Yao Sui1,2, Onur Afacan1,2, Ali Gholipour1,2, and Simon K Warfield1,2
1Harvard Medical School, Boston, MA, United States, 2Boston Children's Hospital, Boston, MA, United States
1Harvard Medical School, Boston, MA, United States, 2Boston Children's Hospital, Boston, MA, United States
We developed a deep learning methodology that enables high-quality MRI super-resolution reconstruction through powerful deep learning techniques, while in parallel, eliminates the dependence on training datasets, and in turn, allows super-resolution tailored to the individual patient.
Architecture of our SRR approach. The generative network offers an HR image excited by an input. The degradation networks degrade the output of the generative network to fit the LR inputs, respectively, with an MSE loss. A TV criterion is used to regularize the generative network. The input can be an arbitrary volume of the same size as the HR reconstruction. The training allows for the SRR tailored to the individual patient as it is performed on the LR images acquired from the specific patient.
Qualitative results on the HCP dataset. Our approach (SSGNN) yielded the best image quality. In particular, SSGNN offered finer anatomical structures of the cerebellum at a lower noise level, and in turn, achieved superior reconstructions to the direct HR acquisitions as well as the five baselines.
