Deep Image Reconstruction using Unregistered Measurements without Groundtruth
This addresses a key limitation in biomedical imaging by enabling reconstruction without groundtruth data, making it widely applicable to tasks where registered pairs are unavailable.
The paper tackles the problem of needing registered image pairs for training deep learning reconstruction models by proposing U-Dream, an unsupervised method that trains on unregistered, artifact-corrupted images, achieving high-quality reconstructions as validated in accelerated MRI with nonrigid deformations.
One of the key limitations in conventional deep learning based image reconstruction is the need for registered pairs of training images containing a set of high-quality groundtruth images. This paper addresses this limitation by proposing a novel unsupervised deep registration-augmented reconstruction method (U-Dream) for training deep neural nets to reconstruct high-quality images by directly mapping pairs of unregistered and artifact-corrupted images. The ability of U-Dream to circumvent the need for accurately registered data makes it widely applicable to many biomedical image reconstruction tasks. We validate it in accelerated magnetic resonance imaging (MRI) by training an image reconstruction model directly on pairs of undersampled measurements from images that have undergone nonrigid deformations.