Data Augmentation for Improving Proliferative Diabetic Retinopathy Detection in Eye Fundus Images

Abstract

Proliferative diabetic retinopathy (PDR) is an advanced diabetic retinopathy stage, characterized by neovascularization, which leads to ocular complications and severe vision loss. However, the available DRlabeled retinal image datasets have a small representation of images of the severest DR grades, and thus there is lack of PDR cases for training DR grading models. Additionally, the criteria for labelling these images in the publicly available datasets is not always clear, with some images which do not show typical PDR lesions being labeled as PDR due to the presence of photo-coagulation treatment and laser marks. This problem, together with the datasets' high class imbalance, leads to a limited variability of the samples, which the typical data augmentation and class balancing cannot fully mitigate. We propose a heuristicbased data augmentation scheme based on the synthesis of neovessel (NV)-like structures that compensates for the lack of PDR cases in DR-labeled datasets. The proposed neovessel generation algorithm relies on the general knowledge of common location and shape of these structures. NVs are generated and introduced in pre-existent retinal images which can then be used for enlarging deep neural networks' training sets. The data augmentation scheme was tested on multiple datasets, and allows to improve the model's capacity to detect NVs.

Development of preprocessing methods and revised EfficientNet for diabetic retinopathy detection

“…In other words, the preprocessing methods proposed in this paper can effectively remain more of the dataset and reduce the possibility that the image quality is too poor and thus the image is rejected. The usable and good dataset is obtained using data augmentation, which is a technique to increase the diversity of a training set by applying the random, horizontal_flip, vertical_flip, and height_shift_range parameters in ImageDataGenerator (Keras Library) 40 …”

Medical image data augmentation: techniques, comparisons and interpretations

“…In some works, retinal features (such as lesion and vascular features) have been developed and added to new images. For instance, NeoVessel (NV)-like structures have been synthesized in a heuristic image augmentation (Ara´ujo et al 2020 ) to improve detection of proliferative DR which is an advanced DR stage characterized by neovascularization. In this augmentation, different NV kinds (trees, wheels, brooms) have been generated depending on the expected shape and location of NVs to synthesize new images.…”

Deep Learning Based Convolutional Neural Network Structured New Image Classification Approach for Eye Disease Identification

“…In the definition of many hazards encountered in the field of bio-medicine, image processing is now used in the literature [8,9] in the diagnosis of brain tumour [10,11], cancer [12,13], microorganism detection [14,15], eye diseases [16,17], MRI imaging [18,19], lung, liver and other diseases. Deep learning is focused on computer programs that simulate human brain functions.…”