Olivier Pauly

Olivier Pauly Dipl.-Ing. Univ. SUPELEC Dipl.-Ing. Univ. TUM E-Mail: Phone: +49 89 289 19437 Address: Technische Universität München Fakultät für Informatik, I-16 Boltzmannstr. 3 85748 Garching b. München Germany Room: MI 03.13.043 Research interests Active research projects News Publications Workshops Teaching Student Supervision Background Research interests Machine learning in medical applications Pattern recognition and analysis Medical image understanding Tissue classication Computer aided diagnosis Similarity, metric, distance learning Active research projects Reconstruction and Registration of Histology and Phase Contrast Images for Clinical Validation of Imaging Modalities Before its introduction into the hospital, a new imaging modality has to be validated. In other words, appearing structures need to be correlated to the imaged tissues. Such a cross validation is only meaningful when performed against the gold standard which is histology. Currently, cross validation is performed by qualitative comparison of 3D datasets to 2D histology slices. Since the acquisition of a consistent 3D histology volume is a challenging task, its comparison to the corresponding dataset always remained qualitative. The classic histology procedure can be divided in four steps: pre processing, cutting, post processing and imaging of the tissues. In the first step, the sample is chemically processed to preserve the tissues and is then embedded in a paraffin block. By using a microtome, it is cut in very thin slices, and put on a glass slide. During post processing the sample is stained to enhance the structures of interest. The imaging is performed with a camera mounted in a microscope, or with a dedicated scanner. Several difficulties inherent to this process can have a dramatic influence on the quality of the reconstructed histology volume. For instance, since the cutting process is done manually, problems like flipping, bending or ripping of the slides may happen. If the knife starts to wear off, some banding will appear over the slices. Moreover, a few slices could be missing. Finally since the staining color is time dependent, variation in the color of the slices can occur. In this project, we propose to improve the histology procedure and to develop methods towards a consistent reconstruction of 3D histology volumes. Non Invasive Histology of Atherosclerotic Plaque Stroke is the third leading cause of death in Germany. It is a neurology injury, whereby the oxygen supply to parts of the brain gets cut off. About 80% of these strokes are due to ischemia, i.e. an occlusion of a blood vessel leading to an interrupted blood flow. Stenosis inside the carotid artery imaged using four different MR weightings Special setting in this project is the arteria carotis. Plaque is most likely to develop at the branching of the arteria carotis communis into the arteria carotis interna (leading to the brain) and the arteria carotis externa. This can lead to an abnormal narrowing, called a stenosis. According to the American Heart Association these plaques can be divided into different types, based on their consistency and structure. Until now the decision about a surgery was only based on the degree of the stenosis and not on the type of plaque causing it. This is a faulty approach since there is a plaque type (Type IV) which constitutes a relevant clinical danger, although it does not necessary come along with a stenosis. Unlike most other image modalities MR images do not only give information about the degree of the stenosis, but also about the consistency of the plaque. Using different weighted MR images it is possible to correctly classify plaque into the types defined by the AHA. The main goal of this project is to create a classification tool based on T1, T2, Proton Density and 'Time of flight' weighted images. To achieve this goal the arteria carotis and the plaque have to be segmented from the images. Furthermore various features of the plaque have to be extracted in order to get information needed for the classification. Assessment of Fluid Tissue Interaction Using Multi-Modal Image Fusion for Characterization and Progression of Coronary Atherosclerosis Coronary artery diseases such as atherosclerosis are the leading cause of death in the industrialized world. In this project, we develop computational tools for segmentation and registration problems on intravascular images including IVUS (Intravascular Ultrasound) and OCT (Optical Coherence Tomography). One sample component of this project is Automatic Stent Implant Follow-up from Intravascular OCT Pullbacks. The stents are automatically detected and their distribution is analyzed for monitoring of the stents: their malpositioning and/or tissue growth over stent struts. Organ Recognition Automatic localization of multiple anatomical structures in medical images provides important semantic information with potential benefits to diverse clinical applications. In this project, we investigate hierachical regression methods based on Random Forests and Random Ferns. Such hierarchical approaches permit to subdivide efficiently the feature space and to create a partition over it. In each cell of the resulting partition, data can be easily modeled using simple mathematical models such as constant or linear. The combination of these models over the whole partition results then in a complex non-linear model. Similarity/Metric/Distance Learning for Medical Applications Many medical applications such as registration or tracking can be seen as the optimization of an objective function which involves a data term or similarity measure. Classical similarity measures rely for instance on image intensities, gradients or intensity statistics. In the case of noise or background clutter which is very frequent in the case of medical imaging, they might lead to registration/tracking errors. In this project, we investigate different approches and applications of learning a similarity measure directly from the data, leading to a more robust data term which is adapted to the image characteristics.

News 29.12.2011 : I submitted my Ph.D. thesis 24.11.2011 : The first draft of my Ph.D. thesis is under construction 01.11.2011 : I am now finishing my Ph.D. within Joint Helmholtz/TUM research group 19.09.2011 : Oral presentation at MICCAI 2011 in Toronto for our paper on Multiple Organ Localization. Our work was among the runners up for a young scientist award. Here you can find the slides of my presentation: paulyMICCAI2011presentation.pdf 01.08.2011 : I am at Microsoft Research Cambridge as a Research intern - 3 months Publications 2012 Y. Chen, T. Hrabe, S. Pfeffer, O. Pauly, D. Mateus, N. Navab, F. Foerster Detection and Identification of Macromolecular Complexes in Cryo-Electron Tomograms Using Support Vector Machines IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2012), Barcelona, Spain, May 2 - 5, 2012 (bib) 2011 O. Pauly, D. Mateus, N. Navab STARS: A New Ensemble Partitioning Approach ICCV Workshop on Information Theory in Computer Vision and Pattern Recognition (ITINCVPR 2011), Madrid, Spain, November 2011 (bib) A. Safi, M. Baust, O. Pauly, V. Castaneda, T. Lasser, D. Mateus, N. Navab, R. Hein, M. Ziai Computer-Aided Diagnosis of Pigmented Skin Dermoscopic Images MICCAI Workshop on Medical Content-based Retrieval for Clinical Decision Support, Toronto, Canada, September 2011 (bib) O. Pauly, D. Mateus, N. Navab Building Implicit Dictionaries based on Extreme Random Clustering for Modality Recognition MICCAI Workshop on Medical Content-based Retrieval for Clinical Decision Support, Toronto, Canada, September 2011 (bib) O. Pauly, B. Glocker, A. Criminisi, D. Mateus, A. Martinez-Möller, S. Nekolla, N. Navab Fast Multiple Organs Detection and Localization in Whole-Body MR Dixon Sequences To appear in Proc. Medical Image Computing and Computer-Assisted Intervention (MICCAI 2011), Toronto, Canada, September 2011 (bib) 2010 O. Pauly, D. Mateus, N. Navab ImageCLEF 2010 Working Notes on the Modality Classification Subtask. Cross Language Image Retrieval Workshop (ImageCLEF? 2010), Medical Retrieval, Padua, Italy, September 2010 (bib) O. Pauly, H. Heibel, N. Navab A Machine Learning Approach for Deformable Guide-Wire Tracking in Fluoroscopic Sequences. Medical Image Computing and Computer-Assisted Intervention (MICCAI 2010), Beijing, China, September 2010 (bib) A. Taki, O. Pauly, S.K. Setarehdan, G. Unal, N. Navab IVUS-based histology of atherosclerotic plaques: improving longitudinal resolution SPIE Medical Imaging, San Diego, California, USA, 13-18 February 2010 (bib) 2009 O. Pauly, N. Padoy, H. Poppert, L. Esposito, H-H. Eckstein, N. Navab Towards Application-specific Multi-modal Similarity Measures: a Regression Approach. MICCAI Workshop on Probabilistic Models in Medical Image Analysis (PMMIA), London, UK, September 2009. (bib) A. Taki, A. Roodaki, O. Pauly, S.K. Setarehdan, G. Unal, N. Navab A new method for characterization of coronary plaque composition via IVUS images IEEE International Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2009), Boston, Massachusetts, USA, June 28 - July 1, 2009 (bib) O. Pauly, N. Padoy, H. Poppert, L. Esposito, N. Navab Wavelet Energy Map: A Robust Support for Multi-modal Registration of Medical Images IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Miami, Florida (USA), June 2009. (bib) 2008 O. Pauly, G. Unal, G. Slabaugh, S. Carlier, T. Fang Semi-Automatic Matching of OCT and IVUS Images For Image Fusion SPIE Medical Imaging, San Diego, California (USA), February 2008. (bib) Workshops 2nd MICCAI Workshop on Computer Vision for Intravascular and Intracardiac Imaging Organizers: G. Unal, I. A. Kakadiaris, N. Navab, M. Sonka Coordination Assistant: O. Pauly Program Committee: Jolanda Wentzel, Andreas Wahle, Guy Cloutier, Petia Radeva, J.H.C. Reiber, Jouke Dijkstra, Aytul Ercil Invited Speakers: Stéphane Carlier, Johannes Rieber in conjunction with MICCAI 2008, New York , USA, September 6 - 10, 2008 Teaching Summer Term 2011 Hauptseminar/Master Seminar:Machine Learning Methods for Computer Vision Applications Computer Aided Medical Procedures II Winter Term 2010-2011 Hauptseminar/Master Seminar:Machine Learning Methods for Computer Vision Applications Summer Term 2010 Hauptseminar/Master Seminar:Machine Learning Methods for Computer Vision Applications Computer Aided Medical Procedures II Summer Term 2009 Computer Aided Medical Procedures II Student Supervision MRI-Based Tissue Classification for Non-Invasive Histology of Atherosclerotic Plaques - Vladimir Golkov - Bachelor Thesis Filter Bank Learning for Thrombus Segmentation - Vladimir Golkov - IDP Identification of Macromolecular Complexes in Cryo-electron Tomograms using Support Vector Machine and Combined Correlation Functions - Yuxiang Chen - Diploma Thesis (Co-supervision with Dr. F. Förster) Random Forests for Cell Detection - Olivia Klose - IDP Background Since 2008 Ph.D. student at the CAMPAR team Technische Universität München, with Prof. Dr. Nassir NAVAB 2004-2007 Engineering degree from the Mechanics Faculty, Technical University Munich, Germany. Double Degree Program with Supelec, Specialization in Medical Engineering 2002-2004 Engineering degree from the Supelec, Ecole Superieure d'Electricite, France. 3rd year: Double Degree Program with Technical University of Munich, Germany 2000-2002 Classes préparatoires scientifiques: two-year post-'A'-level preparatory courses for entrance exams to French engineering schools 2000 German-French Scientific Baccalaureat (Equivalent to A-levels). Passed with the highest distinction (mention Très Bien).