US 12,322,512 B2
Using a set of machine learning diagnostic models to determine a diagnosis based on a skin tone of a patient
Elliot Swart, Phoeniz, AZ (US); Elektra Efstratiou Alivisatos, Cambridge, MA (US); Joseph Ferrante, Cambridge, MA (US); and Elizabeth Asai, Boston, MA (US)
Assigned to Digital Diagnostics Inc, Coralville, IA (US)
Filed by Digital Diagnostics Inc., Coralville, IA (US)
Filed on May 13, 2024, as Appl. No. 18/662,798.
Application 18/662,798 is a continuation of application No. 17/619,173, granted, now 12,014,828, previously published as PCT/US2020/037765, filed on Jun. 15, 2020.
Claims priority of provisional application 62/862,844, filed on Jun. 18, 2019.
Prior Publication US 2024/0296956 A1, Sep. 5, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/90 (2017.01); A61B 5/00 (2006.01); A61B 5/103 (2006.01); G06T 7/00 (2017.01); G06V 10/56 (2022.01); G06V 10/72 (2022.01); G06V 10/764 (2022.01); G06V 40/10 (2022.01); G16H 50/20 (2018.01)
CPC G16H 50/20 (2018.01) [A61B 5/1032 (2013.01); A61B 5/441 (2013.01); A61B 5/7267 (2013.01); A61B 5/7275 (2013.01); G06T 7/0014 (2013.01); G06T 7/90 (2017.01); G06V 10/56 (2022.01); G06V 10/72 (2022.01); G06V 10/764 (2022.01); G06V 40/10 (2022.01); A61B 2576/02 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30088 (2013.01); G06T 2207/30168 (2013.01); G06V 2201/03 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A method for determining a diagnosis based on a base skin tone of a patient, the method comprising:
determining a base skin tone of a patient by:
generating a calibrated base skin tone image using an image of the patient and a reference calibration profile;
determining a numerical representation of each pixel of the calibrated base skin tone image;
generating an aggregate representation by performing a statistical operation based on the numerical representation of each pixel;
identifying a point in a color space corresponding to the aggregate representation; and
mapping the point in the color space into a discrete value in a classification system;
receiving a concern image of a portion of the patient's skin;
inputting at least the concern image into at least one machine learning model; and
receiving, as output from the at least one machine learning model, information from which the diagnosis is derived, wherein the diagnosis is at least partially derived based on the base skin tone, wherein determining the diagnosis further comprises:
modifying the information from which the diagnosis is derived based on the base skin tone; and
determining the diagnosis based on the modified information.