TUM
Klinikum rechts der Isar Technische Universität München
Neuro-Kopf-Zentrum
Abteilung für Neuroradiologie


Forschungsgruppen und Projekte

 

Data Mining





As an emerging research area data mining aims at automatically extracting knowledge from large amounts of data. We address challenges from neuroscience with data mining approaches. Major challenges we are working on are for example to investigate the activity of the brain during rest and detecting psychiatric and neurodegenerative diseases from functional magnetic resonance (fMRI) and diffusion tensor (DTI) images. We focus especially on the application and development of approaches to clustering and classification but also work on graph mining and outlier detection. By grouping similar data objects, clustering methods provide an overview on the data. Clustering fibers from DTI images for example contributes to a better understanding of the complex structure of the brain. Provided that class labels are available for the data (e.g. healthy, disease A, disease B) classification methods can be applied to learn a predictive model. We apply classification methods to discover disease associated changes in brain structure and function.

Contact: Dr. Claudia Plant
eMail: plant -- at -- lrz.tum.de

Members

Dr. Claudia Plant
M.Sc. Junming Shao
Dipl.-Inf. Andrew Zherdin
Dr. Afra Wohlschläger
Prof. Dr. Claus Zimmer

Cooperation Partners


  • Klinikum Rechts der Isar:
    Dr. Harald Gündel, PD Dr. Markus Ploner, Dr. Alexander von Kalckreuth, Dr. Michael Valet, Dr. Valentin Riedl, Dipl.-Psych. Enrico Schulz, Dr. Till Sprenger, Dipl.-Psych. Laura Tiemann, Prof. Tölle (Neurology), Dr. Christian Sorg (Psychiatry)
  • University of Munich:
    Prof. Christian Böhm, Dipl.-Bioinf. Annahita Oswald, Dipl.-Bioinf. Bianca Wackersreuther
  • Helmholtz-Zentrum München
    Prof. Fabian Theis, Dr. Klaus Hahn
  • University of Rostock:
    Prof. Stefan Teipel
  • UMIT, Hall in Tirol, Austria:
    Prof. Christian Baumgartner
  • Trinity College Dublin, Ireland:
    Dr. Michael Ewers
  • Salford University, UK:
    Prof. Miklas Scholz
  • Carnegie Mellon University, Pittsburgh, USA:
    Prof. Christos Faloutsos
  • Florida State University, Tallahassee, USA:
    Prof. Anke Meyer-Baese


 

Selected Publications

Edited Books

Plant, C., Böhm C. (2010). Database Technology for Life Sciences and Medicine. World Scientific Books. Böhm C., Eder, J., Plant, C. (2011). Database Systems for Bio-medical Applications. Special Issue of Transactions on Large-Scale Data- and Knowledge-Centered Systems (TLDKS) Springer.

Data Mining

Plant, C. (2012). Dependency Clustering Across Measurement Scales. In: ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining (KDD), acceptance rate 17%.

Feng, J., He, X., Konte, B., Böhm, C. Plant, C. (2012). Summarization-based Mining Bipartite Graphs. In: ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining (KDD), acceptance rate 17%.

Plant, C., Thai, S. M., Shao, J., Theis, F. J., Meyer-Baese, A., Böhm, C. (2012). Measuring Non-Gaussianity by Phi-Transformed and Fuzzy Histograms. In: Advances in Artificial Neural Systems.

Shao, J., Plant, C., Yang, Q., Böhm, C. (2011). Detection of Arbitrarily Oriented Synchronized Clusters in High-dimensional Data. In: IEEE Int. Conf. on Data Mining (ICDM), acceptance rate 12%.

He, X., Feng, J., Plant, C. (2011). Automatically Spotting Information-rich Nodes in Graphs. In: IEEE ICDM Int. Workshop on Data Mining in Networks (DAMNet), acceptance rate 33%.

Plant, C., Böhm, C. (2011). INCONCO: Interpretable Clustering of Numerical and Categorical Objects. In: ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining (KDD), pp. 1127-1135, acceptance rate 17.5%.

Plant, C. (2011). SONAR: Signal De-mixing for Robust Correlation Clustering. In: SIAM Int. Conf. on Data Mining (SDM), pp. 319-330, acceptance rate 25%.

Müller, N., Haegler, K., Shao, J., Plant, C., Böhm, C. (2011). Weighted Graph Compression for Parameter-free Clustering with PaCCo. In: SIAM Int. Conf. on Data Mining (SDM), pp. 932-942, acceptance rate 25%.

Plant, C., Böhm, C. (2010). Parallel EM-Clustering: Fast Convergence by Asynchronous Model Updates. In: IEEE ICDM Int. Workshop on Knowledge Discovery using Cloud and Distributed Computing Platforms (KDCloud), pp. 178-185.

Plant, C., Theis, F., Meyer-Baese, A., Böhm, C. (2010). Information-theoretic Model Selection for Independent Components. In: Int. Conf. on Latent Variable Analysis and Signal Separation (LVAICA), pp. 254-262.

Shao, J., Böhm, C., Yang, Q., Plant, C. (2010). Synchronization-based Outlier Detection. In: European Conf. on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pp. 245-260, acceptance rate 18%.

Böhm, C., Fiedler, F., Oswald, A. Plant, C., Wackersreuther, B. (2010). ITCH: Information-theoretic Cluster Hierarchies. In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pp. 151-167, acceptance rate 18%.

Böhm, C., Plant, C., Shao, J., Yang, Q., (2010). Clustering by Synchronization. In: ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining (KDD), pp. 583-592, acceptance rate 17%.

Böhm, C., Oswald, A., Plant, C., Plavinski, M., Wackersreuther, B. (2010). SkyDist: Data Mining on Skyline Objects. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp.461-470, acceptance rate 23%.

Böhm, C., Goebl, S., Oswald, A. Plant, C., Plavinski, M., Wackersreuther, B. (2010). Integrative Parameter-Free Clustering of Data with Mixed Type Attributes. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 38-47, acceptance rate 23%.

Plant, C., Wohlschläger A., Zherdin, A. (2009). Interaction-based Clustering of Multivariate Time Series. In: IEEE Int. Conf. on Data Mining (ICDM), pp.914-919, acceptance rate 18%.

Böhm, C., Noll, R., Plant, C., Wackersreuther, B. (2009). Density-based Clustering using Graphics Processing Units. In: ACM Conference on Information and Knowledge Management (CIKM), pp. 691-670, acceptance rate 15%.

Böhm, C., Fiedler, F., Oswald, A., Plant, C., Wackersreuther, B. (2009). Probabilistic Skyline Queries. In: ACM Conference on Information and Knowledge Management (CIKM), pp. 651-660, acceptance rate 15%.

Plant, C., Böhm, C. (2009). Novel Trends in Clustering. Book chapter in Furtado. P. (Ed.): Evolving Application Domains of Data Warehousing and Mining: Trends and Solutions. (IGI Global Press), pp. 158-211.

Böhm, C., Noll, R., Plant, C., Wackersreuther, B., Zherdin, A. (2009). Data Mining Using Graphics Processing Units. In Trans. on Large Scale Data and Knowl. Cent. Syst., LNCS 5740, pp. 63-90.

Böhm, C., Plant, C. (2009) High Dimensional Indexing. Chapter in Liu, L., Özsu, T. (Ed): Encyclopedia of Database Systems (Springer), pp. 1309-1314.

Böhm, C., Läer, L., Plant, C., Zherdin, A. (2009). Model-based Classification of Data with Time Series-valued Attributes. In: Datenbanksysteme für Business, Technologie und Web (BTW) (German Database Conference), pp. 287-296.

Böhm, C., Noll, R., Plant, C., Zherdin, A. (2009). Index-supported Similarity Join on Graphics Processors. In: Datenbanksysteme für Business, Technologie und Web (BTW) (German Database Conference), pp. 57-66.

Böhm, C., Haegeler, K., Müller, N.S., Plant, C. (2009). CoCo: Coding Cost for Parameter-free Outlier Detection. In: ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD), pp. 149-158, acceptance rate 18%.

Böhm, C., Faloutsos, C., Plant, C. (2008). Outlier-robust Clustering using Independent Components. In: ACM SIGMOD Int. Conf. on Management of Data (SIGMOD), pp. 185-198, acceptance rate 18%.

Plant, C. (2008). Knowledge Extraction and Data Mining Algorithms for Complex Biomedical Data. Book chapter in: Wagner, D. (Ed.) Ausgezeichnete Informatikdissertationen 2007 (Köllen), pp.229-238.

Böhm C., Plant, C. (2008). HISSCLU: A Hierarchical Density-based Algorithm for Semi-supervised Clustering. In: Int. Conf. on Extending Database Technology (EDBT), pp. 440-451, acceptance rate 18%.

Böhm C., Faloutsos, C., Pan, J.-Y., Plant, C. (2007). RIC: Parameter-free Noise-robust Clustering. In: ACM Transactions on Knowledge Discovery from Data (TKDD), 1(3), article 10, pp.10:1-10:28.

Böhm C., Ooi, B. C., Plant, C. , Yan, Y. (2007). Efficiently Processing Continuous k-NN Queries on Data Streams. In: Int. Conf. on Data Engeneering (ICDE), pp. 156-165, acceptance rate 19%.

Böhm C., Faloutsos, C., Pan, J.-Y., Plant, C. (2006). Robust Information-theoretic Clustering. In: ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD), pp. 65-75, acceptance rate 11%.

Damjanovic, D., Plant, C., Balko, S., Schek, H.-J. (2005). User-Adaptable Browsing and Relevance Feedback in Image Databases. In: DELOS Workshop on Future Digital Library Management Systems (System Architecture & Information Access).

Baumgartner, C., Kailing, K., Kriegel, H.-P., Kröger, P., Plant, C. (2004). Subspace Selection for Clustering High-Dimensional Data. In: IEEE Int. Conf. on Data Mining (ICDM), pp. 11-18, acceptance rate 9%.

Data Mining in Neuroimaging

Shao, J. , Myers, N., Yang, Q., Feng, J., Böhm, C., Plant, C., Förstl, H., Kurz, A., Zimmer, C., Meng, C., Riedl, V., Wohlschläger, A. (2012): Prediction of Alzheimer's; Disease using Individual Structural Connectivity Networks. In: Neurobiology of Aging, impact factor 6.4.

Schulz, E., Zherdin, A., Tiemann, L., Plant, C., Ploner, M. (2012): Decoding an Individuals Sensitivity to Pain from Multivariate Analysis of EEG Data. In: Cerabral Cortex 22(5), pp. 1118-1123 impact factor 6.8.

Plant, C., Sorg, C., Riedl, V., Akhrif, A., Zherdin, A., Wohlschläger A. (2011). Homogeneity-based Feature Extraction for Classification of Early-stage Alzheimer's Disease from Functional Magnetic Resonance Images. In: ACM SIGKDD Workshop on Data Mining for Medicine and Healthcare (DMMH), pp. 33-41.

Böhm, C., Feng, J., He, X., Mai, S. T., Plant, C., Shao, J. (2011). A Novel Similarity Measure for Fiber Clustering using Longest Common Subsequence. In: ACM SIGKDD Workshop on Data Mining for Medicine and Healthcare (DMMH), pp. 1-9.

Shao, J., Hahn, K., Yang, Q., Böhm, C., Wohlschläger, A., Myers, N., Plant, C. (2010). Combining Time Series Similarity with Density-based Clustering to Identify Fiber Bundles in the Human Brain. In IEEE ICDM Int. Workshop on Biological Data Mining and its Applications in Healthcare (BioDM), pp. 745-754, acceptance rate 36%. Best Paper Award. Mehr Informationen finden Sie hier.

Shao, J., Hahn, K., Yang, Q., Böhm, C., Wohlschläger, A., Myers, N., Plant, C. (2010). Hierarchical Density-Based Clustering of White Matter Tracts in the Human Brain. In: Int. Journal of Knowledge Discovery in BioInformatics 1(4), pp. 1-25. IGI Global Fourth Annual Excellence in Research Award.

Plant, C., Teipel, S., Oswald, A., Böhm, C. Mourao-Miranda, J., Bokde, A. W., Hampel, H., Ewers, M. (2010). Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimer's disease. Neuroimage 50(1), pp. 162-174, impact factor 5.7.

Böhm, C., Oswald, A., Plant, C., Wackersreuther, B. (2008). A Data Mining Framework for Classification of High-resolution Magnetic Resonance Images. In: ACM SIGKDD Int. Workshop on Mining Medical Data.

Data Mining in Medicine, Life Sciences and Environmental Science

Steinbrücker, F., Meyer-Baese, A., Schlossbauer, T., Plant, C. (2012). Selection of Spatiotemporal Features on Breast MRI to Differentiate Between Malignant and Benign Small Lesions Using Computer-Aided Diagnosis. In: Advances in Artificial Neural Systems.

Yang, Q., Shao, J., Scholz, M., Böhm, C., Plant, C. (2012). Multi-label Classification Models for Sustainable Flood Retention Basins. In: Enviornmental Modelling and Software 32, pp. 27-36, impact factor 2.9.

Plant, C., Ngo, D., Retter, F., Zavala, O., Lobbes, M., Lockwood, M., Meyer-Baese, A. (2012). Computer-aided Diagnosis of Small Lesions and Non-masses in Breast MRI. In: SPIE 8367.

Goebl, S., Plant, C., Lobbes, M., Meyer-Baese, A. (2012). Quantitative Analysis of Breast DCE-MR Images based on ICA and an Empirical Model. In: SPIE 8401.

Retter, F., Plant, C., Burgeth, B., Schlossbauer, T., Meyer-Baese, A. (2011). Improved Computer-aided Diagnosis for Breast Lesions Detection in DCE-MRI Based on Image Registration and Integration of Morphologic and Dynamic Characteristics. In: SPIE 8059.

Görke, R., Meyer-Baese, A., Plant, C., He, H., Emmett, M.R., Nilsson, C., Colman, H., Conrad, C.A. (2011). Graph Clustering Techniques Applied to the Glycomic Response in Glioblastoma Cells to Treatments with STAT3 Phosphorylation Inhibition and Fetal Bovine Serum. In: SPIE 8059.

Meyer-Baese, A., Plant, C., Cappendijk, S., Theis, F. (2010). Robust Stability Analysis of Multi-Time Scale Genetic Regulatory Networks under Parametric Uncertainties. In: Int. Conf. on Bioinformatics and Computational Biology (BIOCOMP), pp. 854-863, acceptance rate 28%.

Yang, Q., Shao, J., Scholz, M., Plant, C. (2010). Feature selection methods for characterizing and classifying adaptive Sustainable Flood Retention Basins. Water Research 45(3), pp. 993-1004, impact factor 4.4.

Theis, F., Müller, N., Plant, C., Böhm, C. (2010). Robust second-order source separation identifies experimental responses in biomedical imaging. Proc. of Int. Conf. on Latent Variable Analysis and Signal Separation (LVAICA), pp. 466-473

Plant, C. , Böhm C., Tilg, B., Baumgartner, C. (2006). Enhancing Instance-based Classification with Local Density: A New Algorithm for Classifying Unbalanced Biomedical Data, Bioinformatics, 22 (8), pp. 981-988, impact factor 5.7.

Plant C., Osl, M., Tilg, B., Baumgartner, C. (2006). Feature Selection on High Throughput SELDI-TOF Mass-Spectronometry Data for Identifying Biomarker Candidates in Ovarian and Prostate Cancer. In: IEEE ICDM Workshop on Mining Biomedical Data, pp. 174-179, acceptance rate 25%.

Plant C., Böhm C. , Tilg, B., Baumgartner, C. (2006). Enhancing Instance-based Classification on High-throughput MS/MS Data: Metabolic Syndrome as an Example. In: Gemeinsame Jahrestagung der Deutschen, Österreichischen und Schweizerischen Gesellschaft für Biomedizinische Technik (BMT)

Baumgartner, C., Baumgartner, D., Eberle, M., Plant, C., Matyas, G., Steinmann, B. (2005) Genotype-phenotype Correlation in Patients with fibrillin-1 Gene Mutations. Proc. of 3rd Int. Conf. on Biomedical Engineering, (BioMED), pp. 561-566.

Poster Gallery

Shao, J., Wohlschläger, A., Hahn, C., Böhm, C., Plant, C. (2009). Density-based Clustering of White Matter Tracts in the Human Brain with Dynamical Time Warping. Poster presented at European Workshop on Mining Massive Data Sets (EMMDS).

Zherdin, A., Sorg, C., Läer, L., von Kalckreuth, A., Gündel, H., Valet, M., Sprenger, T., Tölle, T.R., Plant, C., Wohlschläger, A.M. (2009). Model-Based Classification: Differential Changes in Functional Connectivity between Patients with Somatoform Pain Disorder and Healthy Controls. Poster presented at Human Brain Mapping.

Plant, C., Sorg, C., Riedl, V., Wohlschläger, A. (2009). Reduced Regional Integration in the Default Network of Patients with Very Mild Alzheimer's Disease Detected by Bootstrapping Rest-fMRI. Poster presented at Human Brain Mapping.