System and method for using three dimensional infrared imaging for libraries of standardized medical imagery

• US 8,811,692 B2
• Filed: 04/15/2008
• Issued: 08/19/2014
• Est. Priority Date: 04/17/2007
• Status: Expired due to Fees

• Current Assignee: Francine J. Prokoski
• Original Assignee: Francine J. Prokoski
• Inventors: Prokoski, Francine J.
• Primary Examiner(s): Fuelling, Michael
• Application Number:
  US12/596,634
• Publication Number:
  US 20100191541A1
• Time in Patent Office: 2,317 Days
• Field of Search: 705/2
• US Class Current: 382/128
• CPC Class Codes: A61B 5/0064 Body surface scanning
• CPC Class Codes: A61B 5/0086 using infrared radiation
• CPC Class Codes: A61B 5/015 By temperature mapping of body part
• CPC Class Codes: A61B 5/1077 Measuring of profiles
• CPC Class Codes: A61B 5/411 Detecting or monitoring allergy or intolerance reactions to an allergenic agent or substance
• CPC Class Codes: A61B 5/415 the glands, e.g. tonsils, adenoids or thymus
• CPC Class Codes: A61B 5/418 lymph vessels, ducts or nodes
• CPC Class Codes: A61B 5/4519 Muscles A61B5/389, A61B5/224 take precedence
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G01K 13/20 Clinical contact thermometers for use with humans or animals
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

Calibrated infrared and range imaging sensors are used to produce a true-metric three-dimensional (3D) surface model of any body region within the fields of view of both sensors. Curvilinear surface features in both modalities are caused by internal and external anatomical elements. They are extracted to form 3D Feature Maps that are projected onto the skin surface. Skeletonized Feature Maps define subpixel intersections that serve as anatomical landmarks to aggregate multiple images for models of larger regions of the body, and to transform images into precise standard poses. Features are classified by origin, location, and characteristics to produce annotations that are recorded with the images and feature maps in reference image libraries. The system provides an enabling technology for searchable medical image libraries.

Claims

1. A method for establishing a searchable library of human images using a computerized system, comprising:

generating with a primary mode of medical imaging a three dimensional (3D) mesh of a whole body model linked to anatomical landmarks that can be seen in imagery produced by a plurality of medical imaging modes, each mode having a different type of imaging sensor, the 3D segment mesh serving as a reference and causing minimal interference with said plurality of imaging modes performed simultaneously, said 3D reference mesh enabling comparison of images of different 3D orientation;

calibrating by the computerized system a geometry of a primary mode sensor in order to standardize images for automated comparison, including images generated by said plurality of imaging modes, said imaging modes comprising different types of sensors, ranges of sensitivity, and resolution;

applying by the computerized system standards for acceptable image quality from said plurality of imagers;

applying by the computerized system standards for metadata accompanying transmission or storage of said images;

providing access control provisions for transmission and storage of the images;

applying by the computerized system procedures for detecting and correcting errors in the images; and

storing standardized images in the library.

2. A method as in claim 1, wherein the calibrating step further comprises:

specifying a body-centric coordinate system;

identifying a defined axis for each anatomical division of the body, the anatomical divisions including regions, sub-regions, and body segments within a region;

determining three specified landmark points in each division used for standardization, the three landmark points for each segment defining a facet;

combining facets to form a faceted 3D model; and

replacing facet edges by transition curves to form a three dimensional (3D) model.

3. A method as in claim 1, wherein storing standardized images in the library further comprises processing the images in accordance with the standards for acceptable quality and for metadata.

4. A method as in claim 2, further comprising automatic standardization through contemporaneous use of three dimensional infrared imaging (3D/IR).

5. A method as in claim 4, further comprising:

extracting feature maps from the 3D/IR images;

establishing a directory of reference points for each division of the body;

using three designated reference points to standardize a pose for each image; and

storing standardized images in a database along with the metadata for each.

6. A method for standardizing medical images such that the subject appears in a standard pose, comprising:

simultaneously capturing images of the subject from thermal infrared, range, and a medical imaging sensor;

producing a 3D/IR image through intrinsic and extrinsic calibration of the range and infrared sensors;

extracting anatomical curvilinear line segment features from the three dimensional thermal images by performing locally adaptive filtering to enhance visualization of internal and external anatomical structures including blood vessels and skin folds;

selecting three or more landmark points either manually or automatically where the anatomical landmark points to be selected are specified for the body part being imaged;

transforming the 3D/IR image into a standard pose specified for the area of the body imaged by transforming the plane determined by the three selected points into an orientation and position specified for that standard pose; and

transforming the medical sensor image into standard pose by overlaying the medical sensor image on the 3D/IR image through intrinsic and extrinsic calibration of the IR and medical sensors.

7. The method of claim 6, wherein the medical image sensor is an IR sensor.

8. The method of claim 6, further comprising differentiating internal and external features in infrared images by the further steps of:

extracting curvilinear line segment features from range and thermal image layers in a body map;

determining which features appear in both layers;

designating features that appear in both thermal and range images as external features; and

designating features that appear in the thermal but not in the range images as internal features.

9. The method of claim 6, further comprising differentiating veins from arteries in infrared images by the further steps of:

determining whether temperature is monotonically varying along the feature;

determining direction of apparent thermal flow in accordance with said monotonic temperature variation;

determining temporal rate of temperature variation at any point along the feature;

determining pulse rate; and

estimating changes in internal depth from changes in detected feature width and temperature using standard vascular model for the area of the body, or from any prior designation of veins, arteries, and nerves in images of a specified patient.