Current Issue : October - December Volume : 2011 Issue Number : 1 Articles : 5 Articles
We propose a medical image segmentation approach based on the Active Shape Model theory. We apply this method for cervical vertebra detection. The main advantage of this approach is the application of a statistical model created after a training stage. Thus, the knowledge and interaction of the domain expert intervene in this approach. Our application allows the use of two different models, that is, a global one (with several vertebrae) and a local one (with a single vertebra). Two modes of segmentation are also proposed: manual and semiautomatic. For the manual mode, only two points are selected by the user on a given image. The first point needs to be close to the lower anterior corner of the last vertebra and the second near the upper anterior corner of the first vertebra. These two points are required to initialize the segmentation process. We propose to use the Harris corner detector combined with three successive filters to carry out the semiautomatic process. The results obtained on a large set of X-ray images are very promising....
The highly disordered refractive index distribution in skin causes multiple scattering of incident light and limits optical imaging and therapeutic depth. We hypothesize that localized mechanical compression reduces scattering by expulsing unbound water from the dermal collagen matrix, increasing protein concentration and decreasing the number of index mismatch interfaces between tissue constituents. A swept-source optical coherence tomography (OCT) system was used to assess changes in thickness and group refractive index in ex vivo porcine skin, as well as changes in signal intensity profile when imaging in vivo human skin. Compression of ex vivo porcine skin resulted in an effective strain of -58.5%, an increase in refractive index from 1.39 to 1.50, and a decrease in water volume fraction from 0.66 to 0.20. In vivo OCT signal intensity increased by 1.5?dB at a depth of 1?mm, possibly due to transport of water away from the compressed regions. These finding suggest that local compression could be used to enhance light-based diagnostic and therapeutic techniques....
We describe a computational framework for the quantitative assessment of contractile responses of isolated neonatal cardiac myocytes. To the best of our knowledge, this is the first report on a practical and accessible method for the assessment of contractility in neonatal cardiocytes. The proposed methodology is comprised of digital video recording of the contracting cell, signal preparation, representation by polar Fourier descriptors, and contractility assessment. The different processing stages are variants of mathematically sound and computationally robust algorithms very well established in the scientific community. The described computational approach provides a comprehensive assessment of the neonatal cardiac myocyte contraction without the need of elaborate instrumentation. The versatility of the methodology allows it to be employed in determining myocyte contractility almost simultaneously with the acquisition of the \r\nCa2+ transient and other correlates of cell contraction. The proposed methodology can be utilized to evaluate changes in contractile behavior resulting from drug intervention, disease models, transgeneity, or other common applications of neonatal cardiocytes....
Diffuse Optical Tomography (DOT) is an optical imaging modality that has various clinical applications. However, the spatial resolution and quantitative accuracy of DOT is poor due to strong photon scatting in biological tissue. Structural a priori information from another high spatial resolution imaging modality such as Magnetic Resonance Imaging (MRI) has been demonstrated to significantly improve DOT accuracy. In addition, a contrast agent can be used to obtain differential absorption images of the lesion by using dynamic contrast enhanced DOT (DCE-DOT). This produces a relative absorption map that consists of subtracting a reconstructed baseline image from reconstructed images in which optical contrast is included. In this study, we investigated and compared different reconstruction methods and analysis approaches for regular endogenous DOT and DCE-DOT with and without MR anatomical a priori information for arbitrarily-shaped objects. Our phantom and animal studies have shown that superior image quality and higher accuracy can be achieved using DCE-DOT together with MR structural a priori information. Hence, implementation of a combined MRI-DOT system to image ICG enhancement can potentially be a promising tool for breast cancer imaging....
This paper presents an automatic detection method for thin boundaries of silver-stained endothelial cells (ECs) imaged using light microscopy of endothelium mono-layers from rabbit aortas. To achieve this, a segmentation technique was developed, which relies on a rich feature space to describe the spatial neighbourhood of each pixel and employs a Support Vector Machine (SVM) as a classifier. This segmentation approach is compared, using hand-labelled data, to a number of standard segmentation/thresholding methods commonly applied in microscopy. The importance of different features is also assessed using the method of minimum Redundancy, Maximum Relevance (mRMR), and the effect of different SVM kernels is also considered. The results show that the approach suggested in this paper attains much greater accuracy than standard techniques; in our comparisons with manually labelled data, our proposed technique is able to identify boundary pixels to an accuracy of 93%. More significantly, out of a set of 56 regions of image data, 43 regions were binarised to a useful level of accuracy. The results obtained from the image segmentation technique developed here may be used for the study of shape and alignment of ECs, and hence patterns of blood flow, around arterial branches....
Loading....