An Automated Framework to Segment and Classify Gliomas Using Efficient Shuffled Complex Evolution Convolutional Neural Network

Abstract

Detection of Glioma and its segmentation can be a very challenging task for clinicians and radiologists. Accuracy in classifying glioma is required where brain tumorsgrow from the star-shaped glial cells among adults. Magnetic Resonance Imaging (MRI) indicates the human soft tissue and its anatomical structure away from displaying the location, histological traits, and location of the lesions used to diagnose glioma clinically. An automated framework for the identification of gliomas is presented. Feature extraction will present much higher imaging features such as texture, color, contrast, and shape. The Gabor filters can carry out multi-resolution decomposition due to localization with regard to spatial frequency. The Shuffle Complex Evolution (SCE) algorithm will combine Controlled random search, a complex mix, competition, evolution, and the adaptation of the world’s population Nelder-Mead Simplex for all the benefits of optimal solutions. The CNN process is in an input texture that collects statistics within the spatial domain. The CNNs are normally capable of capturing spatial features, and spectral analysis can capture all scale-invariant features. This work implements an automated method for classifying the Gliomas with an optimized shuffled complex evolution CNN.