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

arXiv: https://arxiv.org/abs/2403.10695 · HTML: https://mlsanity.com/paper/2403.10695/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 56 references that are in the map.
- First posted on arXiv 15 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [Structure-Preserving Super Resolution with Gradient Guidance](https://mlsanity.com/paper/2003.13081/) (2020)
- [A Gentle Introduction to Deep Learning in Medical Image Processing](https://mlsanity.com/paper/1810.05401/) (2018)
- [PYRO-NN: Python Reconstruction Operators in Neural Networks](https://mlsanity.com/paper/1904.13342/) (2019)
- [Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2310.04148/) (2023)
- [Gradient Variance Loss for Structure-Enhanced Image Super-Resolution](https://mlsanity.com/paper/2202.00997/) (2022)
- [Motion-compensated MR CINE reconstruction with reconstruction-driven motion estimation](https://mlsanity.com/paper/2302.02504/) (2023)
- [Edge-Aware Deep Image Deblurring](https://mlsanity.com/paper/1907.02282/) (2019)
- [Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Series](https://mlsanity.com/paper/2401.16039/) (2024)
- [Projection-to-Projection Translation for Hybrid X-ray and Magnetic Resonance Imaging](https://mlsanity.com/paper/1911.08163/) (2019)
- [Guided Frequency Loss for Image Restoration](https://mlsanity.com/paper/2309.15563/) (2023)
- [Sub2Full: split spectrum to boost OCT despeckling without clean data](https://mlsanity.com/paper/2401.10128/) (2024)

## Built on by (most cited first, 5 of 5)

- [TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation](https://mlsanity.com/paper/2405.16847/) (2024)
- [Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?](https://mlsanity.com/paper/2506.02093/) (2025)
- [One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models](https://mlsanity.com/paper/2511.10629/) (2025)
- [Local-Order Auxiliary Losses Can Improve Autoencoder Reconstruction](https://mlsanity.com/paper/2504.04202/) (2025)
- [An update to PYRO-NN: A Python Library for Differentiable CT Operators](https://mlsanity.com/paper/2511.08427/) (2025)

## Abstract (arXiv)

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 urlhttps://github.com/sypsyp97/EagleLoss.