Detection of Hypertension Retinopathy Using Deep Learning and Boltzmann Machines

Triwijoyo, Bambang Krismono; Pradipto, Yosef Dedy

doi:10.1088/1742-6596/801/1/012039

Cited by 21 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researchers employ the DL architectures in mid-level tasks, such as retina vessels segmentation or optic disk separation, that are necessary for high-level tasks such as the classifications of DR or HR. A DL architecture [ 32 ] composed of a deep neural network (DNN), and a random Boltzmann machine (RBM) is used for quantifying any alteration in retinal blood arteries vessels using AVR ratio and OD region determination. They achieve a good detection accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

An Automatic Detection and Classification System of Five Stages for Hypertensive Retinopathy Using Semantic and Instance Segmentation in DenseNet Architecture

Abbas

Qureshi

Ibrahim

2021

Sensors

View full text Add to dashboard Cite

The stage and duration of hypertension are connected to the occurrence of Hypertensive Retinopathy (HR) of eye disease. Currently, a few computerized systems have been developed to recognize HR by using only two stages. It is difficult to define specialized features to recognize five grades of HR. In addition, deep features have been used in the past, but the classification accuracy is not up-to-the-mark. In this research, a new hypertensive retinopathy (HYPER-RETINO) framework is developed to grade the HR based on five grades. The HYPER-RETINO system is implemented based on pre-trained HR-related lesions. To develop this HYPER-RETINO system, several steps are implemented such as a preprocessing, the detection of HR-related lesions by semantic and instance-based segmentation and a DenseNet architecture to classify the stages of HR. Overall, the HYPER-RETINO system determined the local regions within input retinal fundus images to recognize five grades of HR. On average, a 10-fold cross-validation test obtained sensitivity (SE) of 90.5%, specificity (SP) of 91.5%, accuracy (ACC) of 92.6%, precision (PR) of 91.7%, Matthews correlation coefficient (MCC) of 61%, F1-score of 92% and area-under-the-curve (AUC) of 0.915 on 1400 HR images. Thus, the applicability of the HYPER-RETINO method to reliably diagnose stages of HR is verified by experimental findings.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

An Automatic Detection and Classification System of Five Stages for Hypertensive Retinopathy Using Semantic and Instance Segmentation in DenseNet Architecture

Abbas

Qureshi

Ibrahim

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Finally author has concluded that feature based segmentation is the extent for improving the accuracy. The proposed method [2] focused on combined features to train deep neural network with the approach of Boltzmann machines. Author suggested this techniques because of speed and accurate.…”

Section: Related Workmentioning

confidence: 99%

“…3) Pixel assignment 4) Updating the value of centroids. Each pixel will be assigned to centroid which is present nearby based on Euclidean distance and it is given by, arg min dist (k i , p) 2 (1) where ki is the group of centroids and p is the pixel element. In the centroid updation step, the value of each centroid will be revalued by considering the mean of all pixels which are assigned to that cluster.…”

Section: B Segmentationmentioning

confidence: 99%

Detection and Classification of Cotton Wool Spots in Diabetic Retinopathy

Sudha*¹,

Srinivasan²,

Devi³

2019

IJRTE

View full text Add to dashboard Cite

Diabetes is a disorder that occurs when blood sugar level increases. Further increase of blood glucose lead to serious complications and it will affect major organs of our body. Diabetes affects both of the eyes called Diabetic Retinopathy (DR). If it is treated properly eye blindness can be prevented. The main objective of this paper is to detect Cotton Wool Spots (CWS) using morphological operations and the spots are segmented using k-means segmentation. Distinct features are extracted from the segmented image to train and test the Support Vector Machine (SVM) classifier. It is used to classify the lesions and the stages of diabetic retinopathy. It is noticed that sensitivity is 95% and the specificity is 86%.

show abstract

“…Manikis et.al [5], also proposes a framework for diagnosis of hypertensive retinopathy disease with hessian-based segmentation of blood vessels, then calculate the value of the AVR as a sign of the disease. A number of similar studies, ie, performed a diagnosis of hypertensive retinopathy using AVR parameters such as those performed by Ortiz et.al [6], Khitran et.al [7], Triwijoyo et.al [8], Faheem et.al [9] and Muramatsu et.al [10].…”

Section: Introductionmentioning

confidence: 99%

“…The performance parameters are analyzed is accuracy, PPV, NPV, specificity, sensitivity, and AUC. The performance parameters are calculated based on the formula shown in equation (7)(8)(9)(10)(11)(12). Interpretation of the performance parameters especially AUC has two approaches, namely statistically and clinically.…”

mentioning

confidence: 99%

Assessment of Early Hypertensive Retinopathy using Fractal Analysis of Retinal Fundus Image

2018

View full text Add to dashboard Cite

show abstract

Detection of Hypertension Retinopathy Using Deep Learning and Boltzmann Machines

Cited by 21 publications

References 7 publications

An Automatic Detection and Classification System of Five Stages for Hypertensive Retinopathy Using Semantic and Instance Segmentation in DenseNet Architecture

An Automatic Detection and Classification System of Five Stages for Hypertensive Retinopathy Using Semantic and Instance Segmentation in DenseNet Architecture

Detection and Classification of Cotton Wool Spots in Diabetic Retinopathy

Assessment of Early Hypertensive Retinopathy using Fractal Analysis of Retinal Fundus Image

Contact Info

Product

Resources

About