PMID- 28528295
OWN - NLM
STAT- MEDLINE
DCOM- 20180525
LR  - 20181202
IS  - 1361-8423 (Electronic)
IS  - 1361-8415 (Print)
IS  - 1361-8415 (Linking)
VI  - 39
DP  - 2017 Jul
TI  - A machine-learning graph-based approach for 3D segmentation of Bruch's membrane 
      opening from glaucomatous SD-OCT volumes.
PG  - 206-217
LID - S1361-8415(17)30065-8 [pii]
LID - 10.1016/j.media.2017.04.007 [doi]
AB  - Bruch's membrane opening-minimum rim width (BMO-MRW) is a recently proposed 
      structural parameter which estimates the remaining nerve fiber bundles in the 
      retina and is superior to other conventional structural parameters for diagnosing 
      glaucoma. Measuring this structural parameter requires identification of BMO 
      locations within spectral domain-optical coherence tomography (SD-OCT) volumes. 
      While most automated approaches for segmentation of the BMO either segment the 2D 
      projection of BMO points or identify BMO points in individual B-scans, in this 
      work, we propose a machine-learning graph-based approach for true 3D segmentation 
      of BMO from glaucomatous SD-OCT volumes. The problem is formulated as an 
      optimization problem for finding a 3D path within the SD-OCT volume. In 
      particular, the SD-OCT volumes are transferred to the radial domain where the 
      closed loop BMO points in the original volume form a path within the radial 
      volume. The estimated location of BMO points in 3D are identified by finding the 
      projected location of BMO points using a graph-theoretic approach and mapping the 
      projected locations onto the Bruch's membrane (BM) surface. Dynamic programming 
      is employed in order to find the 3D BMO locations as the minimum-cost path within 
      the volume. In order to compute the cost function needed for finding the 
      minimum-cost path, a random forest classifier is utilized to learn a BMO model, 
      obtained by extracting intensity features from the volumes in the training set, 
      and computing the required 3D cost function. The proposed method is tested on 44 
      glaucoma patients and evaluated using manual delineations. Results show that the 
      proposed method successfully identifies the 3D BMO locations and has 
      significantly smaller errors compared to the existing 3D BMO identification 
      approaches.
CI  - Published by Elsevier B.V.
FAU - Miri, Mohammad Saleh
AU  - Miri MS
AD  - Department of Electrical and Computer Engineering, The University of Iowa, Iowa 
      City, IA, 52242, United States.
FAU - Abramoff, Michael D
AU  - Abramoff MD
AD  - Department of Electrical and Computer Engineering, The University of Iowa, Iowa 
      City, IA, 52242, United States; Department of Biomedical Engineering, The 
      University of Iowa, Iowa City, IA, 52242, United States; Department of 
      Ophthalmology and Visual Sciences, The University of Iowa, Iowa City, IA, 52242, 
      United States; Iowa City VA Health Care System, Iowa City, IA, 52246, United 
      States.
FAU - Kwon, Young H
AU  - Kwon YH
AD  - Department of Ophthalmology and Visual Sciences, The University of Iowa, Iowa 
      City, IA, 52242, United States.
FAU - Sonka, Milan
AU  - Sonka M
AD  - Department of Electrical and Computer Engineering, The University of Iowa, Iowa 
      City, IA, 52242, United States; Department of Ophthalmology and Visual Sciences, 
      The University of Iowa, Iowa City, IA, 52242, United States.
FAU - Garvin, Mona K
AU  - Garvin MK
AD  - Department of Electrical and Computer Engineering, The University of Iowa, Iowa 
      City, IA, 52242, United States; Iowa City VA Health Care System, Iowa City, IA, 
      52246, United States. Electronic address: mona-garvin@uiowa.edu.
LA  - eng
GR  - IK2 RX000728/RX/RRD VA/United States
GR  - R01 EY018853/EY/NEI NIH HHS/United States
GR  - R01 EY023279/EY/NEI NIH HHS/United States
PT  - Journal Article
DEP - 20170506
PL  - Netherlands
TA  - Med Image Anal
JT  - Medical image analysis
JID - 9713490
SB  - IM
MH  - Bruch Membrane/*diagnostic imaging/pathology
MH  - Glaucoma/*diagnostic imaging/pathology
MH  - Humans
MH  - Imaging, Three-Dimensional/*methods
MH  - *Machine Learning
MH  - Optic Disk/diagnostic imaging/pathology
MH  - Tomography, Optical Coherence/*methods
PMC - PMC5729043
MID - NIHMS878868
OTO - NOTNLM
OT  - Bruch's membrane opening
OT  - Ophthalmology
OT  - Optic disc
OT  - Retina
OT  - SD-OCT
OT  - Segmentation
EDAT- 2017/05/22 06:00
MHDA- 2018/05/26 06:00
PMCR- 2018/07/01
CRDT- 2017/05/22 06:00
PHST- 2016/03/11 00:00 [received]
PHST- 2017/04/24 00:00 [revised]
PHST- 2017/04/26 00:00 [accepted]
PHST- 2017/05/22 06:00 [pubmed]
PHST- 2018/05/26 06:00 [medline]
PHST- 2017/05/22 06:00 [entrez]
PHST- 2018/07/01 00:00 [pmc-release]
AID - S1361-8415(17)30065-8 [pii]
AID - 10.1016/j.media.2017.04.007 [doi]
PST - ppublish
SO  - Med Image Anal. 2017 Jul;39:206-217. doi: 10.1016/j.media.2017.04.007. Epub 2017 
      May 6.