Quality Evaluation of Fundus Images using Transfer Learning

Pin, Kuntha; Kim, Jung-Yeon; Chang, Jee Ho; Nam, Yunyoung

doi:10.1109/csci51800.2020.00139

Cited by 3 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The DR detection model (DR2Net) was approved for its excellency by its results compared to others. The grading DR model (DR5Net) grades the DR into five classes and not 3 classes like others [10,23]. The achieved results outperform the results of comparable ultramodern techniques, as shown in Table 9.…”

Section: B Results Of Proposed Cnn Models (Methods 2)mentioning

confidence: 86%

“…Figure 3 shows an example of these lesions in the human retina images. Convolutional Neural Network (CNN) strongly appear to be the best method for the automated classification of digital medical images [10][11][12][13]. DR could be diagnosed directly by detecting abnormalities using CNN.…”

Section: Introductionmentioning

confidence: 99%

“…These techniques include the use of image preprocessing techniques such as morphology, enhancement filters, edge detection, histogram manipulation, and the use of neural networks, support vector machines as classification techniques, etc. Deep learning methods such asConvolutional Neural Network (CNN) strongly appear to be the best method for the automated classification of digital medical images[10][11][12][13]. DR could be diagnosed directly by detecting abnormalities using CNN.…”

mentioning

confidence: 99%

“…In the final step, all extracted lesions were classified by the SVM classifier, and they achieved 82.39% sensitivity. We have reviewed methods to detect and classify lesions in fundus images based on CNN's deep learning.Shaban et al proposed in[10] a deep convolutional neural network (CNN) to automatically classify DR severity grades into (1-no DR), (2-moderate DR, which is a combination of two grades (mild and moderate DR)), and (3-severe DR, which is a group of severe NPDR and proliferative DR (PDR)) with a validation accuracy of 88%-89%, sensitivity of 87%Fundus images used in this study are publicly available from EyePACS[22]. Abr`amoff et al[23] used multiple CNNs for the automatic detection of DR lesions in graded fundus images.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Diabetic Retinopathy Detection and Grading using Deep learning

BERBAR¹

2022

Menoufia Journal of Electronic Engineering Research

View full text Add to dashboard Cite

One of the complications of diabetes disease is diabetic retinopathy (DR). Diabetic patients may suffer from total loss of sight. That's if it is not detected and medicated early enough. The early detection of DR is very important during funds screening on a regular basis. Detection and grading of DR are difficult because most fundus images suffer from undersaturation and noise. This paper proposes a new enhancement process as a solution to the poor quality of fundus images. It also proposes two architectures for convolutional neural network (CNN) models. The first one is the binary classifier of DR images into normal and abnormal. The second CNN architecture to classify the severity grades of DR. In this study, we also utilized different pre-trained convolutional neural network models to show the impact on the performance of the use of transfer learning from pre-trained CNN models vs newly defined architectures. The pre-trained CNN models and the two new proposed CNN models are tested using Messidor1, Messidor2, and Kaggle EyePACS datasets. The proposed binary classifier model results in F1-scores of 0.9387, 0.9629, and 0.9430 on the Messidor-1, Messidor-2, and EyePACS datasets, respectively. The proposed second model classifies the five grades with an F1-score of 0.9133, 0.9226, and 0.9393 on the Messidor1, Messidor2, and Kaggle EyePACS datasets, respectively. The new proposed CNN model proved its reliability and efficiency in detecting DR and classifying severity grades of DR in fundus images. Preprocessing techniques enhanced the performance by 10.83% of accuracy and 0.13037 in AUC using the binary model.

show abstract

Section: B Results Of Proposed Cnn Models (Methods 2)mentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Diabetic Retinopathy Detection and Grading using Deep learning

BERBAR¹

2022

Menoufia Journal of Electronic Engineering Research

View full text Add to dashboard Cite

show abstract

“…Transfer learning can help to detect a problem with incomplete information in a dataset, thus allowing for the classification of the datasets into better and worse [29]. Bhatt et al [30] proposed using a knowledge graph to strengthen the [31] proposed an approach based on updating the dataset annotation by interacting with crowd oracles.…”

Section: Related Workmentioning

confidence: 99%

Dataset Quality Assessment with Permutation Testing Showcased on Network Traffic Datasets

Wasielewska¹,

Soukup²,

Čejka³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>Intelligent and autonomous networks require precise and fast mechanisms that ensure error-free and efficient operation. Modern solutions are increasingly based on artificial intelligence, in particular on machine learning, to reliably process huge amounts of data. Therefore, high-quality datasets are essential to train machine learning models. Unfortunately, the problem of assessing the quality of datasets is very challenging and often overlooked. This paper proposes a method for assessing the dataset quality in the context of binary classification. It is based on permutation testing and examines the strength of the relationship between observations and labels. Experiments carried out on simulated and real network datasets show that the method is sensitive to detect errors/mislabels in the labeled dataset. We also present theoretical considerations justifying our results.</p>

show abstract

Evaluation of the Limit of Detection in Network Dataset Quality Assessment with PerQoDA

Wasielewska

Soukup

Čejka

et al. 2023

Communications in Computer and Information Science

View full text Add to dashboard Cite

Machine learning is recognised as a relevant approach to detect attacks and other anomalies in network traffic. However, there are still no suitable network datasets that would enable effective detection. On the other hand, the preparation of a network dataset is not easy due to privacy reasons but also due to the lack of tools for assessing their quality. In a previous paper, we proposed a new method for data quality assessment based on permutation testing. This paper presents a parallel study on the limits of detection of such an approach. We focus on the problem of network flow classification and use well-known machine learning techniques. The experiments were performed using publicly available network datasets.

show abstract

Quality Evaluation of Fundus Images using Transfer Learning

Cited by 3 publications

References 6 publications

Diabetic Retinopathy Detection and Grading using Deep learning

Diabetic Retinopathy Detection and Grading using Deep learning

Dataset Quality Assessment with Permutation Testing Showcased on Network Traffic Datasets

Evaluation of the Limit of Detection in Network Dataset Quality Assessment with PerQoDA

Contact Info

Product

Resources

About