Granted Patent B2

US 12,734,374 · App. 18/756,991 · Granted Sep 15, 2026

Inventors: Maria Luiza Bondar (Waalre, NL); Matthieu Frederic Bal (Geldrop, NL); Alfonso Agatino Isola (Norderstedt, DE)

Assignee: Elekta Inc.

A61N5/1049A61N2005/1074

Abstract

Claims (37)

1 . A system for monitoring anatomical changes in a subject of radiation therapy, the system comprising:

an analysis unit configured to receive and analyze first and subsequent anatomical image data of the subject;

a change state identification unit configured to identify one or more changes between the first and subsequent anatomical image data as respective change states, wherein the change state identification unit is configured to use a trained learning algorithm for change state identification;

a qualitative translator configured to match the respective change states to corresponding qualitative descriptions; and

a reporting unit configured to provide a monitoring report comprising qualitative descriptions of the respective change states.

2 . The system of claim 1 , wherein the trained learning algorithm is configured to analyze historical data of one or more anatomical changes and corresponding change states to improve accuracy of later change state identifications, and wherein the identified one or more changes are used as input for the trained learning algorithm.

3 . The system of claim 1 , wherein the analysis unit is further configured to perform quantitative image data analysis on the first and subsequent anatomical image data.

4 . The system of claim 3 , wherein the quantitative image data analysis includes determining at least one of: one or more region of interest size changes, a distance that a region of interest has shifted, or a total radiation dose that a region of interest has received.

5 . The system of claim 1 , wherein the reporting unit is configured to generate one or more pictograms for inclusion in the monitoring report.

6 . The system of claim 1 , wherein the reporting unit is configured to provide the monitoring report via a graphical user interface with one or more selectable features for displaying additional information.

7 . The system of claim 1 , wherein the analysis unit is further configured to receive dose distribution data of a treatment plan for the subject, and wherein the change state identification unit is further configured to identify change states using one or more changes between the dose distribution data and the subsequent anatomical image data.

8 . A method for monitoring one or more anatomical changes in a subject in radiation therapy, the method comprising:

receiving and analyzing, by an analysis unit, first and subsequent anatomical image data of the subject;

identifying, by a change state identification unit, one or more changes between the first and subsequent anatomical image data as respective change states, wherein identifying changes comprises using a trained learning algorithm for change state identification;

matching, by a qualitative translator, the identified respective change states to corresponding qualitative descriptions; and

providing, by a reporting unit, a monitoring report comprising one or more qualitative descriptions of the identified respective change states.

9 . The method of claim 8 , wherein the trained learning algorithm analyzes historical data of one or more anatomical changes and corresponding change states to improve accuracy of later change state identifications, and wherein the identified one or more changes are used as input for the trained learning algorithm.

10 . The method of claim 8 , further comprising:

performing quantitative image data analysis on the first and subsequent anatomical image data.

11 . The method of claim 8 , further comprising:

generating one or more pictograms for inclusion in the monitoring report.

12 . The method of claim 8 , further comprising:

receiving dose distribution data of a treatment plan for the subject; and

identifying one or more changes between the dose distribution data and the subsequent anatomical image data as respective change states.

13 . A non-transitory computer-readable medium with instructions stored thereon which, when performed by a processor of a computing device, cause the processor to:

receive and analyze first and subsequent anatomical image data of a subject in radiation therapy;

identify one or more changes between the first and subsequent anatomical image data as respective change states, wherein identifying one or more changes comprises using a trained learning algorithm for change state identification;

match the respective change states to corresponding qualitative descriptions; and

provide a monitoring report comprising qualitative descriptions of respective change states.

14 . The non-transitory computer-readable medium of claim 13 , wherein the trained learning algorithm analyzes historical data of one or more anatomical changes and corresponding change states to improve accuracy of later change state identifications, and wherein the identified one or more changes are used as input for the trained learning algorithm.

15 . The non-transitory computer-readable medium of claim 13 , wherein the instructions further cause the processor to:

perform quantitative image data analysis on the first and subsequent anatomical image data.

16 . The non-transitory computer-readable medium of claim 13 , wherein the instructions further cause the processor to:

generate one or more pictograms for inclusion in the monitoring report.

17 . The non-transitory computer-readable medium of claim 13 , wherein the instructions further cause the processor to:

receive dose distribution data of a treatment plan for the subject; and

identify one or more changes between the dose distribution data and the subsequent anatomical image data as the respective change states.

Assignments (2)

Priority Claims (1)

Continuity (2)

References Cited (40)