6533b873fe1ef96bd12d4cc9
RESEARCH PRODUCT
Accurate estimation of retinal vessel width using bagged decision trees and an extended multiresolution Hermite model.
Emanuele TruccoDomenico TegoloCarmen Alina Lupascusubject
Accurate estimationComputer scienceStability (learning theory)Decision treeHealth Informaticscomputer.software_genreSensitivity and SpecificityPattern Recognition AutomatedSet (abstract data type)Parametric surfaceImage Interpretation Computer-AssistedHumansRadiology Nuclear Medicine and imagingFluorescein AngiographyHermite polynomialsDiabetic RetinopathySettore INF/01 - InformaticaRadiological and Ultrasound TechnologyReproducibility of ResultsRetinal VesselsImage EnhancementComputer Graphics and Computer-Aided DesignData setComputer Vision and Pattern RecognitionData miningRetinal images Vessel width Multiresolution Hermite model Ensembles of bagged decision trees Medical image analysiscomputerAlgorithmsTest dataRetinoscopydescription
We present an algorithm estimating the width of retinal vessels in fundus camera images. The algorithm uses a novel parametric surface model of the cross-sectional intensities of vessels, and ensembles of bagged decision trees to estimate the local width from the parameters of the best-fit surface. We report comparative tests with REVIEW, currently the public database of reference for retinal width estimation, containing 16 images with 193 annotated vessel segments and 5066 profile points annotated manually by three independent experts. Comparative tests are reported also with our own set of 378 vessel widths selected sparsely in 38 images from the Tayside Scotland diabetic retinopathy screening programme and annotated manually by two clinicians. We obtain considerably better accuracies compared to leading methods in REVIEW tests and in Tayside tests. An important advantage of our method is its stability (success rate, i.e., meaningful measurement returned, of 100% on all REVIEW data sets and on the Tayside data set) compared to a variety of methods from the literature. We also find that results depend crucially on testing data and conditions, and discuss criteria for selecting a training set yielding optimal accuracy.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2012-12-15 | Medical image analysis |