Modern medical imaging techniques have revolutionized health care over the last decades, providing clinicians with high-resolution 3D images of the inside of the patient's body without the need for invasive procedures. Detailed images of the vascular anatomy can be captured by angiography, providing a valuable source of information when deciding whether a vascular intervention is needed, for planning treatment, and for analyzing the success of therapy. However, increasing level of detail in the images, together with a wide availability of imaging devices, lead to an urgent need for automated techniques for image segmentation and analysis in order to assist the clinicians in performing a fast and accurate examination. To reduce the need for user interaction and increase the speed of vascular segmentation,  we propose a fast and fully automatic vascular skeleton extraction algorithm. This algorithm first analyzes the volume's intensity histogram in order to automatically adapt the internal parameters to each patient and then it produces an approximate skeleton of the patient's vasculature. The skeleton can serve as a seed region for subsequent surface extraction algorithms. Further improvements of the skeleton extraction algorithm include the expansion to detect the skeleton of diseased arteries and the design of a convolutional neural network classifier that reduces false positive detections of vascular cross-sections. In addition to the complete skeleton extraction algorithm, the thesis presents a segmentation algorithm based on modified onion-kernel region growing. It initiates the growing from the previously extracted skeleton and provides a rapid binary segmentation of tubular structures. To provide the possibility of extracting precise measurements from this segmentation we introduce a method for obtaining a segmentation with subpixel precision out of the binary segmentation and the original image. This method is especially suited for thin and elongated structures, such as vessels, since it does not shrink the long protrusions. The method supports both 2D and 3D image data. The methods were validated on real computed tomography datasets and are primarily intended for applications in vascular segmentation, however, they are robust enough to work with other anatomical tree structures after adequate parameter adjustment, which was demonstrated on an airway-tree segmentation.

From a clinical perspective retinal vascular segmentation and analysis are important tasks in aiding quantification of vascular disease progression for such prevalent pathologies as diabetic retinopathy, arteriolosclerosis and hypertension. Combined with the emergence of inexpensive digital imaging, retinal fundus images are becoming increasingly available through public databases fuelling interest in retinal vessel research. Vessel segmentation is a challenging task which needs to fulfil many requirements: the accurate segmentation of both normal and pathological vessels; the extraction of vessels of different sizes from large high contrast to small low contrast; minimal user interaction; low computational requirements; and the potential for application among different imaging modalities. We demonstrate a novel and significant improvement on an emerging stochastic vessel segmentation technique, particle filtering, in terms of improved performance at vascular bifurcations and extensibility. An alternative deterministic approach is also presented in the form of a framework utilising morphological Tramline filtering and non-parametric windows pdf estimation. Results of the deterministic algorithm on retinal images match those of state-of-art unsupervised methods in terms of pixel accuracy. In analysing retinal vascular networks, an important initial step is to distinguish between arteries and veins in order to proceed with pathological metrics such as branching angle, diameter, length and arteriole to venule diameter ratio. Practical difficulties include the lack of intensity and textural differences between arteries and veins in all but the largest vessels and the obstruction of vessels and connectivity by low contrast or other vessels. To this end, an innovative Markov Chain Monte Carlo Metropolis-Hastings framework is formulated for the separation of vessel trees. It is subsequently applied to both synthetic and retinal image data with promising results.

The geometry of an organ’s vascular system determines the blood flow distribution to tissues for exchange of gas and nutrients by determining its vascular resistance. The importance of vascular geometry is evident in the placenta, where insufficient fetoplacental vascularity elevates vascular resistance thereby impairing perfusion, leading to one of the most common and severe pregnancy complications, intrauterine growth restriction (IUGR). The mouse is becoming a widely used model for human placental development due to the increasing availability of mouse models thought to have a placental defect. Vascular geometry can now be imaged and quantified using micro-computed tomography (micro-CT) and results used to estimate resistance to blood flow. This thesis first describes the implementation of contrast agent perfusion and micro-CT imaging of the mouse fetoplacental vasculature throughout late gestation. Application of a vascular segmentation technique is then described and evaluated for quantification of the arterial fetoplacental tree. Normal fetoplacental vascular development in late gestation is described for two common mouse strains, CD1 and C57Bl6 (B6). In B6 placentas, both late gestational capillary growth and thinning of the interhaemal membrane were blunted relative to CD1. Analysis of CD1 and B6 tree geometry revealed a constant number of arterial segments throughout late gestation in both strains but expansion of arterial diameters in B6 only, resulting in decreased B6 arterial resistance and shear stress in late gestation. Strain dependence shows the importance of genetics in fetoplacental vascular development. Quantification of the arterial tree in a mouse model of maternal pre-pregnancy exposure to chemicals commonly found in cigarettes revealed an increase in vascular tortuousity and a reduced number of arteriole sized vessels. This led to an increase in vascular resistance and a predicted decrease in blood flow, which could contribute to the observed reduction in fetal weights. In future studies, the methods described herein can be used in phenotyping numerous mouse models which currently are suspected to have a placental vascular defect.

The geometry of an organ’s vascular system determines the blood flow distribution to tissues for exchange of gas and nutrients by determining its vascular resistance. The importance of vascular geometry is evident in the placenta, where insufficient fetoplacental vascularity elevates vascular resistance thereby impairing perfusion, leading to one of the most common and severe pregnancy complications, intrauterine growth restriction (IUGR). The mouse is becoming a widely used model for human placental development due to the increasing availability of mouse models thought to have a placental defect. Vascular geometry can now be imaged and quantified using micro-computed tomography (micro-CT) and results used to estimate resistance to blood flow. This thesis first describes the implementation of contrast agent perfusion and micro-CT imaging of the mouse fetoplacental vasculature throughout late gestation. Application of a vascular segmentation technique is then described and evaluated for quantification of the arterial fetoplacental tree. Normal fetoplacental vascular development in late gestation is described for two common mouse strains, CD1 and C57Bl6 (B6). In B6 placentas, both late gestational capillary growth and thinning of the interhaemal membrane were blunted relative to CD1. Analysis of CD1 and B6 tree geometry revealed a constant number of arterial segments throughout late gestation in both strains but expansion of arterial diameters in B6 only, resulting in decreased B6 arterial resistance and shear stress in late gestation. Strain dependence shows the importance of genetics in fetoplacental vascular development. Quantification of the arterial tree in a mouse model of maternal pre-pregnancy exposure to chemicals commonly found in cigarettes revealed an increase in vascular tortuousity and a reduced number of arteriole sized vessels. This led to an increase in vascular resistance and a predicted decrease in blood flow, which could contribute to the observed reduction in fetal weights. In future studies, the methods described herein can be used in phenotyping numerous mouse models which currently are suspected to have a placental vascular defect.

Made available in DSpace on 2014-12-17T15:47:58Z (GMT). No. of bitstreams: 1 ItaloMSR_DISSERT.pdf: 4133389 bytes, checksum: 575496a3d8aa350df8e3e86992d9b27b (MD5) Previous issue date: 2011-03-02 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / The vascular segmentation is important in diagnosing vascular diseases like stroke and is hampered by noise in the image and very thin vessels that can pass unnoticed. One way to accomplish the segmentation is extracting the centerline of the vessel with height ridges, which uses the intensity as features for segmentation. This process can take from seconds to minutes, depending on the current technology employed. In order to accelerate the segmentation method proposed by Aylward [Aylward & Bullitt 2002] we have adapted it to run in parallel using CUDA architecture. The performance of the segmentation method running on GPU is compared to both the same method running on CPU and the original Aylward s method running also in CPU. The improvemente of the new method over the original one is twofold: the starting point for the segmentation process is not a single point in the blood vessel but a volume, thereby making it easier for the user to segment a region of interest, and; the overall gain method was 873 times faster running on GPU and 150 times more fast running on the CPU than the original CPU in Aylward / A segmenta??o vascular ? importante no diagn?stico de doen?as como o acidente vascular cerebral e ? dificultada por ru?dos na imagem e vasos muito finos que n?o s?o vistos. Uma maneira de realizar a segmenta??o ? extraindo a centerline do vaso com height ridges, que usa a intensidade como caracter?sticas para a segmenta??o. Este processo pode levar de segundos a minutos, dependendo da tecnologia atual empregada. O m?todo ? implementado em GPU, ou seja, ? executado de maneira paralela em placa gr?fica. O desempenho do m?todo de segmenta??o executado em GPU ? comparado com o mesmo m?todo em CPU e o m?todo original de Aylward em execu??o tamb?m na CPU. O melhoramento do novo m?todo sobre o original ? dupla. O ponto de partida para o processo de segmenta??o n?o ? um ?nico ponto no vaso sangu?neo, mas um volume, tornando assim mais f?cil para o usu?rio a sele??o de uma regi?o de interesse, e, o ganho do m?todo proposto foi 873 vezes mais r?pido sendo executado em GPU e 150 vezes mais r?pido sendo executado em CPU do que o original de Aylward em CPU