Retinal artery/vein classification using genetic-search feature selection
Uloženo v:
| Název: | Retinal artery/vein classification using genetic-search feature selection |
|---|---|
| Autoři: | Bart M. ter Haar Romeny, Tao Tan, Behdad Dashtbozorg, Fan Huang |
| Zdroj: | Computer Methods and Programs in Biomedicine. 161:197-207 |
| Informace o vydavateli: | Elsevier BV, 2018. |
| Rok vydání: | 2018 |
| Témata: | Automated, Artery/vein classification, Retinal Artery, Image Processing, 02 engineering and technology, Pattern Recognition, Sensitivity and Specificity, Pattern Recognition, Automated, Machine Learning, 03 medical and health sciences, 0302 clinical medicine, Models, Computer-Assisted/methods, Image Processing, Computer-Assisted, 0202 electrical engineering, electronic engineering, information engineering, Humans, False Positive Reactions, Retinal Vein/diagnostic imaging, Probability, Electronic Data Processing, Models, Statistical, Retinal Artery/diagnostic imaging, Fundus image, Reproducibility of Results, Statistical, Retinal Vein, Genetic search feature selection, Programming Languages, Artifacts, Algorithms |
| Popis: | 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.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.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.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. |
| Druh dokumentu: | Article |
| Jazyk: | English |
| ISSN: | 0169-2607 |
| DOI: | 10.1016/j.cmpb.2018.04.016 |
| Přístupová URL adresa: | https://pubmed.ncbi.nlm.nih.gov/29852962 https://www.sciencedirect.com/science/article/abs/pii/S0169260717312415 https://europepmc.org/article/MED/29852962 https://www.narcis.nl/publication/RecordID/oai%3Apure.tue.nl%3Apublications%2F6e5556d9-e5f4-47e3-845e-1d05fd4dc4d3 https://research.tue.nl/nl/publications/retinal-arteryvein-classification-using-genetic-search-feature-se https://doi.org/10.1016/j.cmpb.2018.04.016 https://dblp.uni-trier.de/db/journals/cmpb/cmpb161.html#HuangDTR18 |
| Rights: | CC BY NC ND |
| Přístupové číslo: | edsair.doi.dedup.....9ca5129e3e07f215bde00675ccf5f4ad |
| Databáze: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | 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.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.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.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. |
|---|---|
| ISSN: | 01692607 |
| DOI: | 10.1016/j.cmpb.2018.04.016 |