Multi-Population Differential Evolution for Retinal Blood Vessel Segmentation

Kamlesh Mistry, Biju Issac, Seibu Jacob, Jyoti Jasekar, Li Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

171 Downloads (Pure)

Abstract

The retinal blood vessel segmentation plays a significant role in the automatic or computer-assisted diagnosis of retinopathy. Manual blood vessel segmentation is very time-consuming and requires a great amount of domain knowledge. In addition, the blood vessels are only a few pixels wide and cover the entire fundus image. This further hinders the recent systems from automating the retinal blood vessel segmentation efficiently. In this paper, we propose a modified differential evolution (DE) algorithm to carry out automatic retinal blood vessel segmentation. The modified DE employs cross-communication among multiple populations to select three types of features i.e. thick blood vessels, thin blood vessels and non-blood vessels. Multiple classifiers such as neural networks (NN), Support vector machines (SVM), NN based and SVM based ensembles are used to further measure the performance of segmentation. The proposed algorithm is evaluated on three publicly available retinal image datasets like DRIVE, STARE and HRF. It outperformed the state-of-the-art with a high average accuracy of 98.5% along with high sensitivity and specificity.
Original languageEnglish
Title of host publicationProceedings of 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)
Subtitle of host publicationICARCV 2018
PublisherIEEE
Pages424-429
Number of pages6
ISBN (Electronic)9781538695821
ISBN (Print)9781538695838
DOIs
Publication statusPublished - 20 Dec 2018
Event15th International Conference on Control, Automation, Robotics and Vision - Marina Bay Sands Expo and Convention Centre, Singapore
Duration: 18 Nov 201821 Nov 2018
https://www.aconf.org/conf_165882.html

Conference

Conference15th International Conference on Control, Automation, Robotics and Vision
Abbreviated titleICARCV
CountrySingapore
Period18/11/1821/11/18
Internet address

Fingerprint Dive into the research topics of 'Multi-Population Differential Evolution for Retinal Blood Vessel Segmentation'. Together they form a unique fingerprint.

  • Cite this

    Mistry, K., Issac, B., Jacob, S., Jasekar, J., & Zhang, L. (2018). Multi-Population Differential Evolution for Retinal Blood Vessel Segmentation. In Proceedings of 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV) : ICARCV 2018 (pp. 424-429). IEEE. https://doi.org/10.1109/ICARCV.2018.8581322