Accuracy of ultrawide-field fundus ophthalmoscopy-assisted deep learning for detecting treatment-naïve proliferative diabetic retinopathy

Int Ophthalmol. 2019 Oct;39(10):2153-2159. doi: 10.1007/s10792-019-01074-z. Epub 2019 Feb 23.

Abstract

Purpose: We investigated using ultrawide-field fundus images with a deep convolutional neural network (DCNN), which is a machine learning technology, to detect treatment-naïve proliferative diabetic retinopathy (PDR).

Methods: We conducted training with the DCNN using 378 photographic images (132 PDR and 246 non-PDR) and constructed a deep learning model. The area under the curve (AUC), sensitivity, and specificity were examined.

Result: The constructed deep learning model demonstrated a high sensitivity of 94.7% and a high specificity of 97.2%, with an AUC of 0.969.

Conclusion: Our findings suggested that PDR could be diagnosed using wide-angle camera images and deep learning.

Keywords: Deep convolutional neural network; Deep learning; Proliferative diabetic retinopathy; Ultrawide-field fundus ophthalmoscopy.

Publication types

  • Letter

MeSH terms

  • Adult
  • Aged
  • Area Under Curve
  • Deep Learning*
  • Diabetic Retinopathy / diagnosis*
  • Diagnosis, Computer-Assisted / methods*
  • Female
  • Humans
  • Male
  • Middle Aged
  • Ophthalmoscopy / methods*
  • Sensitivity and Specificity