Using reinforcement learning in radiation treatment planning optimization to locate dose-volume objectives
US-2021379404-A1 · Dec 9, 2021 · US
US12403328B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12403328-B2 |
| Application number | US-202217950005-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 21, 2022 |
| Priority date | Sep 21, 2022 |
| Publication date | Sep 2, 2025 |
| Grant date | Sep 2, 2025 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
One or more new metrics are introduced into the treatment planning process. More specifically, a correcting factor/metric referred to herein as the critical/repair ratio index is introduced, and/or a correcting factor/metric referred to herein as the spatial periodicity of critical isodose value is introduced. By using these metrics, the expected sparing from the spatial distribution of dose is better accounted for in treatment modalities including spatially fractionated radiation therapy (SFRT) in general and SFRT with ultra-high dose rates in particular. According to a treatment planning strategy, the target can be covered by a Spread-Out Bragg Peak, to optimize and/or homogenize the dose distribution at the target level but still benefit from the sparing effect of SFRT at the healthy tissue level. Delivery techniques include a dynamic focusing technique and a magnetic beam steering technique. Enhancing dose rate enables maximizing the peak-to-valley dose distribution with SFRT despite patient motion.
Opening claim text (preview).
What is claimed is: 1. A computer system, comprising: a processor; and memory coupled to the processor and comprising instructions that, when executed, cause the processor to perform a method used for planning radiation treatment of a target volume in a patient, the method comprising: accessing, from the memory, a first candidate radiation treatment plan comprising information describing a spatial distribution of radiation beams; determining a distribution of dose in a volume of tissue that is outside of the target volume and intersected by the radiation beams; determining a value of a metric that is a function of the distribution of the dose in the volume of the tissue; and evaluating the first candidate radiation treatment plan using the value of the metric. 2. The computer system of claim 1 , wherein said determining the value of the metric comprises: determining a value for an amount of the volume of the tissue, wherein the volume of tissue is delineated by an isodose surface; and determining a value for an amount of a surface area of the volume of the tissue; wherein the value of the metric is the value of the amount of the volume of the tissue divided by the value of the amount of the surface area. 3. The computer system of claim 1 , wherein said determining the value of the metric comprises determining a spatial periodicity of an isodose surface that delineates the volume of tissue, wherein the spatial periodicity of the isodose surface is constrained by at least one of a maximum value and a minimum value. 4. The computer system of claim 1 , further comprising maximizing a value for an amount of surface area of an isodose surface delineating the volume of the tissue. 5. The computer system of claim 1 , wherein said evaluating further comprises: determining a respective value of the metric for each candidate radiation treatment plan of a plurality of candidate radiation treatment plans including the first candidate radiation treatment plan; and selecting a radiation treatment plan, from the plurality of candidate radiation treatment plans, having a minimum said respective value of the metric. 6. The computer system of claim 1 , wherein the volume of the tissue is a volume selected from the group consisting of: a volume between an isodose surface and the target volume, and a volume of overlap between an organ-at-risk and an isodose surface. 7. The computer system of claim 1 , wherein the method further comprises determining a dose-volume histogram based on the distribution of the dose in the volume of the tissue and a distribution of dose in the target volume. 8. The computer system of claim 1 , wherein said evaluating produces a final radiation treatment plan that is configured to provide a curative dose across the target volume. 9. The computer system of claim 1 , wherein the radiation beams are proton beams, and wherein the dose is delivered by a treatment system to the volume of the tissue in less than one second. 10. The computer system of claim 1 , wherein the method further comprises determining information for configuring focus points for the radiation beams, and wherein the focus points are at points selected from the group consisting of: points at an interface between air and the patient, and points that optimize the value of the metric and provide a curative dose across the target volume. 11. The computer system of claim 1 , wherein the method further comprises determining information for configuring a plurality of magnets that controls directions of the radiation beams, wherein the plurality of magnets comprises a first set of magnets that steer the radiation beams outward from their initial paths, and wherein the plurality of magnets further comprises a second set of magnets downstream of the first set and that steer the radiation beams toward locations in the target volume. 12. A system, comprising: a beam system that generates radiation beams; a nozzle coupled to the beam system and that directs the radiation beams to a target volume; and a control system coupled to the beam system and to the nozzle, the control system comprising a computer system comprising a processor and a memory coupled to the processor; wherein the memory stores a radiation treatment plan comprising information describing a spatial distribution of the radiation beams and a dose-volume histogram (DVH) for the target volume and for a volume of tissue that is outside of the target volume and intersected by the radiation beams, wherein the DVH is based on a value of a metric that is a function of the spatial distribution of a dose in the volume of the tissue; and wherein the beam system and the nozzle are controlled by the control system according to the radiation treatment plan to deliver the dose to the target volume. 13. The system of claim 12 , wherein the value of the metric is equal to an amount of the volume of the tissue divided by a value of an amount of a surface area of the volume of the tissue, wherein the volume of tissue is delineated by an isodose surface. 14. The system of claim 12 , wherein the metric is a spatial periodicity of an isodose surface that delineates the volume of tissue, wherein the value of the metric is constrained by at least one of a maximum value and a minimum value. 15. The system of claim 12 , wherein the volume of the tissue is a volume selected from the group consisting of: a volume between an isodose surface and the target volume, and a volume of overlap between an organ-at-risk and an isodose surface. 16. The system of claim 12 , wherein the dose delivered to the target volume is a curative dose across the target volume. 17. The system of claim 12 , wherein the radiation beams are proton beams, and wherein the dose is delivered by a treatment system to the volume of the tissue in less than one second. 18. The system of claim 12 , wherein the radiation treatment plan further comprises information for configuring focus points for the beams, and wherein the focus points are points selected from the group consisting of: points at an interface between air and a patient, and points that optimize the value of the metric and provide a curative dose across the target volume. 19. The system of claim 12 , further comprising a plurality of magnets that controls directions of the radiation beams, wherein the plurality of magnets comprises a first set of magnets that steer the beams outward from their initial paths, wherein the plurality of magnets further comprises a second set of magnets downstream of the first set and that steer the radiation beams toward locations in the target volume, and wherein the radiation treatment plan further comprises information for configuring the plurality of magnets. 20. A computer-implemented method used for planning radiation treatment of a target volume in a patient, the method comprising: accessing, from a computer system memory, a candidate radiation treatment plan comprising information describing a spatial distribution of radiation beams; determining a distribution of dose in a volume of tissue that is outside of the target volume and intersected by the radiation beams; determining a value of a metric that is a function of surface area of an isodose surface of the volume of tissue; and determining whether the candidate radiation treatment plan satisfies clinical goals for the radiation treatment using the value of the metric. 21. The computer-implemented method of claim 20 , wherein said determining the value of the metric co
Ions; Protons · CPC title
Beam adjustment · CPC title
taking into account previously administered plans applied to the same patient, i.e. adaptive radiotherapy · CPC title
using a specific method of dose optimization · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.