D
Dorin Comaniciu
Researcher at Princeton University
Publications - 632
Citations - 43059
Dorin Comaniciu is an academic researcher from Princeton University. The author has contributed to research in topics: Segmentation & Object detection. The author has an hindex of 74, co-authored 622 publications receiving 40541 citations. Previous affiliations of Dorin Comaniciu include Siemens & Rutgers University.
Papers
More filters
Proceedings ArticleDOI
Combined semantic and similarity search in medical image databases
Sascha Seifert,Marisa Thoma,Florian Stegmaier,Matthias Hammon,Martin Kramer,Martin Huber,Hans-Peter Kriegel,Alexander Cavallaro,Dorin Comaniciu +8 more
TL;DR: A search methodology which enables the physician to fulfill intelligent search scenarios on medical image databases combining ontology-based semantic and appearance-based similarity search is presented.
Journal ArticleDOI
A self-taught artificial agent for multi-physics computational model personalization
Dominik Neumann,Dominik Neumann,Tommaso Mansi,Lucian Mihai Itu,Lucian Mihai Itu,Bogdan Georgescu,Elham Kayvanpour,Farbod Sedaghat-Hamedani,Ali Amr,Jan Haas,Hugo A. Katus,Benjamin Meder,Stefan Steidl,Joachim Hornegger,Dorin Comaniciu +14 more
TL;DR: Vito, a self-taught artificial agent, learns a representative decision process model through exploration of the computational model: it learns how the model behaves under change of parameters, and automatically learns an optimal strategy for on-line personalization.
Proceedings ArticleDOI
Patient-specific modeling of left heart anatomy, dynamics and hemodynamics from high resolution 4D CT
TL;DR: This work proposes to advance the state-of-the-art by exploiting a comprehensive, patient-specific left heart model extracted from 4D Computed Tomography (CT) data, and derives realistic hemodynamics, constrained by the local anatomy, along the entire heart cycle.
Book ChapterDOI
Fast Automatic Segmentation of the Esophagus from 3D CT Data Using a Probabilistic Model
Johannes Feulner,S. Kevin Zhou,Alexander Cavallaro,Sascha Seifert,Joachim Hornegger,Dorin Comaniciu +5 more
TL;DR: A two step method is proposed which first finds the approximate shape of the esophagus shape using a "detect and connect" approach and achieves a mean segmentation error of 2.28mm with less than 9s computation time.
Journal ArticleDOI
A parameter estimation framework for patient-specific hemodynamic computations
TL;DR: A key feature of the proposed method is a warm-start to the optimization procedure, with better initial solution for the nonlinear system of equations, to reduce the number of iterations needed for the calibration of the geometrical multiscale models.