A Hybrid Compression Method for Medical Images Based on Region of Interest Using Artificial Neural Networks

<div>PSNR values of the ROI and NROI versus different values of <span class="nowrap"><svg height="6.1673pt" id="M21" style="vertical-align:-0.2063904pt" version="1.1" viewbox="-0.0498162 -5.96091 10.891 6.1673" width="10.891pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M774 30C773 39 771 49 769 58C758 52 747 48 732 48C616 48 566 133 514 239C556 327 604 374 702 374C716 374 729 369 737 365C743 361 747 361 752 365C761 373 770 389 770 406C770 426 754 448 726 448C689 448 629 431 577 391C534 358 509 327 489 288C438 384 373 448 262 448C175 448 53 373 53 208C53 98 131 -12 262 -12C377 -12 426 52 472 147C516 51 579 -12 687 -12C713 -12 748 -2 774 30ZM451 198C415 110 363 21 272 21C195 21 145 114 145 240C145 353 194 415 250 415C357 415 409 304 451 198Z"></path></g></svg>.</span></div>

Journal of Engineering

fig4

Figure 4

Figure 4: A Hybrid Compression Method for Medical Images Based on Region of Interest Using Artificial Neural Networks 