IP Library Granted Patent US 12,548,236
Granted Patent B2
US 12,548,236 · App. 18/604,831 · Granted Feb 10, 2026

Technique for rendering hidden structures with clip planes

Inventor: Sandra Sudarsky (Bedminster, NJ)
Assignee: Siemens Healthineers AG
G06T15/08G06T15/30G06T15/50G06T19/00G06T2210/41G06T2219/008
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 12,548,236
App. No.
18/604,831
Granted
Feb 10, 2026
Kind
B2
Abstract

A hidden structure of a volumetric data set is rendered in a medical image based on a volumetric data set received from a medical scanner. Reference information indicative of a parameter for a clip plane is received for rendering the hidden structure within the medical image. A differentiable rendering, DR, algorithm is applied on the received volumetric data set, which comprises determining a light accumulation along a viewing ray. The clip plane is approximated by including a smooth approximation to a Dirac delta distribution, which depends on the parameter comprised in the received reference information, in the determining of the light accumulation along the viewing ray. The parameter for the clip plane is optimized by optimizing an objective function. The medical image with the hidden structure visible is output for final rendering, and/or for display.

Claims (32)

1 . A computer-implemented method for rendering a hidden structure of a volumetric data set when rendering a medical image based on the volumetric data set, the computer-implemented method comprising:

receiving the volumetric data set from a medical scanner;

receiving reference information indicative of at least one parameter for a clip plane within the volumetric data set for rendering the hidden structure represented in the received volumetric data set;

applying a differentiable rendering (DR) algorithm on the received volumetric data set for rendering the medical image with the hidden structure, wherein applying the DR algorithm comprises determining a light accumulation along a viewing ray, wherein the clip plane is approximated by including a smooth approximation to a Dirac delta distribution in the determining of the light accumulation along the viewing ray, wherein the smooth approximation to the Dirac delta distribution depends on the at least one parameter comprised in the received reference information, and wherein applying the DR algorithm further comprises optimizing the at least one parameter for the clip plane by optimizing an objective function; and

outputting the medical image with the hidden structure being visible for final rendering and/or for display, the medical image with the hidden structure being visible resulting from the applying of the DR algorithm.

2 . The computer-implemented method according to claim 1 , wherein the hidden structure comprises an implant.

3 . The computer-implemented method according to claim 1 , wherein the hidden structure comprises an anatomical structure.

4 . The computer-implemented method according to claim 1 , wherein the received reference information comprises a medical reference image.

5 . The computer-implemented method according to claim 4 , wherein the objective function comprises a loss function depending on the medical reference image, and wherein optimizing the loss function comprises minimizing and/or maximizing the loss function.

6 . The computer-implemented method according to claim 1 , wherein the received reference information comprises a position relative to an anatomical structure and/or relative to an organ.

7 . The computer-implemented method according to claim 1 , wherein the objective function comprises an image entropy, and wherein optimizing the objective function comprises maximizing the image entropy.

8 . The computer-implemented method according to claim 1 , wherein the at least one parameter of the clip plane comprises a position and/or an orientation of the clip plane within the volumetric data set.

9 . The computer-implemented method according to claim 1 , wherein the smooth approximation to the Dirac delta distribution comprises a Gaussian function.

10 . The computer-implemented method according to claim 1 , wherein the light accumulation is determined by raycasting, path tracing, half-angle slicing, and/or interactive volume lighting.

11 . The computer-implemented method according to claim 1 , wherein the at least one parameter of a clip plane comprises two or more parameters.

12 . The computer-implemented method according to claim 11 wherein the two or more parameters are of two or more clip planes.

13 . The computer-implemented method according to claim 1 , wherein the medical scanner is a computed tomography scanner; a magnetic resonance imaging scanner; an ultrasound scanner; a positron emission tomography scanner; or a single-photon emission computed tomography scanner.

14 . The computer-implemented method according to claim 5 , wherein the received reference information comprises a position relative to an anatomical structure and/or relative to an organ.

15 . The computer-implemented method according to claim 14 , wherein the at least one parameter of the clip plane comprises a position and/or an orientation of the clip plane within the volumetric data set.

16 . The computer-implemented method according to claim 15 , wherein the smooth approximation to the Dirac delta distribution comprises a Gaussian function.

17 . The computer-implemented method according to claim 16 , wherein the light accumulation is determined by raycasting, path tracing, half-angle slicing, and/or interactive volume lighting.

18 . A computing device for rendering a hidden structure of a volumetric data set when rendering a medical image based on the volumetric data set, the computing device comprising:

a first interface configured for receiving the volumetric data set from a medical scanner;

a second interface configured for receiving reference information indicative of at least one parameter for a clip plane within the volumetric data set for rendering the hidden structure represented in the received volumetric data set;

a processor configured to apply a differentiable rendering (DR) algorithm on the received volumetric data set for rendering the medical image with the hidden structure, wherein the application of the DR algorithm comprises determination of a light accumulation along a viewing ray, wherein the clip plane is approximated by including a smooth approximation to a Dirac delta distribution in the determination of the light accumulation along the viewing ray, wherein the smooth approximation to the Dirac delta distribution depends on the at least one parameter comprised in the received reference information, and wherein the application of the DR algorithm further comprises optimization of the at least one parameter for the clip plane by optimization of an objective function; and

an output interface configured for outputting the medical image with the hidden structure being visible for final rendering and/or for display, the medical image with the hidden structure being visible resulting from the application of the DR algorithm.

19 . The computing device according to claim 18 , further comprising:

one or more medical scanners configured for providing the volumetric data set; and

a display device configured for receiving the medical image with the hidden structure from the output interface, wherein the display device is further configured to display and/or render the received medical image with the hidden structure.

20 . A non-transitory computer-readable medium on which program elements are stored that can be read and executed by a processor, in order to render a hidden structure of a volumetric data set when rendering a medical image based on the volumetric data set, wherein the program elements as executed by the processor comprise:

applying a differentiable rendering (DR) algorithm on the volumetric data set for rendering the medical image with the hidden structure, wherein applying the DR algorithm comprises determining a light accumulation along a viewing ray, wherein a clip plane is approximated by including a smooth approximation to a Dirac delta distribution in the determining of the light accumulation along the viewing ray, wherein the smooth approximation to the Dirac delta distribution depends on at least one parameter for the clip plane comprised in received reference information, and wherein applying the DR algorithm further comprises optimizing the at least one parameter for the clip plane by optimizing an objective function; and

outputting the medical image with the hidden structure being visible for final rendering and/or for display, the medical image with the hidden structure being visible resulting from the applying of the DR algorithm.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 9, 2024
From: SIEMENS MEDICAL SOLUTIONS USA, INC.
To: SIEMENS HEALTHINEERS AG
Reel/Frame 067040/0984 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 1, 2024
From: SUDARSKY, SANDRA
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 066964/0927 →
Continuity (1)
Related Publication 20240331269A1 · Oct 3, 2024
References Cited (9)
US 11723748B2 · Li · 2023 [cited by examiner]
Shuang Zhao, Wenzel Jakob, Tzu-Mao Li, “Physics-Based Differentiable Rendering: A Comprehensive Introduction”, 2020, SIGGRAPH '20 Courses, ACM ISBN 978-1-4503-7972-4/20/08, pp. 1-36 (Year: 2020). [cited by examiner]
Felix Petersen, Bastian Goldluecke, Christian Borgelt, Oliver Deussen, “GenDR: A Generalized Differentiable Renderer”, 2022, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. … [cited by examiner]
Knoll, Aaron, et al. “Volume ray casting with peak finding and differential sampling.” IEEE Transactions on Visualization and Computer Graphics 15.6 (2009): 1571-1578. [cited by applicant]
Kronander, Joel, et al. “Efficient visibility encoding for dynamic illumination in direct vol. rendering.” IEEE Transactions on Visualization and Computer Graphics 18.3 (2011): 447-462. [cited by applicant]
Li, Tzu-Mao, et al. “Differentiable monte carlo ray tracing through edge sampling.” ACM Transactions on Graphics (TOG) 37.6 (2018): 1-11. [cited by applicant]
Loubet, Guillaume, Nicolas Holzschuch, and Wenzel Jakob. “Reparameterizing discontinuous integrands for differentiable rendering.” ACM Transactions on Graphics (TOG) 38.6 (2019): 1-14. [cited by applicant]
Weiss, et al. “Differentiable Direct vol. Rendering,” IEEE Trans on Visualization and Computer Graphics, vol. 28, No. 1, pp. 562-572, Jan. 2022. [cited by applicant]
Extended European Search Report (EESR) mailed Sep. 4, 2023 in corresponding European Application No. 23164672.0. [cited by applicant]