Detection of Brain tumors (GBM and LGG) using machine Learning Techniques

Over the years, Glioblastoma (GBM) is the most common and malignant form of brain tumor (usually the final stage) that generally occurs in human beings. In its identified way, it's challenging to treat and cure the disease. Whereas Lower Grade Gliomas (LGG) originate from glial cells and can be treated and cured mostly in its identifies stage. However, the assessment of such diseases at an early stage is difficult. Consequently, a computer-aided diagnostic (CAD) program may help test the extent of tumors and can thus assist the physician in the right way. In this paper, we propose a new CAD system to characterize GBM and LGG using enhanced elongated quinary patterns. In this experiment, the Higher-order Spectral (HOS) and texture features extracted from these EQP's were able to distinguish GBM and LGG after subjecting the features to students t-test and Rusboosted trees classifier. Our study yielded the maximum classification accuracy of 95.5 % with ten-fold cross-validation. Thus obtained results confirmed the efficacy of the proposed CAD model in assisting the medical fraternity.Enter your text here...