Abstract
A method is proposed to segment digital posterior-anterior chest X-ray images. The segmentation is achieved through the registration of a deformable prior model, describing the anatomical structures of interest, to the X-ray image. The deformation of the model is performed using a deformation grid. A coarse matching of the model is done using anatomical landmarks automatically extracted from the image, and maps of oriented edges axe used to guide the deformation process, optimized with a probabilistic genetic algorithm. The method is applied to extract the ribcage and delineate the mediastinum and diaphragms. The segmentation is needed for defining the lungs region, used in computer-aided diagnosis systems.

Abstract
A new algorithm for an effective and automatic segmentation of the carotid wall in ultrasonic images is proposed. It combines the speed of thresholding algorithms with the accuracy, flexibility and robustness of a successful geometric active contour model which incorporates an optimal image segmentation model in a level set framework. Due to the multiphase nature of these images, a sequential minimum cross entropy thresholding is used to get a first approximation of the segments, reducing the problem to a two phase segmentation. This thresholding solution is then used as a starting point for a two phase piecewise constant version of a geometric active contour model to reduce noise, smooth contours, improve their position accuracy and close eventual gaps in the carotid wall.

Abstract

Abstract
This paper describes an approach for integrating motion estimation and region clustering techniques with the purpose of obtaining precise multiple motion segmentation. Motivated by the good results obtained in static segmentation we propose a hybrid approach where motion segmentation is achieved within a region-based clustering approach taken the initial result of a spatial pre-segmentation and extended to include motion information. Motion vectors are first estimated with a multiscale variational method applied directly over the input images and then refined by incorporating segmentation results into a region-based warping scheme. The complete algorithm facilitates obtaining spatially continuous segmentation maps which are closely related to actual object boundaries. A comparative study is made with some of the best known motion segmentation algorithms.

Abstract
The study of individual plant cells and their growth structure is an important focus of research in plant genetics. To obtain development information at cellular level, researchers need to perform in vivo imaging of the specimen under study, through time-lapse confocal microscopy. Within this research field it is important to understand mechanisms like cell division and elongation of developing cells. We describe a tool to automatically search for cell division in the Arabidopsis thaliana using information of nuclei shape. The nuclei detection is based on a convergence index filter. Cell division detection is performed by an automatic classifier, trained through cross-validation. The results are further improved by a stability criterion based on the Mahalanobis distance of the shape of the nuclei through time. With this approach, we can achieve a correct detection rate of 94.7%.

Abstract
The study of cell division and growth is a fundamental aspect of plant biology research. In this research the Arabidopsis thaliana plant is the most widely studied model plant and research is based on in vivo observation of plant cell development, by time-lapse confocal microscopy. The research herein described is based on a large amount of image data, which must be analyzed to determine meaningful transformation of the cells in the plants. Most approaches for cell division detection are based on the morphological analysis of the cells' segmentation. However, cells are difficult to segment due to had image quality in the in vivo images. We describe an approach to automatically search for cell division in the Arabidopsis thaliana root meristem using image registration and optical flow. This approach is based on the difference of speeds of the cell division and growth processes (cell division being a much faster process). With this approach, we can achieve a detection accuracy of 96.4%.