Tumor feature visualization with unsupervised learning

Nattkemper TW, Wismuller A (2005)

Zeitschriftenaufsatz | Veröffentlicht | Englisch
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Abstract / Bemerkung
Dynamic contrast enhanced magnetic resonance imaging (DCE MRI) is applied for diagnosis and therapy control of breast cancer. The malignancy of a lesion is expressed in the average signal kinetics of selected regions of interest (ROI) representing the lesion. The technique is reported to characterize malignant tumors with high sensitivity and highly variable specificity. Computer-based diagnosis (CAD) systems have been proposed to analyze and classify signal time curve data, extracted from hand selected ROI in the DCE MRI data. In this paper, we apply the self-organizing map (SOM) to a set of time curve feature vectors of single voxels from seven benign lesions and seven malignant tumors. Applying the SOM we are able to project the time curve values of each voxel on a two-dimensional map. The results show, that the SOM is able to visualize the hidden two-dimensional structure of the six-dimensional signal space. Using the trained SOM, we are able to identify voxels with benign or malignant signal characteristics and to visualize lesion cross-sections with pseudo-colors. A comparison with the established three time points method shows that the SOM has clear potential for deriving visualization parameters in DCE MRI analysis. (c) 2005 Elsevier B.V. All rights reserved.
self-organizing maps; multivariate image analysis; visualization; dynamic contrast; enhanced magnetic resonance imaging; breast cancer diagnosis; unsupervised learning; artificial neural networks
Page URI


Nattkemper TW, Wismuller A. Tumor feature visualization with unsupervised learning. MEDICAL IMAGE ANALYSIS. 2005;9(4):344-351.
Nattkemper, T. W., & Wismuller, A. (2005). Tumor feature visualization with unsupervised learning. MEDICAL IMAGE ANALYSIS, 9(4), 344-351. https://doi.org/10.1016/j.media.2005.01.004
Nattkemper, Tim Wilhelm, and Wismuller, A. 2005. “Tumor feature visualization with unsupervised learning”. MEDICAL IMAGE ANALYSIS 9 (4): 344-351.
Nattkemper, T. W., and Wismuller, A. (2005). Tumor feature visualization with unsupervised learning. MEDICAL IMAGE ANALYSIS 9, 344-351.
Nattkemper, T.W., & Wismuller, A., 2005. Tumor feature visualization with unsupervised learning. MEDICAL IMAGE ANALYSIS, 9(4), p 344-351.
T.W. Nattkemper and A. Wismuller, “Tumor feature visualization with unsupervised learning”, MEDICAL IMAGE ANALYSIS, vol. 9, 2005, pp. 344-351.
Nattkemper, T.W., Wismuller, A.: Tumor feature visualization with unsupervised learning. MEDICAL IMAGE ANALYSIS. 9, 344-351 (2005).
Nattkemper, Tim Wilhelm, and Wismuller, A. “Tumor feature visualization with unsupervised learning”. MEDICAL IMAGE ANALYSIS 9.4 (2005): 344-351.

9 Zitationen in Europe PMC

Daten bereitgestellt von Europe PubMed Central.

Computer-aided interpretation approach for optical tomographic images.
Klose CD, Klose AD, Netz UJ, Scheel AK, Beuthan J, Hielscher AH., J Biomed Opt 15(6), 2010
PMID: 21198194
Survey of the visual exploration and analysis of perfusion data.
Preim B, Oeltze S, Mlejnek M, Gröeller E, Hennemuth A, Behrens S., IEEE Trans Vis Comput Graph 15(2), 2009
PMID: 19147886
Estimating kinetic parameter maps from dynamic contrast-enhanced MRI using spatial prior knowledge.
Kelm BM, Menze BH, Nix O, Zechmann CM, Hamprecht FA., IEEE Trans Med Imaging 28(10), 2009
PMID: 19369150
Classification of dynamic contrast-enhanced magnetic resonance breast lesions by support vector machines.
Levman J, Leung T, Causer P, Plewes D, Martel AL., IEEE Trans Med Imaging 27(5), 2008
PMID: 18450541
Multiparameter classifications of optical tomographic images.
Klose CD, Klose AD, Netz U, Beuthan J, Hielscher AH., J Biomed Opt 13(5), 2008
PMID: 19021375
Multiscale analysis of MR-mammography data.
Lessmann B, Nattkemper TW, Kessar P, Pointon L, Khazen M, Leach MO, Degenhard A., Z Med Phys 17(3), 2007
PMID: 17879813
Segmentation and grading of brain tumors on apparent diffusion coefficient images using self-organizing maps.
Vijayakumar C, Damayanti G, Pant R, Sreedhar CM., Comput Med Imaging Graph 31(7), 2007
PMID: 17572068
1H NMR metabonomics of plasma lipoprotein subclasses: elucidation of metabolic clustering by self-organising maps.
Suna T, Salminen A, Soininen P, Laatikainen R, Ingman P, Mäkelä S, Savolainen MJ, Hannuksela ML, Jauhiainen M, Taskinen MR, Kaski K, Ala-Korpela M., NMR Biomed 20(7), 2007
PMID: 17212341
Interactive visual analysis of perfusion data.
Oeltze S, Doleisch H, Hauser H, Muigg P, Preim B., IEEE Trans Vis Comput Graph 13(6), 2007
PMID: 17968089

23 References

Daten bereitgestellt von Europe PubMed Central.

U.M.B.S.S. Comparison between radiological and artificial neural network diagnosis in clinical screening
Degenhard, Phys. Meas.: Special Issue: Simulation and modelling applied to medicine 23(), 2002
Morphofunctional visualization of dynamic MR-mammography
Englmeier, 2004
Current and future uses of positron emission tomography in breast cancer imaging.
Eubank WB, Mankoff DA., Semin Nucl Med 34(3), 2004
PMID: 15202103
MR imaging of the breast with rotating delivery of excitation off resonance: clinical experience with pathologic correlation.
Harms SE, Flamig DP, Hesley KL, Meiches MD, Jensen RA, Evans WP, Savino DA, Wells RV., Radiology 187(2), 1993
PMID: 8475297
Dynamic sequential 3D gadolinium-enhanced MRI of the whole breast.
Heiberg EV, Perman WH, Herrmann VM, Janney CG., Magn Reson Imaging 14(4), 1996
PMID: 8782170
Contrast-enhanced MRI of the breast: accuracy, value, controversies, solutions.
Heywang-Kobrunner SH, Viehweg P, Heinig A, Kuchler C., Eur J Radiol 24(2), 1997
PMID: 9097051
Clinical testing of high-spatial-resolution parametric contrast-enhanced MR imaging of the breast.
Kelcz F, Furman-Haran E, Grobgeld D, Degani H., AJR Am J Roentgenol 179(6), 2002
PMID: 12438042

Exploration of time-varying data for medical diagnosis
Kohle, 2002

Kohonen, 1989
Self-organizing maps
Kohonen, 2000
Improved diagnostic accuracy in dynamic contrast enhanced MRI of the breast by combined quantitative and qualitative analysis.
Liu PF, Debatin JF, Caduff RF, Kacl G, Garzoli E, Krestin GP., Br J Radiol 71(845), 1998
PMID: 9691895


Classification of signal-time curves from dynamic MR mammography by neural networks.
Lucht RE, Knopp MV, Brix G., Magn Reson Imaging 19(1), 2001
PMID: 11295347
Self-organizing map for cluster analysis of a breast cancer database.
Markey MK, Lo JY, Tourassi GD, Floyd CE Jr., Artif Intell Med 27(2), 2003
PMID: 12636975
Diagnostic performance characteristics of architectural features revealed by high spatial-resolution MR imaging of the breast.
Nunes LW, Schnall MD, Siegelman ES, Langlotz CP, Orel SG, Sullivan D, Muenz LA, Reynolds CA, Torosian MH., AJR Am J Roentgenol 169(2), 1997
PMID: 9242744

Breast fibroadenoma: mapping of pathophysiologic features with three-time-point, contrast-enhanced MR imaging--pilot study.
Weinstein D, Strano S, Cohen P, Fields S, Gomori JM, Degani H., Radiology 210(1), 1999
PMID: 9885614
Cluster analysis of biomedical image time-series
Wismüller, Int. J. Comput. Vision 46(2), 2002

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

PMID: 15907392
PubMed | Europe PMC

Suchen in

Google Scholar