IP Library Granted Patent US 12,551,720
Granted Patent B2
US 12,551,720 · App. 18/376,521 · Granted Feb 17, 2026

Method and apparatus to facilitate administering therapeutic radiation to a patient

Inventors: Elena Czeizler (Helsinki, FI); Esa Kuusela (Espoo, FI); Mikko Hakala (Rajamaki, FI); Shahab Basiri (Siuntio, FI)
Assignee: Siemens Healthineers International AG
A61N5/1031G06T7/0012G06T9/002G06T9/004G06T9/20G06T2207/10081G06T2207/20084G06T2207/30004
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 12,551,720
App. No.
18/376,521
Granted
Feb 17, 2026
Kind
B2
Abstract

A control circuit accesses patient image content as well as field geometry information regarding a particular radiation treatment platform. The control circuit then generates a predicted three-dimensional dose map for the radiation treatment plan as a function of both the patient image content and the field geometry information.

Claims (34)

1 . An apparatus to facilitate providing a radiation treatment plan to administer therapeutic radiation to a patient via a particular radiation treatment platform, the apparatus comprising:

a memory having image content regarding the patient and field geometry information regarding the particular radiation treatment platform stored therein, wherein the field geometry information comprises image content of at least one of location positions of a radiation source vis-à-vis a gantry, gantry angles, collimator angles, and jaw positions, wherein the image content regarding the patient and the field geometry information image content have a same resolution;

a control circuit operably coupled to the memory, the control circuit being configured to:

access the image content regarding the patient;

access the field geometry information;

generate a predicted three-dimensional dose map that will result when treating the patient with the radiation treatment plan as a function of both the image content regarding the patient and the field geometry information.

2 . The apparatus of claim 1 wherein the image content regarding the patient comprises, at least in part, at least one organ mask and at least one computed tomography image.

3 . The apparatus of claim 2 wherein the at least one organ mask comprises, at least in part, a contoured planning target volume and at least one contoured organ-at-risk.

4 . The apparatus of claim 1 wherein the control circuit is configured to generate the predicted three-dimensional dose map by providing the image content regarding the patient and the field geometry information as input to a convolutional neural network model that processes the field geometry information together with the image content regarding the patient to generate the predicted three-dimensional dose map.

5 . The apparatus of claim 4 wherein the control circuit is configured to provide the image content regarding the patient and the field geometry information as input to the convolutional neural network model as stacks of two-dimensional images.

6 . The apparatus of claim 5 wherein the control circuit is configured to provide the stacks of two-dimensional images via corresponding channels.

7 . The apparatus of claim 6 wherein the channels comprise, at least in part:

a computed tomography images channel;

a contoured planning target volume images channel;

a contoured organ-at-risk images channel; and

a field geometry information channel.

8 . The apparatus of claim 7 wherein the field geometry information provided via the field geometry information channel is encoded as imagery.

9 . A method to facilitate providing a radiation treatment plan to administer therapeutic radiation to a patient via a particular radiation treatment platform, the method comprising:

providing a memory having image content regarding the patient and field geometry information regarding the particular radiation treatment platform stored therein; and

by a control circuit operably coupled to the memory, wherein the field geometry information comprises image content of at least one of location positions of a radiation source vis-à-vis a gantry, gantry angles, collimator angles, and jaw positions, wherein the image content regarding the patient and the field geometry information image content have a same resolution:

accessing the image content regarding the patient;

accessing the field geometry information; and

generating a predicted three-dimensional dose map that will result when treating the patient with the radiation treatment plan as a function of both the image content regarding the patient and the field geometry information.

10 . The method of claim 9 wherein the image content regarding the patient comprises, at least in part, at least one organ mask and at least one computed tomography image.

11 . The method of claim 10 wherein the at least one organ mask comprises, at least in part, a contoured planning target volume and at least one contoured organ-at-risk.

12 . The method of claim 9 wherein generating the predicted three-dimensional dose map comprises providing the image content regarding the patient and the field geometry information as input to a convolutional neural network model that processes the field geometry information together with the image content regarding the patient to generate the predicted three-dimensional dose map.

13 . The method of claim 12 wherein providing the image content regarding the patient and the field geometry information as input to the convolutional neural network model comprises providing the image content regarding the patient and the field geometry information as input to the convolutional neural network model as stacks of two-dimensional images.

14 . The method of claim 13 wherein providing the stacks of two-dimensional images comprises providing the stacks of two-dimensional images via corresponding channels.

15 . The method of claim 14 wherein the channels comprise, at least in part:

a computed tomography images channel;

a contoured planning target volume images channel;

a contoured organ-at-risk images channel; and

a field geometry information channel.

16 . The method of claim 15 wherein the field geometry information provided via the field geometry information channel is encoded as imagery.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 4, 2023
From: CZEIZLER, ELENA; KUUSELA, ESA; HAKALA, MIKKO; BASIRI, SHAHAB
To: VARIAN MEDICAL SYSTEMS INTERNATIONAL AG
Reel/Frame 065118/0952 →
CHANGE OF NAME Recorded Oct 4, 2023
From: VARIAN MEDICAL SYSTEMS INTERNATIONAL AG
To: SIEMENS HEALTHINEERS INTERNATIONAL AG
Reel/Frame 065119/0238 →
Continuity (2)
Continuation 16898643 · Jun 11, 2020
Related Publication 20240042238A1 · Feb 8, 2024
References Cited (17)
US 9827445B2 · Cordero Marcos · 2017 [cited by applicant]
US 10850121B2 · Moore · 2020 [cited by applicant]
US 11813479B2 · Czeizler · 2023 [cited by examiner]
US 20080081991A1 · West · 2008 [cited by examiner]
US 20130142310A1 · Fahimian · 2013 [cited by examiner]
US 20170087383A1 · Peltola · 2017 [cited by applicant]
US 20180243584A1 · Nord · 2018 [cited by applicant]
US 20180243586A1 · Ramezanzadeh Moghadam · 2018 [cited by examiner]
US 20190030370A1 · Hibbard · 2019 [cited by applicant]
CN 103561817A · 2014 [cited by applicant]
WO 2018048575A1 · 2018 [cited by applicant]
Fan, Jiawei et al.; Automatic Treatment Planning Based on Three-Dimensional Dose Distribution Predicted from Deep Learning Technique; first published Nov. 2018 in American Association of Physicists in Medicine, https://… [cited by applicant]
International Search Report and Written Opinion from related Application No. PCT/EP2021/065720 dated Sep. 24, 2021; 12 pages. [cited by applicant]
Kearney, Vasant et al.; DoseNet: a Volumetric Dose Prediction Algorithm Using 3D Fully-Convolutional Neural Networks; Physics in Medicine & Biology, 63(23) Dec. 2018; IOP Publishing; 12 pages. [cited by applicant]
Nguyen, Dan et al.; Dose Prediction with U-net: A Feasibility Study for Predicting Dose Distributions from Contours Using Deep Learning on Prostate IMRT Patients; Published 2017; arXiv preprint arXiv:1709.09233; 17 page… [cited by applicant]
Czeizler, Elena et al.; 3D Dose Prediction Model for Head and Neck Cancer Patients by Combining Field Geometry Information with Patient Images; AAPM 61st Annual Meeting & Exhibition, Jul. 14, 2019—Meeting Program—Abstra… [cited by applicant]
First Office Action from related Chinese Application No. 202180039426.6 dated Sep. 16, 2025; English translation included; 22 pages. [cited by applicant]