Abstract:
The invention provides a method for determining a confidence value for an image segmentation. The method includes obtaining an image, wherein the image comprises a view of an anatomical structure and a model of the anatomical structure is obtained, wherein the model comprises a plurality of nodes. The image is processed to generate a plurality of image segmentation outputs, wherein each image segmentation output comprises a set of values for the view, wherein each value of the set of values is associated with a node of the plurality of nodes of the model. For each node of the model, a confidence value is determined based on the plurality of values corresponding to the node. A confidence map of the anatomical structure is generated based on the confidence value of each node.
Abstract:
An ultrasonic diagnostic imaging system has a user control by which a user positions the user's selection of a heart chamber border in relation to two machine-drawn heart chamber tracings. The user's border is positioned by a single degree of freedom control which positions the border as a function of a single user-determined value. This overcomes the vagaries of machine-drawn borders and their mixed acceptance by clinicians, who can now create repeatably-drawn borders and exchange the control value for use by others to obtain the same results.
Abstract:
An ultrasonic diagnostic imaging system and method enable the automatic acquisition of standard view planes of the heart in real time, such as the AP4, AP3, and AP2 views. A 3D image of the heart is acquired and the processed in conjunction with a geometrical heart model. The heart model is fitted to the heart in its acquired pose to segment the desired image planes from the 3D image data. During successive image acquisition intervals the image planes are tracked through successive image data as multi-plane system to update a display of the multiple images. The successive image acquisitions can be volume image acquisitions or multi-plane acquisitions of just the tracked image planes during each acquisition interval.
Abstract:
An ultrasound imaging system performs real-time image analysis of the 3D ultrasound images to identify anatomical structure and landmarks in the 3D images, so that it can be determined if a region of interest of a target anatomical structure is present. If the region of interest is not present, the location of the region of interest outside the field of view volume is inferred from the anatomical structure and landmarks that are detected within the field of view. A relative displacement between the reference anatomical plane and a position and orientation of the 3D ultrasound imaging probe can then be derived so that ultrasound guidance information can be given.
Abstract:
An ultrasonic imaging system produces more diagnostic cardiac images of the left ventricle by plotting the longitudinal medial axis of the chamber between the apex and mitral valve plane as a curved line evenly spaced between the opposite walls of the myocardium. Transverse image planes are positioned orthogonal to the curved medial axis with control points positioned in the short axis view on lines evenly spaced around and emanating from the medial axis. If the short axis view is of an oval shaped chamber the transverse image is stretched to give the heart a more rounded appearance resulting in better positioning of editing control points.
Abstract:
An ultrasonic diagnostic imaging system has a user control by which a user positions the user's selection of a heart chamber border in relation to two myocardial boundaries identified by a deformable heart model. The user's border is positioned by a single degree of freedom control which positions the border as a function of a single user- determined value. This overcomes the vagaries of machine-drawn borders and their mixed acceptance by clinicians, who can now create repeatably-drawn borders and exchange the control value for use by others to obtain the same results.
Abstract:
An ultrasound system has a number of user selectable ultrasound imaging modes, the actuation of which automatically invokes the making of automated measurements or quantification in real time as imaging is performed in the mode. The user can thereby see if the images being acquired are suitable and robust enough for desired quantification and measurement. The system will further automatically combine or perform statistical analysis of several images or temporally different images such a group mean and standard deviation. Confidence assessment of the measurements may also be computed.