Published Paper Details:

The growing application of artificial intelligence (AI) in medical imaging has significantly improved diagnostic capabilities. However, the high computational demands of deep learning models have raised concerns regarding energy consumption and environmental sustainability. This paper explores an innovative green computing approach to optimizing AI-based medical imaging systems. By leveraging model pruning, quantization, and edge computing, this paper propose an energy-efficient framework that minimizes carbon footprints while maintaining diagnostic accuracy. The study evaluates the energy savings and performance trade-offs in MRI, CT scans, and X-rays, comparing traditional AI-based models with optimized green AI systems. Experimental results indicate that sustainable AI models can significantly reduce energy consumption without compromising diagnostic efficiency. This research provides a foundation for further advancements in eco-friendly AI applications in healthcare.