Abstract: A method and system for segmenting multiple brain structures in 3D magnetic resonance (MR) images is disclosed. After intensity standardization of a 3D MR image, a meta-structure including center positions of multiple brain structures is detected in the 3D MR image. The brain structures are then individually segmented using marginal space learning (MSL) constrained by the detected meta-structure.

Abstract: A fetal parameter or anatomy is measured or detected from three-dimensional ultrasound data. An algorithm is machine-trained to detect fetal anatomy. Any machine training approach may be used. The machine-trained classifier is a joint classifier, such that one anatomy is detected using the ultrasound data and the detected location of another anatomy. The machine-trained classifier uses marginal space such that the location of anatomy is detected sequentially through translation, orientation and scale rather than detecting for all location parameters at once. The machine-trained classifier includes detectors for detecting from the ultrasound data at different resolutions, such as in a pyramid volume.

Abstract: A method and system for brain tumor segmentation in multi-spectral 3D MRI images is disclosed. A trained probabilistic boosting tree (PBT) classifier is used to determine, for each voxel in a multi-spectral 3D MR image sequence, a probability that the voxel is part of a brain tumor. The brain tumor is then segmented in the multi-spectral 3D MRI image sequence using graph cuts segmentation based on the probabilities determined using the trained PBT classifier and intensities of the voxels in the multi-spectral 3D MR image sequence.

Abstract: A method and system for detection of deformable structures in medical images is disclosed. Deformable structures can represent blood flow patterns in images such as Doppler echocardiograms. A probabilistic, hierarchical, and discriminant framework is used to detect such deformable structures. This framework integrates evidence from different primitive levels via a progressive detector hierarchy, including a series of discriminant classifiers. A target deformable structure is parameterized by a multi-dimensional parameter, and primitives or partial parameterizations of the parameter are determined. An input image is received, and a series of primitives are sequentially detected using the progressive detector hierarchy, in which each detector or classifier detects a corresponding primitive. The final detector detects configuration candidates for the deformable structure.

Abstract: A method for detecting fetal anatomic features in ultrasound images includes providing an ultrasound image of a fetus, specifying an anatomic feature to be detected in a region S determined by parameter vector ?, providing a sequence of probabilistic boosting tree classifiers, each with a pre-specified height and number of nodes. Each classifier computes a posterior probability P(y|S) where y?{?1,+1}, with P(y=+1|S) representing a probability that region S contains the feature, and P(y=?1|S) representing a probability that region S contains background information. The feature is detected by uniformly sampling a parameter space of parameter vector ? using a first classifier with a sampling interval vector used for training said first classifier, and having each subsequent classifier classify positive samples identified by a preceding classifier using a smaller sampling interval vector used for training said preceding classifier.

Abstract: A method and system for segmenting multiple brain structures in 3D magnetic resonance (MR) images is disclosed. After intensity standardization of a 3D MR image, a meta-structure including center positions of multiple brain structures is detected in the 3D MR image. The brain structures are then individually segmented using marginal space learning (MSL) constrained by the detected meta-structure.

Abstract: A method and system for brain tumor segmentation in multi-spectral 3D MRI images is disclosed. A trained probabilistic boosting tree (PBT) classifier is used to determine, for each voxel in a multi-spectral 3D MR image sequence, a probability that the voxel is part of a brain tumor. The brain tumor is then segmented in the multi-spectral 3D MRI image sequence using graph cuts segmentation based on the probabilities determined using the trained PBT classifier and intensities of the voxels in the multi-spectral 3D MR image sequence.

Abstract: A fetal parameter or anatomy is measured or detected from three-dimensional ultrasound data. An algorithm is machine-trained to detect fetal anatomy. Any machine training approach may be used. The machine-trained classifier is a joint classifier, such that one anatomy is detected using the ultrasound data and the detected location of another anatomy. The machine-trained classifier uses marginal space such that the location of anatomy is detected sequentially through translation, orientation and scale rather than detecting for all location parameters at once. The machine-trained classifier includes detectors for detecting from the ultrasound data at different resolutions, such as in a pyramid volume.

Abstract: A method and system for detection of deformable structures in medical images is disclosed. Deformable structures can represent blood flow patterns in images such as Doppler echocardiograms. A probabilistic, hierarchical, and discriminant framework is used to detect such deformable structures. This framework integrates evidence from different primitive levels via a progressive detector hierarchy, including a series of discriminant classifiers. A target deformable structure is parameterized by a multi-dimensional parameter, and primitives or partial parameterizations of the parameter are determined. An input image is received, and a series of primitives are sequentially detected using the progressive detector hierarchy, in which each detector or classifier detects a corresponding primitive. The final detector detects configuration candidates for the deformable structure.