Reconstruction of spectra from truncated free induction decays by deep learning in proton magnetic resonance spectroscopy
Hyochul Lee, Hyeong Hun Lee, Hyeonjin Kim
Abstract
Purpose To explore the applicability of convolutional neural networks (CNNs) in the reconstruction of spectra from truncated FIDs (tFIDs) in 1 H‐MRS, which can be valuable in situations in which data sampling is highly limited, such as spectroscopic magnetic resonance fingerprinting. Methods Rat brain FIDs were simulated at 9.4 T based on in vivo data (N = 11) and randomly truncated by retaining 8, 16, 32, 64, 128, 256, 512, and 1024 (null truncation) points (denoted as tFID 8 , tFID 16 , … tFID 1024 ). Using a U‐net, 3 CNNs were individually trained (N = 40 000) in time domain only (FID to FID [ FID CNN FID ]), in frequency domain only (spectrum to spectrum [ spec CNN spec ]), and across the domains (FID to spectrum [ FID CNN spec ]) to map the truncated data to their fully sampled versions. The CNNs were tested on the simulated data (N = 5000), and the CNN with the best performance was further tested on the in vivo data, for which the CNN‐predicted fully sampled data were analyzed using the LCModel and the results were compared with those from the original, fully sampled data. Results The best result on the simulated data was obtained with spec CNN spec , which effectively recovered the spectral details even for those input spectra that appear as a hump due to substantial FID truncation (spectra from tFID 16 and tFID 32 ). Overall, its performance was significantly degraded on the in vivo data. Nonetheless, using spec CNN spec , several coupled spins in addition to the major singlets can be quantified from tFID 128 with the error no larger than 10%. Conclusion Upon the availability of more realistically simulated training data, CNNs can also be used in the reconstruction of spectra from truncated FIDs.