Reflective mode multi-spectral time-resolved optical imaging methods and apparatuses for tissue classification
Certain aspects relate to apparatuses and techniques for non-invasive optical imaging that acquires a plurality of images corresponding to both different times and different frequencies. Additionally, alternatives described herein are used with a variety of tissue classification applications, including assessing the presence and severity of tissue conditions, such as burns and other wounds.
1. A method of assessing burn severity comprising:
positioning a subject approximate to a light source and an image acquisition device;
illuminating a tissue region of the subject using the light source;
acquiring a plurality of images of the tissue region using the image acquisition device, a first subset of the plurality of images captured at different times and a second subset of the plurality of images captured at different frequency bands;
classifying a burn status of areas of the tissue region based at least in part on photoplethysmography (PPG) data derived from the first subset of the plurality of images acquired with the image acquisition device and on multispectral data derived from the second subset of the plurality of images;
generating a classified image based at least in part on the plurality of images and the burn status of the areas of the tissue region; and
segmenting individual pixels of the classified image among a plurality of tissue categories based at least in part on the burn status of the areas of the tissue region corresponding to the individual pixels.
2. The method of claim 1 , further comprising illuminating the tissue region with approximately uniform intensity from the light source.
3. The method of claim 1 , further comprising displaying the classified image of the tissue region, the classified image comprising a first representation of pixels classified as the excised skin and a different second representation of pixels classified as the burn.
4. The method of claim 1 , further comprising calculating an estimate of a degree of burn of at least one area of the tissue region.
5. The method of claim 1 , further comprising:
identifying a portion of the tissue region corresponding to healthy tissue and a portion of the tissue region corresponding to necrotic tissue; and
determining a margin for debridement at an interface between the healthy tissue and the necrotic tissue based on the plurality of images.
6. The method of claim 5 , further comprising debriding the tissue region within the margin for debridement.
7. The method of claim 1 , wherein the tissue region comprises approximately a total body surface area of the subject, the method further comprising calculating an estimate of a percentage of total burned body surface area of the subject based at least in part on the classifying the burn status.
8. The method of claim 7 , wherein the plurality of images depict a plurality of regions of the total body surface area of the subject, the method further comprising calculating the estimate of the percentage of the total burned body surface area of the subject based at least in part on classifying the burn status of the plurality of regions of the total body surface area of the subject.
9. The method of claim 8 , further comprising stitching together portions of the plurality of images depicting the plurality of regions of the subject based at least in part on performing a cross-correlation of the plurality of regions.
10. The method of claim 9 , wherein the stitching further comprises detecting an edge of a body section of the subject.
11. The method of claim 7 , wherein calculating the estimate of the percentage of total burned body surface area of the subject further comprises:
classifying areas corresponding to one or more of a first degree of burns, a second degree of burns, and a third degree of burns across the total body surface area of the subject; and
calculating the estimate of the percentage of the total burned body surface area of the subject at least in part by adding the areas corresponding to the first degree of burns, second degree of burns, and third degree of dividing the added areas by the total body surface area of the subject.
12. The method of claim 1 , wherein the classified image comprises pixels modified or processed to have different visual representations based on the burn status corresponding to the pixels.
13. The method of claim 1 , wherein the segmenting comprises using graph theory, thresholding, k-means clustering, hierarchical clustering, fuzzy clustering, watershed algorithms, edge detection, region growing, statistical grouping, shape recognition, morphological image processing, computer training, or histogram-based methods.
14. An apparatus for assessing burn severity of a subject comprising:
one or more light sources configured to illuminate a tissue region;
one or more image acquisition devices configured to receive light reflected from the tissue region; and
a processor configured to:
control the one or more light sources and the one or more image acquisition devices to acquire a plurality of images the tissue region, a first subset of the plurality of images captured at different times and a second subset of the plurality of images captured at different frequency bands;
classify a burn status of areas of the tissue region based on photoplethysmography (PPG) data derived from the first subset of the plurality of images and on multispectral data derived from the second subset of the plurality of images;
generate a classified image based at least in part on the plurality of images and the burn status of the areas of the tissue region; and
segment individual pixels of the classified image among a plurality of tissue categories based at least in part on the burn status of the areas of the tissue region corresponding to the individual pixels.
15. The apparatus of claim 14 , wherein the one or more light sources are configured to illuminate the tissue region with approximately uniform intensity.
16. The apparatus of claim 14 , further comprising a display, wherein the processor is configured to output the classified image to the display, the classified image comprising a first representation of pixels classified as the excised skin and a different second representation of pixels classified as the burn.
17. The apparatus of claim 14 , wherein the processor is configured to:
identify a portion of the tissue region corresponding to healthy tissue and a portion of the tissue region corresponding to necrotic tissue; and
determine a margin for debridement at an interface between the healthy tissue and the necrotic tissue based on the plurality of images.
18. The apparatus of claim 14 , wherein the tissue region comprises approximately a total body surface area of the subject, and wherein the processor is configured to calculate an estimate of a percentage of total burned body surface area of the subject based at least in part on the classified burn status.
19. The apparatus of claim 18 , wherein the plurality of images depict a plurality of regions of the total body surface area of the subject, and wherein the processor is configured to calculate the estimate of the percentage of the total burned body surface area of the subject based at least in part on classification of the burn status of the plurality of regions of the subject.
20. The apparatus of claim 19 , wherein the processor is configured to stitch together portions of the plurality of images depicting the plurality of regions of the subject based at least in part on performing a cross-correlation of the plurality of regions.
21. The apparatus of claim 20 , wherein, to stitch together the portions of the plurality of images, the processor is further configured to detect an edge of a body section of the subject.
22. The apparatus of claim 18 , wherein the processor is configured to:
classify areas corresponding to one or more of a first degree of burns, a second degree of burns, and a third degree of burns across the whole surface of the subject; and
estimate the percentage of the total burned body surface area of the subject based at least in part on adding the areas corresponding to the first degree of burns, second degree of burns, and third degree of and dividing the added areas by the total body surface area of the subject.
23. The apparatus of claim 14 , wherein the processor modifies or processes pixels of the classified image to have different visual representations based on the burn status corresponding to the pixels.
24. The apparatus of claim 14 , wherein the processor is configured to segment individual pixels of the classified image among a plurality of tissue categories based at least in part on the burn status corresponding to the pixel using graph theory, thresholding, k-means clustering, hierarchical clustering, fuzzy clustering, watershed algorithms, edge detection, region growing, statistical grouping, shape recognition, morphological image processing, computer training, or histogram-based methods.