EAGLE: An Edge-Aware Gradient Localization Enhanced Loss for CT Image Reconstruction

TL;DR

EAGLE introduces a novel edge-aware loss function for CT image reconstruction that leverages spectral analysis of gradients to improve image sharpness and detail, outperforming existing methods.

Contribution

The paper proposes Eagle-Loss, a new loss function that enhances CT image quality by focusing on edge and gradient features, addressing limitations of traditional loss functions.

Findings

Eagle-Loss improves visual quality of CT reconstructions.

It surpasses state-of-the-art methods across multiple datasets.

It enhances sharpness and detail in reconstructed images.

Abstract

Computed Tomography (CT) image reconstruction is crucial for accurate diagnosis and deep learning approaches have demonstrated significant potential in improving reconstruction quality. However, the choice of loss function profoundly affects the reconstructed images. Traditional mean squared error loss often produces blurry images lacking fine details, while alternatives designed to improve may introduce structural artifacts or other undesirable effects. To address these limitations, we propose Eagle-Loss, a novel loss function designed to enhance the visual quality of CT image reconstructions. Eagle-Loss applies spectral analysis of localized features within gradient changes to enhance sharpness and well-defined edges. We evaluated Eagle-Loss on two public datasets across low-dose CT reconstruction and CT field-of-view extension tasks. Our results show that Eagle-Loss consistently improves the visual quality of reconstructed images, surpassing state-of-the-art methods across various network architectures. Code and data are available at \url{https://github.com/sypsyp97/Eagle_Loss}.