Enhanced techniques for determination of dental margins in intraoral scans

    公开(公告)号:US10932890B1

    公开(公告)日:2021-03-02

    申请号:US16684427

    申请日:2019-11-14

    Applicant: Pearl Inc.

    Abstract: Systems and methods for enhanced techniques for determination of dental margins in intraoral scans. An example method includes receiving a request including an intraoral scan of a portion of a mouth, the intraoral scan depicting a margin created via adjustment of a tooth. A prepared region depicting the tooth is identified based on the intraoral scan. A representation of the intraoral scan usable as input to a machine learning model is generated, with the representation comprising structured data associated with the point cloud or mesh. Information identifying an estimated margin is determined based on the representation via computing a forward pass of the machine learning model. A response comprising the determined information is generated, with the determined information being usable to fabricate a prosthetic according to the estimated margin.

    Systems and methods for insurance fraud detection

    公开(公告)号:US11328365B2

    公开(公告)日:2022-05-10

    申请号:US17365896

    申请日:2021-07-01

    Applicant: Pearl Inc.

    Abstract: Systems and methods are described for automatically identifying fraud, waste or abuse in health insurance claims submitted to insurance companies by healthcare providers. Insurance claim information and at one image associated with the insurance claim may be received, where the image has been submitted by a healthcare provider to an insurance carrier as supporting evidence of a medical service performed by the healthcare provider. The system may generate a digital signature representing the image, then may compare the digital signature generated for the image to previously generated digital signatures of other images that have been submitted in association with other insurance claims. The system may then determine a likelihood that the given insurance claim is associated with fraud, waste or abuse, based in part on whether the digital signature is identical or close to one or more of the previously generated digital signatures.

Patent Agency Ranking