An illustration of DeCoLearn training procedure.
Abstract
Deep neural networks for medical image reconstruction are traditionally trained using high-quality ground-truth images as training targets. Recent work on Noise2Noise (N2N) has shown the potential of using multiple noisy measurements of the same object as an alternative to having a ground-truth. However, existing N2N-based methods are not suitable for learning from the measurements of an object undergoing nonrigid deformation. This paper addresses this issue by proposing the deformation-compensated learning (DeCoLearn) method for training deep reconstruction networks by compensating for object deformations. A key component of DeCoLearn is a deep registration module, which is jointly trained with the deep reconstruction network without any ground-truth supervision. We validate DeCoLearn on both simulated and experimentally collected magnetic resonance imaging (MRI) data and show that it significantly improves imaging quality.
Model
Validation on Experimentally-Collected 4D MRI Data
A video of DeCoLearn reconstructed images across different slice. LEFT: inverse multi-coil non-uniform fast Fourier transform (MCNUFFT). RIGHT: DeCoLearn.
A video of DeCoLearn reconstructed images across different respiratory phase. LEFT: inverse multi-coil non-uniform fast Fourier transform (MCNUFFT). RIGHT: DeCoLearn.
An illustration of DeCoLearn reconstructed images across different respiratory phase.
An illustration of DeCoLearn reconstructed images compared against several baseline methods.
Paper
