Hybrid Learning Model for Metal Artifact Reduction

Abstract

In today’s healthcare, the human brain imaging is done for finding the tumors and other disorders of the brain. The Magnetic Resonance Imaging (MRI) plays a significant role throughout the complete clinical procedure starting from diagnostics and treatment planning to surgical processes and follow up studies. The MRI of brain allows the clinical expert for the earliest detection and treatment of brain abnormality or any neurological diseases, which is the most treatable stage that gives patients the greatest chance of survival. An artifact is a feature appearing in an image which is not present in the original imaged object. The types of artifacts are herringbone artifact, zipper artifact, motion artifact, aliasing artifact, chemical shift artifact, magnetic susceptibility artifact, central point artifact, Gibbs ringing artifact and intensity inhomogeneity artifact. After segmentation, the features are extracted using Gray level co-occurrence matrix (GLCM) and an CNN, Deep belief network, Proposed hybrid model (Based on CNN and Deep belief network (DBN)) and Morphological Technique with Segmentation Techniques is implemented to classify the brain MRI images as either normal (without tumor) or abnormal (with tumor). Proposed hybrid model for metal artifact reduction and represent though the experiment our proposed model very effective to existing one. Results in Accuracy (in %) Before artifact removal(92.12%), After artifact removal (95.77%)