Chronic foot ulcers present a number of difficulties because they heal slowly, are more prone to infection, and increase the risk of amputation, especially in individuals with Chronic Kidney Disease (CKD). Manual assessments, which are frequently arbitrary and inconsistent, are a major component of traditional wound assessment techniques. The basic paper’s presentation of current technologies makes use of image based wound evaluation; nevertheless, thorough analytics and automation are lacking for tracking the evolution of wounds. We describe a sophisticated AI driven system that uses the UNet architecture to automate the segmentation and comprehensive evaluation of foot ulcers in patients with chronic kidney disease (CKD) in order to overcome these constraints. Our technology combines medical picture analysis with cutting edge deep learning techniques to produce extremely precise, impartial, and repeatable wound assessments. The method automatically extracts and quantifies important wound properties like size, depth, tissue type, and healing trajectory by utilizing a large dataset of annotated wound photos. Compared to traditional methods, our UNet based segmentation model achieves an amazing accuracy of nearly 98%, which makes it highly dependable for clinical application. We further improve the system by adding a real time tracking module that gives medical professionals information about the status of wound healing and predictive analytics to help them customize treatment regimens. This work offers extensive implications for future integration into clinical processes and sets a new standard in wound care management, especially for vulnerable patients with chronic kidney disease (CKD), by offering a scalable, automated approach.