Medical image registration and retrieval For computer assisted clinical diagnosis

Abstract

Medical imaging refers to several different technologies that are newlineused to view the human body in order to diagnose monitor or treat medical newlineconditions Each type of technology gives different information about the area newlineof the body being studied or treated related to possible disease injury or the newlineeffectiveness of medical treatment The view carried by physicians and newlineradiologists is that actual medical imaging techniques are not yet precise newlineenough for an effective clinical diagnosis and treatment newlineThe thesis focuses on presenting novel registration based newlineretrieval for medical images Registration of images is the process of finding a newlinetransformation that will align images in a more comparable way With the newlinecurrent possibilities in medical imaging images can be collected from each newlinepatient using different modalities or using the same modality and different newlineacquisition methods Content Based Medical Image Retrieval CBMIR is valuable to newlineradiologists in assessing medical images by identifying similar images in newlinelarge archives that could assist with decision support Radiology images pose newlinespecific challenges compared with images in the Consumer domain they newlinecontain varying rich and often subtle features that need to be recognized in newlineassessing image similarity newline newline