Res-Unet based blood vessel segmentation and cardio vascular disease prediction using chronological chef-based optimization algorithm based deep residual network from retinal fundus images

Cardiovascular disease (CVD) is a significant contributor to global mortality in our advanced society. The majority of males were attributed to deaths caused by CVD. CVD is the primary cause of mortality. It can be avoided with early detection and accurate diagnosis in its first stages. This research introduces a method for detecting CVD by analysing retinal fundus images. The approach under consideration facilitates disease prediction. The primary procedure involved in retinal vessels is the extraction of tissue data, which is then used for the identification and treatment of CVD. In this step, the retinal pictures are subjected to filtering using a Gaussian filter. The identification of the optic disc is accomplished by the process of binarization and circle fitting, which is then followed by the extraction of statistical data. The segmentation of blood vessels is performed using the Chronological Chef Based Optimisation Algorithm (CCBOA)-based Res-Unet. Subsequently, texture features are extracted. The detection of CVD is achieved by employing a deep neural network (DRN) in conjunction with CCBOA. The CCBOA-based DRN demonstrated exceptional efficiency, achieving the maximum level of accuracy at 89.8%. It also exhibited impressive performance in terms of negative predictive value (NPV) at 86.4%, positive predictive value (PPV) at 86.8%, true negative rate (TNR) at 90.5%, and true positive rate (TPR) at 90.1%.