EUVIMEDEUVIMED entdecken
Crossref

Enhanced Cardiovascular Disease Risk Prediction from Retinal Vasculature using DenseNet121 in DR and HR Patients

Ms.S. Vishnupriya, Ms.S. Ananthika, Ms.R. Dhesika, Ms.S.P. Aarthi, Ms.Henna Shakil

International Journal of Engineering & Extended Technologies Research · 28.03.2026 · 08 (02)

DOI: 10.15662/ijeetr.2026.0802030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 28.03.2026. Verfasst von Ms.S. Vishnupriya und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiovascular disease (CVD) is one of the leading causes of mortality worldwide, and early detection is essential for effective treatment and prevention. Retinal imaging has emerged as a noninvasive method for identifying vascular changes associated with cardiovascular risk. The existing system uses the CVDNet framework based on the ResNet50 architecture to analyze retinal fundus images and predict cardiovascular risk in patients with diabetic retinopathy (DR) and hypertensive retinopathy (HR). Although this approach provides promising results, it may suffer from limited feature reuse and higher parameter redundancy. To address these limitations, the proposed system introduces a DenseNet121–based architecture for improved feature extraction and classification. DenseNet121 enables dense connections between layers, allowing better gradient flow and feature reuse. This architecture reduces the number of parameters while improving learning efficiency. The model analyzes retinal vascular structures and automatically learns discriminative patterns associated with cardiovascular risk. It enhances prediction accuracy and reduces over fitting, especially in medical datasets. The proposed system aims to provide a more reliable, noninvasive, and efficient diagnostic tool for early CVD risk detection. This approach can support clinicians in decision making and preventive care. Overall, the DenseNet121–based system offers improved performance compared to traditional deep learning models

Zitieren

APA

Vishnupriya, M., Ananthika, M., Dhesika, M., Aarthi, M., & Shakil, M. (2026). Enhanced Cardiovascular Disease Risk Prediction from Retinal Vasculature using DenseNet121 in DR and HR Patients. International Journal of Engineering & Extended Technologies Research, 08(02). https://doi.org/10.15662/ijeetr.2026.0802030

Vancouver

Vishnupriya M, Ananthika M, Dhesika M, Aarthi M, Shakil M. Enhanced Cardiovascular Disease Risk Prediction from Retinal Vasculature using DenseNet121 in DR and HR Patients. International Journal of Engineering & Extended Technologies Research. 2026;08(02). doi:10.15662/ijeetr.2026.0802030

BibTeX
@article{Vishnupriya2026,
  author = {Vishnupriya, Ms.S. and Ananthika, Ms.S. and Dhesika, Ms.R. and Aarthi, Ms.S.P. and Shakil, Ms.Henna},
  title = {Enhanced Cardiovascular Disease Risk Prediction from Retinal Vasculature using DenseNet121 in DR and HR Patients},
  journal = {International Journal of Engineering & Extended Technologies Research},
  year = {2026},
  volume = {08},
  number = {02},
  doi = {10.15662/ijeetr.2026.0802030}
}
Kostenlos starten →