X-Ray Image Compression Using Variational Auto-encoder
Zihao Guo, Shuang Zhao, Dongsheng Han, Chenlong Yang · 2022
With the rapid development of medical industry, medical imaging related equipment is becoming more and more advanced, image data are becoming larger and larger, and it is more and more common for medical images to be stored and viewed in the cloud. Therefore, effective image compression of medical images plays a vital role in today's medical information system. In this paper, a variational self-encoder based on deep learning is proposed to compress medical images. We have carried out image compression experiments on CHESTX-Ray8 data set of the National Institute of Health (NIH), and compared the performance with another deep learning compression method and the compression method without deep learning. Experimental results show that this algorithm outperforms other methods in Peak Signal-to-Noise Ratio (PSNR).