Ruprecht-Karls-Universität Heidelberg
HCI->MIP->People->B. Michael Kelm

B. Michael Kelm

B. Michael Kelm

Dr. rer. nat. Dipl.-Ing. M.Sc.
michael.kelm AT

This page is outdated. Please visit my new page at


CSItools - A Matlab toolbox for processing magnetic resonance spectroscopic images (MRSI). New Release 1.1!

GGMRF - Nonlinear least squares fitting with spatial smoothness constraint in the form of a Generalized Gaussian Markov random field.



Detection, Grading and Classification of Coronary Stenoses in Computed Tomography Angiography
Kelm, B.M. ; Mittal, S.; Zheng, Y.; Tsymbal, A.; Dominik ; Vega-Higuera, F.; Zhou, S.K.; Meer, P. & Comaniciu, D.
In: Proc. MICCAI 2011, 2011, pp. 25-32

On oblique random forests
Menze, B.H.; Kelm, B.M. ; Splitthoff, D.N.; Koethe, U. & Hamprecht, F.A.
In: Proc. ECML/PKDD 2011, 2011, pp. 453-469

Using Spatial Prior Knowledge in the Spectral Fitting of Magnetic Resonance Spectroscopic Images
Kelm, B.M. ; Kaster, F.O.; Henning, ; Weber, M.; Bachert, P.; Boesiger, P.; Hamprecht, F.A. & Menze, B.H.
NMR Biomed, 2011
(doi: 10.1002/nbm.1704) (pdf)


Detection of 3D Spinal Geometry Using Iterated Marginal Space Learning
Kelm, B.M. ; Zhou, S.K.; Suehling, M.; Zheng, Y.; Wels, M. & Comaniciu, D.
In: MICCAI 2010 Workshop MCV, Springer-Verlag Berlin Heidelberg, 2010, LNCS (6533): 96--105

Visual representations for supporting an ontology-based semantic navigation of medical volume data
Peters, S.; Kelm, M. ; Huber, M.; Seifert, S.; Elsner, A. & Domik, G.
In: Proc. Computer Graphics and Imaging (CGIM), 2010

Semantic Annotation of Medical Images
Seifert, S.; Kelm, M. ; Moeller, M.; Mukherjee, S.; Cavallaro, A.; Huber, M. & Comaniciu, D.
In: SPIE 2010 Medical Imaging, 2010
(doi: 10.1117/12.844207)


Processing Spectral Images
Görlitz, L.; Menze, B.H.; Kelm, B.M. & Hamprecht, F.A.
Surface and Interface Analysis, 2009, (41)
(doi: 10.1002/sia.3066)

Estimating Kinetic Parameter Maps from Dynamic Contrast-Enhanced MRI using Spatial Prior Knowledge
Kelm, B.M. ; Menze, B.H.; Nix, O.; Zechmann, C. & Hamprecht, F.A.
IEEE Trans Med Imaging, 2009, (28): 1534--1547
(doi: 10.1109/TMI.2009.2019957) (pdf)

Classification of Spectroscopic Images in the DIROlab Environment
Kaster, F.O.; Kelm, B.M. ; Zechmann, C.M.; Weber, M.A.; Hamprecht, F.A. & Nix, O.
In: Proc. World Congress on Medical Physics and Biomedical Engineering, Springer, 2009, pp. 252-255

A comparison of random forest and its Gini importance with standard methods for the feature selection and classification of spectral data
Menze, B.H.; Kelm, B.M. ; Masuch, R.; U. ; Bachert, P.; Petrich, W. & Hamprecht, F.A.
BMC Bioinformatics, 2009, (10): 213
(doi: doi:10.1186/1471-2105-10-213) (pdf)


Mimicking the human expert: pattern recognition for an automated assessment of data quality in MRSI
Menze, B.H.; Kelm, B.M. ; Weber, M.; Bachert, P. & Hamprecht, F.A.
Magnetic Resonance in Medicine, 2008, (59): 1457-1466
(doi: 10.1002/mrm.21519) (pdf)


Semi-Supervised Tumor Detection in MRSI With Discriminative Random Fields
Görlitz, L.; Menze, B.H.; Weber, M.; Kelm, B.M. & Hamprecht, F.A.
In: Pattern Recognition, Springer, 2007, pp. 224-233
(doi: 10.1007/978-3-540-74936-3_23)

Automated Estimation of Tumor Probability in Prostate MRSI: Pattern Recognition vs. Quantification.
Kelm, B.M. ; Menze, B.H.; Zechmann, C.M.; Baudendistel, K.T. & Hamprecht, F.A.
Magn Reson Med, 2007, (57): 150 - 159
(doi: 10.1002/mrm.21112) (pdf)

Can man still beat the machine? Automated vs. manual pattern recognition of 3D MRSI data of prostate cancer patients.
Zechmann, C.M.; Kelm, B.M. ; Zamecnik, P.; Ikinger, U.W.R.; Röll, S.; Delorme, S.; Hamprecht, F.A. & Bachert, P.
In: Proc. of the 16th ISMRM Scientific Meeting and Exhibition, Berlin/Germany, 2007

From Eigenspots to Fisherspots: Latent Spaces in the Nonlinear Detection of Spot Patterns in a Highly Varying Background
Menze, B.H.; Kelm, B.M. & Hamprecht, F.A.
In: Lenz, H. & Decker, R. (eds.), Advances in Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization, Springer, 2007, pp. 255 - 262


On Discriminative and Semi-Supervised Dimensionality Reduction.
Pal, C.; Kelm, M. ; Wang, X.; Druck, G. & McCallum, A.
In: Proc. of the NIPS Workshop - Novel Applications of Dimensionality Reduction, Vancouver/Canada, 2006

Combining Generative and Discriminative Methods for Pixel Classification with Multi-Conditional Learning.
Kelm, B.M. ; Pal, C. & McCallum, A.
In: Proc International Conference on Pattern Recognition, Hong Kong, 2006, pp. 828-832
(doi: 10.1109/ICPR.2006.384) (pdf) (poster)

Optimal Classification of Long Echo Time In Vivo Magnetic Resonance Spectra in the Detection of Recurrent Brain Tumors.
Menze, B.H.; Lichy, M.P.; Bachert, P.; Kelm, B.M. ; Schlemmer, H. & Hamprecht, F.A.
NMR Biomed, 2006, (19): 599 - 609
(doi: 10.1002/nbm.1041)

Bayesian Estimation of Smooth Parameter Maps for Dynamic Contrast-Enhanced MR Images with Block-ICM
Kelm, B.M. ; Müller, N.; Menze, B.H. & Hamprecht, F.A.
In: Proc Computer Vision and Pattern Recognition Workshop (MMBIA), New York/USA, 2006, pp. 96-103
(doi: 10.1109/CVPRW.2006.41) (pdf) (poster)

CLARET: a tool for fully automated evaluation of MRSI with pattern recognition methods.
Kelm, B.M. ; Menze, B.H.; Neff, T.; Zechmann, C.M. & Hamprecht, F.A.
In: Handels, H.e.a. (eds.), Bildverarbeitung für die Medizin 2006 - Algorithmen, Systeme, Anwendungen, Springer, Hamburg/Germany, 2006, Informatik Aktuell, pp. 51-55
(doi: 10.1007/3-540-32137-3_11) (pdf) (poster)

Machine-based rejection of low quality spectra and estimation of brain tumor probabilities from magnetic resonance spectroscopic images.
Menze, B.H.; Kelm, B.M. ; Heck, D.; Lichy, M.P. & Hamprecht, F.A.
In: Handels, H.e.a. (eds.), Bildverarbeitung für die Medizin, Hamburg/Germany, 2006, Informatik Aktuell, pp. 31-36
(doi: 10.1007/3-540-32137-3_7) (pdf)

Estimation of pharmacokinetic parameters using spatial prior knowledge.
Kelm, B.M. ; Menze, B.H.; Mueller, N. & Hamprecht, F.A.
In: Proc. of the 23rd Annual Scientific Meeting of the ESMRMB, Warsaw/Poland, 2006

Automated separation of low quality and artifact spectra by pattern recognition in the processing of MR spectral images.
Menze, B.H.; Kelm, B.M. & Hamprecht, F.A.
In: Proc. of the 14th ISMRM Scientific Meeting and Exhibition, Seattle/USA, 2006


Multi-Conditional Learning for Joint Probability Models with Latent Variables.
Pal, C.; Wang, X.; Kelm, M. & McCallum, A.
In: Proc. of the NIPS Workshop - Advances in Structured Learning for Text and Speech Processing, Vancouver/Canada, 2005
(weblink) (pdf)

Automatische Lokalisation von Tumoren in 1H-NMR-spektroskopischen in vivo Aufnahmen
Kelm, M. ; Menze, B. & Hamprecht, F.
In: GMA-Kongress: Automation als interdisziplinäre Herausforderung, Baden-Baden/Germany, 2005, VDI-Berichte (1883): 457-466

Optimal processing in the automatic detection and localization of brain tumors using MRSI.
Menze, B.H.; Kelm, B.M. ; Lichy, M.P.; Bachert, P.; Schlemmer, H. & Hamprecht, F.A.
In: Proc. of the 13th ISMRM Scientific Meeting and Exhibition, Miami/USA, 2005

Theses & book chapters

Evaluation of Vector-Valued Clinical Image Data Using Probabilistic Graphical Models: Quantification and Pattern Recognition
Kelm, B.M.   (PhD thesis)
University of Heidelberg, 2007
Advisor: Fred A. Hamprecht

Spectral Imaging and Applications
Carlsohn, M.F.; Menze, B.H.; Kelm, B.M. ; Hamprecht, F.A.; Kercek, A.; Leitner, R. & Polder, G.
In: Lukac, R. & Plataniotis, K.N. (eds.), Color Image Processing: Methods and Applications, CRC Press, Image Processing, pp. 393-419, 2006

Demosaicking of Color Images by Means of Conditional Random Fields
Kelm, B.M.   (Master`s thesis)
Oregon State University, October 2003
Advisor: Thomas G. Dietterich

zum Seitenanfang