Method and apparatus of obtaining body depth information for a patient
A method is provided of obtaining body depth information for a patient who is lying on patient support. A patient support depth map of the upper surface of the patient support is obtained without the patient as well as an image and patient depth map of the patient on the patient support. Landmark body positions of the patient are extracted from the image so that points in a region of interest can be mapped to points of a template, using the identified landmark body positions. A body thickness is obtained for said points using the template, the depth value for the respective point and the patient support depth value for the respective point.
1 . A method of obtaining body depth information for a patient situated on patient support, comprising:
obtaining a patient support depth map of an upper surface of the patient support without the patient using a depth camera;
obtaining an image of the patient lying on the patient support using the depth camera;
identifying landmark body positions of the patient from the image;
obtaining a patient depth map of an upper surface of the patient situated on the patient support using the depth camera;
mapping points in a region of interest to points of a template using the identified landmark body positions; and
determining a body thickness for the points in the region of interest using the template, a patient depth value for each respective point in the patient depth map, and a patient support depth value for each respective point in the patient support depth map.
2 . The method of claim 1 , wherein the template comprises a statistical model, the model comprising a function for each of the points enabling a mapping from a depth parameter to a thickness value based on historical measurements of patients on patient supports.
3 . The method of claim 2 , wherein a vertical center position is determined for each of the points as the patient depth value lowered by an anatomy specific ratio of the body thickness.
4 . The method of claim 3 , further comprising displaying an image derived from the patient depth map and the patient support depth map, each representing the body upper and lower surfaces.
5 . The method of claim 1 , wherein mapping points to points of the template comprises warping the depth map by fitting landmark body positions of the template to the identified landmark body positions.
6 . The method of claim 1 , wherein determining a body thickness for the points comprises using a statistical model defined by the template, the model comprising a function for each of the points which maps from a depth parameter to a thickness value.
7 . The method of claim 6 , wherein the statistical model implements a mapping between (i) a depth difference between the patient depth value and the patient support depth value at a point and (ii) the patient body thickness at the point.
8 . The method of claim 1 , comprising determining an overall vertical body center position from the body thickness for the points.
9 . The method of claim 8 , wherein determining the overall vertical body center position comprises obtaining an average body center position for all of the points or a weighted average body center position for all of the points.
10 . The method of claim 8 , wherein determining the overall vertical body center position comprises:
determining a slice center position for each of a set of parallel slices; and
obtaining the overall vertical body center position as the average slice center position for all slices.
11 . The method of claim 10 , wherein each slice is perpendicular to a body axis of the patient, and the average slice center position is taken for multiple slices in the body axis direction.
12 . The method of claim 1 , further comprising obtaining a volume of a region of interest of the patient using the body thickness for the points.
13 . A system for obtaining body depth information for a patient situated on patient support, comprising:
a depth camera configured to:
obtain a patient support depth map of an upper surface of the patient support without the patient;
obtain an image of the patient situated on the patient support;
obtain a patient depth map of the upper surface of the patient situated on the patient support;
at least one processor configured to:
identify landmark body positions of the patient from the image;
map points in a region of interest to points of a template using the identified landmark body positions; and
determine a body thickness for the points in the region of interest using the template, a patient depth value for each respective point in the patient depth map, and a patient support depth value for each respective point in the patient depth map.
14 . The system of claim 13 , wherein the at least one processor is further configured to derive a desired position of the patient support, and to control the position of the patient support to adopt the desired position.
15 . The system of claim 13 , further comprising a display for displaying an image representing the patient depth map, the patient support depth map and one or more estimated vertical center positions.