Projects

OCT Vision

Computer Vision
MedTech
Python
Tailwind CSS

Advanced ophthalmology assistance application for automated corneal segmentation and contact lens fitting analysis.

OCT Vision is a specialized medical imaging tool designed to automate and enhance the measurement of the relationship between the cornea and contact lenses using Anterior Segment Optical Coherence Tomography (AS-OCT) images.

Built as a Bachelor’s Degree project at the Universidade da Coruña, it provides clinicians with high-precision data to facilitate the adaptation of lenses, especially in complex clinical cases like keratoconus or corneal transplants.

✨ Key Features

  • Automated Segmentation: Precisely detects corneal and contact lens surfaces using optimized image processing pipelines (OpenCV).
  • Comprehensive Metric Suite:
    • Vertical & Euclidean Clearances: Precise sagittal gap and safety analysis.
    • Zonal Metrics: Detailed analysis of central vs. peripheral corneal thickness.
    • Curvature & Symmetry: Automated estimation of anterior curvature and symmetry indices.
  • Interactive Visualization: A modern, dark-themed dashboard featuring real-time cross-sectional measurements and a dedicated thickness profile graph.
  • Demo Mode: Built-in library of diverse clinical scans for validation and training.

🛠️ Technical Implementation

The system follows a multi-stage computer vision pipeline, utilizing CLAHE for enhancement, Canny for edge detection, and least-squares polynomial fitting to create accurate geometric models of the eye. The frontend is a premium, responsive interface built with vanilla JavaScript and Tailwind CSS, ensuring a smooth and medical-grade user experience.