Purpose: Recent advances in sodium brain MRI have allowed for increased signal-to-noise ratio, faster imaging and the ability of differentiating intracellular from extracellular sodium concentration, opening a new window of opportunity for clinical application. In gliomas there are significant alterations in sodium metabolism, including increase in total sodium concentration and extracellular volume fraction. The purpose of this study is to assess the feasibility of using sodium MRI quantitative measurements to evaluate gliomas. Methods: Eight patients with treatment naïve gliomas were scanned at 3 Tesla with a homemade 1H/23Na head coil, generating maps of pseudo-intracellular sodium concentration (C1), pseudo-extracellular volume fraction (α2), apparent intracellular sodium concentration (aISC) and apparent total sodium concentration (aTSC). Measurements were made within the contralateral normal appearing putamen, contralateral normal appearing white matter (NAWM) and in solid tumor regions (area of T2-FLAIR abnormality, excluding highly likely areas of edema, cysts, or necrosis). Paired samples t-test were performed comparing NAWM and putamen and between NAWM and solid tumor. Results: Normal appearing putamen demonstrated significantly higher values for aTSC, aISC, C1 (p<0.001), and α2 (p=0.002) when compared to NAWM. Mean average of all solid tumors, when compared to NAWM, demonstrated significantly higher values of aTSC and α2 (p<0.001), and significantly lower values of aISC (p=0.02), There was no significant difference between the values of C1 (p=0.19). Conclusion: Quantitative sodium measurements can be done in glioma patients and also has provided further evidence that total sodium and extracellular volume fraction are increased in gliomas.

Purpose: To develop a deep learning approach to estimate the local capillarylevel input function (CIF) for pharmacokinetic model analysis of DCE-MRI. Methods:A deep convolutional network was trained with numerically simulated data to estimate the CIF. The trained network was tested using simulated lesion data and used to estimate voxel-wise CIF for pharmacokinetic model analysis of breast DCE-MRI data using an abbreviated protocol from women with malignant (n = 25) and benign (n = 28) lesions. The estimated parameters were used to build a logistic regression model to detect the malignancy. Result:The pharmacokinetic parameters estimated using the network-predicted CIF from our breast DCE data showed significant differences between the malignant and benign groups for all parameters. Testing the diagnostic performance with the estimated parameters, the conventional approach with arterial input function (AIF) showed an area under the curve (AUC) between 0.76 and 0.87, and the proposed approach with CIF demonstrated similar performance with an AUC between 0.79 and 0.81. Conclusion:This study shows the feasibility of estimating voxel-wise CIF using a deep neural network. The proposed approach could eliminate the need to measure AIF manually without compromising the diagnostic performance to detect the malignancy in the clinical setting.

No abstract

No abstract