Hybrid Multimodality Medical Image Fusion based on Guided Image Filter with Pulse Coupled Neural Network

Abstract

Multimodal medical image fusion technique is a fast and effective fusion method proposed for creating a highly integrating and informative fused medical image to acquire a more complete and accurate description of the same object. A multimodality medical image fusion technique plays an important role in biomedical research and clinical disease diagnosis. This paper, proposed an efficient hybrid multimodal medical image fusion approach based on combining the multi-level decomposition of an image into a bottom layer containing huge level variations in strength and a feature layer capturing minute level information with pulse coupled neural network fusion rule. The proposed work combines the guided image filtering and pulse coupled neural network for fusion process. Experimental results demonstrate that the proposed method can obtain magnetic resonance imaging (MRI), positron emission tomography (PET) and single photon emission computed tomography (SPECT) are the source images as experimental images. Hybrid fusion algorithms are evaluated using several quality metrics. Compared with other existing techniques the experimental results demonstrate the better processing performance in both subjective and objective evaluation criteria.