Wavelet‐Based Image Registration and Segmentation Framework for the QuantitativeEvaluation of Hydrocephalus

Abstract

Hydrocephalus, characterized by increased fluid in the cerebral ventricles, is traditionally evaluated by a visual assessment of serial CT scans. The complex shape of the ventricular system makes accurate visual comparison of CT scans difficult. The current research developed a quantitative method to measure the change in cerebral ventricular volume over time. Key elements of the developed framework are: adaptive image registration based on mutual information and wavelet multiresolution analysis; adaptive segmentation with novel feature extraction based on the Dual-Tree Complex Wavelet Transform; volume calculation. The framework, when tested on physical phantoms, had an error of 2.3%. When validated on clinical cases, results showed that cases deemed to be normal/stable had a calculated volume change less than 5%. Those with progressive/treated hydrocephalus had a calculated change greater than 20%. These findings indicate that the framework is reasonable and has potential for development as a tool in the evaluation of hydrocephalus.

Computer‐based measurements of joint space analysis using metacarpal morphometry in hand radiograph for evaluation of rheumatoid arthritis

“…Then after obtaining the texture gradient of the image, a modulated gradient is achieved. The modulated gradient is based on texture activity . Its purpose is to suppress the intensity gradient in textured areas, but leave it unmodified in smooth regions.…”

Assessment of hydrocephalus in children based on digital image processing and analysis

“…In the approach proposed by Schnack et al (2001) the growth of a region is additionally supported by mathematical morphology. More advanced methods applied for segmentation of the cerebrospinal fluid include watersheds (Luo et al, 2010), active contours (Zang et al, 2010) and level sets (Bosnjak et al, 2007;Butman and Linguraru, 2008). The latter is, however, prohibitively time consuming for practical use.…”

“…There are also some approaches which use results of image segmentation to estimate the volume of the cerebrospinal fluid and its relation to the brain volume (e.g., Halberstadt and Douglas, 2005;Butman and Linguraru, 2008;Luo et al, 2010;Pustkova et al, 2010) or our previous approach (Węgliński and Fabijańska, 2012a). In all these approaches the volumes are simply determined by counting the number of pixels included into the binary images after segmentation and then multiplying it by a volume of a single pixel.…”

Survey of Modern Image Segmentation Algorithms on CT Scans of Hydrocephalic Brains

“…The problem of CSF segmentation in medical image processing has already been reported [1,2,3,4,5,6,7,8,9,10]. However, study of the literature shows that despite a number of previously developed methods, there is no common and effective solution.…”

“…However, study of the literature shows that despite a number of previously developed methods, there is no common and effective solution. Previous approaches dedicated to the extraction of CSF from both healthy and hydrocephalic brains include thresholding [3,4], region growing [1,5], clustering [6,7], watershed [8] and fastmarching [9,10] methods. These however, are not sufficient for most of present day systems for CSF segmentation, as they are mostly fully automatic approaches.…”