Align Technology, Inc.

General Electric Company

Nbcuniversal Media, LLC

Exxonmobil Upstream Research Company

Computer Sciences Corporation

Optopo Inc.

Ya Xue

Yingjie Li

Chao Shi

Eric P Meyer

Andrey Bushev

Zelko Relic

Michael Alan Stocks

Peter Henry Tu

Xiaoming Liu

Abha Moitra

Steven Matt Gustafson

Aleksandr Sergeevich Karsakov

Mikhail Toporkov

Aleksandr Anikin

Lembit Salasoo

Weizhong Yan

Timothy Gerard Richter

Ser Nam Lim

Jens Rittscher

Jeeyoung Choi

Prasant Potuluri

Jie Yu

Jun Liu

John Robert Hare

Anton Spiridonov

Yuting Qi

Marc Oglesby

Nick Tamburro

Betty Lau

Justin B Moore

Methods for visualizing treatment outcomes are provided. In some embodiments, a method includes obtaining a first 2D image of a patient's teeth from a mobile device, and obtaining an arch model representing an outcome for the patient's teeth after orthodontic treatment. The method can include matching the patient's teeth in the first 2D image to corresponding teeth in the arch model, using a parametric model. The method can also include determining a target position for the patient's teeth, based on a position of the matched corresponding teeth in the arch model. The method can further include generating a second 2D image depicting the patient's teeth in the target position.

Methods for visualizing treatment outcomes

An exemplary method, for preventing an outage in a network, includes collecting network metrics and producing statistical features of the network during a predetermined time window based on statistical analysis of the collected metrics. The method further includes selecting, from the produced statistical features, a first data set of relevant statistical features. Further, the method includes collecting information about a past event, extracting event data from the past event, and vectorizing the extracted event data to form a second data set. The method further includes concatenating the first data set and the second data set to form a third data set and classifying the third data set relative to a model of historical network performance to determine a probability of the outage. Further, the method includes modifying, in response to the probability being above a threshold, the network/activity within the network to avoid onset of the outage.

System and method for outage prediction

Provided herein are systems and methods for detecting the eruption state (e.g., tooth type and/or eruption status) of a target tooth. A patient's dentition may be scanned and/or segmented. A target tooth may be identified. 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 detector can identify and/or output the eruption state of the target tooth, such as whether the target tooth is a fully erupted primary tooth, a permanent partially erupted/un-erupted tooth, or a fully erupted permanent tooth.

Automatic detection of tooth type and eruption status

A method includes receiving an image of a face of a patient, the image including a depiction of teeth; processing the image of the face using one or more trained machine learning model, wherein the one or more trained machine learning model outputs a pixel-level classification of pixels in the image, the pixel level classification comprising a first set of pixels classified as being inside of a bounding shape that bounds a first plurality of teeth depicted in the image and a second set of pixels classified as being outside of the first bounding shape; cropping the image of the face of the patient, wherein the cropped image comprises depictions of the first plurality of teeth; and performing one or more operations on the cropped image of the face of the patient.

Deep learning for tooth detection and evaluation

Methods for simulating orthodontic treatment are provided. In some embodiments, a method includes capturing a first representation, the first representation including a depiction of a patient's teeth. The method can include building a parametric model of the patient's teeth based on the first representation, using one or more case-specific parameters for one or more shapes associated with at least one of the patient's teeth. The method can also include simulating an outcome of a dental treatment plan for the patient's teeth to produce a simulated outcome of the dental treatment plan. The method can further include modifying the parametric model to provide a modified model representing the simulated outcome of the dental treatment plan.

Methods for simulating orthodontic treatment

Systems and methods of simulating dental treatments are disclosed. A method may include capturing a first 2D image of a patient's face, including the patient's teeth, building a parametric 3D model of the patient's teeth based on the 2D image, developing a simulated outcome of a dental treatment of the patient's teeth by rendering the 3D model with the patient's teeth in one or more positions and/or orientations corresponding to the treatment goals of the dental treatment plan, and rendering a second 2D image of the patient's face with teeth according to a simulated outcome of the dental treatment plan. As noted herein, the dental treatment plan may include orthodontic and/or restorative elements. The simulated outcome may correspond to estimated outcomes and/or intended outcomes of the dental treatment plan.

Providing a simulated outcome of dental treatment on a patient

A machine learning model is trained to define bounding shapes around teeth in images. The machine learning model is trained by receiving a training dataset comprising a plurality of images, each image of the plurality of images comprising a face and a provided bounding shape around teeth in the image. The training dataset is input into an untrained machine learning model. The untrained machine learning model is trained based on the training dataset to generate a trained machine learning model that defines bounding shapes around teeth in images, wherein for an input image the trained machine learning model is to output a mask that defines a bounding shape around teeth of the input image, wherein the mask indicates, for each pixel of the input image, whether that pixel is inside of a defined bounding shape or is outside of the defined bounding shape.

A novel technique for unsupervised feature selection is disclosed. The disclosed methods include automatically selecting a subset of a feature of an image. Additionally, the selection of the subset of features may be incorporated with a congealing algorithm, such as a least-square-based congealing algorithm. By selecting a subset of the feature representation of an image, redundant and/or irrelevant features may be reduced or removed, and the efficiency and accuracy of least-square-based congealing may be improved.

Image congealing via efficient feature selection

An approach for seismic data analysis is provided. In accordance with various embodiments, the active learning approaches are employed in conjunction with an analysis algorithm that is used to process the seismic data. Algorithms that may employ such active learning include, but are not limited to, ranking algorithms and classification algorithms.

Seismic data analysis

A method for recommending videos is presented. The method includes generating a cross-usage matrix based upon a data of video sessions for a plurality of videos, generating a temporal matrix based upon release dates of the plurality of videos, generating a cross-temporal matrix based upon the cross-usage matrix and the temporal matrix, computing a global video rank corresponding to each of the plurality of videos based upon the cross-temporal matrix, generating a similarity score corresponding to each pair of videos in the plurality of videos based upon meta-data of the plurality of videos, and generating a local video rank corresponding to each of the plurality of videos relative to another video in the plurality of videos based upon the generated cross-usage matrix, the computed global video rank and the generated similarity score.

Methods and systems for online recommendation

Image concealing via efficient feature selection

Systems and methods perform signature extraction from an acquired spectrum of a pharmaceutical. An acquired spectrum of the pharmaceutical is measured using a spectrometer. The acquired spectrum is obtained from the spectrometer using a processor. A system-response function of the spectrometer is removed from the acquired spectrum using the processor. An intensity of the acquired spectrum is normalized to a predetermined scale using the processor. Fluorescence is removed from the acquired spectrum using the processor. Finally, an extracted signature of the pharmaceutical is obtained from the remainder of the acquired spectrum using the processor. If the acquired spectrum of the pharmaceutical is measured by the spectrometer through a container holding the pharmaceutical, a spectrum of the container is removed from the remainder of the acquired spectrum to produce the extracted signature of the pharmaceutical using the processor.

Spectral signature extraction for drug verification and identification

Growing community of inventors

Niskayuna, NY, United States of America

Ya Xue