A dual-discriminator conditional generative adversarial network (DDcGAN) approach to glioma grade classification with...

Glioma grade is a critical parameter of clinical management. Recent advances in artificial intelligence (AI)-based image fusion have enabled effective integration of structural MRI (sMRI) sequences for glioma grading. This study investigates the application of AI-driven sMRI fusion techniques to improve glioma grade classification with Relative Signal Contrast (RSC) image-biomarker. The sMRI image-weights were collected from BraTS 2023 data-set. AI-based medical image fusion was performed using a Dual-Discriminator Conditional Generative Adversarial Network (DDcGAN). Entropy, standard deviation, peak signal-to-noise ratio, and the structural similarity index measure were determined for comparing fused image quality. In order to compute the RSC, signal intensity data were extracted from active tumor regions, necrotic core, and normal white matter, as volume of interest, in the sMRI images and the fused image pairs for each participant and compared statistically. The evaluation of the fused image quality demonstrated highly satisfactory results. In this study, RSC change between the High-Grade glioma and Low-Grade glioma groups were statistically significant across all sMRI and fused images, with the exception of T₁-weighted images and the T₁+T₂ fused image. ROC analysis in this study demonstrated that the T₁Gd+FLAIR fused image exhibited the highest performance for glioma grading, with an AUC of 0.91, a sensitivity of 0.90, and a specificity of 0.72. DDcGAN-based image fusion demonstrates strong potential for improving glioma grade determination. Among structural MRI sequences, fusion of T₁Gd+ FLAIR provides the most discriminative information, supporting the use of RSC calculated from fused images as an imaging-biomarker for glioma grade classification.