Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Retinal Vessel Segmentation Using a Novel U-Net Architecture with Data Augmentation
https://orcid.org/http://orcid.org/0000-0002-8790-6096
https://orcid.org/http://orcid.org/0009-0005-4116-2406
https://orcid.org/http://orcid.org/0009-0006-4727-1774
https://orcid.org/http://orcid.org/0009-0007-4350-3416
https://orcid.org/http://orcid.org/0009-0009-6594-7442
https://orcid.org/http://orcid.org/0009-0000-7261-7139
https://orcid.org/http://orcid.org/0009-0001-1091-9323
In this paper, the retinal vessel segmentation problem is highlighted and a novel U-Net architecture with data augmentation is proposed to segment the retinal vessel. The proposed architecture is applied to a benchmark dataset like Digital Retinal Images for Vessel Extraction (DRIVE). After performance evaluation, it has been observed that the novel U-Net architecture with augmentation generates a 79.67% F1-Score, 78.48% Recall Rate, 81.38% Precision Rate, and 96.52% accuracy. The result of the proposed architecture proves to be superior with respect to U-Net architecture without data augmentation and other architectures proposes in recent times.
Retinal Vessel Segmentation Using a Novel U-Net Architecture with Data Augmentation
https://orcid.org/http://orcid.org/0000-0002-8790-6096
https://orcid.org/http://orcid.org/0009-0005-4116-2406
https://orcid.org/http://orcid.org/0009-0006-4727-1774
https://orcid.org/http://orcid.org/0009-0007-4350-3416
https://orcid.org/http://orcid.org/0009-0009-6594-7442
https://orcid.org/http://orcid.org/0009-0000-7261-7139
https://orcid.org/http://orcid.org/0009-0001-1091-9323
In this paper, the retinal vessel segmentation problem is highlighted and a novel U-Net architecture with data augmentation is proposed to segment the retinal vessel. The proposed architecture is applied to a benchmark dataset like Digital Retinal Images for Vessel Extraction (DRIVE). After performance evaluation, it has been observed that the novel U-Net architecture with augmentation generates a 79.67% F1-Score, 78.48% Recall Rate, 81.38% Precision Rate, and 96.52% accuracy. The result of the proposed architecture proves to be superior with respect to U-Net architecture without data augmentation and other architectures proposes in recent times.
Retinal Vessel Segmentation Using a Novel U-Net Architecture with Data Augmentation
https://orcid.org/http://orcid.org/0000-0002-8790-6096
https://orcid.org/http://orcid.org/0009-0005-4116-2406
https://orcid.org/http://orcid.org/0009-0006-4727-1774
https://orcid.org/http://orcid.org/0009-0007-4350-3416
https://orcid.org/http://orcid.org/0009-0009-6594-7442
https://orcid.org/http://orcid.org/0009-0000-7261-7139
https://orcid.org/http://orcid.org/0009-0001-1091-9323
In this paper, the retinal vessel segmentation problem is highlighted and a novel U-Net architecture with data augmentation is proposed to segment the retinal vessel. The proposed architecture is applied to a benchmark dataset like Digital Retinal Images for Vessel Extraction (DRIVE). After performance evaluation, it has been observed that the novel U-Net architecture with augmentation generates a 79.67% F1-Score, 78.48% Recall Rate, 81.38% Precision Rate, and 96.52% accuracy. The result of the proposed architecture proves to be superior with respect to U-Net architecture without data augmentation and other architectures proposes in recent times.
Retinal Vessel Segmentation Using a Novel U-Net Architecture with Data Augmentation
Smart Innovation, Systems and Technologies
Bhattacharyya, Siddhartha (Herausgeber:in) / Banerjee, Jyoti Sekhar (Herausgeber:in) / Köppen, Mario (Herausgeber:in) / Chowdhury, Debkumar (Autor:in) / Dey, Arnab Kumar (Autor:in) / Ghosh, Kaustuv (Autor:in) / Banerjee, Rajarshi (Autor:in) / Sil, Sayak (Autor:in) / Rakshit, Sayan (Autor:in) / Saha, Shreyas (Autor:in)
International Conference on Human-Centric Smart Computing ; 2023 ; New Delhi, India
18.02.2024
16 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Retinopathy , Fundus image , Retinal vessel segmentation , Novel U-Net architecture with data augmentation , Digital retinal images for vessel extraction Engineering , Computational Intelligence , User Interfaces and Human Computer Interaction , Data Structures and Information Theory , Artificial Intelligence , Mobile and Network Security
Blood Vessel Segmentation Using FCM–STSA Method for Retinal Fundus Images
| Springer Verlag | 2024
Blood Vessel Segmentation Using FCM–STSA Method for Retinal Fundus Images
| Springer Verlag | 2024
Skip connection information enhancement network for retinal vessel segmentation
| Springer Verlag | 2024
Retinal vessel segmentation method based on RSP-SA Unet network
| Springer Verlag | 2024
| DOAJ | 2017