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
Simultaneous Registration and Modeling of Deformable Shapes
TL;DR: The Direct Factorization method is proposed that extends a structure from motion method and yields a linear closedform solution that simultaneously registers the deformable shapes at arbitrary dimensions and constructs the linear bases.
Patent
Method and System for Multiple Object Detection by Sequential Monte Carlo and Hierarchical Detection Network
TL;DR: In this paper, a plurality of objects in an image is sequentially detected in an order specified by a trained hierarchical detection network, where the order for object detection is automatically determined.
Proceedings ArticleDOI
Using needle detection and tracking for motion compensation in abdominal interventions
TL;DR: A method of using the needle detection and tracking to compensate breathing motion in 2D fluoroscopic videos and can provide motion compensation for abdominal interventions is presented.
Journal ArticleDOI
Prediction of Patient Management in COVID-19 Using Deep Learning-Based Fully Automated Extraction of Cardiothoracic CT Metrics and Laboratory Findings.
Thomas Weikert,Saikiran Rapaka,Sasa Grbic,Thomas J. Re,Shikha Chaganti,David J. Winkel,Constantin Anastasopoulos,Tilo Niemann,Benedikt J. Wiggli,Jens Bremerich,Raphael Twerenbold,Gregor Sommer,Dorin Comaniciu,Alexander W. Sauter +13 more
TL;DR: In this article, the potential of these parameters to predict patients' needs for intensive care (yes/no) was analyzed using logistic regression and receiver operating characteristic curves, which can be accessed using automated image analysis.
Patent
Providing real-time marker detection for a stent in medical imaging
TL;DR: In this paper, a real-time marker detection in medical imaging of a stent was provided, based on automatic initialization using a subset of frames of image data from the plurality of frames.