Amin Katouzian

Dr. Amin Katouzian Senior Research Scientist Chair for Computer Aided Medical Procedures & Augmented Reality Fakultät für Informatik Technische Universität München Boltzmannstr. 3 85748 Garching b. München Room: MI 03.13.053 Phone: +49 89 289 17081 Fax: +49 89 289 17059 E-Mail: Skype ID: Amin.Katouzian

Education

• Ph.D. in Biomedical Engineering, Columbia University, New York, USA
• M.Sc. in Electrical Engineering, Fairleigh Dickinson University, New Jersey, USA
• B.Sc. in Electrical Engineering, Sistan & Baluchestan University, IRAN

Awards

• Samsung GRO Award of $100,000 per year up to three years.
• Volcano Corporation (Rancho Cordova, CA) Fellowship, $78,100, Sep. 2008-Sep. 2010.
• Siemens (Princeton, NJ) Fellowship, $50,000, Jun. 2007-Dec. 2007.
• Boston Scientific (Fremont, CA) Fellowship, $122,500, Jan. 2006-Jun. 2007.
• Colonel Fairleigh S. Dickinson (Teaneck, NJ) Scholarship, $7,500, Jan. 2002-Sep. 2003.
• Third place in North New Jersey IEEE student paper presentation contest, graduate category, Teaneck, NJ, March 2003.

Research Interests

• Computer Aided Surgery and Diagnosis.
• Augmented Reality in Medical Procedures.
• Computer Vision for Medical Applications.
• Telemedicine.
• Multidimensional Cue Extraction and Pattern Recognition.
• Reconstruction, Registration, Visualization, and Segmentation of 2-4D Images.
• Multiresolution Analysis.
• Speech Recognition and Perception.

Active Research Projects

Estimation of Flow Parameters from X-ray Data This project focuses on the quantification of blood flow based on 2D and 3D angiographic X-ray image data, which is of particular interest during minimally invasive interventional procedures such as recanalizations of stenotic vessels and embolizations of arteries that feed tumors or vascular malformations in the patient's brain, for example. Our projects cover the evaluation of model-based approaches involving CFD (computational fluid dynamics) simulations as well as methods that aim at estimating the optical flow in the images and deriving quantitative blood flow information from these results.

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.

Knowledge Propagation Models for Image Registration To register modalities with complex intensity relationships, we leverage machine learning algorithm to cast it into a mono modal registration problem. This is done by extracting tissue specific features for propagating anatomical/structural knowledge from one modalitiy to an other through an online learnt propagation model. The registration and propagation steps are iteratively performed and refined. For proof-of-concept, we employ it for registering (1) Immunofluorescence to Histology images and (2) Intravascular Ultrasound to Histology Images.

OCT Tissue Classification Optical coherence tomography (OCT), employing light rather than ultrasound, is a high-resolution imaging technology that permits a precise assessment of biological tissue. Used intravascular, OCT is increasingly used for assessing safety and efficacy of intracoronary devices, such as drug-eluting stents and bioabsorbable stents. Obtained images provide insights regarding stent malposition, overlap, and neointimal thickening, among others. Recent OCT histopathology correlation studies have shown that OCT can be used to identify plaque composition, and hence it is possible to distinguish “normal” from “abnormal” neointimal tissue based on its visual appearance. The aim of this project is to develop a novel method for the automatic analysis of tissue in IVOCT. Automatic tissue classification will allow for a quantitative and potentially more time-efficient and objective analysis of IVOCT data. For instance, classifying neointimal tissue as either “mature” or “immature” can be used to assess the disease state of patients; as a potential predictor of late stent-failure events such as stent thrombosis and restenosis.

Ultrasound Based Tissue Characterization clinicians are challenged when colocated heterogeneous tissue backscatter mixed signals appearing as non-unique intensity patterns in B-mode ultrasound image. Tissue characterization algorithms have been developed to assist clinicians to identify such heterogeneous tissues and assess lesion stage. We propose a novel technique coined as Stochastic Driven Histology (SDH) that is able to provide information about co-located heterogeneous tissues. It employs learning of tissue specific ultrasonic backscattering statistical physics and signal confidence primal from labeled data for predicting heterogeneous tissue composition in plaques. We employ a random forest for the purpose of learning such a primal using sparsely labeled and noisy samples. In clinical deployment, the posterior prediction of different lesions constituting the plaque is estimated.

Hashing forests for morphological search and retrieval in neuroscientific image databases In this project, for the first time, we propose a data-driven search and retrieval (hashing) technique for large neuron image databases. The presented method is established upon hashing forests, where multiple unsupervised random trees are used to encode neurons by parsing the neuromorphological feature space into balanced subspaces. We introduce an inverse coding formulation for retrieval of relevant neurons to effectively mitigate the need for pairwise comparisons across the database. Experimental validations show the superiority of our proposed technique over the state-of-the art methods, in terms of recall for a particular code size. This demonstrates the potential of this approach for effective morphology preserving encoding and retrieval in large neuron databases.

Student Projects

• Implementation and development of a new service to report, analyze, visualize neurons for neuroscientists in Python (IDP, Finished).
• Cardiac Magnetic Resonance Image Analysis and Modeling for Patients with Implantable Cardioverter Defibrillators (ICDs) (Master Thesis, Finished).
• Integration of a WiFi^? Interface and Win7 C#-GUI development for control and surveillance of a Heart Assist Device in animal experiments (IDP, Finished).
• Knowledge propagation models for deformable image registration (Master Thesis, Finished).
• Implementation and development of wavelet-packet-based tissue characterization for IVUS image in C++ and MeVisLab^? (IDP, Finished).

Reviewer

• Journal of Medical Image Analysis.
• Journal of IEEE Transaction on Medical Imaging.
• Journal of IEEE Transaction on Biomedical Engineering.
• Journal of IEEE Transaction on Information Technology in Biomedicine.
• Journal of Digital Signal Processing.
• Journal of Computers in Biology and Medicine.
• Journal of Computerized Medical Imaging and Graphics
• Journal of Cardiovascular Imaging.
• Journal of Cardiovascular Magnetic Resonance.
• Medical Image Computing and Computer Assisted Intervention (MICCAI) 2013.
• Design of Medical Devices Conference, Europe 2013.
• International Symposium on Mixed and Augmented Reality (ISMAR) 2012.
• Medical Image Computing and Computer Assisted Intervention (MICCAI) 2012.
• 15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)-CVII.

Editorial Activity

• Program Committee: International Conference on Systems in Medicine and Biology (ICSMB), Kharagpur, India, 2016.
• Steering Committee: the 18th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)-CVII/STENT workshop, Munich, Germany, 2015.
• Program Committee, the MICCAI workshop on Computing and Visualization for Intravascular Imaging and Computer Assisted Stenting MICCAI-CVII-STENT, Boston, USA, 2014.
• Executive Committee, the 4th International Conference on Information Processing in Computer-Assisted Interventions (IPCAI), Heidelberg, Germany, 2013.
• Program Committee, the 15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)-CVII, Toronto, Canada, 2011.

Invited Talks

• PicoSEC^?-MCNet Training Workshop, “The necessity of personalized monitoring for patients with cardiovascular disease,” Munich, March 19th 2015.
• Otto-von-Guericke University (Magdeburg, Germany), Computer Science Department, “Computer-assisted decision support for coronary atherosclerosis diagnosis and treatment,” February 5th, 2015.
• Tehran University, Electrical Engineering and Computer Science Department, “Computer-assisted decision support for coronary atherosclerosis diagnosis and treatment,” January 25th, 2015.
• MICCAI-CVII workshop, "The missing link in healthcare system; personalized monitoring," MIT Boston, 2014.
• University of Barcelona, Computer Vision Center, "patient-Specific Translational research on Atherosclerosis and Diagnosis (STAnD^?)@CAMP@TUM". February 22nd, 2013.
• PicoSEC^?-EndoTOFPET-US workshop on intraoperative imaging and navigation solutions, January 16th, 2013.
• Technical University of Munich, Department of Mathematics, "Applications of multiscale analysis in quantification of atherosclerosis disease," November 10th, 2011.
• Sabanci University (Istanbul, Turkey), Department of Engineering and Natural Sciences, "Quantifying Atherosclerosis: IVUS Imaging For Lumen Border Detection and Plaque Characterization," December 22nd, 2010.
• Volcano Corporation (Sacramento, CA), "Detection of Lumen Border in IVUS images via Three-Dimensional Brushlet Analysis," June 28th, 2009.

Patent

• Ali Kamen, Lance Ladic, Sebastian Pölsterl, Adnan Kastrati, Amin Katouzian, Nassir Navab, “A novel cost-effective method for stratification of CAD patients for revascularization procedure based on minimizing the adverse effect,” 2013.
• Debdoot Sheet, Amrita Chaudhary, Jyotirmoy Chatterjee, Ajoy Kumar Ray, Amin Katouzian, "Methods and System for Characterizing Tissues in Optical Coherence Tomography," 2013.
• Amin Katouzian, Nassir Navab, “Intelligent Implanted Health Sensing Device and Assembly”, 2012.
• Amin Katouzian, Andrew F. Laine, Debdoot Sheet, Athanasios Karamalis, Abouzar Eslami, Stephane G. Carlier, Nassir Navab, “System and Method for Characterizing Tissues in Intravascular Ultrasound using Statistical Physics," 2012.
• Amin Katouzian, Elsa D. Angelini, Auranuch Lorsakul, Bernhard Sturm, Andrew F. Laine, “Denoising and Lumen Border Detection of Intravascular Ultrasound via Segmentation of Directional Wavelet Representations,” Serial No. 61/200,987, December 5, 2008.
• Amin Katouzian, Babak Baseri, Elisa E. Konofagou, Andrew F. Laine, “Systems and Methods for Intravascular Tissue Characterization and Border Detection,” WO2009023626, 2009.
• Amin Katouzian, Elisa E. Konofagou, Andrew F. Laine, “Unsupervised Texture-Derived Atherosclerotic Plaque Characterization Algorithm through Backscattered Intravascular Ultrasound Signals,” Serial No. 60/991,508, November 30, 2007.
• Amin Katouzian, Elisa E. Konofagou, Andrew F. Laine, “Intravascular Ultrasound (IVUS) Tissue Characterization and Border Detection through Backscattered Signals by Wavelet Packet Analysis,” Serial No. 60/955,249, August 10, 2007.

Publication

2017
	A. Guha Roy, S. Conjeti, D. Sheet, A. Katouzian, N. Navab, C. Wachinger Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data Proceedings of MICCAI 2017: Medical Image Computing and Computer-Assisted Intervention − MICCAI 2017 (bib)
	S. Conjeti, M. Paschali, A. Katouzian, N. Navab Deep Multiple Instance Hashing for Scalable Medical Image Retrieval The first two authors contributed equally. 20th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Canada 2017. The original publication is available online at link.springer.com (bib)
	A. Kazi, S. Conjeti, A. Katouzian, N. Navab Coupled Manifold Learning for Retrieval Across Modalities In Computer Vision Workshop (ICCVW), 2017 IEEE International Conference on (pp. 1321-1328). IEEE (bib)
	M. Riva, C. Hennersperger, F. Milletari, A. Katouzian, F. Pessina, B. Gutierrez-Becker, A. Castellano, N. Navab, L. Bello 3D intra-operative ultrasound and MR image-guidance: pursuing an ultrasound-based management of brainshift to enhance neuronavigation International Journal of Computer Assisted Radiology and Surgery, in press. (bib)
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)
	S. Conjeti, A. Katouzian, A. Kazi, S. Mesbah, D. Beymer, T.F. Syeda Mahmood, N. Navab Metric Hashing Forests Medical Image Analysis, Special Issue MICCAI 2015, Best Paper Award, 2016. (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)
	A. Shah, S. Conjeti, N. Navab, A. Katouzian Deeply learnt hashing forests for content based image retrieval in prostate MR images SPIE Medical Imaging, San Diego, California, USA, March 2016 (bib)
	S. Conjeti, S. Mesbah, M. Negahdar, P. Rautenberg, , N. Navab, A. Katouzian Neuron-Miner: An Advanced Tool for Morphological Search and Retrieval in Neuroscientific Image Databases Neuroinformatics (Accepted March 2016). (bib)
	S. Conjeti, A. Katouzian, A. Guha Roy, L. Peter, D. Sheet, S. Carlier, A. Laine, N. Navab Supervised Domain Adaptation of Decision Forests: Transfer of models trained in vitro for in vivo intravascular ultrasound tissue characterization Medical Image Analysis, 2016 (bib)
2015
	S. Conjeti, S. Mesbah, A. Kumaraswamy, P. Rautenberg, N. Navab, A. Katouzian Hashing forests for morphological search and retrieval in neuroscientific image databases Proceedings of the 18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI), Munich, Germany, October 2015 (bib)
	S. Conjeti, S. Mesbah, A. Kumaraswamy, P. Rautenberg, N. Navab, A. Katouzian Hashing forests for morphological search and retrieval in neuroscientific image databases Proceedings of the 18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI), Munich, Germany, October 2015 (bib)
	S. Pölsterl, N. Navab, A. Katouzian Fast Training of Support Vector Machines for Survival Analysis Machine Learning and Knowledge Discovery in Databases (bib)
	J. Zimmermann, S. Rashid, H. Peng, A. Katouzian, N. Navab, D. Ennis Cardiac MRI derived epicardial fat maps to assist VT ablation procedures for subjects with implantable devices International Symposium on BIOMEDICAL IMAGING: From Nano to Macro, New York, USA, April 2015 (bib)
	M. Yigitsoy, A. Katouzian, N. Navab Structure Propagation for Deformable Image Stitching International Symposium on Biomedical Imaging: From Nano to Macro, New York, USA, April 2015 (bib)
	M. Yigitsoy, V. Belagiannis, A. Djurka, A. Katouzian, S. Ilic, F. Pernus, A. Eslami, N. Navab Random Ferns for Multiple Target Tracking in Microscopic Retina Image Sequences International Symposium on Biomedical Imaging: From Nano to Macro, New York, USA, April 2015 (bib)
	D. Sheet, S. P. K. Karri, A. Katouzian, , A. K. Ray, J. Chatterjee Deep Learning of Tissue Specific Speckle Representations in Optical Coherence Tomography and Deeper Exploration for In situ Histology International Symposium on BIOMEDICAL IMAGING: From Nano to Macro, New York, USA, April 2015 (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)
	A. Guha Roy, S. Conjeti, S. Carlier, P. K. Dutta, A. Kastrati, A. Laine, N. Navab, A. Katouzian, D. Sheet Lumen Segmentation in Intravascular Optical Coherence Tomography using Backscattering Tracked and Initialized Random Walks IEEE Journal of Biomedical and Health Informatics, 2015 (In Press) (bib)
	A. Guha Roy, S. Conjeti, S. Carlier, A. Konig, A. Kastrati, P. K. Dutta, A. Laine, N. Navab, D. Sheet, A. Katouzian Bag of forests for modelling of tissue energy interaction in optical coherence tomography for atherosclerotic plaque susceptibility assessment Proceedings of International Symposium on Biomedical Imaging (ISBI), Brooklyn, NY, USA, April 2015 (bib)
	S. Conjeti, M. Yigitsoy, D. Sheet, J. Chatterjee, N. Navab, A. Katouzian Mutually Coherent Structural Representation for Image Registration through Joint Manifold Embedding and Alignment Proceedings of International Symposium on Biomedical Imaging (ISBI), Brooklyn, NY, USA, April 2015 (bib)
	S. Conjeti, M. Yigitsoy, T. Peng, D. Sheet, J. Chatterjee, C. Bayer, N. Navab, A. Katouzian Deformable Registration of immunofluorescence and Histology using iterative Cross-modal Propagation Proceedings of International Symposium on Biomedical Imaging (ISBI), Brooklyn, NY, USA, April 2015 (bib)
2014
	R. Brosig, P. Maday, M. Kowarschik, A. Katouzian, S. Demirci, N. Navab Blood Flow Quantification using 1D CFD Parameter Identification Proc. SPIE 9034, Medical Imaging 2014: Image Processing, San Diego, CA, USA, Feb 19-23 2014. (bib)
	, S. Conjeti, P. B. Noël, S. Carlier, N. Navab, A. Katouzian Full-Wave Intravascular Ultrasound Simulation from Histology Medical Image Computing and Computer-Assisted Intervention, MICCAI, 2014 (bib)
	M. Friebe, A. Katouzian, P. Matthies, S. O. Cho Miniaturized cold emission low energy X-ray tubes for MRI guided intraoperative radiation therapy - A technical feasibility study Poster presentation and book of abstracts, IGIC 2014, Magdeburg (bib)
	M. Friebe, H.-W. Henke, P. Matthies, A. Katouzian, G. Krombach MRI biopsy with semi-automated biopsy needle in Slicer 3D environment Poster presentation and book of abstracts, IGIC 2014, Magdeburg (bib)
2013
	D. Sheet, A. Karamalis, A. Eslami, P. B. Noël, J. Chatterjee, A. K. Ray, A. Laine, S. Carlier, N. Navab, A. Katouzian Joint Learning of Ultrasonic Backscattering Statistical Physics and Signal Confidence Primal for Characterizing Atherosclerotic Plaques using Intravascular Ultrasound Medial Image Analysis, 2013, (bib)
	D. Sheet, , S. P. K. Karri, , A. Katouzian, , N. Navab, J. Chatterjee, A. K. Ray In situ histology of mice skin through transfer learning of tissue energy interaction in optical coherence tomography Journal of Biomedical Optics, 2013. (bib)
	D. Sheet, A. Karamalis, A. Eslami, P. B. Noël, , , J. Chatterjee, A. K. Ray, A. Laine, S. Carlier, N. Navab, A. Katouzian Hunting for necrosis in the shadows of intravascular ultrasound Special Issue, Computerized Medical Imaging and Graphics, 2013, (bib)
	S. Kraft, A. Karamalis, D. Sheet, E. Drecoll, E. Rummeny, N. Navab, P. B. Noël, A. Katouzian Introducing nuclei scatterer patterns into histology-based intravascular ultrasound simulation framework To appear in: SPIE Medical Imaging 2013 (bib)
	D. Sheet, A. Karamalis, S. Kraft, P. B. Noël, T. Vag, A. Sadhu, A. Katouzian, N. Navab, J. Chatterjee, A. K. Ray Random Forest learning of ultrasonic statistical physics and object spaces for lesion detection in 2D sonomammography To appear in: SPIE Medical Imaging 2013 (bib)
	A. Eslami, A. Karamalis, A. Katouzian, N. Navab Segmentation By Retrieval With Guided Random Walks: Application To Left Ventricle Segmentation in MRI Medical Image Analysis, vol. 17, no. 2, 2013, www.sciencedirect.com.ezproxy.cul.columbia.edu/science/article/pii/S136184151200151X (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)
	A. Katouzian, , S. Carlier, , N. Navab, A. Laine A State-of-the-Art Review on Segmentation Algorithms in Intravascular Ultrasound (IVUS) Images Special Issue, IEEE Transactions on Information Technology in Biomedicine, 16, 5, 823 - 834, 2012, (bib)
	A. Katouzian, A. Karamalis, A. Konig, S. Carlier, N. Navab Ambiguity in detection of necrosis in IVUS plaque characterization algorithms European Society of Cardiology, Munich, Germany, 2012 (bib)
	A. Katouzian, A. Karamalis, D. Sheet, E. Konofagou, B. Baseri, S. Carlier, A. Eslami, A. Konig, N. Navab, A. Laine Iterative Self-Organizing Atherosclerotic Tissue Labeling in Intravascular Ultrasound Images and Comparison with Virtual Histology IEEE Transactions on Biomedical Engineering (bib)
	A. Katouzian, A. Karamalis, , A. Eslami, N. Navab IVUS-Histology Image Registration 5th Workshop on Biomedical Image Registration, Nashville, USA, July, 2012 (bib)
	A. Karamalis, A. Katouzian, S. Carlier, N. Navab Confidence Estimation in IVUS Radio-Frequency Data with Random Walks In Proc. 9th IEEE International Symposium on Biomedical Imaging (ISBI), Barcelona, Spain, 2012 (bib)
	A. Bigdelou, A. Katouzian, N. Navab Model-based visualization of usability data to support analysis in complex domains 21th International Conference of Usability Professionals Association (UPA), Henderson, Nevada, USA, June 2012 (bib)
	A. Katouzian, A. Karamalis, A. Laine, N. Navab A Systematic Approach Toward Reliable Atherosclerotic Plaque Characterization in IVUS Images Bildverarbeitung für die Medizin, Berlin, 2012, Germany (bib)