Structure-Consistent Restoration Network for Cataract Fundus Image Enhancement

Li, Heng; Liu, Haofeng; Fu, Huazhu; Shu, Hai; Zhao, Yitian; Hu, Yan; Liu, Jiang

doi:10.1007/978-3-031-16434-7_47

Cited by 21 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Built on this same degradation pipeline, Liu et al propose the Pyramid Constraint Network (PCENet) to enhance clinically-relevant representation [16]. Li et al present the Structure-Consistent Restoration Network (SCRNet) for cataract fundus images, which lays its foundation on the consistency of high-frequency components [13]. On the other hand, unpaired image translation based enhancement methods rely on adversarial training and do not require explicit modeling of image degradation.…”

Section: Introductionmentioning

confidence: 99%

Learning Enhancement From Degradation: A Diffusion Model For Fundus Image Enhancement

Cheng¹,

Li²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

The quality of a fundus image can be compromised by numerous factors, many of which are challenging to be appropriately and mathematically modeled. In this paper, we introduce a novel diffusion model based framework, named Learning Enhancement from Degradation (LED), for enhancing fundus images. Specifically, we first adopt a data-driven degradation framework to learn degradation mappings from unpaired high-quality to low-quality images. We then apply a conditional diffusion model to learn the inverse enhancement process in a paired manner. The proposed LED is able to output enhancement results that maintain clinically important features with better clarity. Moreover, in the inference phase, LED can be easily and effectively integrated with any existing fundus image enhancement framework. We evaluate the proposed LED on several downstream tasks with respect to various clinically-relevant metrics, successfully demonstrating its superiority over existing state-of-the-art methods both quantitatively and qualitatively. The source code is available at https://github.com/QtacierP/LED.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning Enhancement From Degradation: A Diffusion Model For Fundus Image Enhancement

Cheng¹,

Li²,

Huang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Traditional fundus image enhancement methods [3]- [6] were mainly based on handcrafted priors, and they could not satisfactorily handle the complexity of varied low-quality cases. To solve this issue, the deep learning methods were proposed to learn more general priors from large amounts of paired low-quality and highquality images [7]- [14]. Therefore, the existing methods resort to either i) synthetic image pairs, such as synthesizing lowquality fundus images by degrading real high-quality ones [7], or ii) unpaired supervision models, such as CycleGAN-like ones [11], [15], for enhancement.…”

mentioning

confidence: 99%

Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework

Erjian¹,

Fu²,

Zhou³

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep learning based image enhancement models have largely improved the readability of fundus images in order to decrease the uncertainty of clinical observations and the risk of misdiagnosis. However, due to the difficulty of acquiring paired real fundus images at different qualities, most existing methods have to adopt synthetic image pairs as training data. The domain shift between the synthetic and the real images inevitably hinders the generalization of such models on clinical data. In this work, we propose an end-to-end optimized teacherstudent framework to simultaneously conduct image enhancement and domain adaptation. The student network uses synthetic pairs for supervised enhancement, and regularizes the enhancement model to reduce domain-shift by enforcing teacher-student prediction consistency on the real fundus images without relying on enhanced groundtruth. Moreover, we also propose a novel multi-stage multiattention guided enhancement network (MAGE-Net) as the backbones of our teacher and student network. Our MAGE-Net utilizes multi-stage enhancement module and retinal structure preservation module to progressively integrate the multi-scale features and simultaneously preserve the retinal structures for better fundus image quality enhancement. Comprehensive experiments on both real and synthetic datasets demonstrate that our framework outperforms the baseline approaches. Moreover, our method also benefits the downstream clinical tasks.

show abstract

A Novel Local-Global Spatial Attention Network for Cortical Cataract Classification in AS-OCT

Xiao¹,

Zhang²,

Sun³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Structure-Consistent Restoration Network for Cataract Fundus Image Enhancement

Cited by 21 publications

References 22 publications

Learning Enhancement From Degradation: A Diffusion Model For Fundus Image Enhancement

Learning Enhancement From Degradation: A Diffusion Model For Fundus Image Enhancement

Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework

A Novel Local-Global Spatial Attention Network for Cortical Cataract Classification in AS-OCT

Contact Info

Product

Resources

About