Multimodal evaluation for medical image segmentation

This paper is a joint effort between five institutionsthat introduces several novel similarity measures andcombines them to carry out a multimodal segmentationevaluation. The new similarity measures proposed arebased on the location and the intensity values of themisclassified voxels as well as on the connectivity andthe boundaries of the segmented data. We showexperimentally that the combination of these measuresimprove the quality of the evaluation. The study that weshow here has been carried out using four differentsegmentation methods from four different labs applied toa MRI simulated dataset of the brain. We claim that ournew measures improve the robustness of the evaluation andprovides better understanding about the differencebetween segmentation methods.

An empirical study of machine learning techniques applied to image watermarking

A study of how the machine learning technique, known as gentleboost, could improve different digital watermarking methods such as LSB, DWT, DCT2 and Histogram shifting.

Mirror image atrial dilatation in adult patients with atrial fibrillation and congenital heart disease.

BACKGROUND: Atrial fibrillation (AF) is largely regarded to be initiated from left atrial (LA) dilatation, with subsequent dilatation of the right atrium (RA) in those who progress to chronic AF. We hypothesized that in adult patients with right-sided congenital heart disease (CHD) and AF, RA dilatation will predominate with subsequent dilatation of the left atrium, as a mirror image. METHODS: Adult patients with diagnosis of right-sided, ASD or left-sided CHD who had undergone an echocardiographic study and electrocardiographic recording in 2007 were included. RA and LA area were measured from the apical view. AF was diagnosed from a 12-lead electrocardiogram or Holter recording. A multivariate logistic regression model was used to identify predictors of AF and linear regression models were performed to measure relationship between RA and LA area and AF. RESULTS: A total of 291 patients were included in the study. Multivariate analysis showed that age (p=0.0001), RA (p=0.025) and LA area (p=0.0016) were significantly related to AF. In patients with pure left-sided pathologies, there was progressive and predominant LA dilatation that paralleled the development of AF from none to paroxysmal to chronic AF. In patients with pure right-sided pathologies, there was a mirror image of progressive and predominant RA dilatation with the development of AF. CONCLUSION: We observed a mirror image atrial dilatation in patients with right sided disease and AF. This may provide novel mechanistic insight as to the origin of AF in these patients and deserves further studying in the form of targeted electrophysiological studies.

Investment, duration, and exit strategies for corporate and independent venture capital-backed start-ups

We propose a model of investment, duration, and exit strategies for start-ups backed by venture capital (VC) funds that accounts for the high level of uncertainty, the asymmetry of information between insiders and outsiders, and the discount rate. Our analysis predicts that start-ups backed by corporate VC funds remain for a longer period of time before exiting and receive larger investment amounts than those financed by independent VC funds. Although a longer duration leads to a higher likelihood of an exit through an acquisition, a larger investment increases the probability of an IPO exit. These predictions find strong empirical support.

A multidimensional segmentation evaluation for medical image data.

Evaluation of segmentation methods is a crucial aspect in image processing, especially in the medical imaging field, where small differences between segmented regions in the anatomy can be of paramount importance. Usually, segmentation evaluation is based on a measure that depends on the number of segmented voxels inside and outside of some reference regions that are called gold standards. Although some other measures have been also used, in this work we propose a set of new similarity measures, based on different features, such as the location and intensity values of the misclassified voxels, and the connectivity and the boundaries of the segmented data. Using the multidimensional information provided by these measures, we propose a new evaluation method whose results are visualized applying a Principal Component Analysis of the data, obtaining a simplified graphical method to compare different segmentation results. We have carried out an intensive study using several classic segmentation methods applied to a set of MRI simulated data of the brain with several noise and RF inhomogeneity levels, and also to real data, showing that the new measures proposed here and the results that we have obtained from the multidimensional evaluation, improve the robustness of the evaluation and provides better understanding about the difference between segmentation methods.

Positioning an underwater vehicle through image mosaicking

Mosaics have been commonly used as visual maps for undersea exploration and navigation. The position and orientation of an underwater vehicle can be calculated by integrating the apparent motion of the images which form the mosaic. A feature-based mosaicking method is proposed in this paper. The creation of the mosaic is accomplished in four stages: feature selection and matching, detection of points describing the dominant motion, homography computation and mosaic construction. In this work we demonstrate that the use of color and textures as discriminative properties of the image can improve, to a large extent, the accuracy of the constructed mosaic. The system is able to provide 3D metric information concerning the vehicle motion using the knowledge of the intrinsic parameters of the camera while integrating the measurements of an ultrasonic sensor. The experimental results of real images have been tested on the GARBI underwater vehicle

A study of governance practices in corporate foundations

Implementation of social investments through corporate foundations is growing and, therefore, it is important to study their governance aspects better. Governance is conceptualized as a set of control and incentive mechanisms to overcome the so-called agency conflicts, which originate from the separation of property and management in for-profit organizations, a concept also applied to nonprofit institutions. It is argued that corporate foundations have the characteristics both of companies and of civil society organizations, which distinguishes them from both types of organizations. This paper analyses a study in which a set of governance mechanisms, adapted from those identified by a literature review of corporate and nonprofit governance, was selected for study. It is an exploratory descriptive case study, which analyzed data about eight organizations collected through publications and interviews with their CEOs. The data analysis indicates that it is appropriate to distinguish the different organization types and to apply the agency theory. Research results indicate that the selected governance mechanisms may be adapted and used in corporate foundations. However, they are only partially applied in the observed cases, which suggests the need for further studies that might consolidate these practices in such organizations.

From Translation to Rewriting : the Interplay of Text and Image in The Fairy Tales of Charles Perrault and The Bloody Chamber and Other Stories

Abstract :This article examines the interplay of text and image in The Fairy Tales of Charles Perrault (1977), translated by Angela Carter and illustrated by Martin Ware, as a form of intersemiotic dialogue that sheds new light on Carter's work. It argues that Ware's highly original artwork based on the translation not only calls into question the association of fairy tales with children's literature (which still characterizes Carter's translation), but also captures an essential if heretofore neglected aspect of Carter's creative process, namely the dynamics between translating, illustrating and rewriting classic tales. Several elements from Ware's illustrations are indeed taken up and elaborated on in The Bloody Chamber and Other Stories (1979), the collection of "stories about fairy stories" that made Carter famous. These include visual details and strategies that she transposed to the realm of writing, giving rise to reflections on the relation between visuality and textuality.RésuméCet article considère l'interaction du texte et de l'image dans les contes de Perrault traduits par Angela Carter et illustrés par Martin Ware (The Fairy Tales of Charles Perrault, 1977) comme une forme de dialogue intersémiotique particulièrement productif. Il démontre que les illustrations originales de Ware ne mettent pas seulement en question l'assimilation des contes à la littérature de jeunesse (qui est encore la perspective adoptée par la traductrice dans ce livre), mais permettent aussi de saisir un aspect essentiel bien que jusque là ignoré du procession de création dans l'oeuvre de Carter, à savoir la dynamique qui lie la traduction, l'illustration et la réécriture des contes classiques. Plusieurs éléments des illustrations de Ware sont ainsi repris et élaborés dans The Bloody Chamber and Other Stories (1979), la collection de "stories about fairy stories" qui rendit Carter célèbre. La transposition de détails et de stratégies visuelles dans l'écriture donnent ainsi l'occasion de réflexions sur les rapports entre la visualité et la textualité.

Weighted Shape-based Averaging with Neighborhood Prior Model for Multiple Atlas Fusion-based Medical Image Segmentation

In medical imaging, merging automated segmentations obtained from multiple atlases has become a standard practice for improving the accuracy. In this letter, we propose two new fusion methods: "Global Weighted Shape-Based Averaging" (GWSBA) and "Local Weighted Shape-Based Averaging" (LWSBA). These methods extend the well known Shape-Based Averaging (SBA) by additionally incorporating the similarity information between the reference (i.e., atlas) images and the target image to be segmented. We also propose a new spatially-varying similarity-weighted neighborhood prior model, and an edge-preserving smoothness term that can be used with many of the existing fusion methods. We first present our new Markov Random Field (MRF) based fusion framework that models the above mentioned information. The proposed methods are evaluated in the context of segmentation of lymph nodes in the head and neck 3D CT images, and they resulted in more accurate segmentations compared to the existing SBA.

The role of energetic value in dynamic brain response adaptation during repeated food image viewing.

The repeated presentation of simple objects as well as biologically salient objects can cause the adaptation of behavioral and neural responses during the visual categorization of these objects. Mechanisms of response adaptation during repeated food viewing are of particular interest for better understanding food intake beyond energetic needs. Here, we measured visual evoked potentials (VEPs) and conducted neural source estimations to initial and repeated presentations of high-energy and low-energy foods as well as non-food images. The results of our study show that the behavioral and neural responses to food and food-related objects are not uniformly affected by repetition. While the repetition of images displaying low-energy foods and non-food modulated VEPs as well as their underlying neural sources and increased behavioral categorization accuracy, the responses to high-energy images remained largely invariant between initial and repeated encounters. Brain mechanisms when viewing images of high-energy foods thus appear less susceptible to repetition effects than responses to low-energy and non-food images. This finding is likely related to the superior reward value of high-energy foods and might be one reason why in particular high-energetic foods are indulged although potentially leading to detrimental health consequences.

Learning spatial filters for multispectral image segmentation

We present a novel filtering method for multispectral satellite image classification. The proposed method learns a set of spatial filters that maximize class separability of binary support vector machine (SVM) through a gradient descent approach. Regularization issues are discussed in detail and a Frobenius-norm regularization is proposed to efficiently exclude uninformative filters coefficients. Experiments carried out on multiclass one-against-all classification and target detection show the capabilities of the learned spatial filters.