Coarse-Super-Resolution-Fine Network (CoSF-Net): A Unified End-to-End Neural Network for 4D-MRI with Simultaneous Motion Estimation and Super-Resolution

TL;DR

This paper introduces CoSF-Net, a deep learning model that simultaneously enhances 4D-MRI resolution and estimates motion, improving image quality for better tumor management in radiation therapy.

Contribution

The paper presents a novel unified neural network that jointly performs super-resolution and motion estimation for 4D-MRI, addressing limitations of current methods.

Findings

Accurately estimates deformable vector fields between respiratory phases.

Improves spatial resolution of 4D-MRI with enhanced anatomical features.

Demonstrates robustness and feasibility on multiple patient datasets.

Abstract

Four-dimensional magnetic resonance imaging (4D-MRI) is an emerging technique for tumor motion management in image-guided radiation therapy (IGRT). However, current 4D-MRI suffers from low spatial resolution and strong motion artifacts owing to the long acquisition time and patients' respiratory variations; these limitations, if not managed properly, can adversely affect treatment planning and delivery in IGRT. Herein, we developed a novel deep learning framework called the coarse-super-resolution-fine network (CoSF-Net) to achieve simultaneous motion estimation and super-resolution in a unified model. We designed CoSF-Net by fully excavating the inherent properties of 4D-MRI, with consideration of limited and imperfectly matched training datasets. We conducted extensive experiments on multiple real patient datasets to verify the feasibility and robustness of the developed network. Compared with existing networks and three state-of-the-art conventional algorithms, CoSF-Net not only accurately estimated the deformable vector fields between the respiratory phases of 4D-MRI but also simultaneously improved the spatial resolution of 4D-MRI with enhanced anatomic features, yielding 4D-MR images with high spatiotemporal resolution.