Article Preview
Top1. Introduction
In clinical studies, it has been found that brain tumors in adults occupy the 13th place in frequency of all cancers, and they are the fifth most common cause of cancer death in the under 65-year-old population because of their particularly poor prognosis in brain. In addition, the cells of brain tumors could grow quickly, and could spread throughout the brain (Bakas et al., 2017A; Bauer et al., 2013; Tasic et al., 2015; Pepe et al., 2013). Among brain tumors, the glioblastoma multiforme (GBM) is one of the most common and most aggressive malignant primary tumors in brain, where the incidence of the GBM is 2 to 3 per 100,000 people in the United States and Europe. The GBM accounts for 12% to 15% of all intracranial tumors and 50% to 60% of astrocytic tumors. In clinical, the treatments for the patients with brain tumors typically include maximum safe resection, percutaneous radiation, chemotherapy, surgical operation etc. (Menze et al., 2015; CBTC, 2015; Egger et al., 2013; Duyn, 2012).
Studies show that patients with brain tumors may benefit from early diagnoses in order to receive primary care or undergo surgical procedures to address their progressive symptoms (Bakas et al., 2017B; Iturria-Medina et al., 2016; Wang, 2013; Egger et al., 2013; Ahmed et al., 2015). Some modalities of biomarkers have been proved to be sensitive to brain tumors in the detection, including the measure of the volume of brain tumors through the MRI scans. Therefore, a robust model which could offer the analysis of volumes of disease patterns with systematic quantitative measurements is important to help to pursue the major objective of carrying out mass screening campaigns of medical imaging in the early detection clinically (Guo, 2017A; Tohka, 2014; Wang et al., 2011; Masood et al., 2013).
Image segmentation refers to the partitioning of an image into disjoint regions with respect to a chosen property, for example, brain tissues, image patterns, textures of colors in MRI scans (Guo, 2017B; West et al., 2012; Yushkevich et al., 2006). Since the segmentation of cancer nuclei and detection of the GBM disease patterns is crucial early steps on supporting of brain tumor diagnosis, it has become one of the important areas of research in assess patients with brain tumor in medical community (Martono et al., 2016; Ahmed et al., 2015; Paul et al., 2015). This study seeks to address the challenge for providing a model for detecting brain tumors involving ‘omics’ indicative of brain tumors pathologically in digital pathology imaging, as well as the quantitative analysis of the GBS disease patterns in the samples of the anatomic sections of a T1w 3D MRI, in order to assist physicians in quantifying volumes of brain tumors in clinical.