Dorin Comaniciu

TL;DR: A network of 1D and 3D landmarks is trained to quickly parse the 3D CT data and estimate which organs and landmarks are present as well as their most probable locations and boundaries, and this approach can be obtained in about 20 seconds with state-of-the-art accuracy.

TL;DR: This work proposes a new learning method by simultaneously modeling both the object appearance and the parameter search strategy as a unified behavioral task for an artificial agent and shows that given only a sequence of annotated images, the agent can automatically and strategically learn optimal paths that converge to the sought anatomical landmark location.

TL;DR: This paper introduces database-guided segmentation as a new data-driven paradigm that directly exploits expert annotation of interest structures in large medical databases and proposes a feature selection mechanism and the corresponding metric.

TL;DR: A novel multiscale joint segmentation and model fitting solution which extends the robust mean shift-based analysis to the linear scale-space theory and can be applied for the analysis of blob-like structures in various other applications.

TL;DR: In this paper, a method and system for determining fractional flow reserve (FFR) for a coronary artery stenosis of a patient is disclosed, where a set of features for the stenosis is extracted from the medical image data of the patient, and an FFR value is determined based on the extracted set of feature using a trained machine-learning based mapping.