I-SECRET: Importance-Guided Fundus Image Enhancement via Semi-supervised Contrastive Constraining

Cheng, Pujin; Lin, Li; Huang, Yijin; Lyu, Junyan; Tang, Xiaoying

doi:10.1007/978-3-030-87237-3_9

Cited by 22 publications

(33 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of deep learning, fundus image restoration has witnessed a significant progress. CNNs [1], [2], [22], [23], [34]- [39] apply a powerful learning model to restore LQ fundus images. For instance, Zhao et al [23] propose an end-to-end deep CNN to remove the lesions on the fundus images of cataract patients.…”

Section: A Fundus Image Restorationmentioning

confidence: 99%

“…As shown in Fig. 1 (d), the two CNN-based methods [1], [2] trained with synthesized data fail in real fundus image restoration.…”

Section: Introductionmentioning

confidence: 98%

“…Restoration results of models trained with synthetic data on RF. The two CNN-based methods, I-SECRET [1] and Cofe-Net [2], fail to reconstruct the real clinical degraded fundus images. related macular degeneration [11], [12].…”

Section: Introductionmentioning

confidence: 99%

“…Recently, deep Convolutional Neural Networks (CNNs) have been widely used in natural image restoration and enhancement [16]- [18], e.g., super resolution [19]- [25], deraining [26], deblurring [27]- [31], enlighten [32], [33], etc. Inspired by the success of natural image restoration, CNNs have also been applied to fundus image restoration [1], [2], [22], [23], [34]- [39]. Although impressive results have been achieved, CNN-based methods show limitations in capturing long-range dependencies.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical Benchmark

Deng

Cai

Chen

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Section: A Fundus Image Restorationmentioning

confidence: 99%

“…As shown in Fig. 1 (d), the two CNN-based methods [1], [2] trained with synthesized data fail in real fundus image restoration.…”

Section: Introductionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical Benchmark

Deng

Cai

Chen

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

“…Multimodal ophthalmic images can be effectively employed to extract retinal structures, identify biomarkers, and diagnose diseases. For example, fundus im-ages can depict critical anatomical structures such as the macula, optic disc, and retinal vessels (RVs) [3,11,14]. Optical coherence tomography angiography (OCTA) can efficiently and accurately generate volumetric angiography images [15,21].…”

Section: Introductionmentioning

confidence: 99%

Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-teacher Multi-target Domain Adaptation

Peng¹,

Li²,

Cheng³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Unsupervised domain adaptation has been proposed recently to tackle the so-called domain shift between training data and test data with different distributions. However, most of them only focus on singletarget domain adaptation and cannot be applied to the scenario with multiple target domains. In this paper, we propose RVms, a novel unsupervised multi-target domain adaptation approach to segment retinal vessels (RVs) from multimodal and multicenter retinal images. RVms mainly consists of a style augmentation and transfer (SAT) module and a dual-teacher knowledge distillation (DTKD) module. SAT augments and clusters images into source-similar domains and source-dissimilar domains via Bézier and Fourier transformations. DTKD utilizes the augmented and transformed data to train two teachers, one for source-similar domains and the other for source-dissimilar domains. Afterwards, knowledge distillation is performed to iteratively distill different domain knowledge from teachers to a generic student. The local relative intensity transformation is employed to characterize RVs in a domain invariant manner and promote the generalizability of teachers and student models. Moreover, we construct a new multimodal and multicenter vascular segmentation dataset from existing publicly-available datasets, which can be used to benchmark various domain adaptation and domain generalization methods. Through extensive experiments, RVms is found to be very close to the target-trained Oracle in terms of segmenting the RVs, largely outperforming other state-of-the-art methods.

show abstract

Structure-Consistent Restoration Network for Cataract Fundus Image Enhancement

Liu

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

I-SECRET: Importance-Guided Fundus Image Enhancement via Semi-supervised Contrastive Constraining

Cited by 22 publications

References 23 publications

RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical Benchmark

RFormer: Transformer-Based Generative Adversarial Network for Real Fundus Image Restoration on a New Clinical Benchmark

Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-teacher Multi-target Domain Adaptation

Structure-Consistent Restoration Network for Cataract Fundus Image Enhancement

Contact Info

Product

Resources

About