TY - JOUR
T1 - Validating retinal fundus image analysis algorithms
T2 - issues and a proposal.
AU - Trucco, Emanuele
AU - Ruggeri, Alfredo
AU - Karnowski, Thomas
AU - Giancardo, Luca
AU - Chaum, Edward
AU - Hubschman, Jean Pierre
AU - Al-Diri, Bashir
AU - Cheung, Carol Y.
AU - Wong, Damon
AU - Abràmoff, Michael
AU - Lim, Gilbert
AU - Kumar, Dinesh
AU - Burlina, Philippe
AU - Bressler, Neil M.
AU - Jelinek, Herbert F.
AU - Meriaudeau, Fabrice
AU - Quellec, Gwénolé
AU - Macgillivray, Tom
AU - Dhillon, Bal
PY - 2013/5
Y1 - 2013/5
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84883286209&partnerID=8YFLogxK
U2 - 10.1167/iovs.12-10347
DO - 10.1167/iovs.12-10347
M3 - Article
C2 - 23794433
AN - SCOPUS:84883286209
VL - 54
SP - 3546
EP - 3559
JO - Unknown Journal
JF - Unknown Journal
IS - 5
ER -