Hybrid Quantum Classical Auto-Encoder for Medical Image Compression

Mr. Shaik Kareem1*, Singampalli Nagendra 2*

1Assistant Professor, Visakha Institute of Engineering & Technology (Autonomous), Visakhapatnam, Andhra Pradesh, India

2 Pg Research Scholar, Department of Computer Applications, Visakha Institute of Engineering & Technology (Autonomous), Visakhapatnam, Andhra Pradesh, India

ABSTRACT :
The continuous growth of digital healthcare infrastructures and the widespread adoption of advanced medical imaging technologies such as Brain CT, Brain MRI, and chest X-ray have resulted in a rapid increase in medical image data. These imaging modalities play a crucial role in clinical diagnosis, treatment planning, and patient monitoring. However, the large size of these images creates major challenges in data storage, network bandwidth utilization, and timely access, especially in telemedicine and remote healthcare systems. To overcome these challenges, this project presents a Quantum-Inspired Autoencoder based framework for efficient medical image compression. The proposed approach combines convolutional neural network (CNN) autoencoders with quantum-inspired feature representation techniques to generate compact and meaningful image encodings. Initially, the medical images are pre-processed and normalized, followed by feature learning through a convolutional encoder.

KEYWORDS :

Hybrid Quantum-Classical Computing, Medical Image Compression, Quantum-Enhanced Artificial Neural Network (QANN), Quantum-Inspired Autoencoder, Deep Learning, Convolutional Neural Network (CNN), Quantum Feature Extraction, Medical Image Reconstruction, Brain MRI, Brain CT, Chest X-ray, Super-Resolution, Telemedicine, PSNR, SSIM