Early Stage Brain Tumor Detection on MRI Image Using a Hybrid Technique

Md. Ahasan Kabir

20202020 IEEE Region 10 Symposium (TENSYMP)14 citationsDOI

Abstract

One of the robust issues facing the world today is a brain tumor, out of many diseases in the medical sciences. Brain Tumor is a cellular proliferation in the brain that is uncontrolled. Early detection and diagnosis can reduce the mortality rate significantly. In this paper, a tumor detection algorithm has proposed based on support vector machine (SVM) and artificial neural network. The proposed algorithm is divided into gradient intensity smoothing based edge preservation, image enhancement, SVM based segmentation, features extraction, and classification. To measure the performances of the proposed algorithm is tested on the BRATS dataset image. Experimental result has shown that the proposed algorithm achieved 97.7% accuracy, which is better than many existing algorithms.

Topics & Concepts

Support vector machineArtificial intelligenceComputer sciencePattern recognition (psychology)Image segmentationSmoothingSegmentationStage (stratigraphy)Feature extractionEdge detectionArtificial neural networkImage (mathematics)Enhanced Data Rates for GSM EvolutionComputer visionImage processingPaleontologyBiologyBrain Tumor Detection and ClassificationDigital Imaging for Blood DiseasesAdvanced Neural Network Applications