hide
Free keywords:
-
Abstract:
Introduction To make 7T CEST MRI more available for radiologists, we developed a deepCEST pipeline for 7T MRI that predicts CEST contrasts from just one scan with robustness against B1 inhomogeneities. The pipeline includes an uncertainty quantification and a confidence map to evaluate the quality of the predictions. The proposed approach results in a reduction of 50% of the measurement time and delivers the predicted CEST contrast with in 1 sec. Methods The input data for a neural network (NN) consisted of 7T in vivo raw Z-spectra of a single B1 level, and a B1 map. The 7T raw data was acquired using the 3D snapshot GRE MIMOSA CEST3 at a Siemens MAGNETOM 7T scanner. These inputs were mapped voxel-wise on target data consisting of Lorentzian amplitudes conventionally generated by 5-pool-Lorentzian fitting performed on normalized, denoised, B0- and B1-corrected Z-spectra. The network consisted of two fully connected hidden layers with RELU activation and was trained with Gaussian negative log likelihood loss. The output layer consisted of 10 nodes with linear activation to obtain the amplitudes and uncertainty of the 5-pool Lorentzian fit. Results Figure 1a, b, d and e shows the Lorentzian fit and the prediction of the amide and rNOE contrast in a tumor patient. Figure 1c, f shows the segmented uncertainty map over all contrasts with a threshold of 10%. The first row shows the predictions and uncertainty for the measurement made with a bad shim. Such a strong B0 shift was not part of the training distribution. Therefore, the predictions and fits do not match. Consequently, the NN outputs a high uncertainty for these voxels (Fig. 1c). In the second row of (Fig. 1), the Z-spectra of the patient was centered, resulting in NN predictions that agree well with the fit, and only a low uncertainty is yielded. Discussion The deepCEST approach has already shown very promising results for 3T, the clear advantage of 7T data is the better SNR and higher spectral resolution. The 7T deepCEST approach uses only one B1 level, this saves about 50% of scan time (now 6:42 min), but still predicts accurately with low uncertainty (Fig. 2) and provides both B0- and B1-corrected homogeneous CEST contrast.
