PMID- 30605812
OWN - NLM
STAT- MEDLINE
DCOM- 20200325
LR  - 20200325
IS  - 1879-0534 (Electronic)
IS  - 0010-4825 (Linking)
VI  - 105
DP  - 2019 Feb
TI  - Automated geographic atrophy segmentation for SD-OCT images based on two-stage 
      learning model.
PG  - 102-111
LID - S0010-4825(18)30417-7 [pii]
LID - 10.1016/j.compbiomed.2018.12.013 [doi]
AB  - Automatic and reliable segmentation for geographic atrophy in spectral-domain 
      optical coherence tomography (SD-OCT) images is a challenging task. To develop an 
      effective segmentation method, a two-stage deep learning framework based on an 
      auto-encoder is proposed. Firstly, the axial data of cross-section images were 
      used as samples instead of the projection images of SD-OCT images. Next, a 
      two-stage learning model that includes offline-learning and self-learning was 
      designed based on a stacked sparse auto-encoder to obtain deep discriminative 
      representations. Finally, a fusion strategy was used to refine the segmentation 
      results based on the two-stage learning results. The proposed method was 
      evaluated on two datasets consisting of 55 and 56 cubes, respectively. For the 
      first dataset, our method obtained a mean overlap ratio (OR) of 89.85 +/- 6.35% and 
      an absolute area difference (AAD) of 4.79 +/- 7.16%. For the second dataset, the 
      mean OR and AAD were 84.48 +/- 11.98%, 11.09 +/- 13.61%, respectively. Compared with 
      the state-of-the-art algorithms, experiments indicate that the proposed algorithm 
      can provide more accurate segmentation results on these two datasets without 
      using retinal layer segmentation.
CI  - Copyright (c) 2018 Elsevier Ltd. All rights reserved.
FAU - Xu, Rongbin
AU  - Xu R
AD  - Shandong Provincial Key Laboratory of Network based Intelligent Computing, School 
      of Information Science and Engineering, University of Jinan, Jinan, China.
FAU - Niu, Sijie
AU  - Niu S
AD  - Shandong Provincial Key Laboratory of Network based Intelligent Computing, School 
      of Information Science and Engineering, University of Jinan, Jinan, China. 
      Electronic address: sjniu@hotmail.com.
FAU - Chen, Qiang
AU  - Chen Q
AD  - School of Computer Science and Engineering, Nanjing University of Science and 
      Technology, Nanjing, 210094, China.
FAU - Ji, Zexuan
AU  - Ji Z
AD  - School of Computer Science and Engineering, Nanjing University of Science and 
      Technology, Nanjing, 210094, China.
FAU - Rubin, Daniel
AU  - Rubin D
AD  - Department of Medicine (Biomedical Informatics Research), Stanford University 
      School of Medicine Stanford, CA, 94305, USA; Department of Radiology, Stanford 
      University, Stanford, CA, 94305, USA.
FAU - Chen, Yuehui
AU  - Chen Y
AD  - Shandong Provincial Key Laboratory of Network based Intelligent Computing, School 
      of Information Science and Engineering, University of Jinan, Jinan, China.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20181228
PL  - United States
TA  - Comput Biol Med
JT  - Computers in biology and medicine
JID - 1250250
SB  - IM
MH  - Geographic Atrophy/*diagnostic imaging
MH  - Humans
MH  - *Image Interpretation, Computer-Assisted
MH  - *Machine Learning
MH  - Retina/*diagnostic imaging
MH  - *Tomography, Optical Coherence
OTO - NOTNLM
OT  - Deep learning
OT  - Geographic atrophy
OT  - Image segmentation
OT  - Spectral-domain optical coherence tomography
OT  - Stack sparse auto-encoder
EDAT- 2019/01/04 06:00
MHDA- 2020/03/26 06:00
CRDT- 2019/01/04 06:00
PHST- 2018/09/20 00:00 [received]
PHST- 2018/12/27 00:00 [revised]
PHST- 2018/12/27 00:00 [accepted]
PHST- 2019/01/04 06:00 [pubmed]
PHST- 2020/03/26 06:00 [medline]
PHST- 2019/01/04 06:00 [entrez]
AID - S0010-4825(18)30417-7 [pii]
AID - 10.1016/j.compbiomed.2018.12.013 [doi]
PST - ppublish
SO  - Comput Biol Med. 2019 Feb;105:102-111. doi: 10.1016/j.compbiomed.2018.12.013. 
      Epub 2018 Dec 28.