Advancements in Healthcare Medical Imaging through SHO optimized CNN

Medical Imaging is a pre-eminent field of healthcare that is important for medical intervention and clinical analysis of the human anatomy. Advancement in healthcare imaging helps diagnose, monitor and treat medical diseases through the improved quality of imaging techniques, namely X-ray, MRI and CT scans. The evolvement of the Convolutional Neural Network (CNN) provides the potential for early detection and effective prognosis of the disease with deeper insights. The functionality to learn and adapt the spatial hierarchical features automatically makes CNN better suited for the task. To improve the efficacy of CNN, the parameters are tuned synergistically through a swarm-based metaheuristic approach named Spotted Hyena Optimizer (SHO). As a real-world implication, we have accessed the suggested model utilizing two benchmark datasets. The dominance of the suggested approach has been authenticated by present-day methods in terms of parameters namely accuracy, error rate, min, avg, std, accuracy, sensitivity and specificity and it can be concluded that the said approach is a reliable and efficient having the ability to resolve the healthcare imaging complication.