A Practical Approach to Automated Segmentation of Brain Tumours in MRI [article]

Aleksandar Miladinovic
2020 figshare.com  
Expert brain tumor identification on multimodal Magnetic Resonance (MR) images is a very time-consuming process for medical experts. Therefore, throughout the last decade, significant effort has been invested in the development of novel approaches applying computer-aided techniques for brain tumor segmentation. Automated brain tumor segmentation aims to separate and label different tumor tissues, including: (1) active tumor cells, (2) necrotic core, and (3) edema from normal brain tissues of
more » ... y Matter (GM), White Matter (WM), and Cerebrospinal fluid (CSF). Even though experts from the brain tumor research area can accurately characterize and identify brain tissue abnormalities, the automated process of tumor segmentation is not straightforward. Many accurate approaches are only evaluated on a single data type coming from a particular brain tumor type, and thus, being far away from a practical clinical application [1]. The aim of this work is to implement a software framework to apply and evaluate a recent technique of automated brain tumor segmentation in realistic clinical settings. We will use the algorithms on a coherent study data set and evaluate how they perform based on a small annotated data set. The algorithm choice will be based on quantitative evaluations from [2], [3]. Additionally, internal requirements for the selection will be defined (i.e. degree of user supervision, robustness on the various data, etc.). The dataset consists of multi-contrast MR clinical images from [2], [3], as well as, images from the repository of Medical University of Vienna. The robustness of the selected approach will be evaluated using test data from [2], [3]. The performance measure includes segmentation accuracy of each tumor sub-region defined in 1-3, brain tumor type and the severity of the pathological case. The expected outcome of this project is a toolbox for brain tumor segmentation using existing algorithms. The robustness of the state-of-the-art approaches will be evaluated providing a rough estimation of how f [...]
doi:10.6084/m9.figshare.13108292.v1 fatcat:rekjw5ipfjb3xkvlwhuqcqzd3u