Noise Reduction in Biomedical Images : A Differential Evolution Approach

ISBN-13: 9783639175851 / Angielski / Miękka / 2009 / 128 str.

Vikas Gupta

Opis

Tomographic imaging modalities MRI,OCT & PET areproving to be immensely helpful in the diagnosis ofvarious pathologies in clinicalenvironments. Images from these modalities span therange from organ level to tissue level and representthe condensation of information associated with theobjects that are imaged. The potential of thisinformation increases signi cantly, if these images are effectivelyprocessed and analyzed. However, thequality of medical images is,usually, compromised dueto the undesirable noisewhich reduces the SNR of these images. The degradation ofimages by noise in uences the diagnosis of criticaldiseases in clinical environments.A novel noise reduction method based on wavelets anddifferential evolution hasbeen proposed in this work. The proposed method wastested on the images thatwere acquired from MRI, OCT and PET. The applicationof this method improvedSNR by a cosiderable amount while the loss in CNR waskept at minimum level. A comprehensive analysis ofprocessed images, on the basis of different imagequality indices, showed that the proposed method,effectively,reduces noise without sacri cing the image resolution.

O autorze

Vikas Gupta was born in Bareilly(India). Motivated by his desire
to study human biology from a technical perspective, he graduated
with a degree in biomedical engineering from MIT,Manipal. After
working for a year in SIEMENS, he joined a masters research
program in NTU(Singapore) where he worked on noise reduction
methods for biomedical images.