Skip to main content
. Author manuscript; available in PMC: 2020 May 1.
Published in final edited form as: Magn Reson Med. 2019 Jan 21;81(5):3346–3357. doi: 10.1002/mrm.27641

Figure 1.

Figure 1.

Schematic of the convolutional encoder – model decoder (CEMD) architecture, which utilizes a convolutional neural network (CNN) to learn a low-rank representation of input spectra and uses known models for the baseline and peak components of spectra to train the CNN.