PMID- 24474272
OWN - NLM
STAT- MEDLINE
DCOM- 20140414
LR  - 20220321
IS  - 1552-5783 (Electronic)
IS  - 0146-0404 (Linking)
VI  - 55
IP  - 2
DP  - 2014 Feb 26
TI  - Automated segmentation of optic nerve head structures with optical coherence 
      tomography.
PG  - 1161-8
LID - 10.1167/iovs.13-13310 [doi]
AB  - PURPOSE: To quantify and characterize the difference between automated and manual 
      segmentation of optic nerve head structures with spectral-domain optical 
      coherence tomography (SD-OCT). METHODS: Optic nerve head radial scans in 107 
      glaucoma patients and 48 healthy controls were conducted with SD-OCT. Independent 
      segmentations of the internal limiting membrane (ILM) and Bruch's membrane 
      opening (BMO) were performed manually with custom software and with an automated 
      algorithm in each radial scan. The minimum distance between BMO and ILM, termed 
      BMO-minimum rim width (BMO-MRW) was calculated with each segmentation method. 
      Absolute differences between automated and manual segmentations of ILM (DeltaILM) and 
      BMO (DeltaBMO), and the resulting computation of BMO-MRW (DeltaBMO-MRW) were computed. 
      Finally, the relationship between image quality score and DeltaILM and DeltaBMO was 
      explored. RESULTS: The median (interquartile range, IQR) DeltaILM was 8.9 (6.5, 13.4) 
      mum in patients and 7.3 (5.3, 9.9) mum in controls. The corresponding values for 
      DeltaBMO were 11.5 (6.6, 22.1) mum and 12.4 (6.8, 25.4) mum. Subject-averaged DeltaILM was 
      higher in patients than controls (P < 0.01); however, mean DeltaBMO was not (P = 
      0.09). The median (IQR) subject-averaged absolute DeltaBMO-MRW was 13.4 (10.6, 16.8) 
      mum in patients and 12.1 (10.0, 16.8) mum in controls and not statistically 
      different (P = 0.21). Mean image quality score was statistically higher in 
      controls than patients (P = 0.03) but not related to subject-averaged DeltaILM or 
      DeltaBMO. CONCLUSIONS: In individual scans, the median difference in ILM and BMO 
      segmentations was <2 and <3 image pixels, respectively. There were no differences 
      between patients and controls in DeltaBMO-MRW.
FAU - Almobarak, Faisal A
AU  - Almobarak FA
AD  - Department of Ophthalmology and Visual Sciences, Dalhousie University, Halifax, 
      Nova Scotia, Canada.
FAU - O'Leary, Neil
AU  - O'Leary N
FAU - Reis, Alexandre S C
AU  - Reis AS
FAU - Sharpe, Glen P
AU  - Sharpe GP
FAU - Hutchison, Donna M
AU  - Hutchison DM
FAU - Nicolela, Marcelo T
AU  - Nicolela MT
FAU - Chauhan, Balwantray C
AU  - Chauhan BC
LA  - eng
GR  - MOP11357/Canadian Institutes of Health Research/Canada
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20140226
PL  - United States
TA  - Invest Ophthalmol Vis Sci
JT  - Investigative ophthalmology & visual science
JID - 7703701
SB  - IM
MH  - Aged
MH  - Algorithms
MH  - Bruch Membrane/pathology
MH  - Epiretinal Membrane/pathology
MH  - Glaucoma, Open-Angle/*diagnosis
MH  - Humans
MH  - Intraocular Pressure
MH  - Middle Aged
MH  - Optic Disk/*pathology
MH  - Optic Nerve Diseases/*diagnosis
MH  - Tomography, Optical Coherence/*methods
MH  - Visual Fields
OTO - NOTNLM
OT  - glaucoma
OT  - optic nerve head
OT  - optical coherence tomography
EDAT- 2014/01/30 06:00
MHDA- 2014/04/15 06:00
CRDT- 2014/01/30 06:00
PHST- 2014/01/30 06:00 [entrez]
PHST- 2014/01/30 06:00 [pubmed]
PHST- 2014/04/15 06:00 [medline]
AID - iovs.13-13310 [pii]
AID - 10.1167/iovs.13-13310 [doi]
PST - epublish
SO  - Invest Ophthalmol Vis Sci. 2014 Feb 26;55(2):1161-8. doi: 10.1167/iovs.13-13310.