Granted Patent B2

US 12,702,496 · App. 18/342,974 · Granted Aug 11, 2026

Inventors: Catherine M. Shachaf (Los Gatos, CA); Amit Shachaf (Los Gatos, CA); Kevin Manbeck (Los Gatos, CA)

Assignee: Orlucent, Inc.

A61B34/25A61B5/0035A61B5/0071A61B5/0077A61B5/444A61B5/7275G16H50/30A61B2034/107A61B2090/373

Abstract

Claims (33)

1 . A method for assessing tissue remodeling risk, comprising:

(a) collecting a plurality of images of a lesion located in a target region of a subject's skin, wherein the plurality of images comprises (1) a set of visible light images of the lesion and (2) a set of fluorescent images of the lesion, wherein a fluorescent marker is configured to provide fluorescence when bound to one or more biomarkers associated with tissue remodeling; and

(b) using at least one processor and a non-transitory computer readable storage medium encoded with a computer program:

(I) processing the plurality of images to determine an optimal image pair for the target region, wherein the optimal image pair comprises: (i) a visible light image selected from (1), and (ii) a fluorescent image selected from (2), wherein the optimal image pair is determined automatically using the at least one processor based on (i) a position of the lesion within each of the set of visible light images and each of the set of fluorescent images, (ii) a degree of similarity or correlation between each of the set of visible light images and each of the set of fluorescent images, and (iii) a focus quality of each of the set of visible light images and each of the set of fluorescent images, wherein the visible light image comprises a first set of visual characteristics, wherein the fluorescent image comprises a second set of visual characteristics, wherein at least a portion of the second set of visual characteristics is not visible in the first set of visual characteristics, and wherein at least a portion of the first set of visual characteristics is not visible in the second set of visual characteristics;

(II) segmenting the visible light image to identify a border of the lesion, wherein the segmenting of the visible light image comprises converting the visible light image into an intensity image;

(III) adding the border of the lesion identified from the visible light image to the fluorescent image based on a location of the fluorescent marker;

(IV) generating an assessment of the target region based at least on the optimal image pair, wherein the generating of the assessment of the target region comprises evaluating an aggregate score for the optimal image pair,

wherein the aggregate score comprises a visible score for the visible light image and a fluorescent score for the fluorescent image, wherein the visible score is based on a first set of metrics associated with the first set of visual characteristics in the visible light image, wherein the first set of metrics comprises one or more of the following: size, shape, volume, color, or surface texture of the lesion and its surrounding area, wherein the fluorescent score is based on a second set of metrics associated with the second set of visual characteristics in the fluorescent image, and wherein the second set of metrics comprises one or more of the following: size, shape, area or extent of tissue remodeling, pixel intensity, fluorescence intensity, patterns or texture in the target region beneath the subject's skin and surrounding the lesion,

wherein the visible score comprises one or more measures of asymmetry, border irregularity, color variegation, and diameter of the lesion based at least in part on the border of the lesion identified by the segmenting in (II), and

wherein the fluorescent score comprises one or more measures of intensity and texture of fluorescence in the fluorescent image based at least in part on the border of the lesion added to the fluorescent image in (III); and

(V) displaying on a graphical user interface the assessment, the optimal image pair, and a schematic showing a location of the target region on the subject's body, wherein the assessment of the target region is indicative of a probability of tissue remodeling at the target region.

2 . The method of claim 1 , wherein the lesion comprises a mole on the subject's skin.

3 . The method of claim 1 , wherein the visible light image and the fluorescent image are selected to be complementary or matching with each other.

4 . The method of claim 2 , wherein the first set of visual characteristics is associated with the mole and the skin of the subject, and wherein the second set of visual characteristics is associated with underlying tissue beneath the skin and surrounding the mole.

5 . The method of claim 1 , wherein the optimal image pair is a first optimal image pair, and wherein after (I) and prior to (IV) the method further comprises:

displaying an option on the graphical user interface to a user, wherein the option permits the user to accept or reject the first optimal image pair; and

receiving an input from the user in response to the option displayed on the graphical user interface.

6 . The method of claim 5 , further comprising:

processing the plurality of images to determine a second optimal image pair for the target region when the input is indicative of the user rejecting the first optimal image pair, wherein the second optimal image pair is different from the first optimal image pair.

7 . The method of claim 5 , comprising: continuing with (IV) and (V) when the input is indicative of the user accepting the first optimal image pair.

8 . The method of claim 5 , further comprising:

processing the plurality of images to determine a plurality of other optimal image pairs for the target region when the input is indicative of the user rejecting the first optimal image pair; and

displaying the plurality of other optimal image pairs on the graphical user interface.

9 . The method of claim 2 , wherein the probability of tissue remodeling is associated with a probability of development of melanoma in the mole, and wherein the assessment is useable to determine a clinical diagnosis or course of action based on the probability of development of melanoma in the mole.

10 . The method of claim 1 , wherein the segmenting of the visible light image is used to generate the first set of metrics.

11 . The method of claim 1 , wherein the visible light image and the fluorescent image are adjusted and aligned to a set of coordinates within the optimal image pair.

12 . The method of claim 1 , further comprising: comparing the optimal image pair to one or more reference images.

13 . The method of claim 12 , wherein the one or more reference images comprise a reference image pair.

14 . The method of claim 13 , wherein the reference image pair comprises (1) a visible light reference image that is not from the set of visible light images and (2) a fluorescent reference image that is not from the set of fluorescent images.

15 . The method of claim 13 , wherein the optimal image pair comprises fiducials, and wherein the reference image pair does not comprise fiducials.

16 . The method of claim 13 , wherein the optimal image pair comprises a first set of fiducials that are located at a predefined location and/or orientation relative to the lesion, and wherein the reference image pair comprises a set of fiducials that are located near a boundary of each reference image within the reference image pair.

17 . The method of claim 1 , wherein the generating of the assessment of the probability of tissue remodeling is performed automatically by the at least one processor.

18 . The method of claim 1 , further comprising segmenting the fluorescent image, wherein the segmenting of the fluorescent image is used to generate the second set of metrics, and wherein the segmenting of the fluorescent image comprises segmenting the fluorescent image into a plurality of zones surrounding the target region.

Assignments (1)

Continuity (3)

References Cited (149)