US 11,972,572 B2
Intraoral scanning system with excess material removal based on machine learning
Mikhail Minchenkov, Zhukovsky (RU); Ran Katz, Hod Hasharon (IL); Pavel Agniashvili, Moscow (RU); Chad Clayton Brown, Cary, NC (US); and Jonathan Coslovsky, Rehovot (IL)
Assigned to Align Technology, Inc., San Jose, CA (US)
Filed by Align Technology, Inc., San Jose, CA (US)
Filed on Jan. 20, 2022, as Appl. No. 17/580,554.
Application 17/580,554 is a continuation of application No. 16/865,162, filed on May 1, 2020, granted, now 11,238,586.
Claims priority of provisional application 62/933,902, filed on Nov. 11, 2019.
Claims priority of provisional application 62/868,777, filed on Jun. 28, 2019.
Claims priority of provisional application 62/842,425, filed on May 2, 2019.
Prior Publication US 2022/0148173 A1, May 12, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 15/00 (2011.01); A61C 9/00 (2006.01); A61C 13/34 (2006.01); G06F 18/2431 (2023.01); G06N 3/044 (2023.01); G06N 3/08 (2023.01); G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 17/00 (2006.01); G06T 19/20 (2011.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01); G06V 20/64 (2022.01)
CPC G06T 7/11 (2017.01) [A61C 9/0053 (2013.01); A61C 13/34 (2013.01); G06F 18/2431 (2023.01); G06N 3/044 (2023.01); G06N 3/08 (2013.01); G06T 7/0012 (2013.01); G06T 17/00 (2013.01); G06T 19/20 (2013.01); G06V 10/454 (2022.01); G06V 10/82 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/10048 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30036 (2013.01); G06T 2207/30052 (2013.01); G06T 2210/41 (2013.01); G06T 2219/008 (2013.01); G06T 2219/2021 (2013.01); G06V 20/653 (2022.01); G06V 2201/03 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
an intraoral scanner to generate a plurality of intraoral scans of a dental site; and
a computing device comprising a processor and a memory, the computing device to:
receive the plurality of intraoral scans of the dental site;
perform the following operations for each intraoral scan of the plurality of intraoral scans:
process an input comprising data from the intraoral scan using a trained machine learning model that has been trained to classify regions of dental sites, wherein the trained machine learning model generates an output comprising, for each point in the intraoral scan, an indication as to whether the point belongs to a first dental class or a second dental class;
determine, based on the output, one or more first points in the intraoral scan that are classified as belonging to the first dental class and one or more second points in the intraoral scan that are classified as belonging to the second dental class; and
modify the intraoral scan to hide or remove data for the one or more first points that are classified as belonging to the first dental class; and
generate a virtual three-dimensional (3D) model of at least a portion of the dental site based on stitching together modified versions of the plurality of intraoral scans in which the data for the one or more first points classified as belonging to the first dental class has been hidden or removed, wherein the stitching is performed using the one or more second points classified as belonging to the second dental class and without using the one or more first points classified as belonging to the first dental class, and wherein the virtual 3D model lacks the one or more first points classified as belonging to the first dental class.