Statistical framework for validation without ground truth of choroidal thickness changes detection

Ronchetti, T; Jud, C; Maloca, PM; Orgül, S; Giger, AT; Meier, C; Scholl, HPN; Chun, RKM; Liu, Q; To, CH; Považay, B; Cattin, PC

Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/81557

DC Field	Value	Language
dc.contributor	School of Optometry	-
dc.creator	Ronchetti, T	-
dc.creator	Jud, C	-
dc.creator	Maloca, PM	-
dc.creator	Orgül, S	-
dc.creator	Giger, AT	-
dc.creator	Meier, C	-
dc.creator	Scholl, HPN	-
dc.creator	Chun, RKM	-
dc.creator	Liu, Q	-
dc.creator	To, CH	-
dc.creator	Považay, B	-
dc.creator	Cattin, PC	-
dc.date.accessioned	2019-10-28T05:46:03Z	-
dc.date.available	2019-10-28T05:46:03Z	-
dc.identifier.uri	http://hdl.handle.net/10397/81557	-
dc.language.iso	en	en_US
dc.publisher	Public Library of Science	en_US
dc.rights	© 2019 Ronchetti et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.	en_US
dc.rights	The following publication Ronchetti T, Jud C, Maloca PM, Orgül S, Giger AT, Meier C, et al. (2019) Statistical framework for validation without ground truth of choroidal thickness changes detection. PLoS ONE 14(6): e0218776, is available athttps://doi.org/10.1371/journal.pone.0218776	en_US
dc.title	Statistical framework for validation without ground truth of choroidal thickness changes detection	en_US
dc.type	Journal/Magazine Article	en_US
dc.identifier.volume	14	-
dc.identifier.issue	6	-
dc.identifier.doi	10.1371/journal.pone.0218776	-
dcterms.abstract	Monitoring subtle choroidal thickness changes in the human eye delivers insight into the pathogenesis of various ocular diseases such as myopia and helps planning their treatment. However, a thorough evaluation of detection-performance is challenging as a ground truth for comparison is not available. Alternatively, an artificial ground truth can be generated by averaging the manual expert segmentations. This makes the ground truth very sensitive to ambiguities due to different interpretations by the experts. In order to circumvent this limitation, we present a novel validation approach that operates independently from a ground truth and is uniquely based on the common agreement between algorithm and experts. Utilizing an appropriate index, we compare the joint agreement of several raters with the algorithm and validate it against manual expert segmentation. To illustrate this, we conduct an observational study and evaluate the results obtained using our previously published registration-based method. In addition, we present an adapted state-of-the-art evaluation method, where a paired t-test is carried out after leaving out the results of one expert at the time. Automated and manual detection were performed on a dataset of 90 OCT 3D-volume stack pairs of healthy subjects between 8 and 18 years of age from Asian urban regions with a high prevalence of myopia.	-
dcterms.bibliographicCitation	PLoS one, 2019, v. 14, no. 6, e0218776	-
dcterms.isPartOf	PLoS one	-
dcterms.issued	2019	-
dc.identifier.scopus	2-s2.0-85068959291	-
dc.identifier.pmid	31251762	-
dc.identifier.eissn	1932-6203	-
dc.identifier.artn	e0218776	-
dc.description.validate	201910 bcma	-
dc.description.oa	published_final	-
Appears in Collections:	Journal/Magazine Article