Non-rigid retinal image registration using an unsupervised structure-driven regression network

Zou, Beiji; He, Zhiyou; Zhao, Rongchang; Zhu, Chengzhang; Liao, Wangmin; Li, Shuo

doi:10.1016/j.neucom.2020.04.122

Cited by 15 publications

(12 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The findings were extracted and categorized according to the datasets, similarity metrics, modalities, transformation, and ROIs. Additionally, evaluation metrics, including DSCs and time were reported in tables; it was found that the least run-time was 0.0027s and 0.021s, respectively, for brain and retinal images [92,94], and the best mean DSC was 97% for the brain images [79]. Furthermore, the novelties of all papers are summarized (Table 4) to provide new ideas for active readers in…”

Section: Discussionmentioning

confidence: 99%

“…MRI [3,80,81,64,66,68,69,71,73,79,82,83,84,85] and CT [86,87,88] imaging were used at about 61% and 22%, respectively. In the next rank, X-ray [73,89,90] constitutes about 5%, and there are Multispectral imaging (MSI) [91,92], the fluorescein angiographic image [93,94], and the optical coherence tomography [94] fundus image for retina imaging, accumulated about 8%.…”

Section: Literature Review Analysismentioning

confidence: 99%

See 1 more Smart Citation

Medical image registration using unsupervised deep neural network: A scoping literature review

Abbasi

Tavakoli

Boveiri

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Literature Review Analysismentioning

confidence: 99%

Medical image registration using unsupervised deep neural network: A scoping literature review

Abbasi

Tavakoli

Boveiri

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

“…Image registration. Zou et al (2020) proposed an unsupervised architecture for non-rigid retinal image registration. They formulated the image registration task as a parameterized deformation function.…”

Section: Image Processingmentioning

confidence: 99%

Applications of Deep Learning in Fundus Images: A Review

Li¹,

Bo²,

Hu³

et al. 2021

Preprint

View full text Add to dashboard Cite

The use of fundus images for the early screening of eye diseases is of great clinical importance. Due to its powerful performance, deep learning is becoming more and more popular in related applications, such as lesion segmentation, biomarkers segmentation, disease diagnosis and image synthesis. Therefore, it is very necessary to summarize the recent developments in deep learning for fundus images with a review paper. In this review, we introduce 143 application papers with a carefully designed hierarchy. Moreover, 33 publicly available datasets are presented. Summaries and analyses are provided for each task. Finally, limitations common to all tasks are revealed and possible solutions are given. We will also release and regularly update the state-of-the-art results and newly-released datasets at https://github.com/nkicsl/Fundus Review to adapt to the rapid development of this field.

show abstract

“…[3][4][5][6][7] Although several studies have been proposed, it is still a challenge since most methods are design to solve specific problems and the lack of ground truth would degrade the clinical practice. 8 To solve abovementioned problems, a retinal image registration framework is proposed. In this work, we generate an initial matching integration method based on Bayesian theory.…”

Section: Introductionmentioning

confidence: 99%

“…Many features have been applied to retinal images, including bifurcations of retinal vasculature, vasculature skeletons, fovea, optic disc, and other morphological features 3–7 . Although several studies have been proposed, it is still a challenge since most methods are design to solve specific problems and the lack of ground truth would degrade the clinical practice 8 …”

Section: Introductionmentioning

confidence: 99%

Retinal fundus image registration framework using Bayesian integration and asymmetric Gaussian mixture model

Zhang

Jia

Zhuo

et al. 2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Retinal image registration, which is applied in diagnosing and treating eye diseases, plays an important role in medical image analysis. Existing methods suffer from problems due to different imaging viewpoints, times, quality, modalities, and retinal disasters. In this paper, we propose an efficient retinal images registration framework that overcomes these challenges without supervision. We present a layer-wise matching method to achieve a uniform distribution of features in both image-space and scale-space. Then, a novel method called Bayesian integration is generated to accumulate more meaningful inputs. We use the results of different matches as priors, assign a score to each match, and categorize them using a dynamic threshold. Finally, in accordance with previous work, we transform the problem into a probabilistic model, with the asymmetric Gaussian mixture model representing the distribution. A robust estimation is performed on a non-rigid transformation. The experimental results demonstrate that our proposed framework is robust to kinds of retinal image degradation and produces a more stable and accurate result than state-of-the-art methods.

show abstract

Non-rigid retinal image registration using an unsupervised structure-driven regression network

Cited by 15 publications

References 36 publications

Medical image registration using unsupervised deep neural network: A scoping literature review

Medical image registration using unsupervised deep neural network: A scoping literature review

Applications of Deep Learning in Fundus Images: A Review

Retinal fundus image registration framework using Bayesian integration and asymmetric Gaussian mixture model

Contact Info

Product

Resources

About