Esther Dura

Modeling user preferences in content-based image retrieval

This paper is concerned with content-based image retrieval from a stochastic point of view. The semantic gap problem is addressed in two ways. First, a dimensional reduction is applied using the (pre-calculated) distances among images. The dimension of the reduced vector is the number of preferences that we allow the user to choose from, in this case, three levels. Second, the conditional probability distribution of the random user preference, given this reduced feature vector, is modeled using a proportional odds model. A new model is fitted at each iteration. The score used to rank the image database is based on the estimated probability function of the random preference. Additionally, some memory is incorporated in the procedure by weighting the current and previous scores. Also, a novel evaluation procedure is proposed in this work based on the empirical commutative distribution functions of the relevant and non-relevant retrieved images. Good experimental results are achieved in very different experimental setups and tested in different databases. HighlightsA novel method for image retrieval have been proposed based on Generalized Linear Model.The model aims to bridge the semantic gap between low level features and user preferences.A drastic dimension reduction of feature vector is achieved by using a distance matrix.A broad set of experiments has been carried out for different databases.A new evaluation procedure has been proposed based on the empirical commutative distribution functions of the relevant and non-relevant retrieved images.

Modeling of female human body shapes for apparel design based on cross mean sets

Abstract This paper is concerned with a method to build prototypes of human bodies that can be used for apparel design. One of the most important issues in the apparel development process is to define a sizing system to provide a good fitting for the majority of the population. Since anthropometric measures do not present the same linear growth with size in each dimension, it is very important to find a prototype that represents as accurately as possible each class in the sizing system. In this paper we propose a method based on the concept of random compact mean set to define prototypes in apparel design. From a cloud of 3D points obtained with a 3D scanner a solid that represents the human body is obtained. 2D cross sections of this solid are extracted at certain heights corresponding to key points of the body. These different cross-sections can be seen as a realization of a random compact set in the plane. A very popular definition on mean set is applied to each sample of 2D cross sections, and finally the prototype is obtained as the 3D reconstruction of these 2D mean sections. As a real example, the proposed methodology is applied to the 3D database obtained from a anthropometric survey of the Spanish female population conducted in this country in 2006.

Evaluation of the registration of temporal series of contrast-enhanced perfusion magnetic resonance 3D images of the liver

The registration of 2D and 3D images is one of the key tasks in medical image processing and analysis. Accurate registration is a crucial preprocessing step for many tasks; consequently, the evaluation of its accuracy becomes necessary. Unfortunately, this is a difficult task, especially when no golden pattern (true result) is available and when the signal values may have changed between successive images to be registered. This is the case this paper deals with: we have a series of 3D images, magnetic resonance images (MRI) of the liver and adjacent areas that have to be registered. They have been taken while a contrast is diffused through the liver tissue, so intensity of each observed point changes for two reasons: contrast diffusion/perfusion and deformation of the liver (due to body movement and breathing). In this paper, we introduce a new method to automatically compare two or more registration algorithms applied to the same case of a perfusion magnetic resonance dynamic image so that the best of them can be chosen when no ground truth is available. This is done by modeling the function that gives the intensity at a given point as a functional datum, and using statistical techniques to assess its change in comparison with other functions. An example of the application is shown by comparing two parametrizations of a B-spline based registration algorithm. The main result of the proposed method is a suggestive evidence to guide the physician in the process of selecting a registration algorithm, that recommends the algorithm of minimal complexity but still suitable for the case to be analyzed.

Mathematical Morphology for Color Images: An Image-Dependent Approach

This paper proposes one possibility to generalize the morphological operations (particularly, dilation, erosion, opening, and closing) to color images. First, properties of a desirable generalization are stated and a brief review is done on former approaches. Then, the method is explained, which is based on a total ordering of the colors in an image induced by its color histogram; this is valid for just one image and may present problems in smoothly coloured images. To solve these drawbacks a refinement consisting of smoothing the histogram and using a joint histogram of several images is presented. Results of applying the so-defined morphological operations on several sets of images are shown and discussed.

Automatic segmentation of the spine by means of a probabilistic atlas with a special focus on ribs suppression. Preliminary results

Spine is a structure commonly involved in several prevalent diseases. In clinical diagnosis, therapy, and surgical intervention, the identification and segmentation of the vertebral bodies are crucial steps. However, automatic and detailed segmentation of vertebrae is a challenging task, especially due to the proximity of the vertebrae to the corresponding ribs and other structures such as blood vessels. In this study, to overcome these problems, a probabilistic atlas of the spine, including cervical, thoracic and lumbar vertebrae has been built to introduce anatomical knowledge in the segmentation process, aiming to deal with overlapping gray levels and the proximity to other structures. From a set of 3D images manually segmented by a physician (training data), a 3D volume indicating the probability of each voxel of belonging to the spine has been developed, being necessary the generation of a probability map and its deformation to adapt to each patient. To validate the improvement of the segmentation using the atlas developed in the testing data, we computed the Hausdorff distance between the manually-segmented ground truth and an automatic segmentation and also between the ground truth and the automatic segmentation refined with the atlas. The results are promising, obtaining a higher improvement especially in the thoracic region, where the ribs can be found and appropriately eliminated.

A local level set method for liver segmentation in functional MR imaging

Functional Magnetic Resonance (fMR) is a medical image technique in which a contrast is injected in the vascular system so that blood diffusion along it can be observed as variations of the signal intensity. The uptake variations of the contrast agent are used in early detection of tumorous tissue. For the diagnostic to be accurate, successive volumes must be correctly registered. For binary registration prior segmentation of the 3D fMR data is required. Here we present a local 3D level-set segmentation method which preserves details and edges, along with its multi-scale version which has the advantage of a great acceleration with respect to the single-scale version. Results of liver segmentation of real fMR medical images are provided.

Mean sets for building 3D probabilistic liver atlas from perfusion MR images

This paper is concerned with liver atlas construction. One of the most important issues in the framework of computational abdominal anatomy is to define an atlas that provides a priori information for common medical task such as registration and segmentation. Unlike other approaches already proposed so far (to our knowledge), in this paper we propose to use the concept of random compact mean set to build probabilistic liver atlases. To accomplish this task a two-tier process was carried out. First a set of 3D images was manually segmented by a physician. We see the different 3D segmented shapes as a realization of a random compact set. Secondly, elements of two known definitions of mean set were applied to build a probabilistic atlas that captures the variability of the cases, keeping nevertheless the essential shape of the liver.

A method for liver segmentation in perfusion MR images using probabilistic atlases and viscous reconstruction

Magnetic resonance (MR) tomographic images are routinely used in diagnosis of liver pathologies. Liver segmentation is needed for these types of images. It is therefore an important requirement for later tasks such as comparison among studies of different patients, as well as studies of the same patient (including those taken during the diffusion of a contrast, as in perfusion MR imaging). However, automatic segmentation of the liver is a challenging task due to certain reasons such as the high variability of liver shapes, similar intensity values and unclear contours between the liver and surrounding organs, especially in perfusion MR images. In order to overcome these limitations, this work proposes the use of a probabilistic atlas for liver segmentation in perfusion MR images, and the combination of the information gathered with that provided by level-based segmentation methods. The process starts with an under-segmented shape that grows slice by slice using morphological techniques (namely, viscous reconstruction); the result of the closest segmented slice and the probabilistic information provided by the atlas. Experiments with a collection of manually segmented liver images are provided, including numerical evaluation using widely accepted metrics for shape comparison.

Automatic Segmentation of the Spine by Means of a Probabilistic Atlas With a Special Focus on Ribs Suppression

Purpose The development of automatic and reliable algorithms for the detection and segmentation of the vertebrae are of great importance prior to any diagnostic task. However, an important problem found to accurately segment the vertebrae is the presence of the ribs in the thoracic region. To overcome this problem, a probabilistic atlas of the spine has been developed dealing with the proximity of other structures, with a special focus on ribs suppression. Methods The data sets used consist of Computed Tomography images corresponding to 21 patients suffering from spinal metastases. Two methods have been combined to obtain the final result: firstly, an initial segmentation is performed using a fully automatic level‐set method; secondly, to refine the initial segmentation, a 3D volume indicating the probability of each voxel of belonging to the spine has been developed. In this way, a probability map is generated and deformed to be adapted to each testing case. Results To validate the improvement obtained after applying the atlas, the Dice coefficient (DSC), the Hausdorff distance (HD), and the mean surface‐to‐surface distance (MSD) were used. The results showed up an average of 10 mm of improvement accuracy in terms of HD, obtaining an overall final average of 15.51 ± 2.74 mm. Also, a global value of 91.01 ± 3.18% in terms of DSC and a MSD of 0.66 ± 0.25 mm were obtained. The major improvement using the atlas was achieved in the thoracic region, as ribs were almost perfectly suppressed. Conclusion The study demonstrated that the atlas is able to detect and appropriately eliminate the ribs while improving the segmentation accuracy.

Iteratively Learning a Liver Segmentation Using Probabilistic Atlases: Preliminary Results

This works deals with the concept of liver segmentation by using a priori information based on probabilistic atlases and segmentation learning based of previous steps. A probabilistic atlas is here understood as a probability or membership map that tells how likely is that a point belongs to a shape drawn from the shape distribution at hand. We devise a procedure to segment Perfusion Magnetic Resonance liver images that combines both: a probabilistic atlas of the liver and a segmentation algorithm based on global information of previous simpler segmentation steps, local information from close segmented slices and finally a mathematical morphology procedure, namely viscous reconstruction, to fill the shape. Preliminary results of the algorithm are provided.