A targeted Gd 3؉ -based contrast agent has been developed that detects tumor cell death by binding to the phosphatidylserine (PS) exposed on the plasma membrane of dying cells. Although this agent has been used to detect tumor cell death in vivo, the differences in signal intensity between treated and untreated tumors was relatively small. As cell death is often spatially heterogeneous within tumors, we investigated whether an image analysis technique that parameterizes heterogeneity could be used to increase the sensitivity of detection of this targeted contrast agent. Two-dimensional (2D) Minkowski functionals (MFs) provided an automated and reliable method for parameterization of image heterogeneity, which does not require prior assumptions about the number of regions or features in the image, and were shown to increase the sensitivity of detection of the contrast agent as compared to simple signal intensity analysis. Magn Reson Med 61:1218 -1224, 2009.
Abstract-In this paper we present current achievements in computer aided ECG analysis and their applicability in real world medical diagnosis process. Most of the current work is covering problems of removing noise, detecting heartbeats and rhythm-based analysis. There are some advancements in particular ECG segments detection and beat classifications but with limited evaluations and without clinical approvals. This paper presents state of the art advancements in those areas till present day. Besides this short computer science and signal processing literature review, paper covers future challenges regarding the ECG signal morphology analysis deriving from the medical literature review. Paper is concluded with identified gaps in current advancements and testing, upcoming challenges for future research and a bullseye test is suggested for morphology analysis evaluation.
In this paper we present a mathematical model for collaborative filtering implementation in stock market predictions. In popular literature collaborative filtering, also known as Wisdom of Crowds, assumes that group has a greater knowledge than the individual while each individual can improve groups performance by its specific information input. There are commercially available tools for collaborative stock market predictions and patent protected web-based software solutions. Mathematics that lies behind those algorithms is not disclosed in the literature, so the presented model and algorithmic implementation are the main contributions of this work.
This chapter covers natural language processing techniques and their application in predicitve models development. Two case studies are presented. First case describes a project where textual descriptions of various situations in call center of one telecommunication company were processed in order to predict churn. Second case describes sentiment analysis of business news and describes practical and testing issues in text mining projects. Both case studies depict different approaches and are implemented in different tools. Language of the texts processed in these projects is Croatian which belongs to the Slavic group of languages with more complex morphologies and grammar rules than English. Chapter concludes with several points on the future research possible in this domain.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.