HRINet: Alternative Supervision Network for High-resolution CT image Interpolation

TL;DR

This paper introduces HRINet, a novel high-resolution CT image interpolation network that combines supervised and unsupervised training to improve the quality and structural accuracy of interpolated medical images.

Contribution

The paper proposes HRINet, a new network architecture that effectively interpolates high-resolution CT images using an alternative supervision strategy combining ACAI and GANs.

Findings

Significant quantitative improvements on 256² and 512² images.

Enhanced structural correctness of interpolated images.

Tradeoff observed between structural accuracy and image sharpness.

Abstract

Image interpolation in medical area is of high importance as most 3D biomedical volume images are sampled where the distance between consecutive slices significantly greater than the in-plane pixel size due to radiation dose or scanning time. Image interpolation creates a number of new slices between known slices in order to obtain an isotropic volume image. The results can be used for the higher quality of 3D reconstruction and visualization of human body structures. Semantic interpolation on the manifold has been proved to be very useful for smoothing image interpolation. Nevertheless, all previous methods focused on low-resolution image interpolation, and most of them work poorly on high-resolution image. We propose a novel network, High Resolution Interpolation Network (HRINet), aiming at producing high-resolution CT image interpolations. We combine the idea of ACAI and GANs, and propose a novel idea of alternative supervision method by applying supervised and unsupervised training alternatively to raise the accuracy of human organ structures in CT while keeping high quality. We compare an MSE based and a perceptual based loss optimizing methods for high quality interpolation, and show the tradeoff between the structural correctness and sharpness. Our experiments show the great improvement on 256 2 and 5122 images quantitatively and qualitatively.