Content-based image retrieval (CBIR) aims at retrieving from a database objects that are similar to an object provided by a query, by taking into consideration a set of extracted features. While CBIR has been widely applied in the two-dimensional image domain, the retrieval of3D objects from medical image datasets using CBIR remains to be explored. In this context, the development of descriptors that can capture information specific to organs or structures is desirable. In this work, we focus on the retrieval of two anatomical structures commonly imaged by Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) techniques, the left ventricle of the heart and blood vessels. Towards this aim, we developed the Area-Distance Local Descriptor (ADLD), a novel 3D local shape descriptor that employs mesh geometry information, namely facet area and distance from centroid to surface, to identify shape changes. Because ADLD only considers surface meshes extracted from volumetric medical images, it substantially diminishes the amount of data to be analyzed. A 90% precision rate was obtained when retrieving both convex (left ventricle) and non-convex structures (blood vessels), allowing for detection of abnormalities associated with changes in shape. Thus, ADLD has the potential to aid in the diagnosis of a wide range of vascular and cardiac diseases.
The diagnosis of cardiovascular disease is usually assisted by resonance angiography (MRA) or computed tomography angiography (CTA) imaging. The identification of abnormal vascular architecture from angiographic three-dimensional images is therefore crucial to the diagnosis of cardiovascular disease. Automated detection and quantification of vascular structure and architecture thus holds significant clinical value. In this work, we employ a Lindenmayer system to represent vascular trees from angiographic images and describe a quantitative measure based on the Tokunaga taxonomy to differentiate vascular architectures. Synthetic vessel architectures with varying bifurcation patterns were compared and results showed that this architectural measure is proportional to the level of branching. In real MRA images, this measure was able to differentiate between normal and abnormal intracerebral vasculature containing an aneurysm. Hence, this methodology not only allows for compact representation of vascular architectures but also provides a quantitative metric of bifurcation complexity, which has the potential to characterize different types of vascular abnormalities.
Neutron Stimulated Emission Computed Tomography (NSECT) is an emerging noninvasive imaging technique that measures the distribution of isotopes from biological tissue using fast-neutron inelastic scattering reaction. As a high-energy neutron beam illuminates the sample, the excited nuclei emit gamma rays whose energies are unique to the emitting nuclei. Tomographic images of each element in the spectrum can then be reconstructed to represent the spatial distribution of elements within the sample using a first generation tomographic scan. NSECT's high radiation dose deposition, however, requires a sampling strategy that can yield maximum image quality under a reasonable radiation dose. In this work, we introduce an NSECT sinogram sampling technique based on the Normalized Mutual Information (NMI) of the reconstructed images. By applying the Radon Transform on the ground-truth image obtained from a carbon-based synthetic phantom, different NSECT sinogram configurations were simulated and compared by using the NMI as a similarity measure. The proposed methodology was also applied on NSECT images acquired using MCNP5 Monte Carlo simulations of the same phantom to validate our strategy. Results show that NMI can be used to robustly predict the quality of the reconstructed NSECT images, leading to an optimal NSECT acquisition and a minimal absorbed dose by the patient.
The analysis of vascular structure based on vessel diameters, density and distance between bifurcations is an important
step towards the diagnosis of vascular anomalies. Moreover, vascular network extraction allows the study of angiogenesis. This work describes a technique that detects bifurcations in vascular networks in magnetic resonance angiography and computed tomography angiography images. Initially, a vessel tracking technique that uses the Hough transform and a matrix composed of second order partial derivatives of image intensity is used to estimate the scale and vessel direction, respectively. This semi-automatic technique is capable of connecting isolated tracked vessel segments and extracting a full tree from a vascular network with minimal user intervention. Vessel shape descriptors such as curvature are then used to identify bifurcations during tracking and to estimate the next branch direction. We have initially applied this technique on synthetic datasets and then on real images.
Segmentation of blood vessels from magnetic resonance angiography (MRA) or computed tomography angiography (CTA) images is a complex process that usually takes a lot of computational resources. Also, most vascular
segmentation and detection algorithms do not work properly due to the wide architectural variability of the
blood vessels. Thus, the construction of convincing synthetic vascular trees makes it possible to validate new
segmentation methodologies. In this work, an extension to the traditional Lindenmayer system (L-system) that
generates synthetic 3D blood vessels by adding stochastic rules and parameters to the grammar is proposed. Towards this aim, we implement a parser and a generator of L-systems whose grammars simulate natural features
of real vessels such as the bifurcation angle, average length and diameter, as well as vascular anomalies, such as
aneurysms and stenoses. The resulting expressions are then used to create synthetic vessel images that mimic
MRA and CTA images. In addition, this methodology allows for vessel growth to be limited by arbitrary 3D
surfaces, and the vessel intensity profille can be tailored to match real angiographic intensities.