An Endometrial Cancer Image Compression With Lossless Region of Interest
Medical Imaging is an important keystone of modern healthcare and will continue to play a role of ever
increasing importance at all levels of the healthcare system due to advances in imaging technology (US,CT, MR and
Molecular Imaging). Due to this big data of medical images compression is required to achieve efficient transmission and
storage. The proposed procedure is applied to diverse ultrasound cancerous images (endometrial cancer). Hence diagnosis of
this type of uterus cancer in the premier stage is crucial, certain segmentation algorithms are applied and these will separate
the infected region from the background which will be easy for the medical practitioners to decide the cancer and steer
medication. The US image which is developed from an organ is applied to SRAD filter for preprocessing and the filtered
image is given to level set segmentation and finally the contextual part of the image is encoded selectively on the high priority
basis with a very low compression rate using wavelet decomposition.
Index Terms— Endometrial cancer segmentation; Lossless compression; Speckle noise; Ultrasound image.