公开(公告)号：US20230255728A1

公开(公告)日：2023-08-17

申请号：US18306530

申请日：2023-04-25

Applicant: Align Technology, Inc.

Inventor： Yuxiang Wang ,  Andrew Jang ,  Bruce Cam ,  Rohit Tanugula ,  Chunhua Li ,  Jun Sato ,  Luyao Cai ,  Pavel Pokotilov ,  Kangning Su ,  John Y. Morton

IPC: A61C7/00 ,  A61C7/08

CPC classification number: A61C7/002 ,  A61C7/08

Abstract: Methods for designing orthodontic appliances are provided. In some embodiments, a method includes receiving a treatment plan for a patient's dentition and generating an aligner model representing an aligner configured to implement a treatment stage of the treatment plan. The aligner model can include a thickness map having a thickness parameter for each location of the aligner model. The method can include adjusting the thickness map by using the aligner model to evaluate an outcome when the aligner is applied to the patient's dentition, and iteratively reducing the value of each thickness parameter of the thickness map based on the evaluation until a resulting thickness is determined for each thickness parameter. The method can also include providing instructions to manufacture the aligner based on the aligner model with the resulting thickness for each thickness parameter of the thickness map.

公开(公告)号：US11589955B2

公开(公告)日：2023-02-28

申请号：US16584794

申请日：2019-09-26

Applicant: Align Technology, Inc.

Inventor： Viktoria Medvinskaya ,  Arno Kukk ,  Andrey Cherkas ,  Anna Akopova ,  Yuxiang Wang ,  Rohit Tanugula ,  Reza Shirazi Aghjari ,  Andrew Jang ,  Chunhua Li ,  Jun Sato ,  Luyao Cai

IPC: A61C7/00 ,  G06F17/18 ,  G06N20/00 ,  A61C7/08 ,  G06F30/23 ,  G16H50/50 ,  G01N33/44 ,  B33Y80/00 ,  A61C9/00 ,  A61C13/34 ,  B29C33/38 ,  B29C51/30 ,  G06F30/27 ,  B29C73/00 ,  G06F30/20 ,  G06F119/18 ,  G06F113/22 ,  G06F111/10 ,  B33Y50/00 ,  B29L31/00

Abstract: Embodiments relate to an aligner breakage solution that tests damage to an aligner using machine learning. A method includes processing data from a digital design for an orthodontic aligner by a trained machine learning model and outputting, by the trained machine learning model, a probability that the orthodontic aligner associated with the digital design will be damaged during manufacturing of the orthodontic aligner. The method further includes making a comparison of the probability that the orthodontic aligner associated with the digital design will be damaged during manufacturing of the orthodontic aligner to a probability threshold and determining whether the orthodontic aligner is a high risk orthodontic aligner based on a result of the comparison. Responsive to determining that the orthodontic aligner is a high risk orthodontic aligner, the method includes performing at least one of a) a corrective action or b) selecting a manufacturing flow for high risk orthodontic aligners.