Two-Stage Self-Supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Images

06/29/2021
by   Zhiyang Lu, et al.
13

The thick-slice magnetic resonance (MR) images are often structurally blurred in coronal and sagittal views, which causes harm to diagnosis and image post-processing. Deep learning (DL) has shown great potential to re-construct the high-resolution (HR) thin-slice MR images from those low-resolution (LR) cases, which we refer to as the slice interpolation task in this work. However, since it is generally difficult to sample abundant paired LR-HR MR images, the classical fully supervised DL-based models cannot be effectively trained to get robust performance. To this end, we propose a novel Two-stage Self-supervised Cycle-consistency Network (TSCNet) for MR slice interpolation, in which a two-stage self-supervised learning (SSL) strategy is developed for unsupervised DL network training. The paired LR-HR images are synthesized along the sagittal and coronal directions of input LR images for network pretraining in the first-stage SSL, and then a cyclic in-terpolation procedure based on triplet axial slices is designed in the second-stage SSL for further refinement. More training samples with rich contexts along all directions are exploited as guidance to guarantee the improved in-terpolation performance. Moreover, a new cycle-consistency constraint is proposed to supervise this cyclic procedure, which encourages the network to reconstruct more realistic HR images. The experimental results on a real MRI dataset indicate that TSCNet achieves superior performance over the conventional and other SSL-based algorithms, and obtains competitive quali-tative and quantitative results compared with the fully supervised algorithm.

READ FULL TEXT

page 3

page 8

05/26/2022

Learning to segment with limited annotations: Self-supervised pretraining with regression and contrastive loss in MRI

Obtaining manual annotations for large datasets for supervised training ...
03/31/2021

MR Slice Profile Estimation by Learning to Match Internal Patch Distributions

To super-resolve the through-plane direction of a multi-slice 2D magneti...
06/23/2021

STRESS: Super-Resolution for Dynamic Fetal MRI using Self-Supervised Learning

Fetal motion is unpredictable and rapid on the scale of conventional MR ...
08/29/2022

SB-SSL: Slice-Based Self-Supervised Transformers for Knee Abnormality Classification from MRI

The availability of large scale data with high quality ground truth labe...
03/18/2021

Dementia Severity Classification under Small Sample Size and Weak Supervision in Thick Slice MRI

Early detection of dementia through specific biomarkers in MR images pla...
11/15/2021

Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learning

Gleason grading from histopathology images is essential for accurate pro...
03/20/2020

Self-Supervised Light Field Reconstruction Using Shearlet Transform and Cycle Consistency

The image-based rendering approach using Shearlet Transform (ST) is one ...