US 11,869,182 B2
Systems and methods for segmentation and measurement of a skin abnormality
Chris Kane, Oxford (GB); Leonardo Rubio Navarro, Oxford (GB); Adeala Zabair, Oxford (GB); Anna Chabokdast, Oxford (GB); and James Klatzow, Oxford (GB)
Assigned to Fuel 3D Technologies Limited, Oxford (GB)
Appl. No. 17/252,217
Filed by Fuel 3D Technologies Limited, Oxford (GB)
PCT Filed Jun. 14, 2019, PCT No. PCT/GB2019/051657
§ 371(c)(1), (2) Date Dec. 14, 2020,
PCT Pub. No. WO2019/239147, PCT Pub. Date Dec. 19, 2019.
Claims priority of application No. 1809768 (GB), filed on Jun. 14, 2018; and application No. 1818241 (GB), filed on Nov. 8, 2018.
Prior Publication US 2021/0366108 A1, Nov. 25, 2021
Int. Cl. G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 7/12 (2017.01); G06T 7/174 (2017.01); G06T 7/187 (2017.01); G06T 7/64 (2017.01); G06T 7/62 (2017.01); G06T 7/50 (2017.01); A61B 5/00 (2006.01); G06T 3/40 (2006.01); G06T 7/40 (2017.01); G06T 19/20 (2011.01); G06F 18/2431 (2023.01)
CPC G06T 7/0012 (2013.01) [A61B 5/004 (2013.01); A61B 5/444 (2013.01); A61B 5/7264 (2013.01); G06F 18/2431 (2023.01); G06T 3/40 (2013.01); G06T 7/11 (2017.01); G06T 7/12 (2017.01); G06T 7/187 (2017.01); G06T 7/40 (2013.01); G06T 7/50 (2017.01); G06T 7/62 (2017.01); G06T 7/64 (2017.01); G06T 19/20 (2013.01); A61B 2503/40 (2013.01); G06T 7/174 (2017.01); G06T 2207/10048 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30088 (2013.01); G06T 2207/30096 (2013.01); G06T 2219/2021 (2013.01); G06V 2201/03 (2022.01); G06V 2201/032 (2022.01)] 14 Claims
OG exemplary drawing
 
1. A method of identifying at least one portion of the skin of an animal which is a region of interest, the method comprising:
receiving a temperature dataset indicating the temperature of each of a plurality of points on the skin of the animal;
using the temperature dataset to obtain an initial segmentation of the skin which classifies the skin into at least one portion of the skin which is part of the region of interest and at least one portion which is not part of the region of interest, and
using a three dimensional model of the profile of the skin to enhance the initial segmentation by identifying at least one area of the initial segmentation which incorrectly classifies skin as part of the region of interest, and correcting the identified incorrect classification.