Automatic Generation of Synthetic Retinal Fundus Images: Vascular Network

Bonaldi, Lorenza; Menti, Elisa; Ballerini, Lucia; Ruggeri, Alfredo; Trucco, Emanuele

doi:10.1016/j.procs.2016.07.010

Cited by 28 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in [2] Fiorini et al used a system that generated the retinal background and the fovea and another system to generate the optic disc by using a large dictionary of patches with no vessels that are later registered. After that, the authors developed a complementary work that is mainly focused on vessel generation [3]. Although their method allows the generation of high-quality and large resolution images, the process of concatenating the generation of the main parts of the images is a considerable complex computational algorithm that relies on how well the images are registered.…”

Section: Introductionmentioning

confidence: 99%

Retinal Image Synthesis for Glaucoma Assessment Using DCGAN and VAE Models

Diaz-Pinto

Colomer

Naranjo

et al. 2018

Intelligent Data Engineering and Automated Learning – IDEAL 2018

View full text Add to dashboard Cite

The performance of a Glaucoma assessment system is highly affected by the number of labelled images used during the training stage. However, labelled images are often scarce or costly to obtain. In this paper, we address the problem of synthesising retinal fundus images by training a Variational Autoencoder and an adversarial model on 2357 retinal images. The innovation of this approach is in synthesising retinal images without using previous vessel segmentation from a separate method, which makes this system completely independent. The obtained models are image synthesizers capable of generating any amount of cropped retinal images from a simple normal distribution. Furthermore, more images were used for training than any other work in the literature. Synthetic images were qualitatively evaluated by 10 clinical experts and their consistency were estimated by measuring the proportion of pixels corresponding to the anatomical structures around the optic disc. Moreover, we calculated the mean-squared error between the average 2D-histogram of synthetic and real images, obtaining a small difference of 3 × 10 −4. Further analysis of the latent space and cup size of the images was performed by measuring the Cup/Disc ratio of synthetic images using a state-of-the-art method. The results obtained from this analysis and the qualitative and quantitative evaluation demonstrate that the synthesised images are anatomically consistent and the system is a promising step towards a model capable of generating labelled images.

show abstract

Section: Introductionmentioning

confidence: 99%

Retinal Image Synthesis for Glaucoma Assessment Using DCGAN and VAE Models

Diaz-Pinto

Colomer

Naranjo

et al. 2018

Intelligent Data Engineering and Automated Learning – IDEAL 2018

View full text Add to dashboard Cite

show abstract

“…The traditional biomedical imaging synthesizing uses the medical and biological prior knowledge accumulated by humans, combined with complex simulation methods to produce realistic results. Probably most well-known efforts are the work (Fiorini et al 2014), the work (Bonaldi et al 2016), GENESIS (Bower, Cornelis, and Beeman 2015), NEURON (Carnevale and Hines 2006), L-Neuron (Ascoli , synthesized image given a binary tubular annotation and a reference image. Although their generated images could show pleasant visual appearance, the diabetic retinopathy symptoms and retina physiological details are either lost or incorrect as verified by the ophthalmologists.…”

Section: Synthesizing Biomedical Imagesmentioning

confidence: 99%

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

Niu

et al. 2019

AAAI

View full text Add to dashboard Cite

Though deep learning has shown successful performance in classifying the label and severity stage of certain disease, most of them give few evidence on how to make prediction. Here, we propose to exploit the interpretability of deep learning application in medical diagnosis. Inspired by Koch's Postulates, a well-known strategy in medical research to identify the property of pathogen, we define a pathological descriptor that can be extracted from the activated neurons of a diabetic retinopathy detector. To visualize the symptom and feature encoded in this descriptor, we propose a GAN based method to synthesize pathological retinal image given the descriptor and a binary vessel segmentation. Besides, with this descriptor, we can arbitrarily manipulate the position and quantity of lesions. As verified by a panel of 5 licensed ophthalmologists, our synthesized images carry the symptoms that are directly related to diabetic retinopathy diagnosis. The panel survey also shows that our generated images is both qualitatively and quantitatively superior to existing methods.

show abstract

“…The general synthesis of blood vessels (more from a medical perspective) is discussed in [276] where Generative Adversarial Networks (GANs) are employed. The synthesis of fundus imagery is discussed entirely with a medical background [24,36,64,75] where again the latter two papers rely on GAN technology. Within the biometric context, finger vein [87] as well as sclera [42] data synthesis has been discussed and rather realistic results have been achieved.…”

Section: Eye-based Vascular Traitsmentioning

confidence: 99%

“…as provided by Volk 23 or Remidio. 24 The D-EYE system excels by its small-scale device being magnetically attached to an iPhone. 25 It has to be noted that all these reported solutions for mobile fundus photography (i.e.…”

Section: Eye-based Vascular Traitsmentioning

confidence: 99%

See 1 more Smart Citation

State of the Art in Vascular Biometrics

Uhl

2019

Handbook of Vascular Biometrics

View full text Add to dashboard Cite

The investigation of vascular biometric traits has become increasingly popular during the last years. This book chapter provides a comprehensive discussion of the respective state of the art, covering hand-oriented techniques (finger vein, palm vein, (dorsal) hand vein and wrist vein recognition) as well as eye-oriented techniques (retina and sclera recognition). We discuss commercial sensors and systems, major algorithmic approaches in the recognition toolchain, available datasets, public competitions and open-source software, template protection schemes, presentation attack(s) (detection), sample quality assessment, mobile acquisition and acquisition on the move, and finally eventual disease impact on recognition and template privacy issues.

show abstract

Automatic Generation of Synthetic Retinal Fundus Images: Vascular Network

Cited by 28 publications

References 17 publications

Retinal Image Synthesis for Glaucoma Assessment Using DCGAN and VAE Models

Retinal Image Synthesis for Glaucoma Assessment Using DCGAN and VAE Models

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

State of the Art in Vascular Biometrics

Contact Info

Product

Resources

About