PMID- 33279356
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20211008
LR  - 20211008
IS  - 2173-5794 (Electronic)
IS  - 2173-5794 (Linking)
VI  - 96
IP  - 4
DP  - 2021 Apr
TI  - Ganglion cell layer analysis with deep learning in glaucoma diagnosis.
PG  - 181-188
LID - S0365-6691(20)30385-3 [pii]
LID - 10.1016/j.oftal.2020.09.010 [doi]
AB  - OBJECTIVE: To determine and compare the diagnostic precision in glaucoma of two 
      deep learning models using infrared images of the optic nerve, eye fundus, and 
      the ganglion cell layer (GCL). METHODS: We have selected a sample of normal and 
      glaucoma patients. Three infrared images were registered with a spectral-domain 
      optical coherence tomography (SD-OCT). The first corresponds to the confocal scan 
      image of the fundus, the second is a cut-out of the first centered on the optic 
      nerve, and the third was the SD-OCT image of the GCL. Our deep learning models 
      are developed on the MatLab platform with the ResNet50 and VGG19 pre-trained 
      neural networks. RESULTS: 498 eyes of 298 patients were collected. Of the 498 
      eyes, 312 are glaucoma and 186 are normal. In the test, the precision of the 
      models was 96% (ResNet50) and 96% (VGG19) for the GCL images, 90% (ResNet50) and 
      90% (VGG19) for the optic nerve images and 82% (ResNet50) and 84% (VGG19) for the 
      fundus images. The ROC area in the test was 0.96 (ResNet50) and 0.97 (VGG19) for 
      the GCL images, 0.87 (ResNet50) and 0.88 (VGG19) for the optic nerve images, and 
      0.79 (ResNet50) and 0.81 (VGG19) for the fundus images. CONCLUSIONS: Both deep 
      learning models, applied to the GCL images, achieve high diagnostic precision, 
      sensitivity and specificity in the diagnosis of glaucoma.
CI  - Copyright (c) 2020 Sociedad Espanola de Oftalmologia. Publicado por Elsevier 
      Espana, S.L.U. All rights reserved.
FAU - Diaz-Aleman, Valentin Tinguaro
AU  - Diaz-Aleman VT
AD  - Unidad de Glaucoma. Servicio de Oftalmologia. Hospital Universitario de Canarias, 
      Santa Cruz de Tenerife, Espana. Electronic address: vtdac@hotmail.com.
FAU - Fumero Batista, Francisco Jose
AU  - Fumero Batista FJ
AD  - Departamento de Ingenieria Informatica y de Sistemas. Facultad de Fisica. 
      Universidad de La Laguna, Santa Cruz de Tenerife, Espana.
FAU - Alayon Miranda, Silvia
AU  - Alayon Miranda S
AD  - Departamento de Ingenieria Informatica y de Sistemas. Facultad de Fisica. 
      Universidad de La Laguna, Santa Cruz de Tenerife, Espana.
FAU - Angel-Pereira, Denisse
AU  - Angel-Pereira D
AD  - Unidad de Glaucoma. Servicio de Oftalmologia. Hospital Universitario de Canarias, 
      Santa Cruz de Tenerife, Espana.
FAU - Arteaga-Hernandez, Victor Javier
AU  - Arteaga-Hernandez VJ
AD  - Unidad de Glaucoma. Servicio de Oftalmologia. Hospital Universitario de Canarias, 
      Santa Cruz de Tenerife, Espana.
FAU - Sigut Saavedra, Jose Francisco
AU  - Sigut Saavedra JF
AD  - Departamento de Ingenieria Informatica y de Sistemas. Facultad de Fisica. 
      Universidad de La Laguna, Santa Cruz de Tenerife, Espana.
LA  - eng
LA  - spa
PT  - Journal Article
TT  - Analisis de la capa de celulas ganglionares con deep learning en el diagnostico 
      de glaucoma.
DEP - 20201202
PL  - Spain
TA  - Arch Soc Esp Oftalmol (Engl Ed)
JT  - Archivos de la Sociedad Espanola de Oftalmologia
JID - 101715860
SB  - IM
OTO - NOTNLM
OT  - Aprendizaje profundo
OT  - Celulas ganglionares
OT  - Deep learning
OT  - Ganglion cells
OT  - Glaucoma
OT  - Tomografia
OT  - Tomography
EDAT- 2020/12/07 06:00
MHDA- 2020/12/07 06:01
CRDT- 2020/12/06 20:41
PHST- 2020/05/25 00:00 [received]
PHST- 2020/09/12 00:00 [revised]
PHST- 2020/09/16 00:00 [accepted]
PHST- 2020/12/07 06:00 [pubmed]
PHST- 2020/12/07 06:01 [medline]
PHST- 2020/12/06 20:41 [entrez]
AID - S0365-6691(20)30385-3 [pii]
AID - 10.1016/j.oftal.2020.09.010 [doi]
PST - ppublish
SO  - Arch Soc Esp Oftalmol (Engl Ed). 2021 Apr;96(4):181-188. doi: 
      10.1016/j.oftal.2020.09.010. Epub 2020 Dec 2.