Retinal artery/vein classification using genetic-search feature selection

Autor: Bart M. ter Haar Romeny, Behdad Dashtbozorg, Tao Tan, Fan Huang
Přispěvatelé: Medical Image Analysis
Rok vydání: 2018
Předmět:
Power graph analysis
Computer science
Image quality
Image Processing
Retinal Artery
02 engineering and technology
Fundus (eye)
Pattern Recognition
Automated
030218 nuclear medicine & medical imaging
Machine Learning
chemistry.chemical_compound
0302 clinical medicine
Models
Image Processing
Computer-Assisted
Computer-Assisted/methods
0202 electrical engineering
electronic engineering
information engineering
Image resolution
Statistical
Computer Science Applications
Feature (computer vision)
cardiovascular system
020201 artificial intelligence & image processing
Artifacts
Algorithms
Automated
Image Processing
Computer-Assisted/methods
Artery/vein classification
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Health Informatics
Feature selection
Pattern Recognition
Sensitivity and Specificity
03 medical and health sciences
Humans
False Positive Reactions
Retinal Vein/diagnostic imaging
Probability
Electronic Data Processing
Models
Statistical
Pixel
business.industry
Retinal Artery/diagnostic imaging
Fundus image
Reproducibility of Results
Pattern recognition
Retinal
Retinal Vein
Genetic search feature selection
chemistry
Programming Languages
Artificial intelligence
Focus (optics)
business
Software
Zdroj: Computer Methods and Programs in Biomedicine, 161, 197-207. Elsevier Ireland Ltd
ISSN: 0169-2607
DOI: 10.1016/j.cmpb.2018.04.016
Popis: Background and objectives: The automatic classification of retinal blood vessels into artery and vein (A/V) is still a challenging task in retinal image analysis. Recent works on A/V classification mainly focus on the graph analysis of the retinal vasculature, which exploits the connectivity of vessels to improve the classification performance. While they have overlooked the importance of pixel-wise classification to the final classification results. This paper shows that a complicated feature set is efficient for vessel centerline pixels classification. Methods: We extract enormous amount of features for vessel centerline pixels, and apply a genetic-search based feature selection technique to obtain the optimal feature subset for A/V classification. Results: The proposed method achieves an accuracy of 90.2%, the sensitivity of 89.6%, the specificity of 91.3% on the INSPIRE dataset. It shows that our method, using only the information of centerline pixels, gives a comparable performance as the techniques which use complicated graph analysis. In addition, the results on the images acquired by different fundus cameras show that our framework is capable for discriminating vessels independent of the imaging device characteristics, image resolution and image quality. Conclusion: The complicated feature set is essential for A/V classification, especially on the individual vessels where graph-based methods receive limitations. And it could provide a higher entry to the graph-analysis to achieve a better A/V labeling.
Databáze: OpenAIRE
Externí odkaz: