US 11,832,958 B2
Automatic image-based skin diagnostics using deep learning
Ruowei Jiang, Toronto (CA); Junwei Ma, Toronto (CA); He Ma, North York (CA); Eric Elmoznino, Toronto (CA); Irina Kezele, Toronto (CA); Alex Levinshtein, Thornhill (CA); Julien Despois, Paris (FR); Matthieu Perrot, Orsay (FR); Frederic Antoinin Raymond Serge Flament, Paris (FR); and Parham Aarabi, Richmond Hill (CA)
Assigned to L'OREAL, Paris (FR)
Filed by L'OREAL, Paris (FR)
Filed on Dec. 13, 2022, as Appl. No. 18/080,331.
Application 18/080,331 is a continuation of application No. 16/702,895, filed on Dec. 4, 2019, granted, now 11,553,872.
Claims priority of provisional application 62/775,117, filed on Dec. 4, 2018.
Prior Publication US 2023/0123037 A1, Apr. 20, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 5/00 (2006.01); G06T 7/00 (2017.01); G06V 40/16 (2022.01); G06N 3/08 (2023.01); G06V 10/82 (2022.01); G06N 3/045 (2023.01); G06V 10/44 (2022.01); G06V 40/18 (2022.01)
CPC A61B 5/441 (2013.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/0012 (2013.01); G06V 10/454 (2022.01); G06V 10/82 (2022.01); G06V 40/171 (2022.01); G06T 2207/30088 (2013.01); G06V 40/174 (2022.01); G06V 40/18 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A skin diagnostic device comprising:
a memory configured to store and provide a convolutional neural network (CNN) configured to classify pixels of an image to determine a plurality (N) of respective skin sign diagnoses for each of a plurality (N) of respective skin signs wherein the CNN comprises a deep neural network for image classification configured to generate the N respective skin sign diagnoses and wherein the CNN is trained using skin sign data for each of the N respective skin signs; and
at least one processor coupled to the memory and configured to receive the image and process the image using the CNN to generate the N respective skin sign diagnoses,
wherein the CNN comprises:
an encoder phase for image classification and configured to encode features to a final encoder phase feature net; and
a decoder phase configured to receive the final encoder phase feature net for decoding by a plurality (N) of respective parallel skin sign branches to generate each of the N respective skin sign diagnoses.