Content-based Image Retrieval for Biomedical Image Archives:
Achievements, Problems, and Prospects
A MICCAI 2007 Workshop, October 29th,
2007
Home | Scope | Organizers | Important Dates | Submissions
| Registration | Preliminary Program
Preliminary Program:
Confirmed Invited
Talks:
Dr.
Christian
Barillot
CNRS Director of Research
CNRS / INRIA Research Unit
Visages Project
Campus Universitaire de Beaulieu, Rennes, France
"Integration of Distributed and Heterogeneous resources in Neuroimaging"
This talk will report about the Neurobase
project which aimed at proposing a system architecture for federating, through
the Internet, information sources in neuroimaging, where sources are stacks of
heterogeneous image data and medical image processing algorithms which are
distributed in different experimental sites, hospitals or research centers.
More precisely, this project consisted in the creation of a shared semantic
reference, suitable for supporting various neuroimaging applications, and a
computer architecture for accessing and sharing relevant distributed
information over the Internet. The chosen overall architecture will be
described, based on a mediator/wrapper approach and on a semantic model and the
preliminary results. We exhibit the experience coming from a real workbench
will be presented. Perspectives will be drawn on extending and disseminating this
work on more specific neuroimaging applications.
web site: www.irisa.fr/visages/neurobase
http://www.irisa.fr/prive/barillot/
Dr.
Yanxi Liu
Associate Professor of Computer Science and Electrical Engineering,
Adjunct
Professor of Radiology Department,
Associate
Research Professor of the Robotics Institute,
"Discriminative Subspace-Driven Biomedical Image Classification,
Indexing and Retrieval"
This paper summarizes our work and our
understanding on image classification, indexing and retrieval for a diverse set
of biomedical images: from volumetric pathological neuroimage (CT),
hyper-spectral microscopic cellular image, to high resolution MR images of
neurodegenerative diseases. We focus our exploration in high dimensional feature
spaces. Our computer algorithms search for the most effective discriminative
subspaces through statistical learning. Using concrete clinical data sets, we
demonstrate the effectiveness of such a methodology with high image sensitivity
and specificity, as well as enhanced computational efficiency for on-line image
classification/retrieval.
Authors:
Y. Liu, L. Teverovskiy, N.A. Lazar, W.E. Rothfus, F. Dellaert, A. Moore, J. Schneider
and T. Kanade
http://www.cse.psu.edu/~yanxi/
Accepted Papers:
Liana Stanescu, Dan Dumitru
Burdescu, Anca Ion,
Content-based region query in databases with color images from digestive
area
Xiaoning Qian, Hemant D. Tagare, Robert K. Fulbright,
Rodney Long and Sameer Antani,
Yale University, New Haven, CT,
USA, National Library of Medicine, Bethesda, USA
Indexing
of Complete and Partial 2-D Shapes for NHANES II
Tsz-Wai Rachel Lo, J. Paul Siebert, and Ashraf F. Ayoub,
Department of Computing Science,
University of Glasgow, Glasgow, UK,
Glasgow Dental Hospital and School,
An
Implementation of the Scale Invariant Feature Transform in the 2.5D Domain
E. Balmashnova, B. Platel, L.M.J. Florack, and B.M. ter Haar Romeny,
Eindhoven University of
Technology, The Netherlands
Content
based image retrieval by means of scale-space top-points and differential
invariants
Ying Chi, Peter M M Cashman,
Fernando Bello, and Richard I Kitney,
Dept of Bioengineering, Imperial
College London, London, Department of
Surgical Oncology and Technology, Imperial College & Mary’s Hospital
Campus, London,
An Automatic Liver Segmentation
Initialization Information Retrieval Strategy for a CBIR System and a new Liver
Volume Segmentation method for CT and MRI Datasets
Scott Doyle, Mark Hwang, Shivang Naik, Michael
Feldman, John Tomaszeweski, and Anant Madabhushi,
Department of Biomedical
Engineering, Rutgers University, USA, Department of Surgical Pathology,
University of Pennsylvania, USA.
Using Manifold Learning for
Content-Based Image Retrieval of Prostate Histopathology
Jinman Kim, Liviu Constantinescu, Weidong Cai, and
David Feng,
University of Sydney, Australia;
Hong Kong Polytechnic University,
Content-based
Dual-Modality Biomedical Data Retrieval using Co-Aligned Functional and
Anatomical Features
Marcela X. Ribeiro, Andre G. R. Balan, Agma J. M.
Traina, and Caetano Traina Jr,
Department of Computer Science,
Enhancing
Medical Image Retrieval through Association Rules
Hitoshi Iyatomi and
Koichi Ogawa,
Hosei University faculty of Engineering, Japan,
Identification
of Shot-Body-Regions from Clinical Photographs using Support Vector Machine Classifiers
William Horsthemke, Daniela
Raicu, and Jacob Furst,
DePaul University, Chicago, IL, USA.
Task-Oriented Medical Image
Retrieval