Comparison of classifier performance for information fusion in automated Diabetic Retinopathy screening

Meindert Niemeijer; Michael D Abràmoff; Niranjan Joshi; Michael Brady

doi:10.1109/ISBI.2011.5872499

Back

Conference proceeding

Comparison of classifier performance for information fusion in automated Diabetic Retinopathy screening

Meindert Niemeijer, Michael D Abràmoff, Niranjan Joshi and Michael Brady

2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp.685-688

03/2011

DOI: 10.1109/ISBI.2011.5872499

View Online

Abstract

Diabetic Retinopathy (DR) is a vascular disorder affecting the retina due to prolonged Diabetes. It can lead to sudden vision loss in advanced stages. Screening and routine monitoring is the most effective way of avoiding vision loss due to DR. Abramoff et al. developed and evaluated an automated DR screening system. One of the most important parts of this system, the information fusion module, combines information obtained from different images and various image properties. Niemeijer et al. compared several methods for DR information fusion and concluded that k-Nearest Neighbour (kNN) provided the best performance for their system. The aim of this work was to compare performance of the Random Forest (RF) classifier with that of the kNN classifier for DR information fusion. We performed experiments on a dataset containing images from 10303 eye examinations. Additionally we also compared performance of the two classifiers in an important sub-problem of DR screening - red lesion detection. In both the experiments, the RF classifier showed significantly better performance.

Diabetes

Diabetic Retinopathy

Radio frequency

Training

Sensitivity

Retinopathy

information fusion

Vegetation

CAD

kNN

Lesions

Random Forest

Details

Title: Subtitle: Comparison of classifier performance for information fusion in automated Diabetic Retinopathy screening
Creators: Meindert Niemeijer - Dept. of Ophthalmology & Visual Sci., Univ. of Iowa, Iowa City, IA, USA
Michael D Abràmoff - Dept. of Ophthalmology & Visual Sci., Univ. of Iowa, Iowa City, IA, USA
Niranjan Joshi - Wolfson Med. Vision Lab., Univ. of Oxford, Oxford, UK
Michael Brady - Wolfson Med. Vision Lab., Univ. of Oxford, Oxford, UK
Resource Type: Conference proceeding
Publication Details: 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp.685-688
Publisher: IEEE
DOI: 10.1109/ISBI.2011.5872499
ISSN: 1945-7928
eISSN: 1945-8452
Language: English
Date published: 03/2011
Academic Unit: Ophthalmology and Visual Sciences; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; Fraternal Order of Eagles Diabetes Research Center
Record Identifier: 9984060879002771

Metrics

7 Record Views