PMID- 35469472
OWN - NLM
STAT- MEDLINE
DCOM- 20230110
LR  - 20230111
IS  - 1724-6016 (Electronic)
IS  - 1120-6721 (Linking)
VI  - 33
IP  - 1
DP  - 2023 Jan
TI  - Artificial intelligence based detection of age-related macular degeneration using 
      optical coherence tomography with unique image preprocessing.
PG  - 65-73
LID - 10.1177/11206721221096294 [doi]
AB  - PURPOSE: The aim of the study is to improve the accuracy of age related macular 
      degeneration (AMD) disease in its earlier phases with proposed Capsule Network 
      (CapsNet) architecture trained on speckle noise reduced spectral domain optical 
      coherence tomography (SD-OCT) images based on an optimized Bayesian non-local 
      mean (OBNLM) filter augmentation techniques. METHODS: A total of 726 local SD-OCT 
      images were collected and labelled as 159 drusen, 145 dry AMD, 156 wet AMD and 
      266 normal. Region of interest (ROI) was identified. Speckle noise in SD-OCT 
      images were reduced based on OBNLM filter. The processed images were fed to 
      proposed CapsNet architecture to clasify SD-OCT images. Accuracy rates were 
      calculated in both public and local dataset. RESULTS: Accuracy rate of local 
      SD-OCT image dataset classification was achieved to a value of 96.39% after 
      performing data augmentation and speckle noise reduction with OBNLM. The 
      performance of proposed CapsNet was also evaluated on the public Kaggle dataset 
      under the same processing procedures and the accuracy rate was calculated as 
      98.07%. The sensitivity and specificity rates were 96.72% and 99.98%, 
      respectively. CONCLUSIONS: The classification success of proposed CapsNet may be 
      improved with robust pre-processing steps like; determination of ROI and denoised 
      SD-OCT images based on OBNLM. These impactful image preprocessing steps yielded 
      higher accuracy rates for determining different types of AMD including its 
      precursor lesion on the both local and public dataset with proposed CapsNet 
      architecture.
FAU - Celebi, Ali Riza Cenk
AU  - Celebi ARC
AUID- ORCID: 0000-0002-7952-1241
AD  - Department of Ophthalmology, Acibadem University School of Medicine, Istanbul, 
      Turkey.
FAU - Bulut, Erkan
AU  - Bulut E
AD  - Department of Ophthalmology, Beylikduzu Public Hospital, Istanbul, Turkey.
FAU - Sezer, Aysun
AU  - Sezer A
AD  - United'Informatique et d'Ingenierie des Systemes, 52849ENSTA-ParisTech, 
      Universite de Paris-Saclay, Villefranche Sur Mer, Provence-Alpes-Cote d'azur, 
      France.
LA  - eng
PT  - Journal Article
DEP - 20220425
PL  - United States
TA  - Eur J Ophthalmol
JT  - European journal of ophthalmology
JID - 9110772
SB  - IM
MH  - Humans
MH  - *Artificial Intelligence
MH  - Tomography, Optical Coherence/methods
MH  - Bayes Theorem
MH  - Retina
MH  - *Wet Macular Degeneration/diagnosis
OTO - NOTNLM
OT  - AMD
OT  - Capsule network
OT  - OBNLM
OT  - SD-OCT
OT  - data augmentation
OT  - deep learning
EDAT- 2022/04/27 06:00
MHDA- 2023/01/11 06:00
CRDT- 2022/04/26 05:53
PHST- 2022/04/27 06:00 [pubmed]
PHST- 2023/01/11 06:00 [medline]
PHST- 2022/04/26 05:53 [entrez]
AID - 10.1177/11206721221096294 [doi]
PST - ppublish
SO  - Eur J Ophthalmol. 2023 Jan;33(1):65-73. doi: 10.1177/11206721221096294. Epub 2022 
      Apr 25.