ASSESSING PERIPHERAL VASCULAR DISEASE FROM A THERMAL IMAGE

• US 20150206301A1
• Filed: 01/22/2014
• Published: 07/23/2015
• Est. Priority Date: 01/22/2014
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: MESTHA, Lalit Keshav, XU, Beilei
• Granted Patent: US 9,256,937 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01J 2005/0077 Imaging
• CPC Class Codes: G01J 5/0025 Living bodies ear thermometers G01J5/0011; detecting, measuring or recording for diagnostic purposes A61B5/00
• CPC Class Codes: G01J 5/08 Optical arrangements
• CPC Class Codes: G01J 5/10 using electric radiation detectors
• CPC Class Codes: G01J 5/485 Temperature profile
• CPC Class Codes: G01J 5/60 using determination of colour temperature
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30088 Skin; Dermal
• CPC Class Codes: G06T 2207/30104 Vascular flow; Blood flow; Perfusion
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

What is disclosed is a system and method for assessing peripheral vascular disease from a thermal image captured using a thermal imaging system. In one embodiment the present method involves the following. First, a thermal image is received of a region of exposed skin of a peripheral body part of a subject being monitored for PVD. The thermal image was acquired by a thermal imaging system. Pixels in the thermal image each have a corresponding temperature value. The thermal image is analyzed to stratify the peripheral body part into a plurality of skin surface regions. A skin surface temperature for each respective skin surface region is identified based on pixels in the thermal image associated with those regions. The temperatures are then extracted such that a progression of temperatures can be ascertained. A method for forecasting the progression for future times is also disclosed.

Claims

1. A method for assessing peripheral vascular disease from a thermal image, the method comprising:

receiving a thermal image of an area of exposed skin of at least one peripheral body part of a subject of interest being monitored for peripheral vascular disease, said thermal image being acquired by a thermal imaging system, said thermal image comprising a plurality of pixels, the value of each pixel corresponding to a skin surface temperature;

analyzing said thermal image to stratify said at least one peripheral body part into a plurality of skin surface regions;

identifying skin surface temperatures for each respective skin surface region based on pixels in said thermal image associated with each region;

determining, based on temperature changes of said at least one said surface region of said peripheral body part, whether said subject has peripheral vascular disease.

2. The method of claim 1, wherein said peripheral body part is any of:

arm, leg, hand, foot, fingers, and toes.

3. The method of claim 1, wherein said determining temperature changes of at least one surface region of said peripheral body part comprises any of:

exceeding a threshold of the average temperature from another similar said surface region, exceeding a threshold of high-order statistics of temperature from another similar surface region, a comparison of temperatures between said peripheral body part and a second similar peripheral body part of said subject, a comparison of temperatures retrieved from a database, a comparison of temperatures of a similar peripheral body part obtained at a different time, and any combinations hereof.

4. The method of claim 3, wherein said threshold is calculated based on any of;

a histogram of temperature distributions of said skin surface regions, and a color difference of said thermal image of said skin surface region.

5. The method of claim 1, wherein said thermal imaging system is any of:

a single-band infrared camera, a multi-band infrared camera in the thermal range, and a hyperspectral infrared camera in the thermal range.

6. The method of claim 1, further comprising:

analyzing said thermal image to stratify a second peripheral body part into a plurality of skin surface regions;

identifying skin surface temperatures for each skin surface region of said similar second peripheral body part based on pixels in said thermal image associated with each respective region to obtain temperature differentials across said stratified skin surface regions;

comparing said temperature differentials of said first and second peripheral body parts; and

determining, as a result of said comparison, whether a subject has peripheral vascular disease.

7. The method of claim 1, wherein identifying said skin surface temperatures based on pixels in said thermal image comprising any of:

averaging pixel values over at least a portion of said skin surface region; and

weighted averaging said pixels over at least a portion of said skin surface region.

8. The method of claim 1, wherein thermal images are acquired of said subject'"'"'s peripheral body part at different times to assess a progression of peripheral vascular disease over time using a predictive model.

9. The method of claim 8, wherein said predictive model is any of:

an autoregressive model, a recursive least square model, and a dynamic state space model.

10. The method of claim 1, wherein determining whether said subject has peripheral vascular disease further comprises:

retrieving, from a database, temperatures of a peripheral body part; and

comparing said retrieved temperature values to said subject'"'"'s temperature values from a reference thermal image.

11. The method of claim 10, wherein said retrieved temperatures are associated with a peripheral body part of another subject.

12. The method of claim 1, wherein, in advance of analyzing said thermal image, further comprising processing said thermal image to isolate pixels associated with said area of exposed skin.

13. A system for assessing peripheral vascular disease from a thermal image, the system comprising:

a memory and a storage device; and

a processor in communication with said memory and storage device, said processor executing machine readable instructions for performing;

receiving a thermal image of an area of exposed skin of at least one peripheral body part of a subject of interest being monitored for peripheral vascular disease, said thermal image being acquired by a thermal imaging system, said thermal image comprising a plurality of pixels, the value of each pixel corresponding to a skin surface temperature;

analyzing said thermal image to stratify said at least one peripheral body part into a plurality of skin surface regions;

identifying skin surface temperatures for each respective skin surface region based on pixels in said thermal image associated with each region;

determining, based on temperature changes of at least one of said surface regions of said peripheral body part, whether said subject has peripheral vascular disease.

14. The system of claim 13, wherein said peripheral body part is any of:

arm, leg, hand, foot, fingers, and toes.

15. The system of claim 13, wherein said determining temperature changes of at least one surface region of said peripheral body part comprises any of:

exceeding a threshold of the average temperature from another similar said surface region, exceeding a threshold of high-order statistics of temperature from another similar surface region, a comparison of temperatures between said peripheral body part and a second similar peripheral body part of said subject, a comparison of temperatures retrieved from a database, a comparison of temperatures of a similar peripheral body part obtained at a different time, and any combinations hereof.

16. The system of claim 15, wherein said threshold is calculated based on any of;

a histogram of temperature distributions of said skin surface regions, and a color difference of said thermal image of said skin surface region.

17. The system of claim 13, wherein said thermal imaging system is any of:

a single-band infrared camera, a multi-band infrared camera in the thermal range, and a hyperspectral infrared camera in the thermal range.

18. The system of claim 13, further comprising:

analyzing said thermal image to stratify a second peripheral body part into a plurality of skin surface regions;

identifying skin surface temperatures for each skin surface region of said similar second peripheral body part based on pixels in said thermal image associated with each respective region to obtain temperature differentials across said stratified skin surface regions;

comparing said temperature differentials of said first and second peripheral body parts; and

determining, as a result of said comparison, whether a subject has peripheral vascular disease.

19. The system of claim 13, wherein identifying said skin surface temperatures based on pixels in said thermal image comprising any of:

averaging pixel values over at least a portion of said skin surface region; and

weighted averaging said pixels over at least a portion of said skin surface region.

20. The system of claim 13, wherein thermal images are acquired of said subject'"'"'s peripheral body part at different times to assess a progression of peripheral vascular disease over time using a predictive model.

21. The system of claim 20, wherein said predictive model is any of:

an autoregressive model, a recursive least square model, and a dynamic state space model.

22. The system of claim 13, wherein determining whether said subject has peripheral vascular disease further comprises:

retrieving, from a database, temperatures of a peripheral body part; and

comparing said retrieved temperature values to said subject'"'"'s temperature values from a reference thermal image.

23. The system of claim 22, wherein said retrieved temperatures are associated with a peripheral body part of another subject.

24. The system of claim 13, wherein, in advance of analyzing said thermal image, further comprising processing said thermal image to isolate pixels associated with said area of exposed skin.

25. The system of claim 13, further comprising:

storing said subject'"'"'s temperature values in a patient record; and

saving said patient record to a historical database.