AI-driven saliency-guided retinal vessel segmentation framework for sustainable digital pathology - Takeaways - MDSpire

AI-driven saliency-guided retinal vessel segmentation framework for sustainable digital pathology

  • By

  • Rajib Guha Thakurta

  • Mohammed E. Seno

  • Masood Ur Rehman

  • Sami Ahmed Haider

  • Marwah A. Halwani

  • Supriya Ashok Bhosale

  • Mukesh Soni

  • April 30, 2026

  • 0 min

Share

  • 1

    The study introduces SGB-Net, an AI-driven framework for improved retinal vessel segmentation using saliency guidance.

  • 2

    SGB-Net integrates a boundary refinement module and a feature-guided encoder-decoder network to enhance vessel edge representation.

  • 3

    The framework was evaluated on DRIVE, STARE, and CHASE_DB1 datasets, achieving Dice scores of 98.30%, 78.40%, and 84.60% respectively.

  • 4

    SGB-Net demonstrates superior performance in preserving thin vessels and reducing false positives compared to existing methods.

  • 5

    The proposed model's robustness makes it suitable for large-scale digital pathology applications and automated retinal analysis.

Original Source(s)

AI-driven saliency-guided retinal vessel segmentation framework for sustainable digital pathology

  • by Rajib Guha Thakurta, Mohammed E. Seno, Masood Ur Rehman, Sami Ahmed Haider, Marwah A. Halwani, Supriya Ashok Bhosale, Mukesh Soni

  • April 30, 2026

Related Content

Steroid Strategies in Diabetic Macular Edema

Inner retinal layer thickness reflects plasma biomarkers in preclinical Alzheimer’s disease

Retinal Age as Disease Biomarker

Fundus-based AI screening can indicate “retinal age” of patients, as well as flag systemic disease risks, says new study

  • May 27, 2026

  • 3 min