Deep learning in the grading of diabetic retinopathy: A review

被引:7
作者
Tajudin, Nurul Mirza Afiqah [1 ]
Kipli, Kuryati [1 ]
Mahmood, Muhammad Hamdi [2 ]
Lim, Lik Thai [3 ]
Mat, Dayang Azra Awang [1 ]
Sapawi, Rohana [1 ]
Sahari, Siti Kudnie [1 ]
Lias, Kasumawati [1 ]
Jali, Suriati Khartini [4 ]
Hoque, Mohammed Enamul [1 ]
机构
[1] Univ Malaysia Sarawak, Dept Elect & Elect Engn, Sarawak 94300, Malaysia
[2] Univ Malaysia Sarawak, Fac Med & Hlth Sci FMHS, Dept Para Clin Sci, Sarawak, Malaysia
[3] Univ Malaysia Sarawak, Fac Med & Hlth Sci FMHS, Dept Ophthalmol, Sarawak, Malaysia
[4] Univ Malaysia Sarawak, Fac Comp Sci & Informat Technol, Sarawak, Malaysia
关键词
ALGORITHM; DIAGNOSIS; IMAGES;
D O I
10.1049/cvi2.12116
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Diabetic Retinopathy (DR) grading into different stages of severity continues to remain a challenging issue due to the complexities of the disease. Diabetic Retinopathy grading classifies retinal images to five levels of severity ranging from 0 to 5, which represents No DR, Mild non-proliferative diabetic retinopathy (NPDR), Moderate NPDR, Severe NPDR, and proliferative diabetic retinopathy. With the advancement of Deep Learning, studies on the application of the Convolutional Neural Network (CNN) in DR grading have been on the rise. High accuracy and sensitivity are the desired outcome of these studies. This paper reviewed recently published studies that employed CNN for DR grading to 5 levels of severity. Various approaches are applied in classifying retinal images which are, (i) by training CNN models to learn the features for each grade and (ii) by detecting and segmenting lesions using information about their location such as microaneurysms, exudates, and haemorrhages. Public and private datasets have been utilised by researchers in classifying retinal images for DR. The performance of the CNN models was measured by accuracy, specificity, sensitivity, and area under the curve. The CNN models and their performance varies for every study. More research into the CNN model is necessary for future work to improve model performance in DR grading. The Inception model can be used as a starting point for subsequent research. It will also be necessary to investigate the attributes that the model uses for grading.
引用
收藏
页码:667 / 682
页数:16
相关论文
共 67 条
  • [1] Automated Analysis of Retinal Images for Detection of Referable Diabetic Retinopathy
    Abramoff, Michael D.
    Folk, James C.
    Han, Dennis P.
    Walker, Jonathan D.
    Williams, David F.
    Russell, Stephen R.
    Massin, Pascale
    Cochener, Beatrice
    Gain, Philippe
    Tang, Li
    Lamard, Mathieu
    Moga, Daniela C.
    Quellec, Gwenole
    Niemeijer, Meindert
    [J]. JAMA OPHTHALMOLOGY, 2013, 131 (03) : 351 - 357
  • [2] Abramoff Michael D, 2010, IEEE Rev Biomed Eng, V3, P169, DOI 10.1109/RBME.2010.2084567
  • [3] Alyoubi W. L., 2020, Inf. Med. Unlocked, V20, DOI DOI 10.1016/J.IMU.2020.100377
  • [4] Diabetic Retinopathy Fundus Image Classification and Lesions Localization System Using Deep Learning
    Alyoubi, Wejdan L.
    Abulkhair, Maysoon F.
    Shalash, Wafaa M.
    [J]. SENSORS, 2021, 21 (11)
  • [5] [Anonymous], Rethinking the inception architecture for computer vision
  • [6] Medical Image Analysis using Convolutional Neural Networks: A Review
    Anwar, Syed Muhammad
    Majid, Muhammad
    Qayyum, Adnan
    Awais, Muhammad
    Alnowami, Majdi
    Khan, Muhammad Khurram
    [J]. JOURNAL OF MEDICAL SYSTEMS, 2018, 42 (11)
  • [7] Transfer learning based robust automatic detection system for diabetic retinopathy grading
    Bhardwaj, Charu
    Jain, Shruti
    Sood, Meenakshi
    [J]. NEURAL COMPUTING & APPLICATIONS, 2021, 33 (20) : 13999 - 14019
  • [8] Deep convolution feature aggregation: an application to diabetic retinopathy severity level prediction
    Bodapati, Jyostna Devi
    Shaik, Nagur Shareef
    Naralasetti, Veeranjaneyulu
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2021, 15 (05) : 923 - 930
  • [9] Ethnicity and ocular imaging
    Bourne, R. R. A.
    [J]. EYE, 2011, 25 (03) : 297 - 300
  • [10] Non-Local Means Denoising
    Buades, Antoni
    Coll, Bartomeu
    Morel, Jean-Michel
    [J]. IMAGE PROCESSING ON LINE, 2011, 1 : 208 - 212