System and method for segmentation and automated measurement of chronic wound images

Patent metadata

Field	Value
Publication number	US-10504624-B2
Application number	US-201815949657-A
Country	US
Kind code	B2
Filing date	Apr 10, 2018
Priority date	Mar 23, 2015
Publication date	Dec 10, 2019
Grant date	Dec 10, 2019

Abstract

Disclosed are systems and methods for automated monitoring of the size, area or boundary of chronic wound images. The disclosure includes use of a probability map that measures the likelihood of wound pixels belonging to granulation, slough or eschar, which can then be segmented using any standard segmentation techniques. Measurement of the wound size, area or boundary occurs automatically and without user input related to outlining, filling in, or making measurement lines over the image on a display.

First claim

The invention claimed is:

1. A method for segmentation and automated measurement of chronic wound images using a smartphone, said method comprising:
obtaining a digital image of a wound using a camera of the smartphone;
automatically determining from the digital image of the wound a boundary of the wound using a processor of the smartphone;
automatically determining an area of the wound from the boundary of the wound using the processor of the smartphone by segmenting pixels of the digital image as belonging to the wound or not being associated with the wound;
automatically transforming each of the one or more pixels segmented as belonging to the wound to a modified Hue-Saturation-Value (HSV) color space; and
automatically classifying each of the one or more pixels segmented as belonging to the wound and transformed to the HSV color space as belonging to one of a tissue group comprised of granulation, slough or eschar tissue based on a distance of each of the one or more pixels segmented and transformed to red, yellow, black and white colors in the modified HSV color space using the processor of the smartphone.

2. The method of claim 1 , further comprising automatically determining by the processor of the smartphone an area of at least one of the tissue groups that comprise the wound.

3. The method of claim 2 , further comprising monitoring wound healing by comparing by the processor of the smartphone at least one of the area of the wound or the area of the at least one of the one or more tissue groups that comprise the wound to previously measured area of the wound or previously measured area of the at least one of the one or more tissue groups that comprise the wound to determine if the wound or the tissue group is changing in area.

4. The method of claim 1 , wherein automatically determining the area of the wound using the processor of the smartphone comprises determining a pixel size for at least the one or more pixels of the digital image that are segmented as belonging to the wound.

5. The method of claim 4 , wherein the pixel size is determined by placing an object of a known size proximate to the wound prior to capturing the digital image of the wound using the camera of the smartphone.

6. The method of claim 5 , wherein determining the pixel size comprises the processor of the smartphone:
detecting the object in the digital image using one or more image analysis algorithms;
measuring a number of pixels that span a given detected edge of the object having the known size; and
determining the pixel size by dividing the known size of the given detected edge by the number of pixels that span the given detected edge of the object.

7. The method of claim 1 , wherein each of the one or more pixels segmented as belonging to the wound are transformed to the modified HSV color space by scaling Saturation (S) and Value (V) components of a HSV color space by:

S
mod

=

log
⁡

(

α
*
S

+
1

)

log
⁡

(

a
+
1

)

⁢

⁢
and

V
mod

=

log
⁡

(

α
*
V

+
1

)

log
⁡

(

a
+
1

)

,

where S mod and V mod are modified Saturation and modified Value of the modified HSV color space, respectively, and a is a constant.

8. The method of claim 1 , wherein each of the one or more pixels segmented as belonging to the wound having the highest probability of being red are classified using the processor of the smartphone as granulation tissue, pixels having the highest probability of being yellow are classified using the processor of the smartphone as slough tissue, and pixels having the highest probability of being black are classified using the processor of the smartphone as eschar tissue.

9. The method of claim 1 , wherein each of the one or more pixels segmented as belonging to the wound having the highest probability of being white are classified using the processor of the smartphone as epibole tissue, normal skin or an object of a known size in the digital image used to determine pixel size.

10. The method of claim 1 , wherein at least some of the one or more pixels segmented as belonging to the wound are further identified as granulation, slough or eschar tissue based on a region-growing algorithm or an optimal thresholding algorithm using the processor of the smartphone.

11. The method of claim 1 , further comprising the processor of the smartphone determining the boundary of the wound as an ordered vector of pixel coordinates.

12. The method of claim 11 , wherein the boundary of the wound is displayed on a display of the smartphone as an overlay on the digital image with a color that's distinguishable from both the wound and surrounding tissue.

13. The method of claim 1 , wherein determining the area of a wound comprises the processor of the smartphone:
determining a maximum distance between two boundary pixel values;
reporting the maximum distance as a length of the wound;
determining a perpendicular maximum distance between two boundary pixels, wherein the perpendicular maximum distance is a maximum distance between two boundary pixels such that a straight line drawn between the two boundary pixels that form the perpendicular maximum distance would be perpendicular to a straight line drawn between the two boundary pixels that form the length of the wound;
reporting the perpendicular maximum distance as a width of the wound;
calculating pixel values of pixels that belong to the wound that are within the boundary of the wound; and
reporting the total pixel values within the wound boundary as the area of the wound.

14. The method of claim 1 , further comprising filtering false positive regions from the digital image.

15. A system for segmentation and au

Assignees

• Ohio State Innovation Foundation

Inventors

• Gurcan Metin N
• Sen Chandan K
• Gordillo Gayle

Classifications

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G16H30/20

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title

• G06F18/2433

  Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection · CPC title

• G06T2207/20076

  Probabilistic image processing · CPC title

• G06T2207/30088

  Skin; Dermal · CPC title