Logo image
Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data
Conference proceeding

Retina lesion and microaneurysm segmentation using morphological reconstruction methods with ground-truth data

Thomas P Karnowski, V Govindasamy, Kenneth W Tobin, Edward Chaum and M D Abramoff
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, Vol.2008, pp.5433-5436
2008
DOI: 10.1109/IEMBS.2008.4650443
PMID: 19163946
url
https://www.osti.gov/servlets/purl/1009928View
Open Access

Abstract

In this work we report on a method for lesion segmentation based on the morphological reconstruction methods of Sbeh et. al. We adapt the method to include segmentation of dark lesions with a given vasculature segmentation. The segmentation is performed at a variety of scales determined using ground-truth data. Since the method tends to over-segment imagery, ground-truth data was used to create post-processing filters to separate nuisance blobs from true lesions. A sensitivity and specificity of 90% of classification of blobs into nuisance and actual lesion was achieved on two data sets of 86 images and 1296 images.
Algorithms Reproducibility of Results Humans Image Interpretation, Computer-Assisted - methods Diabetic Retinopathy - pathology Aneurysm - pathology Diabetic Retinopathy - complications Retinal Artery - pathology Sensitivity and Specificity Image Enhancement - methods Retinoscopy - methods Retina - pathology Pattern Recognition, Automated - methods

Details

Metrics

Logo image