Automated detection of diabetic retinopathy using custom convolutional neural network

Abstract

Diabetic retinopathy is an eye deficiency that affects retina as a result of the patient having diabetes mellitus caused by high sugar levels, which may eventually lead to macular edema. The objective of this study is to design and compare several deep learning models that detect severity of diabetic retinopathy, determine risk of leading to macular edema, and segment different types of disease patterns using retina images. Indian Diabetic Retinopathy Image Dataset (IDRiD) dataset was used for disease grading and segmentation. Since images of the dataset have different brightness and contrast, we employed three techniques for generating processed images from the original images, which include brightness, color and, contrast (BCC) enhancing, color jitters (CJ), and contrast limited adaptive histogram equalization (CLAHE). After image preporcessing, we used pre-trained ResNet50, VGG16, and VGG19 models on these different preprocessed images both for determining the severity of the retinopathy and also the chances of macular edema. UNet was also applied to segment different types of diseases. To train and test these models, image dataset was divided into training, testing, and validation data at 70%, 20%, and 10% ratios, respectively. During model training, data augmentation method was also applied to increase the number of training images. Study results show that for detecting the severity of retinopathy and macular edema, ResNet50 showed the best accuracy using BCC and original images with an accuracy of 60.2% and 82.5%, respectively, on validation dataset. In segmenting different types of diseases, UNet yielded the highest testing accuracy of 65.22% and 91.09% for microaneurysms and hard exudates using BCC images, 84.83% for optic disc using CJ images, 59.35% and 89.69% for hemorrhages and soft exudates using CLAHE images, respectively. Thus, image preprocessing can play an important role to improve efficacy and performance of deep learning models.

Pixel-Boundary-Dependent Segmentation Method for Early Detection of Diabetic Retinopathy

“…Next, the proposed DL-KS segmentation technique is combined with several CNN architectures including Alex-Net [29], Inception-v3 [30], ResNet-50 [29], VGG-16 [31] and VGG-19 [32]. Figure 16 ree other datasets, such as Kaggle [33], Messidor [34], and DDR [35], are also used as the testbed for analyzing the performance of the proposed DS-KL segmentation technique.…”

Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey

“…The experimental results showed that VGG16 with fine-tuning can achieve a higher accuracy of 71.65% than that of GoogLeNet. Albahli et al [144] adopted three pre-trained models, that is, ResNet50, VGG16, and VGG19, to identify both DR severity and the risk of ME. The best accuracy of 82.5% was achieved by ResNet50 performed on original images.…”

Detection of Meals and Physical Activity Events From Free-Living Data of People With Diabetes

“…1,2 Advanced ML techniques based on deep neural networks have been reported for various detection and prediction tasks for people with Type 1 diabetes (T1D), ranging from development of a recurrent neural network (RNN) to predict adverse glycemic events 3 and detection of retinopathy. 4,5 This work focuses on the detection and classification of prior meal and physical activity events from long-term historical data of individuals with T1D. One of the objectives is to assess the need for data reconciliation and imputation because continuous glucose monitoring (CGM) data under free-living conditions may have many missing values, outliers, and incomplete diaries for meals and physical activities.…”