公开(公告)号：US20230083696A1

公开(公告)日：2023-03-16

申请号：US17868575

申请日：2022-07-19

Applicant: SPINTECH, INC.

Inventor： Ewart Mark Haacke ,  Paul David Kokeny

IPC: G01R33/56 ,  G01R33/561 ,  G01R33/565

Abstract: A magnetic resonance imaging (MRI) system can include a processor and a memory. The processor can receive an acquired magnetic resonance (MR) dataset having a first signal-to-noise ratio (SNR). The processor can extract, from the acquired MR dataset, a first set of values corresponding to a first variable having a second SNR and a second set of values corresponding to a second variable. The processor can apply a constraint function that includes a function of the first variable and the second variable. The processor can minimize a cost function according to the constraint function to generate a cost function solution. The processor can input the first variable and the second variable into the cost function solution to generate a modified first variable having a third SNR, the third SNR being greater than the second SNR.

公开(公告)号：US20230281814A1

公开(公告)日：2023-09-07

申请号：US18316340

申请日：2023-05-12

Applicant: SpinTech, Inc.

Inventor： Ewart Mark Haacke ,  Ying Wang

IPC: G06T7/00 ,  A61B5/055 ,  A61B5/00 ,  G06T3/00 ,  G06T7/11 ,  G06V10/25 ,  G06V10/774 ,  G06T7/62

CPC classification number: G06T7/0012 ,  A61B5/055 ,  A61B5/7253 ,  A61B5/7267 ,  G06T3/0093 ,  G06T7/11 ,  G06V10/25 ,  G06V10/774 ,  G06T7/62 ,  G06V2201/03 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/30004 ,  G06T2207/20132

Abstract: Systems and methods for detecting anatomical structures include, for each training subject of a plurality of training subjects, a corresponding MR image, and generating an initial anatomical template based on a first training subject of the plurality of training subjects. A computing device can map MR images of the other training subjects onto a template space by applying a global transformation followed by a local transformation. The computing device can average the mapped MR images with the initial anatomical template to generate a final anatomical template and boundaries of an anatomical structure of interest can be drawn in the final anatomical template. The computing device can fine tune the boundaries using an edge detection algorithm. The final anatomical template can be used to identify boundaries of the anatomical structure(s) of interest automatically (e.g., without human intervention) in non-training subjects.

公开(公告)号：US20220327699A1

公开(公告)日：2022-10-13

申请号：US17735287

申请日：2022-05-03

Applicant: SpinTech, Inc.

Inventor： Ewart Mark Haacke ,  Ying Wang

IPC: G06T7/00 ,  A61B5/055 ,  A61B5/00 ,  G06T3/00 ,  G06T7/11 ,  G06T7/62 ,  G06V10/25 ,  G06V10/774

Abstract: Systems and methods for detecting anatomical structures include, for each training subject of a plurality of training subjects, a corresponding MR image, and generating an initial anatomical template based on a first training subject of the plurality of training subjects. A computing device can map MR images of the other training subjects onto a template space by applying a global transformation followed by a local transformation. The computing device can average the mapped MR images with the initial anatomical template to generate a final anatomical template and boundaries of an anatomical structure of interest can be drawn in the final anatomical template. The computing device can fine tune the boundaries using an edge detection algorithm. The final anatomical template can be used to identify boundaries of the anatomical structure(s) of interest automatically (e g., without human intervention) in non-training subjects.

公开(公告)号：US11651490B2

公开(公告)日：2023-05-16

申请号：US17735287

申请日：2022-05-03

Applicant: SpinTech, Inc.

Inventor： Ewart Mark Haacke ,  Ying Wang

IPC: G06T7/00 ,  A61B5/055 ,  G06T3/00 ,  G06T7/11 ,  G06V10/25 ,  G06T7/62 ,  A61B5/00 ,  G06V10/774

CPC classification number: G06T7/0012 ,  A61B5/055 ,  A61B5/7253 ,  A61B5/7267 ,  G06T3/0093 ,  G06T7/11 ,  G06T7/62 ,  G06V10/25 ,  G06V10/774 ,  G06T2207/10088 ,  G06T2207/20081 ,  G06T2207/20132 ,  G06T2207/30004 ,  G06V2201/03

Abstract: Systems and methods for detecting anatomical structures include, for each training subject of a plurality of training subjects, a corresponding MR image, and generating an initial anatomical template based on a first training subject of the plurality of training subjects. A computing device can map MR images of the other training subjects onto a template space by applying a global transformation followed by a local transformation. The computing device can average the mapped MR images with the initial anatomical template to generate a final anatomical template and boundaries of an anatomical structure of interest can be drawn in the final anatomical template. The computing device can fine tune the boundaries using an edge detection algorithm. The final anatomical template can be used to identify boundaries of the anatomical structure(s) of interest automatically (e g., without human intervention) in non-training subjects.

公开(公告)号：US11789105B2

公开(公告)日：2023-10-17

申请号：US17868575

申请日：2022-07-19

Applicant: SPINTECH, INC.

Inventor： Ewart Mark Haacke ,  Paul David Kokeny

IPC: G01V3/00 ,  G01R33/56 ,  G01R33/565 ,  G01R33/561

CPC classification number: G01R33/5608 ,  G01R33/561 ,  G01R33/565

Abstract: A magnetic resonance imaging (MRI) system can include a processor and a memory. The processor can receive an acquired magnetic resonance (MR) dataset having a first signal-to-noise ratio (SNR). The processor can extract, from the acquired MR dataset, a first set of values corresponding to a first variable having a second SNR and a second set of values corresponding to a second variable. The processor can apply a constraint function that includes a function of the first variable and the second variable. The processor can minimize a cost function according to the constraint function to generate a cost function solution. The processor can input the first variable and the second variable into the cost function solution to generate a modified first variable having a third SNR, the third SNR being greater than the second SNR.

公开(公告)号：US11435424B1

公开(公告)日：2022-09-06

申请号：US17459482

申请日：2021-08-27

Applicant: SPINTECH, INC.

Inventor： Ewart Mark Haacke ,  Paul David Kokeny

IPC: G01N33/48 ,  G01R33/56 ,  G01R33/565 ,  G01R33/561

Abstract: A magnetic resonance imaging (MRI) system can include a processor and a memory. The processor can receive an acquired magnetic resonance (MR) dataset having a first signal-to-noise ratio (SNR). The processor can extract, from the acquired MR dataset, a first set of values corresponding to a first variable having a second SNR and a second set of values corresponding to a second variable. The processor can apply a constraint function that includes a function of the first variable and the second variable. The processor can minimize a cost function according to the constraint function to generate a cost function solution. The processor can input the first variable and the second variable into the cost function solution to generate a modified first variable having a third SNR, the third SNR being greater than the second SNR.