Align Technology, Inc.

Ivan Potapenko

Sergey Grebenkin

Alexander Vovchenko

Dmitry Guskov

Roman Gudchenko

Vasily Paraketsov

Roman Solovyev

Dmitrii Ischeykin

Mikhail Gorodilov

Denis Durdin

Roman A Roschin

Evgenii Vladimirovich Karnygin

Alexander Beliaev

Alexey Vladykin

Elizaveta Ulianenko

Nikolay Zhirnov

Anzhelika Son

Leonid Trofimov

Christopher Eric Cramer

Aleksandr Sergeevich Karsakov

Aleksandr Anikin

Mikhail Toporkov

Anton Baskanov

Provided herein are systems and methods for determining if a 3D tooth model requires trimming or removal of incomplete or missing data (e.g., gingiva covering a portion of a tooth such as a molar). A patient's dentition may be scanned and/or segmented. During dentition segmentation, a determination can be made whether trimming portions of the 3D model is desirable. A recommendation can be made for 3D model trimming based on the determination.

Molar trimming prediction and validation using machine learning

A method for determining tooth numbers of teeth within a dental arch includes receiving a digital scan of a patient's dentition, detecting a cusp associated with at least one tooth in the digital scan, where the cusp is detected based at least in part on a radius of a surface of the cusp, matching a molar shape of the at least one tooth, and identifying the patient's molar tooth based on the molar shape.

Segmentation quality assessment

Provided herein are systems and methods for determining if a 3D tooth model requires trimming or removal of incomplete or missing data (e.g., gingiva covering a portion of a tooth such as a molar). A patient's dentition may be scanned and/or segmented. Features of the patient's teeth can be determined, including a tooth center point of at least three of the patient's teeth. The features of the patient's teeth are used to access a parametric model. A trim plane normal vector is identified for a distal tooth. Trimming of the 3D tooth model is based on the trim plane normal vector.

Methods for automatically segmenting a 3D model of a patient's teeth may include scanning a patient's dentition and converting the scan data into a 3D model, including a sparse voxel representation of the 3D model. Features can be extracted from the sparse voxel representation of the 3D model and input into a machine learning model to train the machine learning model to segment the 3D model into individual dental components.

Machine learning dental segmentation methods using sparse voxel representations

Methods and systems for improving segmentation of a digital model of a patient's dentition into component teeth.

Provided herein are systems and methods for determining if a 3D tooth model requires trimming or removal of incomplete or missing data (e.g., gingiva covering a portion of a tooth such as a molar). A patient's dentition may be scanned and/or segmented. Raw dental features, principal component analysis (PCA) features, and/or other features may be extracted and compared to those of other teeth, such as those obtained through automated machine learning systems. A classifier can identify and/or output probability that the 3D tooth model requires trimming. Trimming of the 3D tooth model can be implemented without human intervention.

Growing community of inventors

Berdsk, Russia

Ivan Potapenko