Danielle Sent

Features in Content-based Image Retrieval Systems: a Survey

This article provides a framework to describe and compare content-based image retrieval systems. Sixteen contemporary systems are described in detail, in terms of the following technical aspects: querying, relevance feedback, result presentation, features, and matching. For a total of 44 systems we list the features that are used. Of these systems, 35 use any kind of color features, 28 use texture, and only 25 use shape features.

Motion planning in environments with danger zones

This paper addresses the problem of path planning for a free-flying object in a (three-dimensional) environment that contains both obstacles and so-called danger zones. The path should (obviously) avoid collisions with the obstacles. The path is allowed to intersect with the danger zones, but this should be avoided as much as possible. We show that under some mild conditions, a path always exists in which the moving object never completely penetrates the danger zones. Based on this result we present a probabilistically complete roadmap method that finds such paths. The methods has been implemented and some experimental results are given.

Medintel: Decision support for general practitioners: a case study

Short consultations and a large and growing amount of available medical information make searching for suitable information difficult for general practitioners. Thus information is often not searched for or not found, diminishing the quality of care. We propose a system that offers decision support by combining medical information sources with data from the electronic patient record. A first evaluation shows that a system like Medintel can be a useful supportive tool and can increase the quality of care provided by general practitioners.

Generalised reliability characteristics for probabilistic networks

BACKGROUND In the medical domain, establishing a diagnosis typically amounts to reasoning about the unobservable truth, based upon a set of indirect observations from diagnostic tests. A diagnostic test may not be perfectly reliable, however. To avoid misdiagnosis, therefore, the reliability characteristics of the test should be taken into account upon reasoning. OBJECTIVE In this paper, we address the issue of modelling the reliability characteristics of diagnostic tests in a probabilistic network. METHOD To this end, we study the mathematical foundation of a tests characteristics and collate them with the probabilities required for a probabilistic network. RESULTS We show that the standard reliability characteristics that are generally available from the literature have to be further detailed and stratified, for example by experts, before they can be included in a network. We demonstrate these modelling issues by means of a real-life probabilistic network in oncology.