公开(公告)号：US20210182622A1

公开(公告)日：2021-06-17

申请号：US17186814

申请日：2021-02-26

Applicant: StraxCorp Pty. Ltd.

Inventor： Yu PENG

IPC: G06K9/62 ,  G06T7/11

Abstract: An image segmentation method system, the system comprising: a training subsystem configured to train a segmentation machine learning model using annotated training data comprising images associated with respective segmentation annotations, so as to generate a trained segmentation machine learning model; a model evaluator; and a segmentation subsystem configured to perform segmentation of a structure or material in an image using the trained segmentation machine learning model. The model evaluator is configured to evaluate the segmentation machine learning model by (i) controlling the segmentation subsystem to segment at least one evaluation image associated with an existing segmentation annotation using the segmentation machine learning model and thereby generate a segmentation of the annotated evaluation image, and (ii) forming a comparison of the segmentation of the annotated evaluation image and the existing segmentation annotation. The method includes deploying the trained segmentation machine learning model for use if the comparison indicates that the segmentation machine learning model is satisfactory.

公开(公告)号：US20180049715A1

公开(公告)日：2018-02-22

申请号：US15560919

申请日：2016-03-23

Applicant: Straxcorp Pty Ltd

Inventor： Roger ZEBAZE ,  Yu PENG

IPC: A61B6/00 ,  A61B6/03

CPC classification number: A61B6/582 ,  A61B6/032 ,  A61B6/469 ,  A61B6/505

Abstract: A method and apparatus for calibrating an image of a specimen or subject obtained with an imaging modality or selecting a region of interest in the image. The apparatus comprises: a graduation support adapted for mounting on the specimen or subject; and one or more calibration graduations supported by the graduation support; the one or more calibration graduations are imagable with the imaging modality, and are distinguishable in the image from the graduation support and from the specimen or subject, and at least one of the calibration graduations have at least one characteristic of known value.