Zobrazit v EDS

Res-Unet based blood vessel segmentation and cardio vascular disease prediction using chronological chef-based optimization algorithm based deep residual network from retinal fundus images.

Uloženo v:
Podrobná bibliografie
Název: Res-Unet based blood vessel segmentation and cardio vascular disease prediction using chronological chef-based optimization algorithm based deep residual network from retinal fundus images.
Autoři: S, Balasubramaniam, Kadry, Seifedine, Dhanaraj, Rajesh Kumar, K, Satheesh Kumar, Manthiramoorthy, Chinnadurai
Zdroj: Multimedia Tools & Applications; Dec2024, Vol. 83 Issue 40, p87929-87958, 30p
Témata: ARTIFICIAL neural networks, FEATURE extraction, OPTIMIZATION algorithms, OPTIC disc, ARTIFICIAL intelligence, RETINAL blood vessels
Abstrakt: Cardiovascular disease (CVD) is a significant contributor to global mortality in our advanced society. The majority of males were attributed to deaths caused by CVD. CVD is the primary cause of mortality. It can be avoided with early detection and accurate diagnosis in its first stages. This research introduces a method for detecting CVD by analysing retinal fundus images. The approach under consideration facilitates disease prediction. The primary procedure involved in retinal vessels is the extraction of tissue data, which is then used for the identification and treatment of CVD. In this step, the retinal pictures are subjected to filtering using a Gaussian filter. The identification of the optic disc is accomplished by the process of binarization and circle fitting, which is then followed by the extraction of statistical data. The segmentation of blood vessels is performed using the Chronological Chef Based Optimisation Algorithm (CCBOA)-based Res-Unet. Subsequently, texture features are extracted. The detection of CVD is achieved by employing a deep neural network (DRN) in conjunction with CCBOA. The CCBOA-based DRN demonstrated exceptional efficiency, achieving the maximum level of accuracy at 89.8%. It also exhibited impressive performance in terms of negative predictive value (NPV) at 86.4%, positive predictive value (PPV) at 86.8%, true negative rate (TNR) at 90.5%, and true positive rate (TPR) at 90.1%. [ABSTRACT FROM AUTHOR]
Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Complementary Index
Popis
Abstrakt:Cardiovascular disease (CVD) is a significant contributor to global mortality in our advanced society. The majority of males were attributed to deaths caused by CVD. CVD is the primary cause of mortality. It can be avoided with early detection and accurate diagnosis in its first stages. This research introduces a method for detecting CVD by analysing retinal fundus images. The approach under consideration facilitates disease prediction. The primary procedure involved in retinal vessels is the extraction of tissue data, which is then used for the identification and treatment of CVD. In this step, the retinal pictures are subjected to filtering using a Gaussian filter. The identification of the optic disc is accomplished by the process of binarization and circle fitting, which is then followed by the extraction of statistical data. The segmentation of blood vessels is performed using the Chronological Chef Based Optimisation Algorithm (CCBOA)-based Res-Unet. Subsequently, texture features are extracted. The detection of CVD is achieved by employing a deep neural network (DRN) in conjunction with CCBOA. The CCBOA-based DRN demonstrated exceptional efficiency, achieving the maximum level of accuracy at 89.8%. It also exhibited impressive performance in terms of negative predictive value (NPV) at 86.4%, positive predictive value (PPV) at 86.8%, true negative rate (TNR) at 90.5%, and true positive rate (TPR) at 90.1%. [ABSTRACT FROM AUTHOR]
ISSN:13807501
DOI:10.1007/s11042-024-18810-y