Lesion Detection and Grading of Diabetic Retinopathy via Two-Stages Deep Convolutional Neural Networks

Yang, Yehui; Li, Tao; Wensi, Li,; Wu, Haimeng; Wang, Fan; Zhang, Wensheng

doi:10.1007/978-3-319-66179-7_61

Cited by 175 publications

(109 citation statements)

References 33 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…For the sake of generality, we select the o O(Antony 2016), a CNN based method within the top-3 entries on Kaggle's challenge. Even now, the performance of o O is still equivalent to the latest method (Wang et al 2017). This method is trained and tested on the image level DR severity stage.…”

Section: Related Work Diabetic Retinopathy Detectionmentioning

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

Section: Related Work Diabetic Retinopathy Detectionmentioning

confidence: 99%

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

Niu

et al. 2019

AAAI

View full text Add to dashboard Cite

show abstract

“…Krause, Jonathan, et al finds that the adjudicated DR grades improve performance substantially in detecting DR [7]. Yang, Yehui, et al developed an algorithm based on two-stage deep convolution neural networks [8]. The algorithm finds the lesion and severity grades in DR in the first stage.…”

Section: Literature Surveymentioning

confidence: 99%

A Deep Learning Neural Network for Detecting the Diabetic Retinopathy

Kumar¹,

Kumar²,

Koushik³

et al. 2019

IJITEE

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is the leading cause of disease to blindness of people globally. The retinal screening examinations of diabetic patients is needed to prevent the disease. There are many untreated and undiagnosed cases present in especially in India. DR requires smart technique to detect it. In this paper, we proposed a deep learning based architecture for detecting the DR. The experiments are done on the DR Dataset available in UCI machine Learning Repository. The results obtained from the experiments are satisfactory.

show abstract

“…In particular, CNN processes the classification task of image which is consumed by several authors. The study in this domain has segmentation of features, and blood vessels [3,4]. Deep CNNs are actually proposed for the purpose of natural image classification, as well as current research is results in performing fast DR fundus images classification.…”

Section: Introductionmentioning

confidence: 99%

Gradient Descent Based Hyparameter Tuning of Xception Architecture for Diabetic Retinopathy Segmentation and Classification

Yazhini,

Loganathan

2020

IJEAT

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a widespread difficulty of diabetes and is considered as a main reason for vision loss in all over the globe. Several difficulties of DR can be avoided by controlling blood glucose level and timely medication. In real time, it is difficult to detect the DR and consumes more time in a manual way. This paper introduces a new Gradient Descent (GD) based Hyper parameter tuned Xception model called GD-Xception model to detect and classify DR images in an effective way. The GD-Xception model involves a series of subprocesses namely preprocessing, segmentation, feature extraction and classification. A set of extensive simulation takes place to ensure the effective outcome of the presented GD-Xception model. The presented model is tested using a DR dataset from Kaggle. The extensive experimental study clearly portrayed the superior outcome of the GD-Xception model with the maximum accuracy, sensitivity and specificity of 99.39%, 98.50% and 99.62% respectively.

show abstract

Lesion Detection and Grading of Diabetic Retinopathy via Two-Stages Deep Convolutional Neural Networks

Cited by 175 publications

References 33 publications

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

Pathological Evidence Exploration in Deep Retinal Image Diagnosis

A Deep Learning Neural Network for Detecting the Diabetic Retinopathy

Gradient Descent Based Hyparameter Tuning of Xception Architecture for Diabetic Retinopathy Segmentation and Classification

Contact Info

Product

Resources

About