FAS-Incept-HR: a fully automated system based on optimized inception model for hypertensive retinopathy classification

Sajid, Muhammad Zaheer; Qureshi, Imran; Youssef, Ayman; Khan, Nauman Ali

doi:10.1007/s11042-023-15556-x

Cited by 1 publication

(6 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Methodsmentioning

confidence: 99%

“…The strength of our proposed model was tested on another disease, hypertensive retinopathy, with the PAK-HR dataset [38], utilizing the training and validation accuracy and loss functions. The strength of our proposed model was tested on another disease, hypertensive retinopathy, with the PAK-HR dataset [38], utilizing the training and validation accuracy and loss functions.…”

Section: Methodsmentioning

confidence: 99%

“…"Only a limited number of research studies have employed deep-learning techniques to diagnose diabetic retinopathy in retinal images. The two studies multi-Stream DNN [3] and Analysis of DR [38] employ DL to identify DR in retinal images. Ref.…”

Section: Sate Of the Art Comparisionmentioning

confidence: 99%

“…Ref. [38] is the most current deep-learning model for DR recognition. Table 8 demonstrates that RDS-DR performs better than [38].…”

Section: Sate Of the Art Comparisionmentioning

confidence: 99%

“…[38] is the most current deep-learning model for DR recognition. Table 8 demonstrates that RDS-DR performs better than [38]. In research [3], as the primary feature extractors, the pretrained DL architectures ResNet-50 and DenseNet-121 are used to create a multi-stream network.…”

Section: Sate Of the Art Comparisionmentioning

confidence: 99%

See 4 more Smart Citations

RDS-DR: An Improved Deep Learning Model for Classifying Severity Levels of Diabetic Retinopathy

Bashir,

Sajid,

Kalsoom

et al. 2023

Diagnostics

Self Cite

View full text Add to dashboard Cite

A well-known eye disorder called diabetic retinopathy (DR) is linked to elevated blood glucose levels. Cotton wool spots, confined veins in the cranial nerve, AV nicking, and hemorrhages in the optic disc are some of its symptoms, which often appear later. Serious side effects of DR might include vision loss, damage to the visual nerves, and obstruction of the retinal arteries. Researchers have devised an automated method utilizing AI and deep learning models to enable the early diagnosis of this illness. This research gathered digital fundus images from renowned Pakistani eye hospitals to generate a new “DR-Insight” dataset and known online sources. A novel methodology named the residual-dense system (RDS-DR) was then devised to assess diabetic retinopathy. To develop this model, we have integrated residual and dense blocks, along with a transition layer, into a deep neural network. The RDS-DR system is trained on the collected dataset of 9860 fundus images. The RDS-DR categorization method demonstrated an impressive accuracy of 97.5% on this dataset. These findings show that the model produces beneficial outcomes and may be used by healthcare practitioners as a diagnostic tool. It is important to emphasize that the system’s goal is to augment optometrists’ expertise rather than replace it. In terms of accuracy, the RDS-DR technique fared better than the cutting-edge models VGG19, VGG16, Inception V-3, and Xception. This emphasizes how successful the suggested method is for classifying diabetic retinopathy (DR).

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%