The Diagnosis Of Diabetic Retinopathy By Means Of Transfer Learning And Fine-Tuned Dense Layer Pipeline

Authors

  • Abdulaziz Abdo Salman Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, Malaysia.
  • Ismail Mohd Khairuddin Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, Malaysia.
  • Anwar P.P. Abdul Majeed Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, Malaysia.
  • Mohd Azraai Mohd Razman Innovative Manufacturing, Mechatronics and Sports Laboratory, Faculty of Manufacturing and Mechatronics Engineering Technology, Universiti Malaysia Pahang (UMP), 26600 Pekan, Pahang Darul Makmur, Malaysia.

DOI:

https://doi.org/10.15282/mekatronika.v2i1.6741

Keywords:

CNN, Transfer Learning, Fine-Tuning

Abstract

Diabetes is a global disease that occurs when the body is disabled pancreas to secrete insulin to convert the sugar to power in the blood. As a result, some tiny blood vessels on the part of the body, such as the eyes, are affected by high sugar and cause blocking blood flow in the vessels, which is called diabetic retinopathy.  This disease may lead to permanent blindness due to the growth of new vessels in the back of the retina causing it to detach from the eyes. In 2016, 387 million people were diagnosed with Diabetic retinopathy, and the number is growing yearly, and the old detection approach becomes worse. Therefore, the purpose of this paper is to computerize the old method of detecting different classes of DR from 0-4 according to severity by given fundus images. The method is to construct a fine-tuned deep learning model based on transfer learning with dense layers. The used models here are InceptionV3, VGG16, and ResNet50 with a sharpening filter. Subsequently, InceptionV3 has achieved 94% as the highest accuracy among other models.  

Downloads

Published

2020-06-12

How to Cite

[1]
A. Abdo Salman, I. Mohd Khairuddin, A. P.P. Abdul Majeed, and M. A. Mohd Razman, “The Diagnosis Of Diabetic Retinopathy By Means Of Transfer Learning And Fine-Tuned Dense Layer Pipeline”, Mekatronika: J. Intell. Manuf. Mechatron., vol. 2, no. 1, pp. 68–72, Jun. 2020.

Issue

Section

Original Article

Most read articles by the same author(s)

1 2 3 4 > >>