An Innovative Model for Detecting Brain Tumors and Glioblastoma Multiforme Disease Patterns

Abstract

In this article, an innovative model is proposed for detecting brain tumors and glioblastoma multiforme disease patterns (DBT-GBM) in medical imaging. The DBT-GBM model mainly includes five steps, the image conversion in the L* component of the L*a*b* space, an image sample region selection, calculation of the average values of colors, image pixel classification using the minimum distance classifier and the segmentation operation. In the approach, the minimum distance classifier is used to classify each pixel by calculating the Euclidean distance between that pixel and each color marker of the pattern. In the experiments, the authors implement the DBT-GBM model into real-time data, the samples of three anatomic sections of a T1w 3D MRI (axial, sagittal and coronal cross-sections) on the GBM-3D-Slicer datasets and the CBTC datasets. The implementation results show that the proposed DBT-GBM robustly detects the GBM disease patterns and cancer nuclei (involving the omics indicative of brain tumors pathologically) in medical imaging, leading to improved segmentation performance in comparison.