Anton Bardera

Automatic Transfer Functions Based on Informational Divergence

In this paper we present a framework to define transfer functions from a target distribution provided by the user. A target distribution can reflect the data importance, or highly relevant data value interval, or spatial segmentation. Our approach is based on a communication channel between a set of viewpoints and a set of bins of a volume data set, and it supports 1D as well as 2D transfer functions including the gradient information. The transfer functions are obtained by minimizing the informational divergence or Kullback-Leibler distance between the visibility distribution captured by the viewpoints and a target distribution selected by the user. The use of the derivative of the informational divergence allows for a fast optimization process. Different target distributions for 1D and 2D transfer functions are analyzed together with importance-driven and view-based techniques.

Medical Image Segmentation Based on Mutual Information Maximization

In this paper we propose a two-step mutual information-based algorithm for medical image segmentation. In the first step, the image is structured into homogeneous regions, by maximizing the mutual information gain of the channel going from the histogram bins to the regions of the partitioned image. In the second step, the intensity bins of the histogram are clustered by minimizing the mutual information loss of the reversed channel. Thus, the compression of the channel variables is guided by the preservation of the information on the other. An important application of this algorithm is to preprocess the images for multimodal image registration. In particular, for a low number of histogram bins, an outstanding robustness in the registration process is obtained by using as input the previously segmented images.

Image Segmentation Using Information Bottleneck Method

In image processing, segmentation algorithms constitute one of the main focuses of research. In this paper, new image segmentation algorithms based on a hard version of the information bottleneck method are presented. The objective of this method is to extract a compact representation of a variable, considered the input, with minimal loss of mutual information with respect to another variable, considered the output. First, we introduce a split-and-merge algorithm based on the definition of an information channel between a set of regions (input) of the image and the intensity histogram bins (output). From this channel, the maximization of the mutual information gain is used to optimize the image partitioning. Then, the merging process of the regions obtained in the previous phase is carried out by minimizing the loss of mutual information. From the inversion of the above channel, we also present a new histogram clustering algorithm based on the minimization of the mutual information loss, where now the input variable represents the histogram bins and the output is given by the set of regions obtained from the above split-and-merge algorithm. Finally, we introduce two new clustering algorithms which show how the information bottleneck method can be applied to the registration channel obtained when two multimodal images are correctly aligned. Different experiments on 2-D and 3-D images show the behavior of the proposed algorithms.

Semi-automated method for brain hematoma and edema quantification using computed tomography

In this paper, a semi-automated method for brain hematoma and edema segmentation, and volume measurement using computed tomography imaging is presented. This method combines a region growing approach to segment the hematoma and a level set segmentation technique to segment the edema. The main novelty of this method is the strategy applied to define the propagation function required by the level set approach. To evaluate the method, 18 patients with brain hematoma and edema of different size, shape and location were selected. The obtained results demonstrate that the proposed approach provides objective and reproducible segmentations that are similar to the manually obtained results. Moreover, the processing time of the proposed method is about 4 min compared to the 10 min required for manual segmentation.

Normalized similarity measures for medical image registration

Two new similarity measures for rigid image registration, based on the normalization of Jensens difference applied to Renyi and Tsallis-Havrda-Charvat entropies, are introduced. One measure is normalized by the first term of Jensens difference, which in our proposal coincides with the marginal entropy, and the other by the joint entropy. These measures can be seen as an extension of two measures successfully applied in medical image registration: the mutual information and the normalized mutual information. Experiments with various registration modalities show that the new similarity measures are more robust than the normalized mutual information for some modalities and a determined range of the entropy parameter. Also, a certain improvement on accuracy can be obtained for a different range of this parameter.

High-Dimensional normalized mutual information for image registration using random lines

Mutual information has been successfully used as an effective similarity measure for multimodal image registration. However, a drawback of the standard mutual information-based computation is that the joint histogram is only calculated from the correspondence between individual voxels in the two images. In this paper, the normalized mutual information measure is extended to consider the correspondence between voxel blocks in multimodal rigid registration. The ambiguity and high-dimensionality that appears when dealing with the voxel neighborhood is solved using uniformly distributed random lines and reducing the number of bins of the images. Experimental results show a significant improvement with respect to the standard normalized mutual information.

Reliability of the ABC/2 Method in Determining Acute Infarct Volume

Infarct volume is used as a surrogate outcome measure in clinical trials of therapies for acute ischemic stroke. ABC/2 is a fast volumetric method, but its accuracy remains to be determined. We aimed to study the accuracy and reproducibility of ABC/2 in determining acute infarct volume with diffusion‐weighted imaging.

Multimodal Data Fusion Based on Mutual Information

Multimodal visualization aims at fusing different data sets so that the resulting combination provides more information and understanding to the user. To achieve this aim, we propose a new information-theoretic approach that automatically selects the most informative voxels from two volume data sets. Our fusion criteria are based on the information channel created between the two input data sets that permit us to quantify the information associated with each intensity value. This specific information is obtained from three different ways of decomposing the mutual information of the channel. In addition, an assessment criterion based on the information content of the fused data set can be used to analyze and modify the initial selection of the voxels by weighting the contribution of each data set to the final result. The proposed approach has been integrated in a general framework that allows for the exploration of volumetric data models and the interactive change of some parameters of the fused data set. The proposed approach has been evaluated on different medical data sets with very promising results.

Breast Density Segmentation: A Comparison of Clustering and Region Based Techniques

This paper presents a comparison of two clustering based algorithms and one region based algorithm for segmenting fatty and dense tissue in mammographic images. This is a crucial step in order to obtain a quantitative measure of the density of the breast. The first algorithm is a multiple thresholding algorithm based on the excess entropy, the second one is based on the Fuzzy C-Means clustering algorithm, and the third one is based on a statistical analysis of the breast. The performance of the algorithms is exhaustively evaluated using a database of full-field digital mammograms containing 150 CC and 150 MLO images and ROC analysis (ground-truth provided by an expert). Results demonstrate that the use of region information is useful to obtain homogeneous region segmentation, although clustering algorithms obtained better sensitivity.

Image registration by compression

Abstract Image registration consists in finding the transformation that brings one image into the best possible spatial correspondence with another image. In this paper, we present a new framework for image registration based on compression. The basic idea underlying our approach is the conjecture that two images are correctly registered when we can maximally compress one image given the information in the other. The contribution of this paper is twofold. First, we show that image registration can be formulated as a compression problem. Second, we demonstrate the good performance of the similarity metric, introduced by Li et al., in image registration. Two different approaches for the computation of this similarity metric are described: the Kolmogorov version, computed using standard real-world compressors, and the Shannon version, calculated from an estimation of the entropy rate of the images.