Preliminary study of multiple b-value diffusion-weighted images and T1 post enhancement magnetic resonance imaging images fusion with Laplacian Re-decomposition (LRD) medical fusion algorithm for glioma grading

Abstract

Background: Grade of brain tumor is thought to be the most significant and crucial component in treatment management. Recent development in medical imaging techniques have led to the introduce non-invasive methods for brain tumor grading such as different magnetic resonance imaging (MRI) protocols. Combination of different MRI protocols with fusion algorithms for tumor grading is used to increase diagnostic improvement. This paper investigated the efficiency of the Laplacian Re-decomposition (LRD) fusion algorithms for glioma grading. Procedures: In this study, 69 patients were examined with MRI. The T1 post enhancement (T1Gd) and diffusionweighted images (DWI) were obtained. To evaluated LRD performance for glioma grading, we compared the parameters of the receiver operating characteristic (ROC) curves. Findings: We found that the average Relative Signal Contrast (RSC) for high-grade gliomas is greater than RSCs for low-grade gliomas in T1Gd images and all fused images. No significant difference in RSCs of DWI images was observed between low-grade and high-grade gliomas. However, a significant RSCs difference was detected between grade III and IV in the T1Gd, b50, and all fussed images. Conclusions: This research suggests that T1Gd images are an appropriate imaging protocol for separating lowgrade and high-grade gliomas. According to the findings of this study, we may use the LRD fusion algorithm to increase the diagnostic value of T1Gd and DWI picture for grades III and IV glioma distinction. In conclusion, this article has emphasized the significance of the LRD fusion algorithm as a tool for differentiating grade III and IV gliomas.

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.…”

A lightweight 3D UNet model for glioma grading

“…Among them, the research finds out the result on CET1w MRIs have the better classifying performance. The reason may be that there are significant differences in the average relative signal strength on CET1w images between HGG and LGG (Khorasani et al 2021). Although CET1w has traditionally been a marker of high grade gliomas (Scott et al 2002), previous studies reported that 14%-45% of nonenhancing supratentorial gliomas are malignant (Mihara et al 1995, Barker et al 1997, Ginsberg et al 1998, Scott et al 2002 and some enhancing gliomas (i.e.…”