Dorin Comaniciu

TL;DR: In this article, various attributes for medical CAD analysis used alone or in combination are disclosed, including: (1) using medical sensor data and context information associated with the configuration of the medical system to provide recommendations for further acts to be performed for more accurate or different diagnosis, (2) recommending further acts and providing an indication of the importance of the further act for further diagnosis, and (3) transmitting patient data to a remote system for CAD diagnosis and using the results of the CAD diagnosis at the remote facility.

TL;DR: A novel system for fast automatic detection and measurement of fetal anatomies that directly exploits a large database of expert annotated fetal anatomical structures in ultrasound images that learns automatically to distinguish between the appearance of the object of interest and background by training a constrained probabilistic boosting tree classifier.

TL;DR: An efficient, robust, and fully automatic segmentation method for 3D cardiac computed tomography (CT) volumes, based on recent advances in learning discriminative object models and exploiting a large database of annotated CT volumes is presented.

TL;DR: In this article, the pose parameter space for an anatomical object is divided into a series of marginal search spaces with increasing dimensionality, and each of the trained deep neural networks can evaluate hypotheses in a current parameter space using discriminative classification or a regression function.

TL;DR: It is illustrated that by judiciously choosing the system modules and performing a careful analysis of the influence of various tuning parameters on the system it is possible to: perform proper statistical inference, automatically set control parameters and quantify limits of a dual-camera real-time video surveillance system.