Search

US-12626463-B2 - System and method for generating a virtual model of a virtual patient

US12626463B2US 12626463 B2US12626463 B2US 12626463B2US-12626463-B2

Abstract

A system for generating a virtual model of a virtual patient including: a template module to provide a morphable virtual 3D mesh template for a virtual model of a human organ; an anatomical parameters module to provide a range of values for each adjustable anatomical parameters of the virtual model, each value associated with a morphed state of the template; a plausibility module to provide at least one relation for the template in at least one morphed state, the relation being between at least two of the parameters; an instantiation module to provide, using a pseudo-random number generator, a parameter set including, for each parameter of the virtual model, a value of the corresponding range of values, while fulfilling the at least one relation; and a generating module to generate the virtual model based on the template in the morphed state corresponding to the selected parameters.

Inventors

  • Seyedsina RAZAVIZADEH

Assignees

  • Siemens Healthineers Ag

Dates

Publication Date
20260512
Application Date
20240318
Priority Date
20230308

Claims (17)

  1. 1 . A computer-implemented system for generating a virtual model of a virtual patient, comprising: a computing device configured to cause the system to, provide a morphable virtual 3D mesh as a template for a virtual model of at least a part of a human organ; provide a range of values for each of a plurality of adjustable anatomical parameters of the virtual model, each value associated with a corresponding morphed state of the template; provide at least one relation to be fulfilled by the template in at least one morphed state, the relation being between at least two of the plurality of adjustable anatomical parameters; provide, using a pseudo-random number generator, a parameter set comprising, for each adjustable anatomical parameter of the virtual model, a value of the corresponding provided range of values, while fulfilling the at least one relation; and generate the virtual model of the virtual patient based on the template in the morphed state corresponding to the provided values of the adjustable anatomical parameters generated by the pseudo-random number generator.
  2. 2 . The system of claim 1 , wherein the human organ is a human heart and the plurality of adjustable anatomical parameters comprise at least one of: a left coronary artery distance; a right coronary artery distance; an aorta diameter; a size of a aortic annulus; a sinotubular junction height; a calcification form of a leaflet of a heart valve; a pose of a heart valve; an opening percentage of a heart valve; a heart valve diameter; a leaflet effective height; a ventriculo-aortic junction height; or a leaflet basal ring diameter.
  3. 3 . The system of claim 2 , wherein the computing device is further configured to cause the system to generate a graphical representation of at least the generated virtual model.
  4. 4 . The system of claim 1 , wherein the computing device is further configured to cause the system to generate a graphical representation of at least the generated virtual model.
  5. 5 . The system of claim 4 , wherein the graphical representation further comprises an indication of a value of at least one adjustable anatomical parameter in each case together with a corresponding indication of how the value is located within the corresponding range of values for the adjustable anatomical parameter.
  6. 6 . The system of claim 5 , wherein the indication of how the value is located within the corresponding range of values for the adjustable anatomical parameter is realized by the graphical representation depicting a slider graphics object comprising a sliding bar and a sliding body movable along within the sliding bar, wherein an extent of the sliding bar represents the range of values, and a position of the sliding body represents a size of the value compared to the range of values.
  7. 7 . The system of claim 4 , further comprising: a graphical user interface enabling a user to interact with the generated graphical representation.
  8. 8 . The system of claim 7 , wherein the graphical user interface further enables the user to make manual changes to the value of at least one adjustable anatomical parameter and wherein the graphical user interface is configured to graphically display a result of the manual changes to the user.
  9. 9 . The system of claim 8 , wherein the computing device is further configured to cause the system run a mathematical simulation of a physiology of the virtual patient corresponding to the virtual model.
  10. 10 . The system of claim 9 , wherein the computing device is further configured to cause the system to generate the graphical representation with a virtual environment comprising a depiction of the generated virtual model, wherein the graphical representation also comprises features indicating at least one physiological property of the virtual patient based on the mathematical simulation of the physiology of the virtual patient.
  11. 11 . The system of claim 4 , wherein the computing device is further configured to cause the system to generate the graphical representation with a virtual environment comprising a depiction of the generated virtual model, wherein the graphical representation also comprises features indicating at least one physiological property of the virtual patient based on a mathematical simulation of a physiology of the virtual patient.
  12. 12 . The system of claim 11 , wherein the computing device is further configured to cause the system to access a medical database and to automatically determine the range of values for at least one of the plurality of adjustable anatomical parameters therefrom.
  13. 13 . The system of claim 1 , wherein the computing device is further configured to cause the system to access a medical database and to automatically determine the range of values for at least one of the plurality of adjustable anatomical parameters therefrom.
  14. 14 . The system of claim 1 , wherein the morphable virtual 3 D mesh is surface rendered or point-cloud rendered.
  15. 15 . A computer-implemented method for generating a virtual model of a virtual patient, comprising: providing a morphable virtual 3 D mesh as a template for a virtual model of at least a part of a human organ; providing a range of values for each of a plurality of adjustable anatomical parameters of the virtual model, each value associated with a corresponding morphed state of the template; providing at least one relation to be fulfilled by the template in at least one morphed state, the relation being between at least two of the plurality of adjustable anatomical parameters; providing, using a pseudo-random number generator, a parameter set comprising, for each adjustable anatomical parameter of the virtual model, a value of the corresponding provided range of values, while fulfilling the at least one relation; and generating the virtual model of the virtual patient based on the template in the morphed state corresponding to the provided values of the adjustable anatomical parameters from the pseudo-random number generator.
  16. 16 . A computer-implemented method for generating a training data set for machine learning, comprising generating N training samples by generating at least N virtual models according to the method of claim 15 .
  17. 17 . A non-transitory, non-volatile, computer-readable data storage medium comprising executable program code, when executed by a computing device, cause the computing device to perform the method of claim 15 .

Description

CROSS-REFERENCE TO RELATED APPLICATION(S) The present application claims priority under 35 U.S.C. § 119 to European Patent Application No. 23160698.9, filed Mar. 8, 2023, the entire contents of which is incorporated herein by reference. FIELD One or more example embodiments of the present invention relates to a computer-implemented system for generating a virtual model of a virtual patient, in particular a virtual model of at least a part of an organ of the virtual patient, and more particular to a virtual model of a heart of the virtual patient. One or more example embodiments of the present invention also relates to a computer-implemented method for generating such a virtual model, to a computer-implemented method for generating a training data set for machine learning, to a computer program, to a data storage medium, and to a data stream. RELATED ART Virtual models, displayed in graphical user interfaces, can contribute to training physicians or other medical personnel. To fulfil the training goals of interventional cardiology procedures (e.g. PCI and TAVR), simulation devices have been introduced that provide virtual patient models. These models are created from real patient datasets to maintain as realistic of an experience as possible. However, due to limited access to complete patient datasets, the number of these virtual models is limited, and the model itself is bound to the physiological properties of the real patient. This, in turn, leads to limited training scenarios and complications that the user of these devices can experience, hence reducing the long-term engagement with the system and achieving the training goals. In addition, creating these models one by one is a long and arduous task, which requires a team of specialized experts to accomplish, and adds further costs to the development process. Furthermore, these datasets are in the grace of their providers (i.e. patients) and can be removed on their demand, rendering the development efforts futile. Data privacy regulations such as the European GDPR further limit the ways in which real patient data can be freely used to generate additional virtual patient models. Also known are physiology engines, which simulate physiological processes based on virtual models. One such physiology engine is the Pulse Physiology engine 4.1.0 (registered trademark) available under http://pulse.kitware.com/. However, without a large variety of virtual models, and a method for generating such virtual models cost-effectively, the known physiology engines have only limited use cases in training physicians or other medical specialists. Known in the prior art are also methods of rendering 3-dimensional virtual models and of changing their shape, for example surface rendering methods as described in the scientific publication by L. Szirmay-Kalo and T. Umenhoffer, “Displacement Mapping on the GPU—State of the Art”, https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1467-8659.2007.01108.x (hereafter cited as “Szirmay-Kalo/Umenhoffer”). Other methods for generating 3-dimensional virtual models include point-cloud rendering techniques such as described in the scientific publication by P. Kivi et al, “Real-Time Rendering of point Clouds with Photorealistic Effects: A Survey”, https://ieeexplore.ieee.org/document/9693528, DOI: 10.1109/ACCESS.2022.3146768, hereafter cited as “Kivi et al.”. This publication reviews real-time photorealistic point cloud rendering methods, which directly ray trace or rasterize point cloud models, with an emphasis on ray tracing and real-time performance. Further, for the training of artificial intelligence entities such as artificial neural networks or the like, usually training data are of the essence. Access to a large number of virtual patient models therefore enables improved training of artificial intelligence entities. SUMMARY One or more example embodiments of the present invention provides an improved system for generating a virtual model of a patient, and a further objective to provide an improved method for generating such a model. One or more example embodiments of the present invention provides an improved method for generating training data for machine learning, and providing a computer program product, a data storage medium and a data stream for implementing any of the improved methods. BRIEF DESCRIPTION OF THE DRAWINGS The accompanying drawings are included to provide a further understanding of the present invention and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments of the present invention and together with the description serve to explain the principles of the invention. Other embodiments of the present invention and many of the intended advantages of the present invention will be readily appreciated as they become better understood by reference to the following detailed description. The elements of the drawings are not necessarily to scale relative to each other. Like refer