Automated detection of malarial retinopathy-associated retinal hemorrhages.

Journal article

PURPOSE: To develop an automated method for the detection of retinal hemorrhages on color fundus images to characterize malarial retinopathy, which may help in the assessment of patients with cerebral malaria. METHODS: A fundus image dataset from 14 patients (200 fundus images, with an average of 14 images per patient) previously diagnosed with malarial retinopathy was examined. We developed a pattern recognition-based algorithm, which extracted features from image watershed regions called sp...

Expand abstract

Authors: Joshi, V; Maude, R; Reinhardt, J; Tang, L; Garvin, M

• Publication status: Published
• Journal: Investigative ophthalmology and visual science
• Volume: 53
• Issue: 10
• Pages: 6582-6588
• Publication date: 2012-10-01
• DOI: 10.1167/iovs.12-10191
• EISSN: 1552-5783
• ISSN: 0146-0404
• Language: English
• Keywords: Algorithms; Retinal Hemorrhage; Predictive Value of Tests; False Negative Reactions; Diagnosis, Computer-Assisted; Humans; False Positive Reactions; Sensitivity and Specificity; Malaria; Area Under Curve; Cross-Over Studies; Pilot Projects; Eye Infections, Parasitic; Image Processing, Computer-Assisted