| An adaptive tissue characterization network for model-free visualization of dynamic contrast-enhanced magnetic resonance image data. | |
| | |
MedLine Citation:
|
PMID: 16229413 Owner: NLM Status: MEDLINE |
Abstract/OtherAbstract:
|
Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has become an important source of information to aid cancer diagnosis. Nevertheless, due to the multi-temporal nature of the three-dimensional volume data obtained from DCE-MRI, evaluation of the image data is a challenging task and tools are required to support the human expert. We investigate an approach for automatic localization and characterization of suspicious lesions in DCE-MRI data. It applies an artificial neural network (ANN) architecture which combines unsupervised and supervised techniques for voxel-by-voxel classification of temporal kinetic signals. The algorithm is easy to implement, allows for fast training and application even for huge data sets and can be directly used to augment the display of DCE-MRI data. To demonstrate that the system provides a reasonable assessment of kinetic signals, the outcome is compared with the results obtained from the model-based three-time-points (3TP) technique which represents a clinical standard protocol for analysing breast cancer lesions. The evaluation based on the DCE-MRI data of 12 cases indicates that, although the ANN is trained with imprecisely labeled data, the approach leads to an outcome conforming with 3TP without presupposing an explicit model of the underlying physiological process. |
| | |
Authors:
|
Thorsten Twellmann; Oliver Lichte; Tim W Nattkemper |
Related Documents
:
|
11802023 - Real-time, cine magnetic resonance imaging for evaluation of the pediatric airway. 9137193 - Imaging assessment of the response of bone tumors to preoperative chemotherapy. 7790953 - Pet studies on brain monoamine transporters with carbon-11-beta-cit in parkinson's dise... |
Publication Detail:
|
Type: Clinical Trial; Journal Article |
Journal Detail:
|
Title: IEEE transactions on medical imaging Volume: 24 ISSN: 0278-0062 ISO Abbreviation: IEEE Trans Med Imaging Publication Date: 2005 Oct |
Date Detail:
|
Created Date: 2005-10-18 Completed Date: 2005-12-20 Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 8310780 Medline TA: IEEE Trans Med Imaging Country: United States |
Other Details:
|
Languages: eng Pagination: 1256-66 Citation Subset: IM |
Affiliation:
|
Applied Neuroinformatics Group, Faculty of Technology, Bielefeld University, Bielefeld, Germany. ttwellma@techfak.uni-bielefeld.de |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
Algorithms Artificial Intelligence Breast Neoplasms / diagnosis* Contrast Media* Female Humans Image Enhancement / methods* Image Interpretation, Computer-Assisted / methods* Imaging, Three-Dimensional / methods* Magnetic Resonance Imaging / methods* Models, Biological Neural Networks (Computer) Pattern Recognition, Automated / methods* Reproducibility of Results Sensitivity and Specificity |
| Chemical | |
Reg. No./Substance:
|
0/Contrast Media |
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Chirp imaging vibro-acoustography for removing the ultrasound standing wave artifact.
Next Document: DTI segmentation using an information theoretic tensor dissimilarity measure.