IP Library Granted Patent US 12,731,253
Granted Patent B2
US 12,731,253 · App. 18/371,020 · Granted Sep 8, 2026

Providing a result dataset

Inventors: Annette Birkhold (Stuttgart, DE); Markus Kowarschik (Erlangen, DE)
Assignee: Siemens Healthineers AG
G06T7/0012G06T12/00G06V10/82G06T2207/30101G06T2210/41
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,731,253
App. No.
18/371,020
Granted
Sep 8, 2026
Kind
B2
Abstract

The disclosure relates to a method for providing a result dataset, a method for providing a trained function, a provisioning unit, a medical imaging device, and a computer program product. The method for providing the result dataset includes capturing medical image data, wherein the medical image data maps a temporal change in an anatomical object in an examination object in a spatially and temporally resolved manner. The method further includes identifying at least one inhomogeneously deforming region of the anatomical object based on the image data and providing the result dataset based on the image data, wherein the result dataset has a dedicated map and/or at least one deformation parameter of the at least one inhomogeneously deforming region.

Claims (58)

1 . A method for providing a result dataset, the method comprising:

capturing medical image data, wherein the medical image data maps a change in an anatomical object in an examination object in a spatially and temporally resolved manner;

identifying at least one inhomogeneously deforming region of the anatomical object based on the medical image data; and

providing the result dataset based on the medical image data,

wherein the result dataset has a dedicated map of the at least one inhomogeneously deforming region, at least one deformation parameter of the at least one inhomogeneously deforming region, or a combination thereof.

2 . The method of claim 1 , wherein a map of an initial state of the anatomical object is identified in the medical image data,

wherein a displacement field is determined for each further state of the anatomical object mapped in the medical image data with respect to the initial state, and

wherein the result dataset is additionally provided based on the displacement fields.

3 . The method of claim 2 , wherein the at least one deformation parameter having in each case a strain tensor is determined as a gradient of the displacement fields.

4 . A method for providing a result dataset, the method comprising:

capturing medical image data, wherein the medical image data maps a change in an anatomical object in an examination object in a spatially and temporally resolved manner;

identifying at least one inhomogeneously deforming region of the anatomical object based on the medical image data;

identifying a map of an initial state of the anatomical object in the medical image data;

determining a displacement field for each further state of the anatomical object mapped in the medical image data with respect to the initial state;

providing the result dataset based on the medical image data and the displacement fields,

wherein the result dataset has a dedicated map of the at least one inhomogeneously deforming region, at least one deformation parameter of the at least one inhomogeneously deforming region, or a combination thereof,

wherein the at least one deformation parameter having in each case a strain tensor is determined as a gradient of the displacement fields, and

wherein the at least one deformation parameter comprises one or more of:

a maximum strain tensor that, for image points of the medical image data mapping a wall of the anatomical object, relates to a temporal maximum of strain on the wall;

strain rate tensors as a time derivative of the strain tensors; or

the strain rate tensors as the time derivative of the strain tensors and a maximum strain rate tensor that, for the image points of the medical image data mapping the wall of the anatomical object, relates to a temporal maximum of a strain rate of the wall.

5 . The method of claim 4 , wherein the capturing of the medical image data comprises acquiring a plurality of projection mappings that map the change in the anatomical object in the examination object from at least partially different projection directions,

wherein an acquisition rate for acquiring the plurality of projection mappings is adjusted in dependence on a heart rate, a respiratory rate, or both the heart rate and the respiratory rate of the examination object,

wherein projection directions of adjacent projection mappings of the plurality of projection mappings have an acute angle to one another, and

wherein the medical image data is reconstructed from the plurality of projection mappings.

6 . The method of claim 5 , wherein the providing of the result dataset comprises reconstructing the dedicated map of the at least one inhomogeneously deforming region from the plurality of projection mappings, and

wherein the reconstructing is spatially and temporally limited to the at least one inhomogeneously deforming region.

7 . The method of claim 6 , wherein an acquisition parameter for the dedicated map of the at least one inhomogeneously deforming region is determined based on the identifying of the at least one inhomogeneously deforming region,

wherein further medical image data is captured by the acquisition parameter, and

wherein the result dataset is additionally provided based on the further medical image data.

8 . The method of claim 7 , wherein the acquisition parameter has at least one projection direction for acquiring further projection mappings of the at least one inhomogeneously deforming region, and

wherein the further medical image data is reconstructed from the further projection mappings.

9 . The method of claim 1 , wherein the capturing of the medical image data comprises acquiring a plurality of projection mappings that map the change in the anatomical object in the examination object from at least partially different projection directions,

wherein an acquisition rate for acquiring the plurality of projection mappings is adjusted in dependence on a heart rate, a respiratory rate, or both the heart rate and the respiratory rate of the examination object,

wherein projection directions of adjacent projection mappings of the plurality of projection mappings have an acute angle to one another, and

wherein the medical image data is reconstructed from the plurality of projection mappings.

10 . The method of claim 9 , wherein the providing of the result dataset comprises reconstructing the dedicated map of the at least one inhomogeneously deforming region from the plurality of projection mappings, and

wherein the reconstructing is spatially and temporally limited to the at least one inhomogeneously deforming region.

11 . The method of claim 1 , wherein an acquisition parameter for the dedicated map of the at least one inhomogeneously deforming region is determined based on the identifying of the at least one inhomogeneously deforming region,

wherein further medical image data is captured by the acquisition parameter, and

wherein the result dataset is additionally provided based on the further medical image data.

12 . The method of claim 11 , wherein the acquisition parameter has at least one projection direction for acquiring further projection mappings of the at least one inhomogeneously deforming region, and

wherein the further medical image data is reconstructed from the further projection mappings.

13 . The method of claim 1 , wherein the anatomical object comprises a hollow organ, a vessel portion, an aneurysm, an organ, a tissue, or a combination thereof.

14 . The method of claim 13 , wherein the at least one inhomogeneously deforming region of the anatomical object is identified based on time intensity curves of image points of the medical image data that maps a wall of the anatomical object.

15 . The method of claim 1 , wherein the identifying of the at least one inhomogeneously deforming region of the anatomical object comprises applying a trained function to input data,

wherein the input data is based on the medical image data, and

wherein at least one parameter of the trained function is adjusted based on a comparison of at least one inhomogeneously deforming training region with at least one inhomogeneously deforming comparison region.

16 . A medical imaging device comprising:

a provisioning unit configured to:

capture medical image data, wherein the medical image data maps a change in an anatomical object in an examination object in a spatially and temporally resolved manner;

identify at least one inhomogeneously deforming region of the anatomical object based on the medical image data; and

provide a result dataset based on the medical image data,

wherein the result dataset has a dedicated map of the at least one inhomogeneously deforming region, at least one deformation parameter of the at least one inhomogeneously deforming region, or a combination thereof.

17 . The medical imaging device of claim 16 , wherein the at least one inhomogeneously deforming region of the anatomical object comprises a local bleb in a wall of the anatomical object.

18 . The medical imaging device of claim 16 , wherein the at least one inhomogeneously deforming region of the anatomical object comprises a deformation that deviates from adjacent tissue of the anatomical object.

19 . The method of claim 1 , wherein the at least one inhomogeneously deforming region of the anatomical object comprises a local bleb in a wall of the anatomical object.

20 . The method of claim 1 , wherein the at least one inhomogeneously deforming region of the anatomical object comprises a deformation that deviates from adjacent tissue of the anatomical object.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 9, 2025
From: BIRKHOLD, ANNETTE; KOWARSCHIK, MARKUS
To: SIEMENS HEALTHINEERS AG
Reel/Frame 072523/0946 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2023
From: SIEMENS HEALTHCARE GMBH
To: SIEMENS HEALTHINEERS AG
Reel/Frame 066267/0346 →
Priority Claims (1)
EP 22197288 · Sep 23, 2022 · regional
Continuity (1)
Related Publication 20240104728A1 · Mar 28, 2024
References Cited (45)
US 7782998B2 · Langan · 2010 [cited by examiner]
US 8029444B2 · Pedrizzetti · 2011 [cited by examiner]
US 10890641B2 · Wang · 2021 [cited by examiner]
US 10949973B2 · Kim · 2021 [cited by examiner]
US 20070282202A1 · Maurice · 2007 [cited by applicant]
US 20090232379A1 · Kohler · 2009 [cited by applicant]
US 20100128946A1 · Fidrich · 2010 [cited by examiner]
US 20110142315A1 · Hsieh · 2011 [cited by applicant]
US 20110142316A1 · Wang · 2011 [cited by examiner]
US 20180199905A1 · Kowarschik et al. · 2018 [cited by applicant]
US 20190066847A1 · Jung · 2019 [cited by examiner]
US 20190223725A1 · Lu · 2019 [cited by examiner]
US 20200188024A1 · Breininger · 2020 [cited by examiner]
US 20200219272A1 · Pizer · 2020 [cited by examiner]
US 20210110196A1 · Syeda-Mahmood · 2021 [cited by examiner]
US 20210248762A1 · Pfister · 2021 [cited by examiner]
US 20210343405A1 · Di Martino · 2021 [cited by applicant]
US 20220005192A1 · Gao · 2022 [cited by examiner]
US 20220122717A1 · Budz · 2022 [cited by examiner]
US 20220330902A1 · Forneris · 2022 [cited by applicant]
US 20230172571A1 · Birkhold · 2023 [cited by applicant]
US 20230316511A1 · Tsai · 2023 [cited by examiner]
CN 113874910A · 2021 [cited by examiner]
CN 115205192A · 2022 [cited by examiner]
CN 116615151A · 2023 [cited by examiner]
CN 115115570B · 2025 [cited by examiner]
DE 102009007366A1 · 2010 [cited by examiner]
DE 102011081480B4 · 2014 [cited by examiner]
EP 2367153B1 · 2014 [cited by applicant]
JP 7024954B2 · 2022 [cited by examiner]
WO WO0180184A1 · 2001 [cited by examiner]
WO WO2018012080A1 · 2018 [cited by examiner]
WO WO2019231844A1 · 2019 [cited by examiner]
WO 2021059243A1 · 2021 [cited by applicant]
Gullett et al. “A deformation gradient tensor and strain tensors for atomistic simulations.” Modelling and Simulation in Materials Science and Engineering 16.1 (2007) (Year: 2007). [cited by examiner]
Li et al. “An Overview of Systems and Techniques for Autonomous Robotic Ultrasound Acquisitions,” in IEEE Transactions on Medical Robotics and Bionics, vol. 3, No. 2, pp. 510-524, May 2021, doi: 10.1109/TMRB.2021.307219… [cited by examiner]
Selskog, Pernilla, et al. “Kinematics of the heart: strain-rate imaging from time-resolved three-dimensional phase contrast Mri.” IEEE Transactions on Medical Imaging 21.9 (2002): 1105-1109 (Year: 2002). [cited by examiner]
Bracamonte, Johane H., et al. “Patient-specific inverse modeling of in vivo cardiovascular mechanics with medical image-derived kinematics as input data: concepts, methods, and applications.” Applied Sciences 12.8 (2022… [cited by examiner]
Jailin, C. et al., “Projection-Based Measurement and Identification. In: , et al. Advancements in Optical Methods & Digital Image Correlation in Experimental Mechanics, vol. 3”. Conference Proceedings of the Society for… [cited by applicant]
Maupu C. et al., “Imaging Modalities for Intracranial Aneurysm: More Than Meets the Eye,” Cardiovasc. Med. 9:793072. doi: 10.3389/fcvm.2022.793072, (Feb. 15, 2022), pp. 1-9. [cited by applicant]
Meuschke Monique et al. “Aneulysis—A system for the visual analysis of aneurysm data”, Computers and Graphics, Elsevier, GB, Bd. 98, (Jun. 10, 2021), pp. 197-209. [cited by applicant]
Rohkohl Christopher et al., “Interventional 4-D Motion Estimation and Reconstruction of Cardiac Vasculature without Motion Periodicity Assumption”, Interventional 4-D Motion Estimation and Reconstruction; Vol. Lecture N… [cited by applicant]
Rohkohl Christopher et al., “Interventional 4D motion estimation and reconstruction of cardiac vasculature without motion periodicity assumption”, Miccai, Medical Image Analysis, vol. 14, issue 5, 2010, pp. 687-694. [cited by applicant]
Signorelli Francesco et al., “Biomechanical Characterization of Intracranial Aneurysm Wall: A Multiscale Study”, World Neurosurgery, vol. 119, Nov. 2018, pp. e882-e889. [cited by applicant]
Zhang J, et al., Abstract for “Irregular pulsation of aneurysmal wall is associated with symptomatic and ruptured intracranial aneurysms”, NeuroIntervent Surg doi:10.1136/neurintsurg-2021-018381, (2021), pp. 1-9. [cited by applicant]