European Journal of Molecular & Clinical Medicine

Digitalinpaintingisthetechniqueoffillinginthemissingregionsofanimageusinginformationfro
mthesurroundingareainavisuallyindistinguishableway.Inthispaper,wetrytoimprovetheExem
plarbasedmethod[2]bymanipulating the values of various parameters like patch size,shape
and size of the mask. We present an analysis of the
impactofvariousgeometricparametersonthequalityofinpaintedimages.Imagedenoisingrefers
totheremovalofunwantednoisefromtheimages.Inmostcases,theimageswhichneedto be
inpainted are noisy, which makes it necessary to
eliminatenoiseandfillinthemissingregionsfromneighboringpixels.Therefore,fillinginofmissi
ngregionsandremovalofnoisearethetwoveryimportanttopicsinimageprocessing.Thispaperals
oaddressestheissueofperformingbothinpaintinganddenoisingsimultaneouslyusingtwodiffer
entapproaches:pipelinedapproachandinterleavedapproach.Theeffectivenessof these
approaches is demonstrated with a number of results onvariousimages.

With the growing interest in conducting multi- centre and multi-modality studies on
neurological disorders, post-reconstruction PET image enhancement methods that take advantage
of available anatomical information are becoming more important. In this work, a novel method
for denoising PET images using the subject’s registered T1-weighted MR image is proposed. The
proposed method combines the non-local means approach with the twicing strategy from the image
denoising literature to restore a reconstructed PET image. Preliminary analysis shows promising
improvements in peak signal to noise ratio (PSNR) and contrast recovery coefficients (CRC) of the
lesions when denoising simulated images reconstructed using the MLEM algorithm.