Medical volume segmentation got the attraction of many researchers; therefore, many techniques have been implemented in terms of medical imaging including segmentations and other imaging processes. This research focuses on an implementation of segmentation system which uses several techniques together or on their own to segment medical volumes, the system takes a stack of 2D slices or a full 3D volumes acquired from medical scanners as a data input. Two main approaches have been implemented in this research for segmenting medical volume which are multi-resolution analysis and statistical modeling. Multi-resolution analysis has been mainly employed in this research for extracting the features. Higher dimensions of discontinuity (line or curve singularity) have been extracted in medical images using a modified multi-resolution analysis transforms such as ridgelet and curvelet transforms. The second implemented approach in this thesis is the use of statistical modeling in medical image segmentation; Hidden Markov models have been enhanced here to segment medical slices automatically, accurately, reliably and with lossless results. But the problem with using Markov models here is the computational time which is too long. This has been addressed by using feature reduction techniques which has also been implemented in this thesis. Some feature reduction and dimensionality reduction techniques have been used to accelerate the slowest block in the proposed system. This includes Principle Components Analysis, Gaussian Pyramids and other methods. The feature reduction techniques have been employed efficiently with the 3D volume segmentation techniques such as 3D wavelet and 3D Hidden Markov models. The system has been tested and validated using several procedures starting at a comparison with the predefined results, crossing the specialists’ validations, and ending by validating the system using a survey filled by the end users explaining the techniques and the results. This concludes that Markovian models segmentation results has overcome all other techniques in most patients’ cases. Curvelet transform has been also proved promising segmentation results; the end users rate it better than Markovian models due to the long time required with Hidden Markov models.

Techn. Univ., Habil.-Schr.--Hamburg, 1992.

Thesis (Ph. D.)--Brandeis University, 2010. / "UMI:3390484." MICROFILM COPY ALSO AVAILABLE IN THE UNIVERSITY ARCHIVES. Includes bibliographical references.

Ocular pathology is one of the main health problems worldwide. The number of people with retinopathy symptoms has increased considerably in recent years. Early adequate treatment has demonstrated to be effective to avoid the loss of the vision. The analysis of fundus images is a non intrusive option for periodical retinal screening. Different models designed for the analysis of retinal images are based on supervised methods, which require of hand labelled images and processing time as part of the training stage. On the other hand most of the methods have been designed under the basis of specific characteristics of the retinal images (e.g. field of view, resolution). This compromises its performance to a reduce group of retinal image with similar features. For these reasons an unsupervised model for the analysis of retinal image is required, a model that can work without human supervision or interaction. And that is able to perform on retinal images with different characteristics. In this research, we have worked on the development of this type of model. The system locates the eye structures (e.g. optic disc and blood vessels) as first step. Later, these structures are masked out from the retinal image in order to create a clear field to perform the lesion detection. We have selected the Graph Cut technique as a base to design the retinal structures segmentation methods. This selection allows incorporating prior knowledge to constraint the searching for the optimal segmentation. Different link weight assignments were formulated in order to attend the specific needs of the retinal structures (e.g. shape). This research project has put to work together the fields of image processing and ophthalmology to create a novel system that contribute significantly to the state of the art in medical image analysis. This new knowledge provides a new alternative to address the analysis of medical images and opens a new panorama for researchers exploring this research area.

Knowledge of the microcirculatory system has added significant value to the analysis of tissue oxygenation and perfusion. While developments in videomicroscopy technology have enabled medical researchers and physicians to observe the microvascular system, the available software tools are limited in their capabilities to determine quantitative features of microcirculation, either automatically or accurately. In particular, microvessel density has been a critical diagnostic measure in evaluating disease progression and a prognostic indicator in various clinical conditions. As a result, automated analysis of the microcirculatory system can be substantially beneficial in various real-time and off-line therapeutic medical applications, such as optimization of resuscitation. This study focuses on the development of an algorithm to automatically segment microvessels, calculate the density of capillaries in microcirculatory videos, and determine the distribution of blood circulation. The proposed technique is divided into four major steps: video stabilization, video enhancement, segmentation and post-processing. The stabilization step estimates motion and corrects for the motion artifacts using an appropriate motion model. Video enhancement improves the visual quality of video frames through preprocessing, vessel enhancement and edge enhancement. The resulting frames are combined through an adjusted weighted median filter and the resulting frame is then thresholded using an entropic thresholding technique. Finally, a region growing technique is utilized to correct for the discontinuity of blood vessels. Using the final binary results, the most commonly used measure for the assessment of microcirculation, i.e. Functional Capillary Density (FCD), is calculated. The designed technique is applied to video recordings of healthy and diseased human and animal samples obtained by MicroScan device based on Sidestream Dark Field (SDF) imaging modality. To validate the final results, the calculated FCD results are compared with the results obtained by blind detailed inspection of three medical experts, who have used AVA (Automated Vascular Analysis) semi-automated microcirculation analysis software. Since there is neither a fully automated accurate microcirculation analysis program, nor a publicly available annotated database of microcirculation videos, the results acquired by the experts are considered the gold standard. Bland-Altman plots show that there is ``Good Agreement" between the results of the algorithm and that of gold standard. In summary, the main objective of this study is to eliminate the need for human interaction to edit/ correct results, to improve the accuracy of stabilization and segmentation, and to reduce the overall computation time. The proposed methodology impacts the field of computer science through development of image processing techniques to discover the knowledge in grayscale video frames. The broad impact of this work is to assist physicians, medical researchers and caregivers in making diagnostic and therapeutic decisions for microcirculatory abnormalities and in studying of the human microcirculation.

A caracterização morfológica para a compreensão de padrões sobre o perfil comportamental e de relações entre determinados parâmetros proporciona um maior entendimento sobre sistemas naturais. Neste sentido, o processamento e análise digital de imagens (PADI) é ferramenta útil e adequada para avaliação dos aspectos morfológicos e morfométricos de seres vivos. Este projeto teve como finalidade o desenvolvimento de técnicas de PADI para a caracterização do perfil de crescimento, propagação e produção de pigmentos do fungo filamentoso Monacus ruber, fornecendo informações importantes para identificação e conhecimento do comportamento deste fungo a partir da variação da concentração das fontes de carbono (glicose) e de nitrogênio (glutamato monossódico - GMS) e do pH do meio. Foram elaborados e identificados parâmetros para a caracterização da fermentação em estado semissólido a partir do PADI, sendo eles área micelial, crescimento radial pigmentar e micelial, espessura, variação da intensidade pigmentar, desvio padrão pigmentar e fator forma ao longo do tempo. Foram realizados experimentos conforme delineamento composto central rotacional (DCCR) 23 com triplicata no ponto central para avaliação de condições ótimas de produção de pigmentos amarelo, laranja e vermelho. As variáveis resposta empregadas foram produção de pigmentos amarelo, laranja, vermelho, área micelial, velocidade micelial, velocidade pigmentar e variação da intensidade pigmentar extracelular. Modelos empíricos foram ajustados e utilizados para maximização da produção de pigmentos. Os resultados mostraram que elevadas concentrações de glicose e GMS e baixo pH favoreceram a produção de pigmentos. As condições otimizadas foram: concentração de glicose de 51,37 g.L-1, concentração de GMS de 8,19 g.L-1 e pH 2,31. Nestas condições, produziram-se 123,05 UA.g-1, 95,98 UA.g-1 e 99,48 UA.g-1 de pigmentos amarelo, laranja e vermelho, respectivamente. A partir dos resultados pôde-se determinar que os parâmetros elaborados para caracterizar os padrões do crescimento e as relações morfológicas com outras variáveis utilizando de técnicas do PADI são ferramentas poderosas para o acompanhamento e rastreabilidade deste bioprocesso. Os resultados obtidos também favorecerão futuros estudos empregando inteligência artificial, como aprendizado de máquina e redes neurais artificiais, para elaboração de modelos e estratégicas de automação e acompanhamento on-line do padrão de crescimento do microrganismo e as relações entre variáveis de processo. / The morphological characterization for the understanding of patterns of the behavioral profile and relations between certain parameters provides a greater understanding about natural systems. In this sense, digital image processing and analysis (DIPA) is a useful and adequate tool for the evaluation of the morphological and morphometric aspects of living beings. This project aimed at the development of DIPA techniques for the characterization of the growth profile, propagation and production of pigments of the filamentous fungus Monacus ruber, providing important information to identify and know the behavior of this fungus from the variation of the concentration of the carbon source (glucose) and the nitrogen source (monosodium glutamate - MSG) and from the variation of the pH of the medium. Parameters for the characterization of the fermentation in semi-solid state were elaborated and identified using DIPA, which were mycelial area, pigmentary and mycelial radial growth, thickness, variation of pigment intensity, pigmentary standard deviation and form factor over time. Experiments were carried out in accordance with the delineation of the central rotational compound (DCRC) 23 with triplicate at the central point to evaluate optimal conditions of production of yellow, orange and red pigments. The response variables employed were yellow, orange, red pigment, mycelial area, mycelial velocity, pigment velocity and extracellular pigment intensity. Empirical models were fitted and used to maximize pigment production. The results showed that high concentrations of glucose and MSG and low pH favored the production of pigments. Optimized conditions were: glucose concentration of 51.37 g.L-1, MSG concentration of 8.19 g.L-1 and pH 2.31. Under these conditions were produced 123.05 AU.g-1, 95.98 AU.g-1 and 99.48 AU.g-1 of yellow, orange and red pigments, respectively. From the results it was possible to determine that the parameters elaborated to characterize growth patterns and morphological relationships with other variables using DIPA techniques are powerful tools for monitoring and traceability of this bioprocess. The results obtained will also favor future studies using artificial intelligence, such as machine learning and artificial neural networks, for the elaboration of automation strategies and online monitoring of the growth pattern of the microorganism and the relations between process variables.

Retina located in the back of the eye is not only a vital part of human sight, but also contains valuable information that can be used in biometric security applications, or for the diagnosis of certain diseases. In order to analyze this information from retinal images, its features of blood vessels, microaneurysms and the optic disc require extraction and detection respectively. We propose a method to extract vessels called MF-FDOG. MF-FDOG consists of using two filters, Matched Filter (MF) and the first-order derivative of Gaussian (FDOG). The vessel map is extracted by applying a threshold to the response of MF, which is adaptively adjusted by the mean response of FDOG. This method allows us to better distinguish vessel objects from non-vessel objects. Microaneurysm (MA) detection is accomplished with two proposed algorithms, Multi-scale Correlation Filtering (MSCF) and Dictionary Learning (DL) with Sparse Representation Classifier (SRC). MSCF is hierarchical in nature, consisting of two levels: coarse level microaneurysm candidate detection and fine level true microaneurysm detection. In the first level, all possible microaneurysm candidates are found while the second level extracts features from each candidate and compares them to a discrimination table for decision (MA or non-MA). In Dictionary Learning with Sparse Representation Classifier, MA and non-MA objects are extracted from images and used to learn two dictionaries, MA and non-MA. Sparse Representation Classifier is then applied to each MA candidate object detected beforehand, using the two dictionaries to determine class membership. The detection result is further improved by adding a class discrimination term into the Dictionary Learning model. This approach is known as Centralized Dictionary Learning (CDL) with Sparse Representation Classifier. The optic disc (OD) is an important anatomical feature in retinal images, and its detection is vital for developing automated screening programs. Currently, there is no algorithm designed to automatically detect the OD in fundus images captured from Asians, which are larger and have thicker vessels compared to Caucasians. We propose such a method to complement current algorithms using two steps: OD vessel candidate detection and OD vessel candidate matching. The proposed extraction/detection approaches are tested in medical applications, specifically the case study of detecting diabetic retinopathy (DR). DR is a complication of diabetes that damages the retina and can lead to blindness. There are four stages of DR and is a leading cause of sight loss in industrialized nations. Using MF-FDOG, blood vessels were extracted from DR images, while DR images fed into MSCF and Dictionary and Centralized Dictionary Learning with Sparse Representation Classifier produced good microaneurysm detection results. Using a new database consisting of only Asian DR patients, we successfully tested our OD detection method. As part of future work we intend to improve existing methods such as enhancing low contrast microaneurysms and better scale selection. In additional, we will extract other features from the retina, develop a generalized OD detection method, apply Dictionary Learning with Sparse Representation Classifier to vessel extraction, and use the new image database to carry out more experiments in medical applications.

<p>The availability of digital models of real 3D objects is becoming more and more important in many different applications (e-commerce, virtual visits etc). Very often the objects to be represented cannot be modeled by means of the classical 3D modeling tools because of the geometrical complexity or color texture. In these cases, devices for the automatic acquisition of the shape and the color of the objects (3D scanners or range scanners) have to be used. </p><p>The scanner presented in this work, a Shape from silhouette scanner, is very cheap (it is based on the use of a simple digital camera and a turntable) and easy to use. While maintaining the camera on a tripod and the object on the turntable, the user acquires images with different rotation angles of the table. The fusion of all the acquired views enables the production of a digital 3D representation of the object.</p><p>Existing Shape from silhouette scanners operate in an indirect way. They subdivide the object definition space in a regular 3D grid and verify that a voxel belongs to the object by verifying that its 2D projection falls inside the silhouette of the corresponding image. Our scanner adopts a direct method: by using a new 3D representation scheme and algorithm, the Marching Intersections data structure, we can directly intersect all the 3D volumes obtained by the silhouettes extracted from the images.</p>

Retina located in the back of the eye is not only a vital part of human sight, but also contains valuable information that can be used in biometric security applications, or for the diagnosis of certain diseases. In order to analyze this information from retinal images, its features of blood vessels, microaneurysms and the optic disc require extraction and detection respectively. We propose a method to extract vessels called MF-FDOG. MF-FDOG consists of using two filters, Matched Filter (MF) and the first-order derivative of Gaussian (FDOG). The vessel map is extracted by applying a threshold to the response of MF, which is adaptively adjusted by the mean response of FDOG. This method allows us to better distinguish vessel objects from non-vessel objects. Microaneurysm (MA) detection is accomplished with two proposed algorithms, Multi-scale Correlation Filtering (MSCF) and Dictionary Learning (DL) with Sparse Representation Classifier (SRC). MSCF is hierarchical in nature, consisting of two levels: coarse level microaneurysm candidate detection and fine level true microaneurysm detection. In the first level, all possible microaneurysm candidates are found while the second level extracts features from each candidate and compares them to a discrimination table for decision (MA or non-MA). In Dictionary Learning with Sparse Representation Classifier, MA and non-MA objects are extracted from images and used to learn two dictionaries, MA and non-MA. Sparse Representation Classifier is then applied to each MA candidate object detected beforehand, using the two dictionaries to determine class membership. The detection result is further improved by adding a class discrimination term into the Dictionary Learning model. This approach is known as Centralized Dictionary Learning (CDL) with Sparse Representation Classifier. The optic disc (OD) is an important anatomical feature in retinal images, and its detection is vital for developing automated screening programs. Currently, there is no algorithm designed to automatically detect the OD in fundus images captured from Asians, which are larger and have thicker vessels compared to Caucasians. We propose such a method to complement current algorithms using two steps: OD vessel candidate detection and OD vessel candidate matching. The proposed extraction/detection approaches are tested in medical applications, specifically the case study of detecting diabetic retinopathy (DR). DR is a complication of diabetes that damages the retina and can lead to blindness. There are four stages of DR and is a leading cause of sight loss in industrialized nations. Using MF-FDOG, blood vessels were extracted from DR images, while DR images fed into MSCF and Dictionary and Centralized Dictionary Learning with Sparse Representation Classifier produced good microaneurysm detection results. Using a new database consisting of only Asian DR patients, we successfully tested our OD detection method. As part of future work we intend to improve existing methods such as enhancing low contrast microaneurysms and better scale selection. In additional, we will extract other features from the retina, develop a generalized OD detection method, apply Dictionary Learning with Sparse Representation Classifier to vessel extraction, and use the new image database to carry out more experiments in medical applications.

Thesis (Ph.D.)--Mississippi State University. Department of Electrical and Computer Engineering. / Title from title screen. Includes bibliographical references.