Análisis de la capa de células ganglionares con deep learning en el diagnóstico de glaucoma

  1. Valentín Tinguaro Díaz Alemán 1
  2. F.J. Fumero 2
  3. Silvia Alayón Miranda 2
  4. Denisse Ángel Pereira 1
  5. V. Arteaga Hernández 1
  6. José Francisco Sigut Saavedra 2
  1. 1 Hospital Universitario de Canarias

    Hospital Universitario de Canarias

    San Cristóbal de La Laguna, España

    GRID grid.411220.4

  2. 2 Universidad de La Laguna

    Universidad de La Laguna

    San Cristobal de La Laguna, España

    GRID grid.10041.34

Archivos de la Sociedad Española de Oftalmologia

ISSN: 0365-6691

Year of publication: 2021

Volume: 96

Issue: 4

Pages: 181-188

Type: Article

Export: RIS
DOI: 10.1016/j.oftal.2020.09.010 GOOGLE SCHOLAR


SCImago Journal Rank

(Indicator corresponding to the last year available on this portal, year 2020)
  • Year 2020
  • SJR Journal Impact: 0.243
  • Best Quartile: Q4
  • Area: Ophthalmology Quartile: Q4 Rank in area: 93/124


(Indicator corresponding to the last year available on this portal, year 2020)
  • Year 2020
  • CiteScore of the Journal : 0.7
  • Area: Ophthalmology Percentile: 24


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.