Scan data retrieval with depth sensor data
In scan data retrieval, a mesh is fit ( 32 ) to surface data of a current patient, such as data from an optical or depth sensor ( 18 ). Meshes are also fit ( 48 ) to medical scan data, such as fitting ( 48 ) to skin surface segments of computed tomography data. The meshes or parameters derived from the meshes may be more efficiently compared ( 34 ) to identify ( 36 ) a previous patient with similar body shape and/or size. The scan configuration ( 38 ) for that patient, or that patient as altered to account for differences from the current patient, is used. In some embodiments, the parameter vector used for searching ( 34 ) includes principle component analysis coefficients. In further embodiments, the principle component analysis coefficients may be projected to a more discriminative space using metric learning.
1. A method for scan data retrieval, the method comprising:
measuring depths relative to a surface of a patient with a depth sensor;
fitting a first mesh to the depths;
searching for a second mesh in a database of meshes fit to medical scan data from different patients, the searching based on a similarity of values of parameters of the first mesh and values of parameters of the meshes in the database; and
configuring a medical scanner to scan the patient, the configuring being based, at least in part, on scan parameters derived from one of the different patients corresponding to the second mesh.
2. The method of claim 1 , wherein the measuring the depths comprises measuring with an optical depth camera while the patient is on a bed of the medical scanner.
3. The method of claim 1 , wherein the fitting of the first mesh to the depths comprises fitting the first mesh as a parameterized deformable model.
4. The method of claim 1 , wherein the fitting of the first mesh to the depths comprises:
detecting a plurality of landmarks represented in the depths relative to the surface of the patient;
deforming a template mesh to the plurality of landmarks; and
fitting the template mesh as deformed to the depths.
5. The method of claim 1 , wherein the meshes fit to the medical scan data comprise meshes fit to computed tomography data representing a skin of the different patients.
6. The method of claim 1 , wherein the meshes fit to the medical scan data comprise meshes fit with a parameterized deformable model.
7. The method of claim 1 , wherein the searching comprises comparing the values of the parameters representing the first mesh with the values of the parameters representing the meshes fit to the medical scan data from the different patients.
8. The method of claim 7 , wherein the searching comprises comparing measures of patient shape as the scan parameters.
9. The method of claim 7 , wherein the searching comprises comparing principle component analysis coefficients as the scan parameters.
10. The method of claim 7 , wherein the comparing the values of the parameters representing the first mesh with the values of the parameters representing the meshes fit to the medical scan from the different patients comprises projecting the values of both the parameters to a metric space and comparing in the metric space.
11. The method of claim 1 , wherein the configuring comprises configuring a scan range, an iso center, or a scan range and an iso center for the patient.
12. The method of claim 1 , further comprising:
deforming a volume for the medical scan data of the one of the different patients based on the first mesh; and
generating a topogram from the deformed volume;
wherein the configuring comprises configuring based on the topogram.