Relevance Mapping based CNN model with OSR-FCA Technique for Multi-label DR Classification

In computer vision, multi-label classification (MLC) is especially important for medical picture analysis. We use MLC to classify diverse stages of diabetic retinopathy (DR) using colour fundus pictures of varying brightness and contrast. As a result, ophthalmologists can now identify the early warning symptoms of DR and the varying stages of DR, allowing them to begin therapy sooner and prevent further difficulties. Using the outlier-based shallow regularization fuzzy clustering approach (OSR-FCA), for classification we present a deep learning method in this paper's picture segmentation task. The fundamental feature of the proposed system is the ability to identify and analyse different degenerative changes in the retina that occur alongside the progression of DR without requiring the patient to undergo costly diagnostic procedures like dye injections. Photographs are first resized, converted to grayscale, cleaned of noise, and the contrast increased by the use of histogram equalization adopting the CLAHE method. The clipping limit of CLAHE is optimized by the help of the rat optimization algorithm, which is applied throughout the histogram process. In addition, a Gaussian metric regularization to the objective function in OSR-FCA is a great way to enhance clustering approaches that use fuzzy membership with sparseness which is based on neutrosophic set. This research proposes a new approach called Relevance Mapping on Multi-Class Label (RMMCL) for locating and viewing regions of interest (ROI) inside a segmented picture. These representations give better explanations for the predictions of the DL model founded on a convolutional neural network-(CNN). The validation of two ML datasets showed the projected model outperformed the existing models by achieving an average correctness of 97.27 percent over five stages of the IDRID dataset.