A Graph Cut Approach to Artery/Vein Classification in Ultra-Widefield Scanning Laser Ophthalmoscopy
- Resource Type
- Authors
- Tom MacGillivray; Gavin Robertson; Graeme Houston; Emanuele Trucco; Enrico Pellegrini; Jano van Hemert
- Source
- IEEE Transactions on Medical Imaging. 37:516-526
- Subject
- Retinal Vein
Computer science
Feature extraction
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Fundus (eye)
030218 nuclear medicine & medical imaging
Ophthalmoscopy
03 medical and health sciences
chemistry.chemical_compound
0302 clinical medicine
Cut
Image Processing, Computer-Assisted
0202 electrical engineering, electronic engineering, information engineering
medicine
Medical imaging
Humans
Computer vision
Electrical and Electronic Engineering
Image resolution
Retina
Radiological and Ultrasound Technology
medicine.diagnostic_test
business.industry
Retinal
Image segmentation
Computer Science Applications
Scanning laser ophthalmoscopy
medicine.anatomical_structure
chemistry
Graph (abstract data type)
020201 artificial intelligence & image processing
Artificial intelligence
business
Algorithms
Software
Blood vessel
- Language
- ISSN
- 1558-254X
0278-0062
The classification of blood vessels into arterioles and venules is a fundamental step in the automatic investigation of retinal biomarkers for systemic diseases. In this paper, we present a novel technique for vessel classification on ultra-wide-field-of-view images of the retinal fundus acquired with a scanning laser ophthalmoscope. To the best of our knowledge, this is the first time that a fully automated artery/vein classification technique for this type of retinal imaging with no manual intervention has been presented. The proposed method exploits hand-crafted features based on local vessel intensity and vascular morphology to formulate a graph representation from which a globally optimal separation between the arterial and venular networks is computed by graph cut approach. The technique was tested on three different data sets (one publicly available and two local) and achieved an average classification accuracy of 0.883 in the largest data set.