A Lightweight Robust Deep Learning Model Gained High Accuracy in Classifying a Wide Range of Diabetic Retinopathy Images

Abstract

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.

A Computer-Aided Diagnostic System to Identify Diabetic Retinopathy, Utilizing a Modified Compact Convolutional Transformer and Low-Resolution Images to Reduce Computation Time

“…Denoised retinal fundus images are processed with CLAHE [ 27 ] to enhance the contrast. Darkness, brightness, and uneven illumination distort the image [ 28 ]. To address this, we converted the RGB color channels to YUV color channels, where the Y channel ( Figure 3 D) represents the lightness components [ 29 ].…”

Generative AI in the Era of Transformers: Revolutionizing Natural Language Processing with LLMs

“…There is also a huge cost in training stateof-the-art LLMs, in terms of computational power and data, making it out of reach for many researchers and organizations. Additionally, LLMs may unintentionally acquire and replicate biases in their training data, which presents difficulties concerning fairness and ethics [9]. Overcoming these problems additionally requires the enhancement of training algorithms, using hardware upgrades, and enforcing strict bias mitigation methods while training and deploying models.…”

DeepChestGNN: A Comprehensive Framework for Enhanced Lung Disease Identification through Advanced Graphical Deep Features

“…The contrast of our images was enhanced by the utilization of contrast-limited adaptive Histogram Equalization (CLAHE), effectively mitigating the issue of noise amplification, a prevalent limitation seen in traditional histogram equalization methods [5]. The CLAHE technique was designed to increase the quality of low-contrast medical images [46]. The amplification in CLAHE is restricted by performing a clipping operation on the histogram at a user-defined value known as the clip limit [47].…”