AN ENHANCED QANN-BASED MEDICAL IMAGE COMPRESSION FRAMEWORK WITH SUPER-RESOLUTION RECONSTRUCTION

Abstract

High-resolution medical pictures, such as CT, MRI, and chest X-rays, require effective compression techniques to reduce storage and transmission costs while maintaining diagnostic quality. Although Quantum-Enhanced Artificial Neural Networks (QANN) improve compression efficiency by extracting quantum features, reconstructed images may still degrade in quality at greater compression ratios. To solve this restriction, this paper expands the QANN-based medical picture compression system with a Super Resolution improvement module. The proposed hybrid approach begins with quantumassisted compression and reconstruction using QANN, followed by Super Resolution processing to recover fine structural features, decrease noise, and improve visual clarity. The Super Resolution module is computationally efficient, allowing for real-time augmentation without dramatically increasing system complexity. A web-based interface built with Flask also allows users to upload medical photos and conduct compression, reconstruction, and Super Resolution enhancements via an interactive platform. Experimental results show that the extended framework greatly enhances reconstructed image quality while maintaining high compression efficiency, making it ideal for bandwidth-constrained and real-time medical imaging applications like telemedicine and remote diagnostics.