Abstract: Segmentation of multi-energy CT data, including data in three or more energy bands. A user is enabled to input one or more region indicators in displayed CT data. At least some data is labelled based on the region indicators. Feature vectors are created for at least some data elements, which are then classified based on the labelled data elements and feature vectors. Feature vectors may be constructed using a Bag of Features or similar process. Classification may be performed using a Support Vector Machine classifier or other machine learning classifier.

Abstract: Segmentation of multi-energy CT data, including data in three or more energy bands. A user is enabled to input one or more region indicators in displayed CT data. Probability maps are generated and may be refined using distance metrics, which may include geodesic and Euclidean distance metrics. Segmentation may be based on the probability maps and/or refined probability maps. Segmentation of medical image data is also disclosed.

Abstract: Systems and methods are provided for graphically representing uncertainty in an assisted decision-making application. A database contains a class vector for each of a plurality of objects of interest. A given class vector includes a plurality of possible classes for its associated object of interest and a corresponding set of confidence values. The database also contains a set of assumptions associated with each confidence value. A user interface displays a plurality of graphics representing the objects of interest. A given graphic includes a set of at least two class icons, each corresponding to one of the plurality of classes associated with its corresponding object of interest. The graphic also includes a qualitative indication of the confidence values associated with the set of classes. The assumptions associated with a given confidence value are retrievable by a user by selecting the class icon associated with the confidence value.

Abstract: Systems and methods are provided for filtering detected events to determine events of interest. A sensor data analysis system identifies a plurality of detected events from provided sensor data and evaluates the sensor data to determine at least one characteristic associated with each event. The sensor data analysis system reports the plurality of detected events and their associated characteristics. At least one affiliated event generator is operative to generate at least one affiliated event and produce at least one event report. A given event report provides at least one characteristic associated with an affiliated event. An event filtering system compares the at least one event report to the detected events to identify at least one affiliated event amongst the plurality of detected events.

Abstract: Systems and methods are provided for graphically representing uncertainty in an assisted decision-making application. A database contains a class vector for each of a plurality of objects of interest. A given class vector includes a plurality of possible classes for its associated object of interest and a corresponding set of confidence values. The database also contains a set of assumptions associated with each confidence value. A user interface displays a plurality of graphics representing the objects of interest. A given graphic includes a set of at least two class icons, each corresponding to one of the plurality of classes associated with its corresponding object of interest. The graphic also includes a qualitative indication of the confidence values associated with the set of classes. The assumptions associated with a given confidence value are retrievable by a user by selecting the class icon associated with the confidence value.

Abstract: Systems and methods are provided for filtering detected events to determine events of interest. A sensor data analysis system identifies a plurality of detected events from provided sensor data and evaluates the sensor data to determine at least one characteristic associated with each event. The sensor data analysis system reports the plurality of detected events and their associated characteristics. At least one affiliated event generator is operative to generate at least one affiliated event and produce at least one event report. A given event report provides at least one characteristic associated with an affiliated event. An event filtering system compares the at least one event report to the detected events to identify at least one affiliated event amongst the plurality of detected events.