Tilmann Steinberg

Learn More
We perform discriminative analysis of brain structures using morphometric information. Spherical harmonics technique and point distribution model are used for shape description. Classification is performed using linear discriminants and support vector machines with several feature selection approaches. We consider both inclusion and exclusion of volume(More)
This paper introduces SCENS, a Secure Content Exchange Negotiation System suitable for the exchange of private digital data that reside in distributed digital repositories. SCENS is an open negotiation system with flexibility, security and scalability. SCENS is currently being designed to support data sharing in scientific research, by providing incentives(More)
Web access patterns can provide valuable information for website designers in making website-based communication more efficient. To extract interesting or useful web access patterns, we use data mining techniques which analyze historical web access logs. In this paper, we present an efficient approach to mine the most interesting web access associations,(More)
Traditional digital library systems have difficulties when managing heterogeneous datasets that have limitations on their distribution. Collections of digital libraries have to be accessed individually and through non-uniform interfaces. By introducing a level of abstraction, a Meta-Digital Library or MetaDL, users gain a central access portal that allows(More)
This paper describes the development of MS-Analyze, a system framework to analyze and detect patterns in brain pathology of multiple sclerosis (MS) as the disease progresses over time. We are building the system to collect, analyze and integrate disparate data extracted from observing the behavior of MS lesions and surrounding pathology on magnetic(More)
MetaDLs are digital libraries (DLs) designed to store and manage the access of metadata rather than original data [1]. They are particularly suited for data that is sensitive in nature (possibly proprietary), complex in structure, of high value (or production cost), and highly heterogeneous. The authors describe such a MetaDL system architecture in [9],(More)
The spherical harmonics (SPHARM) approach has been used for the representation of shapes in many types of biomedical image data. We propose a SPHARM-based similarity comparison for shape sequences that allows fast similarity searches for dynamic objects and demonstrate it using 3D images of a beating heart. By using spherical harmonics to extract a small(More)
Trust in cross-media applications is essential to successful collaboration. Cross media service delivery encompasses different types of security incidents and assumes a level of trust on the part of the participants of any one transaction. As enterprises and participants of cross media transactions become more susceptible to security risks facilitated by(More)
Correlating event streams or development paths of observed behavior that involves disparate types of data is a common problem in many applications including biomedical and clinical diagnosis systems. We present a new formulation of the following dual problem: (a) given multiple event streams for which we have prior knowledge, specify a feature space with(More)
We develop a multimedia system to support the whole process of the anatomical study of brain images. The system provides a segmentation tool to extract regions-of-interest from brain images, an education component to automate the process of reliable segmentation training, a toolbox mechanism to incorporate research components for actual analytical tasks on(More)