A survey of MRI-based medical image analysis for brain tumor studies

Abstract

MRI-based medical image analysis for brain tumor studies is gaining attention in recent times due to an increased need for efficient and objective evaluation of large amounts of data. While the pioneering approaches applying automated methods for the analysis of brain tumor images date back almost two decades, the current methods are becoming more mature and coming closer to routine clinical application. This review aims to provide a comprehensive overview by giving a brief introduction to brain tumors and imaging of brain tumors first. Then, we review the state of the art in segmentation, registration and modeling related to tumor-bearing brain images with a focus on gliomas. The objective in the segmentation is outlining the tumor including its sub-compartments and surrounding tissues, while the main challenge in registration and modeling is the handling of morphological changes caused by the tumor. The qualities of different approaches are discussed with a focus on methods that can be applied on standard clinical imaging protocols. Finally, a critical assessment of the current state is performed and future developments and trends are addressed, giving special attention to recent developments in radiological tumor assessment guidelines.

Medical Big Data: Neurological Diseases Diagnosis Through Medical Data Analysis

“…Such tests are mainly used for swelling and lesions in certain areas, broken bones, heart disease and internal bleeding. In finding brain and spinal cord abnormalities, MRI tests are valuable to investigate detailed images of body structures including tissues, organs, bones and nerves [9][10][11]. MRI tests help physicians to diagnose torn ligaments, tumours, circulation (blood flow) problems, eye disease, inflammation (e.g.…”

Brain tumor classification from multi-modality MRI using wavelets and machine learning

“…Intensity normalization or bias field correction is often applied to balance the effect of magnetic field inhomogeneity [1]. Intensities, neighborhood and texture are common features used in various studies [1][2][3].…”

“…It is hard to fully segment and classify brain tumor from mono-modality scans, because of its complicated structure. MRI provides the ability to capture multiple images known as multimodality images, which can provide the detailed structure of brain to efficiently classify the brain tumor [1]. Figure 1 shows different MRI modalities of brain.…”

The influence of automation on tumor contouring

“…Fully automatic contouring is potentially the most time efficient as it is designed to have little involvement of the physician. However, fully automatic contouring methods have shown limited success and often extensive post-processing is needed (Bauer et al 2013;Sykes 2014). Automation may be introduced in different levels for semi-automatic methods: from automatically generated 3D volumes based on a few 2D contours [e.g., based on the foreground and background seeds ] to computationally adjusting the contour while it is being drawn by the physician [e.g., live-wire tool (Barrett and Mortensen 1997)].…”