I am currently working for Microsoft in the Bing department. I am responsible for developing machine learning techniques for parsing, understanding and managing social data as well as the integration of social data analytics with Bing.com.
Previously, I was a research fellow in Memorial Sloan-Kettering Cancer Center in New York. I am interested in machine learning, image processing and many other emerging technology in data science. Before moving to the US, I received my Dr. rer. nat. (Doctor of Science) in Mathematics and Computer Science from Ruprecht-Karls-Universität Heidelberg in Germany. Even earlier, I studied Engineering Physics in Tsinghua University in Beijing China (B.Eng and M.Eng) and worked on electronic hardware design for physics experiments. I also spent a year in IBM Research China and worked on data visualization.
MICCAI Medical Computer Vision (2013)
PSB Cancer Panomics (2014)
IEEE International Conference on Image Processing (2014)
Applications: clinical/biological cancer research, social data, crowdsourcing
Structured prediction from cheap data: theory and applications
Pattern mining and predictive analysis on tera-bytes of cancer biology imaging data
Cancer clinical EMR record mining and analysis
Pathology reporting automation and pathology image analysis
Learning Across Bio-Imaging Datasets. X. Lou, A.-K. Hadjantonakis, and G. Rätsch.
A rapid and efficient 2D/3D segmentation method for analysis of early mouse embryo and stem cell image data.X. Lou, M. Kang, P. Xenopoulos, S. Muñoz-Descalzo, and A.-K. Hadjantonakis. In Stem Cell Reports, 2014. (In Press).
Active Structured Learning for Cell Tracking: Algorithm, Framework and Usability. X. Lou, M. Schiegg and F. A. Hamprecht. In IEEE Transactions on Medical Imaging, 2014. (In Press).
Structured Learning from Cheap Data. X. Lou, M. Kloft, G. Rätsch, and F. A. Hamprecht. In S. Nowozin, P. V. Gehler, J. Jancsary, and C. Lampert, editors, Advanced Structured Prediction. MIT Press, 2014. (Accepted).
Towards an integrated dynamic model of temporal structure of clinical text notes and interactions with genetic profiles. T. Karaletsos, X. Lou, K. R. Chan, C. Crosbie and G. Rätsch. In NIPS Machine Learning for Clinical Data Analysis and Healthcare (NIPS-MLCDA), 2013.
An Empirical Analysis of Topic Modeling for Mining Cancer Notes. K. R. Chan, X. Lou, and G. Rätsch. In ICDM Biological Data Mining and its Applications in Healthcare (ICDM-BioDM), 2013.
GRED: Graph-Regularized 3D Shape Reconstruction from Highly Anisotropic and Noisy Images. C. Widmer, P. Drewe, X. Lou, S. Umrania, S. Heinrich, G. Rätsch. In arXiv:1309.4426, 2013.
Live Imaging, Identifying, and Tracking Single Cells in Complex Populations In Vivo and Ex Vivo. M. Kang, P. Xenopoulos, S. Muñoz-Descalzo, X. Lou, and A.-K. Hadjantonakis. In Methods in Molecular Biology, pages 1064–3745. Springer, 2013.
Regularization-based Multitask Learning With applications to Genome Biology and Biomedical Imaging. C. Widmer, M. Kloft, X. Lou, and G. Rätsch. In German Journal on Artificial Intelligence (Künstliche Intelligenz), Springer, 2013.
Structured Domain Adaptation Across Imaging Modality: How 2D Data Helps 3D Inference. X. Lou, C. Widmer, M. Kang, G. Rätsch, and A.-K. Hadjantonakis. In NIPS Machine Learning in Computational Biology (NIPS-MLCB), 2012.
Visualization Software for 3D Video Microscopy: A Design Study. H. Leitte, J. Fangerau, X. Lou, B. Hoeckendorf, S. Lemke, A. Maizel, and J. Wittbrodt. In Eurographics/IEEE Symposium on Visualization (EuroVis), 2012.