|
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
- Machine learning in medical applications
- Pattern recognition and analysis
- Medical image understanding
- Tissue classication
- Computer aided diagnosis
- Similarity, metric, distance learning
|
Active research projects
|
|
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.
|
|
|
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.
|
|
|
Efficacious treatment and management of patient with the Coronary Artery Disease (CAD) has drawn a lot of attention especially because of the high prevalence and high mortality rate. Two major treatment options are Coronary Artery Bypass Grafting (CABG) and Percutaneous Coronary Intervention (PCI). CABG is more expensive and invasive, however, the overall prognosis is better than PCI, which is widely considered as a less expensive and minimally-invasive option. It is documented that a large percentage of patients (up to one third) undergoing PCI procedure require repeat procedure after several years. It is beneficial to both patients and payers to identify this high-risk patient group as early as possible based on a series of in-vitro and imaging tests and possibly choose an alternate treatment option. Moreover, the identification of this high-risk patient group within the early months of PCI intervention could also trigger better management of these patients through administering possibly invasive tests (e.g., optical coherence tomography-OCT) to characterize and quantify the disease process and the associated risk. Our project partner at German Heart Center has collected large amount of data from patient cohorts that includes results of commercially available in-vitro tests, imaging tests, and for subset of patients the plasma samples and the follow-up data with clinical outcomes. The goal of this project is to identify features such as blood biomarkers that are predictive of PCI prognosis, to devise an algorithm decision support system to aggregate the biomarker test (including imaging) results and optimize the correlation to the clinical outcome, characterize and validate the system built based on retrospective data.
|
|
|
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.
|
|
|
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.
|
|
|
News
|
- 30.08.2012 : Ph.D. Defense successfully achieved
- 27.07.2012 : Ph.D. Defense scheduled on Thursday 30th of August.
- 23.07.2012 : One journal paper accepted in Ultrasound Med Biol.
- 15.07.2012 : One paper accepted at MICCAI workshop Medical Computer Vision.
- 01.07.2012 : We have one paper accepted to MICCAI and one paper to ECCV.
- 01.03.2012 : We have open Master thesis topics (see description below). If you are interested, please send me an email or come by to my office.
- 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
Open positions
- Driver condition recognition using physiological and vehicle data (Master thesis topic with BMW)
- Automatic Midbrain Localization within 3D transcranial Ultrasound
- Tissue classification in Whole-Body MR
- Organelle tracking and analysis of cytoskeletal changes in vivo microscopic images
- Correction of movement artifacts for 3D reconstruction of in vivo microscopy data
- Open student projects in microscopic imaging
Publications
| 2013 |
|
O. Erat, O. Pauly, S. Weidert, P. Thaller, E. Euler, W. Mutschler, N. Navab, P. Fallavollita
How a Surgeon becomes Superman by visualization of intelligently fused multi-modalities
SPIE Medical Imaging, Orlando, Florida, USA, February 2013
(bib)
|
| 2012 |
|
O. Pauly, A. Katouzian, A. Eslami, P. Fallavollita, N. Navab
Supervised Classification for Customized Intraoperative Augmented Reality Visualization
The 11th IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR), Atlanta, USA, Nov. 5 - 8, 2012.
(bib)
|
|
B. Glocker, O. Pauly, E. Konukoglu, A. Criminisi
Joint Classification-Regression Forests for Spatially Structured Multi-Object Segmentation
12th European Conference on Computer Vision (ECCV), Firenze, Italy, October 7-13 2012.
(bib)
|
|
L. Peter, O. Pauly, S. Jansen, P. Smethurst, W. Ouwehand, N. Navab
Automatic event detection within thrombus formation based on binary integer programming
MICCAI Workshop on Medical Computer Vision, Nice, France, October 2012
(bib)
|
|
A. Plate, A. Ahmadi, O. Pauly, T. Klein, N. Navab, K. Bötzel
3D Sonographic Examination of the Midbrain for Computer-Aided Diagnosis of Movement Disorders
To appear: Ultrasound in Medicine and Biology, ELSEVIER, Christy K. Holland (Editor), accepted for publication July 21 2012
(bib)
|
|
O. Pauly, A. Ahmadi, A. Plate, K. Bötzel, N. Navab
Detection of Substantia Nigra Echogenicities in 3D Transcranial Ultrasound for Early Diagnosis of Parkinson Disease
In Proc. International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nice (FR), October 01-05, 2012
(bib)
|
|
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
Student Supervision
- MRI-Based Tissue Classification for Non-Invasive Histology of Atherosclerotic Plaques - Vladimir Golkov - Bachelor Thesis
- Towards Computer Aided Diagnosis of Parkinson Disease - 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
- Random Forests for Tissue Classification in Whole-body MR - Olivia Klose - Master Thesis
- Human Pose Estimation Using Kinect Depth Data - Joé Lallemand - Diplomarbeit
Background
|
|
|