A Dual Step Strategy for Retinal Thin Vessel Enhancement/Extraction

Wahid, Farha Fatina; Raju, G.

doi:10.1109/aicai.2019.8701376

Cited by 4 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Strength Weakness Vessel segmentation using thresholding [40][41][42] Approximation of vessel pixels using a simple approach When the vessel pixel values are closer to the background, false points are recognized Fuzzy-based segmentation [43] With consistent pixel values, it works great To increase the responsiveness of blood vessels, extensive preprocessing is necessary…”

Section: Methodsmentioning

confidence: 99%

Presentation of a Segmentation Method for a Diabetic Retinopathy Patient’s Fundus Region Detection Using a Convolutional Neural Network

Valizadeh

Ghoushchi

Ranjbarzadeh

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Diabetic retinopathy is characteristic of a local distribution that involves early-stage risk factors and can forecast the evolution of the illness or morphological lesions related to the abnormality of retinal blood flows. Regional variations in retinal blood flow and modulation of retinal capillary width in the macular area and the retinal environment are also linked to the course of diabetic retinopathy. Despite the fact that diabetic retinopathy is frequent nowadays, it is hard to avoid. An ophthalmologist generally determines the seriousness of the retinopathy of the eye by directly examining color photos and evaluating them by visually inspecting the fundus. It is an expensive process because of the vast number of diabetic patients around the globe. We used the IDRiD data set that contains both typical diabetic retinopathic lesions and normal retinal structures. We provided a CNN architecture for the detection of the target region of 80 patients’ fundus imagery. Results demonstrate that the approach described here can nearly detect 83.84% of target locations. This result can potentially be utilized to monitor and regulate patients.

show abstract

Section: Methodsmentioning

confidence: 99%

Presentation of a Segmentation Method for a Diabetic Retinopathy Patient’s Fundus Region Detection Using a Convolutional Neural Network

Valizadeh

Ghoushchi

Ranjbarzadeh

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…In their technique, the enhanced image is subtracted from the input image iteratively, resultant images are fused to create one image, and this image is then enhanced using contrast-limited adaptive histogram equalization (CLAHE) and fuzzy histogram-based equalization (FHBE). Finally, thresholding is used to segment the enhanced image [35]. Ahamed et al also applied CLAHE with the green channel of fundus images and used a multiscale line detection approach in combination with hysteresis thresholding; the results in this technique are refined by morphology [36].…”

Section: Related Workmentioning

confidence: 99%

Aiding the Diagnosis of Diabetic and Hypertensive Retinopathy Using Artificial Intelligence-Based Semantic Segmentation

Arsalan

Owais

Mahmood

et al. 2019

JCM

View full text Add to dashboard Cite

Automatic segmentation of retinal images is an important task in computer-assisted medical image analysis for the diagnosis of diseases such as hypertension, diabetic and hypertensive retinopathy, and arteriosclerosis. Among the diseases, diabetic retinopathy, which is the leading cause of vision detachment, can be diagnosed early through the detection of retinal vessels. The manual detection of these retinal vessels is a time-consuming process that can be automated with the help of artificial intelligence with deep learning. The detection of vessels is difficult due to intensity variation and noise from non-ideal imaging. Although there are deep learning approaches for vessel segmentation, these methods require many trainable parameters, which increase the network complexity. To address these issues, this paper presents a dual-residual-stream-based vessel segmentation network (Vess-Net), which is not as deep as conventional semantic segmentation networks, but provides good segmentation with few trainable parameters and layers. The method takes advantage of artificial intelligence for semantic segmentation to aid the diagnosis of retinopathy. To evaluate the proposed Vess-Net method, experiments were conducted with three publicly available datasets for vessel segmentation: digital retinal images for vessel extraction (DRIVE), the Child Heart Health Study in England (CHASE-DB1), and structured analysis of retina (STARE). Experimental results show that Vess-Net achieved superior performance for all datasets with sensitivity (Se), specificity (Sp), area under the curve (AUC), and accuracy (Acc) of 80.22%, 98.1%, 98.2%, and 96.55% for DRVIE; 82.06%, 98.41%, 98.0%, and 97.26% for CHASE-DB1; and 85.26%, 97.91%, 98.83%, and 96.97% for STARE dataset.

show abstract

“…We could notice a lower performance in the pathological cases, even when dealing with images of adults. Observing the techniques of artificial vision of these works, we can group them in two classes: the works in [2,7,8,14] use image processing techniques without machine learning, the works in [3,11,13,16] employ supervised non-deep, unsupervised, and deep learning. The main weakness of current approaches is that they were designed for processing adult retina.…”

Section: Introductionmentioning

confidence: 99%

Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network

Intriago-Pazmiño

Ibarra-Fiallo

Alonso-Calvo

et al. 2019

Proceedings of the Second International Conference on Data Science, E-Learning and Information Systems

View full text Add to dashboard Cite

In this paper, we describe the experimentation with a convolutional neural network for segmenting retinal net from pathological fundus images of preterm born children. Segmenting retinal net from pathological fundus images is a fundamental task to aid computer diagnosis. We used U-net architecture for training and testing. Testing with ROPFI dataset, we obtained an area under the receiver operating curve equal to 0.9180; when average sensitivity is equal to 0.700, the average specificity is equal to 0.9710. This performance is higher than prior works using a similar dataset.

show abstract

A Dual Step Strategy for Retinal Thin Vessel Enhancement/Extraction

Cited by 4 publications

References 18 publications

Presentation of a Segmentation Method for a Diabetic Retinopathy Patient’s Fundus Region Detection Using a Convolutional Neural Network

Presentation of a Segmentation Method for a Diabetic Retinopathy Patient’s Fundus Region Detection Using a Convolutional Neural Network

Aiding the Diagnosis of Diabetic and Hypertensive Retinopathy Using Artificial Intelligence-Based Semantic Segmentation

Segmenting retinal vascular net from retinopathy of prematurity images using convolutional neural network

Contact Info

Product

Resources

About