EUVIMEDEUVIMED entdecken
Crossref

Retinal neovascularization detection from fundus images using deformable attention ResNet and swarm-hiking optimization

Karpagavadivu Karuppusamy, Baranidharan Thangavel, Kavitha Mettupalayam Subramanian, Sumathi Thangavel

International Ophthalmology · 2026

DOI: 10.1007/s10792-026-04143-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Ophthalmology, 2026. Verfasst von Karpagavadivu Karuppusamy und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence and Data Science, Dr.N.G.P. Institute of Technology, Coimbatore, Tamilnadu, India. kkarpagampg@gmail.com. Hauptthemen laut MEDLINE: Retinal Neovascularization, Retinal Vessels, Deep Learning, Image Interpretation, Computer-Assisted. Die Arbeit nennt 36 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: In the detection of retinal neovascularization (RNV) from fundus images, defining anatomically consistent perivascular regions is challenging due to asymmetric retinal tissue deformation caused by abnormal vessel proliferation in RNV, leading to inaccurate extraction of pathological features. Moreover, early pathological changes in perivascular zones are minute and blend with normal tissue variability, while existing models focused on global retinal features tend to miss these localized abnormalities, resulting in reduced detection accuracy. METHODS: A novel deep learning (DL) framework, Deformable Attention Pyramid ResNet with Perivascular Swarm-Hiking Optimization (DAPR-PSHO) is proposed for precise RNV detection. In this, a Deformable Attention Pyramid Scene Parsing-ResNet (DAPSP-ResNet) is employed, which adaptively adjusts its receptive fields using deformable convolutions to accurately capture irregular vessel structures, and enriches feature extraction by integrating local vessel details with global retinal context. Then, a PeriV-Transformer driven Particle Swarm-Hiking Optimization is introduced, to focus attention on minute perivascular changes while maintaining global retinal context, and fine-tunes transformer parameters, thereby effectively capturing early-stage RNV and enhancing anatomical fidelity indetection. RESULT: The proposed RNV detection model attains a high accuracy of 0.98, precision of 0.985, and recall of 0.986 comparedto the existing models. CONCLUSION: The DAPR-PSHO framework successfully addresses the limitations of global-feature-focused models by eff ectively isolating localized, early-stage abnormalities in perivascular zones, significantly improving RNV detection accuracy and anatomical fidelity.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Retinal NeovascularizationRetinal VesselsDeep LearningImage Interpretation, Computer-AssistedFluorescein AngiographyHumansFundus OculiConvolutional Neural Networks

Stichwörter der Autor:innen

Deep learningDeformable convolutionFundus image analysisRetinal neovascularizationVision transformer

Autor:innen und Institutionen

  • Department of Artificial Intelligence and Data Science, Dr.N.G.P. Institute of Technology, Coimbatore, Tamilnadu, India. kkarpagampg@gmail.com.
  • Department of Electronics Engineering (VLSI Design), K.S. Rangasamy College of Technology, Tiruchengode, Tamilnadu, India.
  • Department of Computer Science and Engineering, SNS College of Technology, Coimbatore, Tamilnadu, India.
  • Department of Information Technology, Govt. College of Engineering, Erode, Tamilnadu, India.

Zitieren

APA

Karuppusamy, K., Thangavel, B., Subramanian, K. M., & Thangavel, S. (2026). Retinal neovascularization detection from fundus images using deformable attention ResNet and swarm-hiking optimization. International Ophthalmology. https://doi.org/10.1007/s10792-026-04143-2

Vancouver

Karuppusamy K, Thangavel B, Subramanian KM, Thangavel S. Retinal neovascularization detection from fundus images using deformable attention ResNet and swarm-hiking optimization. International Ophthalmology. 2026. doi:10.1007/s10792-026-04143-2

BibTeX
@article{Karuppusamy2026,
  author = {Karuppusamy, Karpagavadivu and Thangavel, Baranidharan and Subramanian, Kavitha Mettupalayam and Thangavel, Sumathi},
  title = {Retinal neovascularization detection from fundus images using deformable attention ResNet and swarm-hiking optimization},
  journal = {International Ophthalmology},
  year = {2026},
  doi = {10.1007/s10792-026-04143-2}
}
Kostenlos starten →