公开(公告)号：US20250114008A1

公开(公告)日：2025-04-10

申请号：US18483757

申请日：2023-10-10

Applicant: GE Precision Healthcare LLC

Inventor： Dattesh Dayanand Shanbhag ,  Kavitha Manickam ,  Dawei Gui ,  Maggie MeiKei Fung ,  Ting Ye ,  Chitresh Bhushan ,  Muhan Shao

IPC: A61B5/055 ,  A61B5/00 ,  G06T7/00

Abstract: A method for performing a scan of a subject includes receiving a selected protocol for the scan and triggering, upon receiving a start signal, automatic landmarking of the subject on a table of a magnetic resonance imaging (MRI) scanner utilizing a three-dimensional (3D) camera. The method includes obtaining landmark positioning data from the 3D camera and utilizing the landmark positioning data for localization of the region of interest. The method includes, subsequent to the automatic landmarking, triggering a calibration scan of the subject with the MRI scanner and obtaining calibration data from the MRI scanner and utilizing the calibration data for refining the localization of the region of interest. The method includes generating a geometry plan for subsequent scans utilizing both the landmark positioning data and the calibration data and triggering at least one subsequent scan of the subject with the MRI scanner based on the geometry plan.

公开(公告)号：US10902587B2

公开(公告)日：2021-01-26

申请号：US15994411

申请日：2018-05-31

Applicant: GE Precision Healthcare LLC

Inventor： Kavitha Manickam ,  Jignesh Dholakia ,  Vignesh Singh ,  Sandeep Lakshmipathy

IPC: G06K9/00 ,  G06T7/00 ,  G06K9/66 ,  G06T7/10 ,  G06N3/08

Abstract: A method and system for automatically labeling a spine image is disclosed. The method includes receiving an input spine image and analyzing image features of the input spine image by a deep neural network. The method further includes generating a mask image corresponding to the input spine image by the deep neural network based on image characteristics of a training image dataset. A region of interest in the mask image comprises vertebral candidates of the spine. The training image dataset comprises a plurality of spine images and a plurality of corresponding mask images. The method further includes associating labels with a plurality of image components of the mask image and labeling the input spine image based on labels associated with the mask image.