New Deep Neural Nets for Fine-Grained Diabetic Retinopathy Recognition on Hybrid Color Space

Vo, Holly H.; Verma, Abhishek

doi:10.1109/ism.2016.0049

Cited by 82 publications

(59 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different classification tasks were performed. For example, binary DR classification (Healthy vs DR) task was performed in [33,35], while DR classification with 5 classes was considered in [36,37,32].…”

Section: Discussionmentioning

confidence: 99%

“…In Section 5.1, the performance of the proposed DR classification system is compared with some state-of-the-art methods [39,37] on the EyePACS dataset. In Section 5.2, the performance of the proposed DR classification system is compared with some state-of-the-art methods [36,37] on the Messidor database [9]. A brief summary is provided in Section 5.3.…”

Section: Chapter 5 Performance Evaluation Of the Diabetic Retinopathymentioning

confidence: 99%

“…In this section, we test the performance of the proposed automatic DR classification system on another widely used independent diabetic retinopathy dataset, namely the Messidor database [9], to show the generalization ability of the proposed system. As the label distribution and image quality of the Messidor database are different from those of the EyePACS dataset, thus the basic EDA of Messidor database is first given followed by the comparison of our results with the state-of-the-art results [36,78,37].…”

Section: Performance Evaluation On the Messidor Databasementioning

confidence: 99%

See 2 more Smart Citations

Diabetic Retinopathy Classification Using an Efficient Convolutional Neural Network

Gao

Leung

Miao

2019

2019 IEEE International Conference on Agents (ICA)

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is a diabetic complication that affects the eyes and may lead to blurred vision or even blindness. The diagnosis of DR through retinal fundus images is traditionally performed by ophthalmologists who inspect for the presence and significance of many subtle features, a process which is cumbersome and timeconsuming. As there are many undiagnosed and untreated cases of DR, DR screening of all diabetic patients is a huge challenge. Deep convolutional neural network (CNN) has rapidly become a powerful tool for analyzing medical images. There have been previous works which use deep learning models to detect DR automatically. However, these methods employed very deep CNNs which require vast computational resources. Thus, there is a need for more computationally efficient deep learning models for automatic DR diagnosis. The primary objective of this research is to develop a robust and computationally efficient deep learning model to diagnose DR automatically. In the first part of this thesis, we propose a computationally efficient deep CNN model MobileNet-Dense which is based on the recently proposed MobileNetV2 and DenseNet models. The effectiveness of the proposed MobileNet-Dense model is demonstrated using two widely used benchmark datasets, CIFAR-10 and CIFAR-100.In the second part of the thesis, we propose an automatic DR classification system based on the ensemble of the proposed MobileNet-Dense model and the Mo-bileNetV2 model. The performance of our system is evaluated and compared with iii Abstract some of the state-of-the-art methods using two independent DR datasets, the Eye-PACS dataset and the Messidor database. On the EyePACS dataset, our system achieves a quadratic weighted kappa (QWK) score of 0.852 compared to a QWK score of 0.849 achieved by the benchmark method while using 32% fewer parameters and 73% fewer multiply-adds (MAdds). On the Messidor database, our system outperforms the state-of-the-art method on both Normal/Abnormal and Referable/Non-Referable classification tasks.iv

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Chapter 5 Performance Evaluation Of the Diabetic Retinopathymentioning

confidence: 99%

Section: Performance Evaluation On the Messidor Databasementioning

confidence: 99%

See 1 more Smart Citation

Diabetic Retinopathy Classification Using an Efficient Convolutional Neural Network

Gao

Leung

Miao

2019

2019 IEEE International Conference on Agents (ICA)

View full text Add to dashboard Cite

show abstract

“…AUC Acc. Lesion-based [12] 0.760 -Fisher Vector [12] 0.863 -VNXK/LGI [18] 0.887 0.893 CKML Net/LGI [18] 0.891 0.897 Comprehensive CAD [14] 0.91 -Expert A [14] 0.94 -Expert B [14] 0.92 -Zoom-in-Net 0.957 0.911 Table 3. AUC for referable/nonreferable Method AUC Acc.…”

Section: Methodsmentioning

confidence: 99%

“…For referable/nonreferable, Messidor Grade 0 and 1 is considered as nonreferable, while Grade 2 and 3 is defined to be referable to specialists. 10-fold crossvalidation on entire Messidor is introduced to be compatible with [18,12]. For normal/abnormal classification, the SVM is trained using extracted features from the training set of EyePACS and tested on entire Messidor.…”

Section: Methodsmentioning

confidence: 99%

Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection

Wang

Yin

Shi

et al. 2017

Lecture Notes in Computer Science

230

119

View full text Add to dashboard Cite

Abstract. We propose a convolution neural network based algorithm for simultaneously diagnosing diabetic retinopathy and highlighting suspicious regions. Our contributions are two folds: 1) a network termed Zoom-in-Net which mimics the zoom-in process of a clinician to examine the retinal images. Trained with only image-level supervisions, Zoomin-Net can generate attention maps which highlight suspicious regions, and predicts the disease level accurately based on both the whole image and its high resolution suspicious patches. 2) Only four bounding boxes generated from the automatically learned attention maps are enough to cover 80% of the lesions labeled by an experienced ophthalmologist, which shows good localization ability of the attention maps. By clustering features at high response locations on the attention maps, we discover meaningful clusters which contain potential lesions in diabetic retinopathy. Experiments show that our algorithm outperform the stateof-the-art methods on two datasets, EyePACS and Messidor.

show abstract

Semi-supervised Adversarial Learning for Diabetic Retinopathy Screening

Liu

Xin

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

New Deep Neural Nets for Fine-Grained Diabetic Retinopathy Recognition on Hybrid Color Space

Cited by 82 publications

References 22 publications

Diabetic Retinopathy Classification Using an Efficient Convolutional Neural Network

Diabetic Retinopathy Classification Using an Efficient Convolutional Neural Network

Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection

Semi-supervised Adversarial Learning for Diabetic Retinopathy Screening

Contact Info

Product

Resources

About