Dorin.Comaniciu at


Dorin Comaniciu serves as Vice President at Siemens Healthineers, having global responsibility for Medical Imaging Technologies. His team specializes in using large collections of data to build Artificial Intelligence applications for healthcare. His scientific contributions to medical imaging and machine intelligence translated into multiple clinical products focused on improving the quality of care, specifically in the fields of diagnostic imaging, image-guided therapy, and personalized medicine.

A Top Innovator of Siemens, Dr. Comaniciu is a Fellow of IEEE, ACM, Medical Image Computing and Computer Assisted Intervention Society, and American Institute for Medical and Biological Engineering.

The 3D Transesophageal Echo application for heart valve assessment researched by his team was named a top high-technology product by the 2015 R&D 100 Awards, while the Computed Tomography application for rib and spine assessment received the same honor in 2014. Furthermore, the innovations on automated 3D analysis of left ventricle and quantification of 3D color flow Doppler were nominated for the 2011 Young Investigator's Award of the American College of Cardiology and American Society of Echocardiography. Additionally, the aortic valve implantation technology received the 2010 Innovation Award of the European Association for Cardio-Thoracic Surgery.

His team's work on compressed sensing won the 2014 Challenge on Sub-Nyquist Reconstruction of the International Society for Magnetic Resonance in Medicine, allowing MR imaging up to ten times faster without compromising image quality. The first application of this groundbreaking technology, Compressed Sensing Cardiac Cine, enables diagnostic MRI of patients with arrhythmia or of those with respiratory problems. It received the 2017 R&D 100 Award.

Comaniciu has been featured in the book Innovative Minds and has given multiple keynote talks. A Distinguished Alumnus of Rutgers University's School of Engineering, he received the 2004 Siemens Inventor of the Year Award, 2010 IEEE Longuet-Higgins Prize for 'fundamental contributions to computer vision', and the 2011, 2013, and 2015 Thomas Alva Edison Award for patents on 3D heart modeling, anatomical object detection and personalized valve therapy. He served as the scientific director of the European project Health-e-Child, which was granted the 2008 Europe's Information Society Grand Prize.

Comaniciu is listed on Wikipedia's list of prolific inventors, holding 260 US and international patents in the areas of machine intelligence, medical imaging and computer vision. He has co-authored more than 300 peer-reviewed publications, including best papers in CVPR and MICCAI, and co-wrote the 2014 book Marginal Space Learning for Medical Image Analysis. His publications have 38,000 citations according to Google Scholar. During his early work in computer vision he introduced a popular family of robust methods for image analysis and tracking based on the iterative procedure Mean Shift.

A graduate of the Advanced Management Program at the University of Pennsylvania's Wharton School, Comaniciu received a doctorate in electrical and computer engineering from Rutgers University and a doctorate in electronics and telecommunications from Polytechnic University of Bucharest.

Congratulations to Florin Ghesu for winning MICCAI 2017 Young Scientist Award for his work on Multi-scale Deep Reinforcement Learning for Anatomical Landmarks Detection. Tests on thousands of CT volumes resulted into 0% false-positive and 0% false-negative rates at detecting landmarks in the volume or recognizing their absence from the field-of-view.

Stunning photorealistic medical images generated with Siemens Cinematic Rendering technology: see the images and read an interview on the technology and potential applications. Web version of the article here together with more images.

Paper covering Cinematic Rendering, Artificial Agents for Image Understanding, and Deep Learning for Image Fusion and Physiological Computations.

Read our recent papers on Marginal Space Deep Learning, 3D Deep Learning, Reinforcement Learning for Heart Model Personalization, and Artificial Agent for Anatomical Landmark Detection.

We are hiring in (deep) machine learning, artificial intelligence, sparse methods, registration, computer vision, medical imaging. 3D visualization. Lots of cool projects with high impact. Browse this page and see if you are up to the challenge ... drop me a line ...

Acknowledgement: I gratefully acknowledge the contributions of my former and current collaborators. I enjoyed working along the years with great and wonderful minds from whom I constantly learned. The technologies we create together help the society in multiple ways.

AI-powered Clinical Solutions for Diagnostic Imaging and Therapy

News, Images and Videos
Selected Publications - Most Cited

Please Note: These electronic articles are posted for individual, noncommericial use to ensure timely dissemination of scholarly work. They are intended for teaching and training purposes only. Articles may not be reposted or disseminated without permission by the copyright holder. Copyright holders retain all rights as indicated within each article.























Old but Cool Projects

Cristina, my dear wife.
Alexandra and Antonia, our sweet daughters.
Pictures of Romania.

Maintained since May 1996. Updated 2017.