978-1-5386-2366-4/17/$31.00 ©2017 IEEE Automated Techniques for Brain Tumor Segmentation and Detection: A Review Study Uma-e-Hani, Saeeda Naz * Govt.Girls Postgraduate College No.1, Department of Computer Science, Abbottabad, Pakistan {umaehanie, saeedanaz292}@gmail.com Ibrahim A Hameed Norwegian University of Science and Technology, Norway ibib@ntnu.no Abstract— Brain is the central organ of the human body which controls nervous system. In this paper, we give a brief insight of different techniques and contribution of different people for segmentation and detection of brain tumor. Different methodologies are proposed by different researchers. The MRI scan image considers as a high quality input for experiments as compared to other scans. In the future, we will develop a deep learning based automated brain tumor detection system and will compare with the existing state of the art techniques for better and more accurate results. Keywords—Brain Tumor, MRI, Machine Learning I. INTRODUCTION Brain is the central main part of the human body that controls their nervous system. Brain controls many functions like heart, breathing, talking, walking, thinking ability, consciousness and unconsciousness balance, etc. Therefore, it plays vital and central role of the nervous system of humans. The anatomy of the human brain has shown in Fig 1. Fig. 1. Anatomy of Brain of Human [1] Brain tumor is the irregular growth of cells in human brain [2][3]. A brain tumor has two types, benign which is noncancerous and malignant which is cancerous. Malignant brain tumor has two categories such as primary tumor and secondary tumor. Primary brain tumor arises in the brain and secondary brain tumor arises in the other parts of body and spreads to brain and affect them. According to [4], brain and spinal cord malignant tumor affected 23,800 adults and 100,000 children in the US in a year, only. *Corresponding author: Saeeda Naz The only way of treatments is the surgery and medical imaging test techniques like neurological exam, Computer tomography (CT), Medical Resonance Imaging (MRI), Positron Emission Tomography (PET) etc. are used to diagnose the brain tumor. The most common magnetic resonance imaging (MRI) test used for diagnosing and providing detailed information from images of brain with pulses of radio wave energy. Then the medical expert diagnoses and concluded the abnormality of the organ. Diagnosing brain tumor is very demanding and challenging task for expert in the early stages due to different shapes, appearances, metabolism, divergent sizes of tumor, low contrasted noisy images, diffused and overlap due to tentacle like structure [5][6]. The segmentation is the main preprocessing step for detection of brain tumors. It improves the performance and accuracy of automatic detection of brain tumor. Different types of machine learning based techniques and algorithms are applied to MRI and CT images to detect the brain tumor at the first stage. Fig. 2. Images of MRI Scan, CT Scan and PET The automatic brain tumor system may consist of step stages as shown in Fig. 3. The image acquisition step consists of capturing scanned images (MRI, CT, PET etc.) and some free datasets are BraTS [7], [8], IBSR [9] or BrainWeb [10]. The pre-processing step composes of different techniques of digitization of images, noise removal, image enhancement and sharpening. Likewise, different techniques use for isolation and separation of the region of interest in segmentation step and some free tools for segmentation are available at [11]. Statistics, structured or global features are extracted in the step of features extraction. Finally, different kinds of machine learning models use for classification or clustering for grouping the affected and non-affected parts of the brain and output image display to the physician or expert in diagnosing and making final medical decision.