control people activity like breathing (brain stem), activity like moving muscles to walk (cerebellum), and senses like sight and our memory, emotions, thinking, and personality (cerebrum). Primary brain tumors can be either malignant (contain cancer cells) or benign (do not contain cancer cells). A primary brain tumor is a tumor which begins in the brain tissue. If a cancerous tumor starts elsewhere in the body, it can spread cancer cells, which grow in the brain. These type of tumors are called secondary or metastatic brain tumors.

Complete Chapter List

Search this Book: