Regularizer based on Euler characteristic for retinal blood vessel segmentation

Hakim, Lukman; Kavitha, M.; Yudistira, Novanto; Kurita, Takio

doi:10.1016/j.patrec.2021.05.023

Cited by 12 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep network might perform well when input is accurately pre-processed. Hakim et al [19] presented EC model from topology to compute the numbers of isolated objects on segmented vessel regions, i.e., major contributions of this work. Additionally, they used the numbers of isolated objects in a U-Net such as Deep Convolutional Neural Network (DCNN) framework as a standardizer for training the networks to improve the connectivity among the pixels of vessel region.…”

Section: Literature Reviewmentioning

confidence: 99%

Blood Vessel Segmentation with Classification Model for Diabetic Retinopathy Screening

Alamoudi¹,

Allabun²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Biomedical image processing is finding useful in healthcare sector for the investigation, enhancement, and display of images gathered by distinct imaging technologies. Diabetic retinopathy (DR) is an illness caused by diabetes complications and leads to irreversible injury to the retina blood vessels. Retinal vessel segmentation techniques are a basic element of automated retinal disease screening system. In this view, this study presents a novel blood vessel segmentation with deep learning based classification (BVS-DLC) model for DR diagnosis using retinal fundus images. The proposed BVS-DLC model involves different stages of operations such as preprocessing, segmentation, feature extraction, and classification. Primarily, the proposed model uses the median filtering (MF) technique to remove the noise that exists in the image. In addition, a multilevel thresholding based blood vessel segmentation process using seagull optimization (SGO) with Kapur's entropy is performed. Moreover, the shark optimization algorithm (SOA) with Capsule Networks (CapsNet) model with softmax layer is employed for DR detection and classification. A wide range of simulations was performed on the MESSIDOR dataset and the results are investigated interms of different measures. The simulation results ensured the better performance of the proposed model compared to other existing techniques interms of sensitivity, specificity, receiver operating characteristic (ROC) curve, accuracy, and F-score.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Blood Vessel Segmentation with Classification Model for Diabetic Retinopathy Screening

Alamoudi¹,

Allabun²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…, the EC is computed at different filtration values). The EC has also been used for analyzing data in neuroscience, 5,6 medical imaging, 7,8 cosmology, 9,10 and plant biology. 11 The EC has also been recently used as a descriptor/feature to train simple machine learning models ( e.g.…”

Section: Introductionmentioning

confidence: 99%

“…4 The EC is a descriptor that captures basic topological features of binary elds (e.g., connected components, voids, holes) and can be extended to continuous elds by using ltration/percolation procedures (i.e., the EC is computed at different ltration values). The EC has also been used for analyzing data in neuroscience, 5,6 medical imaging, 7,8 cosmology, 9,10 and plant biology. 11 The EC has also been recently used as a descriptor/feature to train simple machine learning models (e.g., linear regression) that have comparable prediction accuracy to those of CNNs but that are signicantly less computationally expensive to build.…”

Section: Introductionmentioning

confidence: 99%

A fast and scalable computational topology framework for the Euler characteristic

Laky,

Zavala

2024

Digital Discovery

View full text Add to dashboard Cite

show abstract

“…The fundus camera in the retina is utilized to examine the blood vessels, 2,3 and X‐ray imaging technologies can be used to monitor the arteries in the heart. Because the blood vessels are present in both medical pictures gathered from distinct imaging modalities, a single algorithmic technique to segmenting the vessels 4,5 in the retina and coronary angiography would save time and minimize complexity. However, it is extremely difficult due to nonuniform and complicated vascular systems, weak vessel contrast, nonuniform lighting, and the existence of nonbackground elements including bones.…”

Section: Introductionmentioning

confidence: 99%

Highly accurate blood vessel segmentation using texture‐based modified K‐means clustering with deep learning model

Lisha¹,

Sulochana

2023

Concurrency and Computation

View full text Add to dashboard Cite

This paper suggests a blood vessel segmentation using the Texture-Based Modified K-means Clustering (TBMKC) technique to lessen the detrimental effects of light lesions. In the suggested method, the K value is chosen automatically by maximizing the local pixel data of the input image. Utilizing the Gabor Filter and Scale-Invariant Feature Transform (SIFT), respectively, texture and statistical characteristics are used to extract the local information. The number of pixels present in each class is used to alter the cluster centroid using Particle Swarm Optimization (PSO) methods. Local adaptive thresholding is then used to separate the blood vessel pattern. The proposed method is invariant to scales and rotations due to SIFT features. The thresholding output is given to the modified DCNN (Deep Convolutional Neural Network). Finally, the performance of the (MDCNN+ TBMKC+ PSO) scheme is computed over other extant schemes. The outcomes of the adopted scheme is determined and tested using the retinal image from DRIVE, STARE, HRF, and CHASE_DBI databases. The accuracy of the proposed method is 13.41%,

show abstract

Regularizer based on Euler characteristic for retinal blood vessel segmentation

Cited by 12 publications

References 19 publications

Blood Vessel Segmentation with Classification Model for Diabetic Retinopathy Screening

Blood Vessel Segmentation with Classification Model for Diabetic Retinopathy Screening

A fast and scalable computational topology framework for the Euler characteristic

Highly accurate blood vessel segmentation using texture‐based modified K‐means clustering with deep learning model

Contact Info

Product

Resources

About