TY - JOUR
T1 - A Lightweight Robust Deep Learning Model Gained High Accuracy in Classifying a Wide Range of Diabetic Retinopathy Images
AU - Raiaan, Mohaimenul Azam Khan
AU - Fatema, Kaniz
AU - Khan, Inam Ullah
AU - Azam, Sami
AU - Rashid, Md Rafi ur
AU - Mukta, Md Saddam Hossain
AU - Jonkman, Mirjam
AU - De Boer, Friso
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2023
Y1 - 2023
N2 - Diabetic retinopathy (DR) is a common complication of diabetes mellitus, and retinal blood vessel damage can lead to vision loss and blindness if not recognized at an early stage. Manual DR detection using large fundus image data is time-consuming and error-prone. An effective automatic DR detection system can be significantly faster and potentially more accurate. This study aims to classify fundus images into five DR classes, using deep learning methods, with the highest possible accuracy and the lowest possible computational time. Three distinct DR datasets, APTOS, Messidor2, and IDRiD, are merged, resulting in 5,819 raw images. Before training the model, various image preprocessing techniques are applied to remove artifacts and noise from the images and improve their quality. Three augmentation techniques: geometric, photometric, and elastic deformation, are used to create a balanced dataset. A shallow convolutional neural network (CNN) is developed using three blocks of convolutional layers and maxpool layers with a categorical cross-entropy loss function, Adam optimizer, 0.0001 learning rate, and 64 batch size as a base model, and this is also employed to determine the best data augmentation method for further processing. A study to optimize the performance is then conducted by changing different components and hyperparameters of the base model, resulting in our proposed RetNet-10 model. Six cutting-edge models are employed for comparison. Our proposed RetNet-10 model performed the best, with a testing accuracy of 98.65%. MobileNetV2, VGG16, Xception, VGG19, InceptionV3 and ResNet50 achieved testing accuracies of 91.42%, 90.16%,89.57%, 88.21%, 87.68% and 87.23%, respectively. The model is also trained with several k values to assess its robustness. After image processing and data augmentation, using the combined dataset, and fine-tuning the base model, our proposed RetNet-10 model outperformed other automated methods for DR diagnosis.
AB - Diabetic retinopathy (DR) is a common complication of diabetes mellitus, and retinal blood vessel damage can lead to vision loss and blindness if not recognized at an early stage. Manual DR detection using large fundus image data is time-consuming and error-prone. An effective automatic DR detection system can be significantly faster and potentially more accurate. This study aims to classify fundus images into five DR classes, using deep learning methods, with the highest possible accuracy and the lowest possible computational time. Three distinct DR datasets, APTOS, Messidor2, and IDRiD, are merged, resulting in 5,819 raw images. Before training the model, various image preprocessing techniques are applied to remove artifacts and noise from the images and improve their quality. Three augmentation techniques: geometric, photometric, and elastic deformation, are used to create a balanced dataset. A shallow convolutional neural network (CNN) is developed using three blocks of convolutional layers and maxpool layers with a categorical cross-entropy loss function, Adam optimizer, 0.0001 learning rate, and 64 batch size as a base model, and this is also employed to determine the best data augmentation method for further processing. A study to optimize the performance is then conducted by changing different components and hyperparameters of the base model, resulting in our proposed RetNet-10 model. Six cutting-edge models are employed for comparison. Our proposed RetNet-10 model performed the best, with a testing accuracy of 98.65%. MobileNetV2, VGG16, Xception, VGG19, InceptionV3 and ResNet50 achieved testing accuracies of 91.42%, 90.16%,89.57%, 88.21%, 87.68% and 87.23%, respectively. The model is also trained with several k values to assess its robustness. After image processing and data augmentation, using the combined dataset, and fine-tuning the base model, our proposed RetNet-10 model outperformed other automated methods for DR diagnosis.
KW - augmentation
KW - Biomedical imaging
KW - Computational modeling
KW - convolutional neural network
KW - Convolutional neural networks
KW - Diabetes
KW - Diabetic retinopathy
KW - Feature extraction
KW - image preprocessing
KW - k-fold cross validation
KW - model optimization
KW - multi-class classification
KW - Neural networks
KW - Retina
KW - retinal fundus images
KW - Transfer learning
KW - transfer learning models
UR - http://www.scopus.com/inward/record.url?scp=85159704060&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2023.3272228
DO - 10.1109/ACCESS.2023.3272228
M3 - Article
AN - SCOPUS:85159704060
SN - 2169-3536
VL - 11
SP - 42361
EP - 42388
JO - IEEE Access
JF - IEEE Access
ER -