AUTHOR=Huang Chenxi , Tian Ganxun , Lan Yisha , Peng Yonghong , Ng E. Y. K. , Hao Yongtao , Cheng Yongqiang , Che Wenliang 

TITLE=A New Pulse Coupled Neural Network (PCNN) for Brain Medical Image Fusion Empowered by Shuffled Frog Leaping Algorithm

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 13 - 2019

YEAR=2019

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2019.00210

DOI=10.3389/fnins.2019.00210

ISSN=1662-453X

ABSTRACT=Recent researches have been reported to apply image fusion technologies for medical images in a wide range of aspects, such as the diagnosis of brain diseases, the detection of glioma and the diagnosis of Alzheimer. In our study, a new fusion method based on the combination of shuffled frog leaping algorithm (SFLA) and pulse coupled neural network (PCNN) is proposed for the fusion of SPECT images and CT ones to improve the quality of fused brain images. Firstly, the intensity-hue-saturation (IHS) of a SPECT image and a CT image are decomposed using non-subsampled contourlet transform (NSCT) independently, where both low-frequency and high-frequency images using NSCT are obtained. Then, we use the combined SFLA and PCNN for fusion of the high-frequency sub-bands images the fusion of the low-frequency images as well. The SFLA is considered to optimize the PCNN network parameters. Finally, the fused image is produced from the reversed NSCT and the reversed IHS transform. We evaluated our algorithms against standard deviation (SD), mean gradient ( ), spatial frequency (SF) and information entropy (E) using three different sets of brain images. The experimental results demonstrate the superior performance of the proposed fusion method for enhancing both the precision and spatial resolution significantly.