PMID- 33785808
OWN - NLM
STAT- MEDLINE
DCOM- 20211025
LR  - 20211025
IS  - 2045-2322 (Electronic)
IS  - 2045-2322 (Linking)
VI  - 11
IP  - 1
DP  - 2021 Mar 30
TI  - Deep learning and ensemble stacking technique for differentiating polypoidal 
      choroidal vasculopathy from neovascular age-related macular degeneration.
PG  - 7130
LID - 10.1038/s41598-021-86526-2 [doi]
LID - 7130
AB  - Polypoidal choroidal vasculopathy (PCV) and neovascular age-related macular 
      degeneration (nAMD) share some similarity in clinical imaging manifestations. 
      However, their disease entity and treatment strategy as well as visual outcomes 
      are very different. To distinguish these two vision-threatening diseases is 
      somewhat challenging but necessary. In this study, we propose a new artificial 
      intelligence model using an ensemble stacking technique, which combines a color 
      fundus photograph-based deep learning (DL) model and optical coherence 
      tomography-based biomarkers, for differentiation of PCV from nAMD. Furthermore, 
      we introduced multiple correspondence analysis, a method of transforming 
      categorical data into principal components, to handle the dichotomous data for 
      combining with another image DL system. This model achieved a robust performance 
      with an accuracy, sensitivity, specificity, and area under the receiver operating 
      characteristic curve of 83.67%, 80.76%, 84.72%, and 88.57%, respectively, by 
      training nearly 700 active cases with suitable imaging quality and transfer 
      learning architecture. This work could offer an alternative method of developing 
      a multimodal DL model, improve its efficiency for distinguishing different 
      diseases, and facilitate the broad application of medical engineering in a DL 
      model design.
FAU - Chou, Yu-Bai
AU  - Chou YB
AD  - Department of Ophthalmology, Taipei Veterans General Hospital, Taipei, Taiwan.
AD  - School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
FAU - Hsu, Chung-Hsuan
AU  - Hsu CH
AD  - Institute of Statistics, National Yang Ming Chiao Tung University, Hsin Chu, 
      Taiwan.
FAU - Chen, Wei-Shiang
AU  - Chen WS
AD  - Institute of Statistics, National Yang Ming Chiao Tung University, Hsin Chu, 
      Taiwan.
FAU - Chen, Shih-Jen
AU  - Chen SJ
AD  - Department of Ophthalmology, Taipei Veterans General Hospital, Taipei, Taiwan.
AD  - School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
FAU - Hwang, De-Kuang
AU  - Hwang DK
AD  - Department of Ophthalmology, Taipei Veterans General Hospital, Taipei, Taiwan.
AD  - School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
FAU - Huang, Yi-Ming
AU  - Huang YM
AD  - Department of Ophthalmology, Taipei Veterans General Hospital, Taipei, Taiwan.
AD  - School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
FAU - Li, An-Fei
AU  - Li AF
AD  - School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
AD  - Department of Ophthalmology, Cheng Hsin General Hospital, Taipei, Taiwan.
FAU - Lu, Henry Horng-Shing
AU  - Lu HH
AD  - Institute of Statistics, National Yang Ming Chiao Tung University, Hsin Chu, 
      Taiwan. hslu@stat.nctu.edu.tw.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
PT  - Validation Study
DEP - 20210330
PL  - England
TA  - Sci Rep
JT  - Scientific reports
JID - 101563288
SB  - IM
MH  - Choroid Diseases/*diagnostic imaging
MH  - *Deep Learning
MH  - Diagnosis, Differential
MH  - Feasibility Studies
MH  - Humans
MH  - Macular Degeneration/*diagnostic imaging
MH  - Retrospective Studies
MH  - Tomography, Optical Coherence
PMC - PMC8010118
COIS- The authors declare no competing interests.
EDAT- 2021/04/01 06:00
MHDA- 2021/10/26 06:00
PMCR- 2021/03/30
CRDT- 2021/03/31 06:22
PHST- 2020/09/10 00:00 [received]
PHST- 2021/02/09 00:00 [accepted]
PHST- 2021/03/31 06:22 [entrez]
PHST- 2021/04/01 06:00 [pubmed]
PHST- 2021/10/26 06:00 [medline]
PHST- 2021/03/30 00:00 [pmc-release]
AID - 10.1038/s41598-021-86526-2 [pii]
AID - 86526 [pii]
AID - 10.1038/s41598-021-86526-2 [doi]
PST - epublish
SO  - Sci Rep. 2021 Mar 30;11(1):7130. doi: 10.1038/s41598-021-86526-2.