Direkt zum Inhalt | Direkt zur Navigation

Sektionen

agas-news: "Parallelized Energy Minimization for Real-Time Markov Random Field Terrain Classification in Natural Environments" accepted at the ROBIO 2012; Projektpraktikum Robbie 19; AFCEA Preis 2012 für Nicolai Wojke; VDI prize 2012 for master thesis of Susanne Thierfelder; Koblenzer Studenten international erfolgreich mit Roboter Lisa; Koblenzer Studierende schaffen es beim RoboCup German Open ins Finale; Frank Neuhaus erhält Hochschulpreis der Wirtschaft 2012; Detlev Droege has been elected as board member of the COGAIN Association; Computervisualistik veröffentlicht Vorstellungsfilm; "Hierarchical Loop Detection for Mobile Outdoor Robots" accepted at the SPIE - Electronical Imaging 2012; "Moving Vehicle Detection and Tracking in Unstructured Environments" accepted at the ICRA 2012; "Calibration of Multiple Cameras to a 3D Laser Range Finder" accepted at the ESPA 2012; VDI prize for diploma thesis of Christian Winkens; "Spline Templates for Fast Path Planning in Unstructured Environments" accepted at the IROS 2011; "Terrain Classiﬁcation with Markov Random Fields on fused Camera and 3D Laser Range Data" accepted at the ECMR 2011; Johannes Pellenz defends his PhD thesis "Aktive Sensorik für autonome mobile Systeme"; Stipend for diploma thesis of Marc Arends; Weiter…

Startseite → Campus Koblenz → Fachbereich 4: Informatik → Wissenschaftliche Einrichtungen → Institut für Computervisualistik → Active Vision Group → Projects → Structured CAD

Structured CAD - Analysis of Medical Images

Knowledge based analysis of medical image data

Begin: 01.10.2007
End: 30.06.2009

This project faces the challenging problem of the automatic identification of anatomical structures in computed tomography images by using a knowledge base.
Physical attributes, geometrical and inclusion relations are modeled within this database. Apart from that, normvalues are modeled that can be used in structured reports of diagnostic findings. The aim of the project is to facilitate the process of report generation by automatic labeling of images and presenting context-sensitive set phrases.
The project is joint work from parters in industry (Morits Ltd., Rostock), medical science (Universitätsklinikum Schleswig-Holstein) and computer science (Universität Koblenz-Landau).

Our main tasks are (inter alia):

Programming of segmentation tools and databases for the storage of anatomical knowledge
Computation of features for the charactarisation of anatomical structures
Selection of features from this extended database that identify a certain structure in a CT image