DSC-MRI derived relative CBV maps synthesized from IVIM-MRI data:Application in glioma IDH mutation status identification

TL;DR

This study presents a deep learning framework to synthesize DSC-MRI derived rCBV maps from IVIM-MRI data without contrast agents, accurately identifying glioma IDH mutation status and potentially reducing the need for gadolinium-based contrast injections.

Contribution

The paper introduces a novel deep neural network approach to generate DSC-MRI rCBV maps from IVIM-MRI data, demonstrating high accuracy and generalizability for glioma IDH mutation status classification.

Findings

High correlation between real and synthetic rCBV maps (Pearson P > 0.75)

Synthetic maps achieve comparable IDH mutation classification accuracy to real maps (AUC ~0.83)

Synthetic rCBV maps are consistent with real maps within 95% limits of agreement

Abstract

Objectives:To develop a framework for obtaining dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) derived relative cerebral blood volume (rCBV) maps without gadolinium-based contrast agent (GBCA) injection. Methods:This retrospective study included 146 patients (124 IDH wildtype; 22 IDH mutation) diagnosed with glioma. The DSC-MRI-derived rCBV maps were synthesized from intravoxel incoherent motion (IVIM) MRI data by the deep neural network trained only with IDH wildtype data due to thedata imbalance. Linear regression analysis, Pearson correlation coefficient, and Bland-Altman analysis, were done to evaluate the consistency between real and synthetic rCBV maps. The generalizability of the proposed framework was evaluated with IDH mutation data. IDH mutation status identification ability of real and synthetic rCBV maps was analyzed and compared using ROC analysis and the DeLong test. Results:Linear regression analysis shows a linear relationship between real and synthetic rCBV maps with a relatively high Pearson correlation coefficient (IDH wildtype: Pearson P = 0.7536; IDH mutation: Pearson P = 0.8933). Bland-Altman analysis between real and synthetic rCBV maps shows that almost all the data distribute within the 95% limits of agreement (IDH wildtype: 19 of 20 [95%]; IDH mutation: 19 of 20 [95%]). ROC analysis and the DeLong test show that the IDH mutation status identification abilities of real (AUC = 0.8375) and synthetic rCBV (AUC = 0.8325) are comparable and show no significant difference (P = 0.9075). Conclusions:It is feasible to obtain DSC-MRI-derived rCBV maps without the injection of GBCA. The synthetic rCBV map shows high consistency with real one.