4,312 Hits in 6.5 sec

Synthesizing New Retinal Symptom Images by Multiple Generative Models [article]

Yi-Chieh Liu, Hao-Hsiang Yang, Chao-Han Huck Yang, Jia-Hong Huang, Meng Tian, Hiromasa Morikawa, Yi-Chang James Tsai, Jesper Tegner
2019 arXiv   pre-print
Motivated by recent advances in machine learning we specifically explore the potential of generative modeling, using Generative Adversarial Networks (GANs) and style transferring, to facilitate clinical  ...  In the synthesizing step we merge GANs (DCGANs and WGANs architectures) and style transferring for the image generation, whereas the verified step controls the accuracy of the generated images.  ...  Therefore, style transferring can generate new retinal symptom images. Furthermore, generated images from FA images are presented in Fig. 6 and Fig. 7 .  ... 
arXiv:1902.04147v1 fatcat:hcc7m2lnzraujgftnzlarb5r6y

Explainable Diabetic Retinopathy Detection and Retinal Image Generation [article]

Yuhao Niu, Lin Gu, Yitian Zhao, Feng Lu
2021 arXiv   pre-print
Then, to visualize the symptom encoded in the descriptor, we propose Patho-GAN, a new network to synthesize medically plausible retinal images.  ...  We also show that our synthesized images carry the symptoms directly related to diabetic retinopathy diagnosis.  ...  And for a new reference retinal image, it spends dozens of minutes in training new generator.  ... 
arXiv:2107.00296v1 fatcat:t6f3sr4ygngajeb4nedwfl2alq

RF-GANs: A Method to Synthesize Retinal Fundus Images Based on Generative Adversarial Network

Yu Chen, Jun Long, Jifeng Guo, Yugen Yi
2021 Computational Intelligence and Neuroscience  
RF-GAN2 can synthesize realistic retinal fundus images.  ...  To address the problem of data imbalance, this paper proposes a method dubbed retinal fundus images generative adversarial networks (RF-GANs), which is based on generative adversarial network, to synthesize  ...  Acknowledgments is work was supported by the National Natural Science Foundation of China (61300098), the Natural Science Foundation of Heilongjiang Province (F201347), and the Fundamental Research Funds  ... 
doi:10.1155/2021/3812865 pmid:34804140 pmcid:PMC8598326 fatcat:oc256uihj5g6vkyrkvt3xowngy

Accuracy of Using Generative Adversarial Networks for Glaucoma Detection During the COVID-19 Pandemic: A Systematic Review and Bibliometric Analysis (Preprint)

Ali Q. Saeed, Siti Norul Huda Sheikh Abdullah, Jemaima Che-Hamzah, Ahmad Tarmizi Abdul Ghani
2021 Journal of Medical Internet Research  
Among the 59 articles, 30 present actual attempts to synthesize images and provide accurate segmentation/classification using single/multiple landmarks or share certain experiences.  ...  Although this methodology involves an extensive computing budget and optimization process, it saturates the greedy nature of deep learning techniques by synthesizing images and solves major medical issues  ...  Haoqi and Ogawara [51] trained a GAN model to learn the mappings of vessels from retinal images to segmented images for training a model to generate a synthesized image close to a given real image.  ... 
doi:10.2196/27414 pmid:34236992 pmcid:PMC8493455 fatcat:oqcqxrw5nzg7zb42vz33emv6ay

Intelligent Image Synthesis for Accurate Retinal Diagnosis

Dong-Gun Lee, Yonghun Jang, Yeong-Seok Seo
2020 Electronics  
Retinal examination is a commonly performed diagnostic procedure that can be used to inspect the interior of the eye and screen for any pathological symptoms.  ...  The approach proposed in this study can convert vessel images to vessel-centered images with clearer identification, even for low-resolution retinal images.  ...  Supplementary Materials: The datasets used during the current study are available from the following websites (DRIVE: and HRF:  ... 
doi:10.3390/electronics9050767 fatcat:admu5yo72zaulb6wraqxgkyvrm

Attention2AngioGAN: Synthesizing Fluorescein Angiography from Retinal Fundus Images using Generative Adversarial Networks [article]

Sharif Amit Kamran, Khondker Fariha Hossain, Alireza Tavakkoli, Stewart Lee Zuckerbrod
2020 arXiv   pre-print
To eradicate the need for an invasive FA extraction procedure, we introduce an Attention-based Generative network that can synthesize Fluorescein Angiography from Fundus images.  ...  The proposed gan incorporates multiple attention based skip connections in generators and comprises novel residual blocks for both generators and discriminators.  ...  By doing so, they allow diverse and scalable image-to-image translation in multiple domains within a single model.  ... 
arXiv:2007.09191v1 fatcat:umkqgqjhinhezku6g25wb2wvhq

Unilateral acute posterior multifocal placoid pigment epitheliopathy in a convalescent COVID-19 patient

Francisco Olguín-Manríquez, Linda Cernichiaro-Espinosa, Arturo Olguín-Manríquez, Rebeca Manríquez-Arias, Erick Omar Flores-Villalobos, Perla Ayumi Kawakami-Campos
2021 International Journal of Retina and Vitreous  
IRBP is synthesized by retinal photoreceptor cells and acts as an important transport of retinoids between photoreceptors and RPE.  ...  The first phase is related to the onset of the disease and is generally characterized by the development of influenza-like symptoms from mild to moderate.  ... 
doi:10.1186/s40942-021-00312-w pmid:34034832 fatcat:7afhrxo6mfctxgi7zyvturehpy

Modeling and Enhancing Low-quality Retinal Fundus Images [article]

Ziyi Shen, Huazhu Fu, Jianbing Shen, Ling Shao
2020 arXiv   pre-print
However, fundus images captured by operators with various levels of experience have a large variation in quality.  ...  Then, based on the degradation model, a clinically oriented fundus enhancement network (cofe-Net) is proposed to suppress global degradation factors, while simultaneously preserving anatomical retinal  ...  Fig. 3 (b) gives an example with over-exposure and uneven illumination synthesized by our degradation model.  ... 
arXiv:2005.05594v3 fatcat:zaqeggvh3rbgtepo7oz5pnhaey

Quantitative Diagnosis of TCM Syndrome Types Based on Adaptive Resonant Neural Network

Yue Zhao, Yuandi Huang, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
In target recognition, sometimes, there are multiple identical or similar copies of the target to be recognized in the image, and it is difficult to classify and estimate by traditional methods.  ...  The purpose of this study is to further study the correlation between branch retinal vein occlusion and arteriosclerosis by quantitatively measuring retinal vessel diameter and choroidal thickness, to  ...  Acknowledgments is work was supported by School of Chinese Medicine, Hong Kong Baptist University.  ... 
doi:10.1155/2022/2485089 pmid:35785084 pmcid:PMC9249450 fatcat:7rfids5n55hxto3no77jpedtki

Machine Learning Techniques for Ophthalmic Data Processing: A Review

Mhd Hasan Sarhan, Mohammad Ali Nasseri, Daniel Zapp, Mathias Maier, Chris Lohmann, Nassir Navab, Abouzar Eslami
2020 IEEE journal of biomedical and health informatics  
Furthermore, the recent machine learning approaches used for retinal vessels segmentation, and methods of retinal layers and fluid segmentation are reviewed.  ...  Two main imaging modalities are considered in this survey, namely color fundus imaging, and optical coherence tomography.  ...  [90] proposed a framework to synthesize fundus images with their corresponding vessel map segmentation. Two segmentation networks are trained on the real and generated images.  ... 
doi:10.1109/jbhi.2020.3012134 pmid:32750971 fatcat:f4mmjk2ferduzbkpza4hoizzjq

Data augmentation for improving proliferative diabetic retinopathy detection in eye fundus images

Teresa Araujo, Guilherme Aresta, Luis Mendonca, Susana Penas, Carolina Maia, Angela Carneiro, Ana Maria Mendonca, Aurelio Campilho
2020 IEEE Access  
However, the available DR-labeled retinal image datasets have a small representation of images of the severest DR grades, and thus there is lack of PDR cases for training DR grading models.  ...  NVs are generated and introduced in pre-existent retinal images which can then be used for enlarging deep neural networks' training sets.  ...  The method requires vessel tree and lesion binary annotations for training the model. A new retinal image can be synthesized by providing the model the vessel tree and lesion (hemorrhage) masks.  ... 
doi:10.1109/access.2020.3028960 fatcat:3j3owahijvehtdqcizfrvdysna

MultiSDGAN: translation of OCT images to superresolved segmentation labels using multi-discriminators in multi-stages

Paria Jeihouni, Omid Dehzangi, Annahita Amireskandari, Ali R Rezai, Nasser M. Nasrabadi
2021 IEEE journal of biomedical and health informatics  
We aim to avoid early saturation of generator model training leading to poor segmentation accuracies and enhance the process of OCT domain translation by satisfying all the discriminators in multiple scales  ...  This paper proposes a generative adversarial network (GAN) that concurrently learns to increase the image resolution for higher clarity and then segment the retinal layers.  ...  This type of generative modeling competitively employs two trained networks, one being trained to synthesize new data and the other being trained to classify real and synthesized data.  ... 
doi:10.1109/jbhi.2021.3110265 pmid:34516380 fatcat:x355dmanvffotne7lvayswnhya

Assessment of Generative Adversarial Networks for Synthetic Anterior Segment Optical Coherence Tomography Images in Closed-Angle Detection

Ce Zheng, Fang Bian, Luo Li, Xiaolin Xie, Hui Liu, Jianheng Liang, Xu Chen, Zilei Wang, Tong Qiao, Jianlong Yang, Mingzhi Zhang
2021 Translational Vision Science & Technology  
To develop generative adversarial networks (GANs) that synthesize realistic anterior segment optical coherence tomography (AS-OCT) images and evaluate deep learning (DL) models that are trained on real  ...  The GANs can generate realistic AS-OCT images, which can also be used to train DL models.  ...  Generative adversarial networks (GANs), 8 which are inspired by game theory for training a model in an adversarial process, offer a novel method to generate new medical images.  ... 
doi:10.1167/tvst.10.4.34 pmid:34004012 pmcid:PMC8088224 fatcat:3ymhkuwknjerlpnxhg2in5mahu

Early Diagnosis of Multiple Sclerosis Using Swept-Source Optical Coherence Tomography and Convolutional Neural Networks Trained with Data Augmentation

Almudena López-Dorado, Miguel Ortiz, María Satue, María J. Rodrigo, Rafael Barea, Eva M. Sánchez-Morla, Carlo Cavaliere, José M. Rodríguez-Ascariz, Elvira Orduna-Hospital, Luciano Boquete, Elena Garcia-Martin
2021 Sensors  
The original database of OCT images is augmented by a deep convolutional generative adversarial network to expand the CNN's training set.  ...  Results: The retinal structures with greatest discriminant capacity are the GCL++ (44.99% of image points), complete retina (26.71%) and GCL+ (22.93%).  ...  In order to augment the set of CNN training images, synthetic images of retinal thicknesses are generated using GANs.  ... 
doi:10.3390/s22010167 pmid:35009710 pmcid:PMC8747672 fatcat:rea455n3u5dknbeezwxztkwnji

A Comprehensive Review of Deep Learning Strategies in Retinal Disease Diagnosis Using Fundus Images

Balla Goutam, Mohammad Farukh Hashmi, Zong Woo Geem, Neeraj Dhanraj Bokde
2022 IEEE Access  
The same was also reflected in retinal image analysis and successful artificial intelligence models were developed for various retinal disease diagnoses using a wide variety of visual markers obtained  ...  are first illustrated followed by an extensive review of different strategies for each of the five mentioned retinal diseases is presented.  ...  [152] developed a framework for monitoring AMD disease progression from early-stage images by synthesizing future AMD images.  ... 
doi:10.1109/access.2022.3178372 fatcat:65sngfslp5crzchly4tnt4ucy4
« Previous Showing results 1 — 15 out of 4,312 results