International Journal of Innovative Technology and Exploring Engineering · 2020 · 13 citations · 0 references
ComputingComputer ScienceRadiologyComputer VisionFeature EngineeringMachine LearningBrain TumorsDeep LearningMagnetic Resonance ImagingMedical Image AnalysisMedical ImagingTumor ClassificationBrain Tumor DiagnosisClassification AccuracyClassification Accuracy MetricsComputer-aided Tumor DiagnosisCross-validationDeep Learning-based ClassificationDeep Learning-based DiagnosisDeep Learning-based Lesion Classification
Classification of brain tumor for medical applications is considered as an important constraint in computer-aided diagnosis (CAD). In this paper, we study the classification of brain tumor by considering the constraint as a classification problem in order to segregate the tumors among pituitary tumors, gliomatumorand meningioma tumor. This method adopts deep learning principle to extract the brain features from the MRI images. In this study, Recurrent Neural Network is used to classify the extracted features from brain. The experiments are carried out in terms of three fold cross-validation process over MRI brain image dataset. The results show that the proposed RNN classifier classifies the brain tumors effectively with 98% of mean classification accuracy than other existing methods.