Validating retinal fundus image analysis algorithms: issues and a proposal

Trucco, Emanuele and Ruggeri, Alfredo and Karnowski, Thomas and Giancardo, Luca and Chaum, Edward and Hubschman, Jean Pierre and Al-Diri, Bashir and Cheung, Carol Y and Wong, Damon and Abramoff, Michael and Lim, Gilbert and Kumar, Dinesh and Burlina, Philippe and Bressler, Neil M. and Jelinek, Herbert and Meriaudeau, Fabrice and Quellec, Gwenole and MacGillivray, Tom and Dhillon, Bal and UNSPECIFIED and UNSPECIFIED (2013) Validating retinal fundus image analysis algorithms: issues and a proposal. Investigative Ophthalmology & Visual Science, 54 (5). pp. 3546-3559. ISSN 0146-0404

Documents
Validating Retinal Fundus Image Analysis Algorithms Issues and a Proposal.pdf
[img]
[Download]
[img]
Preview
PDF
Validating Retinal Fundus Image Analysis Algorithms Issues and a Proposal.pdf - Whole Document
Available under License Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International.

396kB
Item Type:Article
Item Status:Live Archive

Abstract

This paper concerns the validation of automatic retinal image analysis (ARIA) algorithms. For reasons of space and consistency, we concentrate on the validation of algorithms processing color fundus camera images, currently the largest section of the ARIA literature. We sketch the context (imaging instruments and target tasks) of ARIA validation, summarizing the main image analysis and validation techniques. We then present a list of recommendations focusing on the creation of large repositories of test data created by international consortia, easily accessible via moderated Web sites, including multicenter annotations by multiple experts, specific to clinical tasks, and capable of running submitted software automatically on the data stored, with clear and widely agreed-on performance criteria, to provide a fair comparison.

Keywords:fundus image analysis, reference standards, validation
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:26837
Deposited On:05 Apr 2017 14:02

Repository Staff Only: item control page