Using of Laplacian Re-decomposition image fusion algorithm for glioma grading with SWI, ADC, and FLAIR images

Abstract

Introduction: Based on the tumor’s growth potential and aggressiveness, glioma is most often classified into low or high-grade groups. Traditionally, tissue sampling is used to determine the glioma grade. The aim of this study is to evaluate the efficiency of the Laplacian Re-decomposition (LRD) medical image fusion algorithm for glioma grading by advanced magnetic resonance imaging (MRI) images and introduce the best image combination for glioma grading. Material and methods: Sixty-one patients (17 low-grade and 44 high-grade) underwent Susceptibility-weighted image (SWI), apparent diffusion coefficient (ADC) map, and Fluid attenuated inversion recovery (FLAIR) MRI imaging. To fuse different MRI image, LRD medical image fusion algorithm was used. To evaluate the effectiveness of LRD in the classification of glioma grade, we compared the parameters of the receiver operating characteristic curve (ROC). Results: The average Relative Signal Contrast (RSC) of SWI and ADC maps in high-grade glioma are significantly lower than RSCs in low-grade glioma. No significant difference was detected between low and high-grade glioma on FLAIR images. In our study, the area under the curve (AUC) for low and high-grade glioma differentiation on SWI and ADC maps were calculated at 0.871 and 0.833, respectively. Conclusions: By fusing SWI and ADC map with LRD medical image fusion algorithm, we can increase AUC for low and high-grade glioma separation to 0.978. Our work has led us to conclude that, by fusing SWI and ADC map with LRD medical image fusion algorithm, we reach the highest diagnostic accuracy for low and high-grade glioma differentiation and we can use LRD medical fusion algorithm for glioma grading.

Performance comparison of different medical image fusion algorithms for clinical glioma grade classification with advanced magnetic resonance imaging (MRI)

“…Interestingly, in fused images, RSCs in LGGs are significantly higher than HGGs with PCA, DCHWT, LRD, and DDcGAN algorithms. These values correlate satisfactorily with previous studies and further support the role of tumor cellularity and micro bleeding in HGGs 4 , 5 , 33 . In accordance with the present results, previous studies have demonstrated that tumor cellularity increased with glioma grade, and HGGs have lower ADC values in DWI images than LGGs 34 – 36 .…”

“…Three ROIs were sampled and averaged for each region to improve the comparison's power. Then, RSC was calculated by the following equation 5 , 33 : Is the mean signal intensity of the active tumor region, and Is the mean signal intensity of the white matter in each picture. RSCs in fused images of LGGs and HGGs with different fusion methods were calculated and compared with each other for glioma grading performance.…”

“…In recent years, there has been an increasing interest in introducing different image fusion methods, and researchers have proposed different methods such as generative adversarial network (GAN) 26 , Laplacian Re-Decomposition (LRD) 27 , Principal Component Analysis (PCA) 28 , Structure-Aware 29 , Discrete Cosine Harmonic Wavelet Transform (DCHWT) 30 , Deep-Convolutional Neural network (DNN) 31 , Dual-Discriminator conditional generative adversarial network (DDcGAN) 32 , etc. Some preliminary works 5 , 33 were carried out recently to use medical image fusion methods with MRI images for glioma grade classification purposes. It has now been demonstrated that the accuracy of glioma grade classification can be improved with the fusion of different MRI image weights 5 , 33 .…”

“…Some preliminary works 5 , 33 were carried out recently to use medical image fusion methods with MRI images for glioma grade classification purposes. It has now been demonstrated that the accuracy of glioma grade classification can be improved with the fusion of different MRI image weights 5 , 33 . Recently investigators have examined the effect of different MRI image weights fusion on the accuracy of glioma grade classification.…”

“…Recently investigators have examined the effect of different MRI image weights fusion on the accuracy of glioma grade classification. They suggest that SWI and ADC map fusion have the highest performance for glioma grade classification 33 . For this reason, we will also use SWI and ADC maps in the present study.…”