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

Autor: Ronchetti T; Department of Biomedical Engineering (DBE), University of Basel, Basel, Switzerland.; Institute for Human Centered Engineering (HuCE)-optoLab, Bern University of Applied Sciences, Bern, Switzerland.; OCTlab, Department of Ophthalmology, University Hospital Basel, Basel, Switzerland., Jud C; Department of Biomedical Engineering (DBE), University of Basel, Basel, Switzerland., Maloca PM; OCTlab, Department of Ophthalmology, University Hospital Basel, Basel, Switzerland.; Department of Ophthalmology, University of Basel, Basel, Switzerland.; Moorfields Eye Hospital, London, United Kingdom.; Institute of Molecular and Clinical Ophthalmology Basel (IOB), Basel, Switzerland., Orgül S; Department of Ophthalmology, University of Basel, Basel, Switzerland., Giger AT; Department of Biomedical Engineering (DBE), University of Basel, Basel, Switzerland., Meier C; Institute for Human Centered Engineering (HuCE)-optoLab, Bern University of Applied Sciences, Bern, Switzerland., Scholl HPN; Department of Ophthalmology, University of Basel, Basel, Switzerland.; Institute of Molecular and Clinical Ophthalmology Basel (IOB), Basel, Switzerland.; Wilmer Eye Institute, Johns Hopkins University, Baltimore, Maryland, United States of America., Chun RKM; School of Optometry, The Hong Kong Polytechnic University (PolyU), Hong Kong, PR China., Liu Q; School of Optometry, The Hong Kong Polytechnic University (PolyU), Hong Kong, PR China.; State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, PR China., To CH; School of Optometry, The Hong Kong Polytechnic University (PolyU), Hong Kong, PR China.; State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, PR China., Považay B; Institute for Human Centered Engineering (HuCE)-optoLab, Bern University of Applied Sciences, Bern, Switzerland., Cattin PC; Department of Biomedical Engineering (DBE), University of Basel, Basel, Switzerland.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2019 Jun 28; Vol. 14 (6), pp. e0218776. Date of Electronic Publication: 2019 Jun 28 (Print Publication: 2019).
DOI: 10.1371/journal.pone.0218776
Abstrakt: 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.
Competing Interests: The authors have declared that no competing interests exist.
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje