PMID- 27066311 OWN - NLM STAT- PubMed-not-MEDLINE LR - 20220309 IS - 2164-2591 (Print) IS - 2164-2591 (Electronic) IS - 2164-2591 (Linking) VI - 5 IP - 2 DP - 2016 Mar TI - Automated Segmentability Index for Layer Segmentation of Macular SD-OCT Images. PG - 14 LID - 14 AB - PURPOSE: To automatically identify which spectral-domain optical coherence tomography (SD-OCT) scans will provide reliable automated layer segmentations for more accurate layer thickness analyses in population studies. METHODS: Six hundred ninety macular SD-OCT image volumes (6.0 x 6.0 x 2.3 mm(3)) were obtained from one eyes of 690 subjects (74.6 +/- 9.7 [mean +/- SD] years, 37.8% of males) randomly selected from the population-based Rotterdam Study. The dataset consisted of 420 OCT volumes with successful automated retinal nerve fiber layer (RNFL) segmentations obtained from our previously reported graph-based segmentation method and 270 volumes with failed segmentations. To evaluate the reliability of the layer segmentations, we have developed a new metric, segmentability index SI, which is obtained from a random forest regressor based on 12 features using OCT voxel intensities, edge-based costs, and on-surface costs. The SI was compared with well-known quality indices, quality index (QI), and maximum tissue contrast index (mTCI), using receiver operating characteristic (ROC) analysis. RESULTS: The 95% confidence interval (CI) and the area under the curve (AUC) for the QI are 0.621 to 0.805 with AUC 0.713, for the mTCI 0.673 to 0.838 with AUC 0.756, and for the SI 0.784 to 0.920 with AUC 0.852. The SI AUC is significantly larger than either the QI or mTCI AUC (P < 0.01). CONCLUSIONS: The segmentability index SI is well suited to identify SD-OCT scans for which successful automated intraretinal layer segmentations can be expected. TRANSLATIONAL RELEVANCE: Interpreting the quantification of SD-OCT images requires the underlying segmentation to be reliable, but standard SD-OCT quality metrics do not predict which segmentations are reliable and which are not. The segmentability index SI presented in this study does allow reliable segmentations to be identified, which is important for more accurate layer thickness analyses in research and population studies. FAU - Lee, Kyungmoo AU - Lee K AD - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA, USA ; Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA, USA. FAU - Buitendijk, Gabrielle H S AU - Buitendijk GH AD - Department of Ophthalmology, Erasmus Medical Center, Rotterdam, the Netherlands ; Department of Epidemiology, Erasmus Medical Center, Rotterdam, the Netherlands. FAU - Bogunovic, Hrvoje AU - Bogunovic H AD - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA, USA ; Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA, USA. FAU - Springelkamp, Henriet AU - Springelkamp H AD - Department of Ophthalmology, Erasmus Medical Center, Rotterdam, the Netherlands ; Department of Epidemiology, Erasmus Medical Center, Rotterdam, the Netherlands. FAU - Hofman, Albert AU - Hofman A AD - Department of Epidemiology, Erasmus Medical Center, Rotterdam, the Netherlands ; Netherlands Consortium for Healthy Aging, Netherlands Genomics Initiative, the Hague, the Netherlands. FAU - Wahle, Andreas AU - Wahle A AD - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA, USA ; Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA, USA. FAU - Sonka, Milan AU - Sonka M AD - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA, USA ; Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA, USA ; Department of Ophthalmology and Visual Sciences, University of Iowa Hospitals and Clinics, Iowa City, IA, USA. FAU - Vingerling, Johannes R AU - Vingerling JR AD - Department of Ophthalmology, Erasmus Medical Center, Rotterdam, the Netherlands ; Department of Epidemiology, Erasmus Medical Center, Rotterdam, the Netherlands. FAU - Klaver, Caroline C W AU - Klaver CC AD - Department of Ophthalmology, Erasmus Medical Center, Rotterdam, the Netherlands ; Department of Epidemiology, Erasmus Medical Center, Rotterdam, the Netherlands. FAU - Abramoff, Michael D AU - Abramoff MD AD - Department of Electrical and Computer Engineering, University of Iowa, Iowa City, IA, USA ; Iowa Institute for Biomedical Imaging, University of Iowa, Iowa City, IA, USA ; Department of Ophthalmology and Visual Sciences, University of Iowa Hospitals and Clinics, Iowa City, IA, USA ; Department of Biomedical Engineering, University of Iowa, Iowa City, IA, USA ; Stephen A. Wynn Institute for Vision Research, University of Iowa, Iowa City, IA, USA ; Department of Veterans Affairs, Iowa City VA Medical Center, Iowa City, IA, USA. LA - eng GR - R01 EB004640/EB/NIBIB NIH HHS/United States GR - R01 EY017066/EY/NEI NIH HHS/United States GR - R01 EY018853/EY/NEI NIH HHS/United States PT - Journal Article DEP - 20160405 PL - United States TA - Transl Vis Sci Technol JT - Translational vision science & technology JID - 101595919 PMC - PMC4824284 OTO - NOTNLM OT - image quality OT - intraretinal layer segmentation OT - retinal nerve fiber layer OT - segmentability index OT - spectral-domain optical coherence tomography EDAT- 2016/04/12 06:00 MHDA- 2016/04/12 06:01 PMCR- 2016/04/05 CRDT- 2016/04/12 06:00 PHST- 2015/09/16 00:00 [received] PHST- 2016/01/29 00:00 [accepted] PHST- 2016/04/12 06:00 [entrez] PHST- 2016/04/12 06:00 [pubmed] PHST- 2016/04/12 06:01 [medline] PHST- 2016/04/05 00:00 [pmc-release] AID - MS#: TVST-15-0280 [pii] AID - 10.1167/tvst.5.2.14 [doi] PST - epublish SO - Transl Vis Sci Technol. 2016 Apr 5;5(2):14. doi: 10.1167/tvst.5.2.14. eCollection 2016 Mar.