Image data segmentation
AssigneeKoninklijke Philips N.V.
InventorsRafael Wiemker, Thomas Buelow, Daniel Bystrov, Torbjoern Vik, Heinrich Schulz
Life of this patent
Estimating the term…
Abstract
A method for segmenting image data includes identifying a 2D boundary start position corresponding to tissue of interest in a cross-section of volumetric image data, wherein the start position is identified by a current position of a graphical pointer with respect to the cross-section, generating a preview 2D boundary for the tissue of interest based on the start position, displaying the preview 2D boundary superimposed over the cross-section, and updating the displayed preview 2D boundary if the position of the graphical pointer changes with respect to the cross-section.
Claims19
A method for segmenting image data, comprising:
- generating a preview 2D boundary for tissue of interest which contours the tissue of interest from only a single position which is a single point and corresponds to the tissue of interest in a displayed cross-section of volumetric image data and the single position corresponds to a gradient point in a gradient image used to determine the preview 2D boundary, wherein the single position is identified by a current position of a hovering 2D graphical pointer of an input device displayed on a display device with respect to the displayed cross-section without a mouse click;
- displaying the generated preview 2D boundary superimposed over the displayed cross-section;
- updating the displayed generated preview 2D boundary as the position of the graphical pointer changes with respect to the displayed cross-section;
- and
- in response to an input selecting the displayed generated preview 2D boundary superimposed on the displayed cross-section, segmenting the tissue of interest in the volumetric image data using the selected displayed generated preview 2D boundary.
A segmentor, comprising:
- a processor that determines and displays a preview 2D boundary which contours a tissue of interest in a displayed cross-section of volumetric image data from only single point identified by a current position of a displayed mouse hovering over the displayed cross-section without a mouse click and the current position of the displayed mouse is a single point and corresponds to a gradient point in a gradient image used to determine the preview 2D boundary which contours the tissue of interest, wherein the preview 2D boundary which contours the tissue of interest changes as the current position of the displayed mouse of the input device changes, and segments the tissue of interest in the volumetric image data in response to an input selecting a display of the preview 2D boundary which contours the tissue of interest.
A non-transitory computer readable storage medium encoded with instructions which, when executed by a processor of a computer, cause the computer to perform the act of:
- performing a 3D segmentation of tissue of interest in volumetric image data from a selected previewed 2D boundary which contours and encloses the tissue of interest in a displayed 2D cross-section of the volumetric image data, and the previewed 2D boundary which contours and encloses the tissue of interest is generated based on sole input of a current position of a mouse hovering over the tissue of interest without a mouse click, wherein the current position of mouse is a single point and corresponds to a gradient point in a generated gradient image, and wherein the previewed 2D boundary that contours and encloses the tissue of interest in the displayed 2D cross-section of the volumetric image data is determined using the gradient point in the generated gradient image.
Dependencies are inferred from the claim text.