Retinopathy grading with deep learning and wavelet hyper-analytic activations

Abstract

Recent developments reveal the prominence of Diabetic Retinopathy (DR) grading. In the past few decades, Wavelet-based DR classification has shown successful impacts and the Deep Learning models, like Convolutional Neural Networks (CNN’s), have evolved in offering the highest prediction accuracy. In this work, the features of the input image are enhanced with the integration of Multi-Resolution Analysis (MRA) and a CNN framework without costing more convolution filters. The bottleneck with conventional activation functions, used in CNN’s, is the nullification of the feature maps that are negative in value. In this work, a novel Hyper-analytic Wavelet ( HW) phase activation function is formulated with unique characteristics for the wavelet sub-bands. Instead of dismissal, the function transforms these negative coefficients that correspond to significant edge feature maps . The hyper-analytic wavelet phase forms the imaginary part of the complex activation. And the hyper-parameter of the activation function is selected such that the corresponding magnitude spectrum produces monotonic and effective activations. The performance of 3 CNN models (1 custom, shallow CNN, ResNet with Soft attention, Alex Net for DR) with spatial–Wavelet quilts is better. With the spatial–Wavelet quilts, the Alex Net for DR has an improvement with an 11% of accuracy level (from 87 to 98%). The highest accuracy level of 98% and the highest Sensitivity of 99% are attained through Modified Alex Net for DR. The proposal also illustrates the visualization of the negative edge preservation with assumed image patches. From this study, the researcher infers that models with spatial–Wavelet quilts, with the hyper-analytic activations, have better generalization ability. And the visualization of heat maps provides evidence of better learning of the feature maps from the wavelet sub-bands.

Classification of Diabetic Retinopathy Disease Levels by Extracting Spectral Features Using Wavelet CNN

“…The imaginary part of the complex activation is generated through the hyper-analytic wavelet phase. Chandrasekaran and Loganathan have selected the hyper-parameter of an activation function to ensure effective activations by creating a monotonic magnitude spectrum [ 38 ]. They introduced a computer-aided diagnosis tool called GabROP, which combines discrete wavelet transform-based texture features with multiple deep learning (DL) models.…”

Luminosity Normalized Symmetric Deep Convolute Tubular Classifier for Diabetic Retinopathy Detection

“…Over the last few years, wavelet-based DR detection has been found to have greater influence, and perhaps the Deep Learning models, like CNN's, have progressed in contributing the highest prediction accuracy. In [26], features of the input image were integrated with Multi-Resolution Analysis (MRA), and also the CNN framework was designed without the additional cost involved in more convolution filters. The drawbacks of traditional activation functions were eliminated with the utilization of MRA, therefore contributing to high sensitivity and specificity.…”