Purpose Deuterium metabolic imaging (DMI) maps the uptake of deuterated precursors and their conversion into lactate and other markers of tumor metabolism. Even after leveraging 2H’s short T1s, DMI’s signal‐to‐noise ratio (SNR) is limited. We hypothesize that a multi‐echo balanced steady‐state free precession (ME‐bSSFP) approach would increase SNR compared to chemical shift imaging (CSI), while achieving spectral isolation of the metabolic precursors and products. Methods Suitably tuned 2H ME‐bSSFP (five echo times [TEs], ΔTE = 2.2 ms, repetition time [TR]/flip‐angle = 12 ms/60°) was implemented at 15.2T and compared to CSI (TR/flip‐angle = 95 ms/90°) regarding SNR and spectral isolation, in simulations, in deuterated phantoms and for the in vivo diagnosis of a mouse tumor model of pancreatic adenocarcinoma (N = 10). Results Simulations predicted an SNR increase vs. CSI of 3‐5, and that the peaks of 2H‐water, 2H6,6’‐glucose, and 2H3,3’‐lactate can be well isolated by ME‐bSSFP; phantoms confirmed this. In vivo, at equal spatial resolution (1.25 × 1.25 mm2) and scan time (10 min), 2H6,6’‐glucose’s and 2H3,3’‐lactate’s SNR were indeed higher for bSSFP than for CSI, three‐fold for glucose (57 ± 30 vs. 19 ± 11, P < .001), doubled for water (13 ± 5 vs. 7 ± 3, P = .005). The time courses and overall localization of all metabolites agreed well, comparing CSI against ME‐bSSFP. However, a clearer localization of glucose in kidneys and bladder, the detection of glucose‐avid rims in certain tumors, and a heterogeneous pattern of intra‐tumor lactate production could only be observed using ME‐bSSFP’s higher resolution. Conclusions ME‐bSSFP provides greater SNR per unit time than CSI, providing for higher spatial resolution mapping of glucose uptake and lactate production in tumors.

Purpose To design a new deep learning network for fast and accurate water–fat separation by exploring the correlations between multiple echoes in multi‐echo gradient‐recalled echo (mGRE) sequence and evaluate the generalization capabilities of the network for different echo times, field inhomogeneities, and imaging regions. Methods A new multi‐echo bidirectional convolutional residual network (MEBCRN) was designed to separate water and fat images in a fast and accurate manner for the mGRE data. This new MEBCRN network contains 2 main modules, the first 1 is the feature extraction module, which learns the correlations between consecutive echoes, and the other one is the water–fat separation module that processes the feature information extracted from the feature extraction module. The multi‐layer feature fusion (MLFF) mechanism and residual structure were adopted in the water–fat separation module to increase separation accuracy and robustness. Moreover, we trained the network using in vivo abdomen images and tested it on the abdomen, knee, and wrist images. Results The results showed that the proposed network could separate water and fat images accurately. The comparison of the proposed network and other deep learning methods shows the advantage in both quantitative metrics and robustness for different TEs, field inhomogeneities, and images acquired for various imaging regions. Conclusion The proposed network could learn the correlations between consecutive echoes and separate water and fat images effectively. The deep learning method has certain generalization capabilities for TEs and field inhomogeneity. Although the network was trained only in vivo abdomen images, it could be applied for different imaging regions.

No abstract