SebastianPoelsterl

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Sebastian Pölsterl

photo of
Sebastian Pölsterl
E-Mail:
Phone:
+49 89 289 17071
Address:
Chair for Computer Aided Medical Procedures & Augmented Reality
Fakultät für Informatik
Technische Universität München
Boltzmannstr. 3
85748 Garching b. München, Germany
Room: MI 03.13.041

Awards

Winner of Subchallenge in Prostate Cancer DREAM Challenge

The goal of the Prostate Cancer DREAM challenge is to improve the prediction of survival and toxicity of docetaxel treatment in patients with metastatic castrate resistant prostate cancer (mCRPC). The primary benefit of this challenge will be to establish new quantitative benchmarks for prognostic modeling in mCRPC, with a potential impact for clinical decision making and ultimately understanding the mechanism of disease progression.

Our implementation using a large heterogeneous ensemble of different models was able to secure the win in subchallenge 1b, where the task was to predict the exact time to event (days till death) for all patients in the evaluation set. A detailed description of our solution is available at the challenge's website.

Code

Fast Training of Support Vector Machines for Survival Analysis

Current Projects

Big Data Analysis for Medical Applications

Big Data Analysis for Medical Applications

Widespread use of electronic health records (EHR) led to vast amount of medical data being collected. The data is characterized by large sample size, heterogeneity of variables, unstructured information, missing information, and time-dependent variables, to name a few. These facts render commonly used statistical tools to perform analysis inadequate and require the development of sophisticated algorithms to overcome these challenges. For instance, the set of variables recorded for each patient can naturally be decomposed into groups, known as views. Most machine learning algorithms ignore this multi-view relationship. Instead, they can either be trained on each view separately or on a concatenation of all views to form a single view. Considering these relationships recently came to attention of the research community that proposed co-training, multiple kernel learning and subspace learning to address this problem. Although existing methods show promising results in their respective tasks, it is difficult to apply them to real-world clinical data, where highly heterogeneous features (continuous, categorial, ordinal) and missing values are common, because not all tests can be performed on all patients. As a result, multi-view learning algorithms have rarely been applied to medical problems.

Publications

2016
S. Pölsterl, L. Wang, , S. Conjeti, A. Katouzian, N. Navab
Heterogeneous ensembles for predicting survival of metastatic, castrate-resistant prostate cancer patients
F1000Research vol. 5, no. 2676, 2016 (bib)
R. Bekmukhametov, S. Pölsterl, T. Allmendinger, M. Doan, N. Navab
Automatic Detection of Non-Biological Artifacts in ECGs Acquired During Cardiac Computed Tomography
Machine Learning and Knowledge Discovery in Databases (bib)
S. Pölsterl, S. Conjeti, N. Navab, A. Katouzian
Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection
Artificial Intelligence in Medicine, vol. 72, pp. 1-11, 2016 (bib)
2015
S. Pölsterl, N. Navab, A. Katouzian
Fast Training of Support Vector Machines for Survival Analysis
Machine Learning and Knowledge Discovery in Databases (bib)
S. Pölsterl, M. Singh, A. Katouzian, N. Navab, A. Kastrati, L. Ladic, A. Kamen
Stratification of coronary artery disease patients for revascularization procedure based on estimating adverse effects
BMC Medical Informatics and Decision Making 2015, 15:9 (bib)


UsersForm
Title: -none-
Circumference of your head (in cm):  
Firstname: Sebastian
Middlename:  
Lastname: Poelsterl
Picture: poelsterl_small.jpg
Birthday: 10.02.1986
Nationality: Bavaria
Languages: English, German, Bavarian
Groups: Medical Imaging, Patient Monitoring
Expertise:  
Position: Scientific Staff
Status: Alumni
Emailbefore: sebastian.poelsterl
Emailafter: tum.de
Room: MI 03.13.041
Telephone: +49 89 289 17071
Alumniactivity: The Institute of Cancer Research
Defensedate: 24 May 2016
Thesistitle: Algorithms for Large-scale Learning from Heterogeneous Survival Data
Alumnihomepage:  
Personalvideo01:  
Personalvideotext01:  
Personalvideopreview01:  
Personalvideo02:  
Personalvideotext02:  
Personalvideopreview02:  


Edit | Attach | Refresh | Diffs | More | Revision r1.14 - 25 May 2016 - 15:14 - SebastianPoelsterl

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif