Texture Aware Deep Feature Map Based Linear Weighted Medical Image Fusion

Medical image analysis is a critical job for the clinicians and radiologists to attain minute insights proper diagnosis. The presence of complementary details region interest (ROI) from multiple medical imaging modalities instigates researchers integrate or combine pathological ease clinical In this paper, objective obtain comprehensive that presents composite two multimodal images same ROI. basic idea generate robust fusion weights in form individual weighted matrices could potentially superintend fused outcome input matrices. extraction texture features comes into play with employment fast gray level co-occurrence matrix-mean technique. feature maps source are derived convolution layers on which done evaluate weight map. Linear based spatial domain employed using Post auditioning several relevant strategies baseline hyper-parameter tuning, obtained sets outputs validated via terms standard metrics compared other methods.