Search

EP-4736943-A2 - PATIENT MOTION TRACKING SYSTEM CONFIGURED FOR AUTOMATIC ROI GENERATION

EP4736943A2EP 4736943 A2EP4736943 A2EP 4736943A2EP-4736943-A2

Abstract

The present disclosure relates to a patient motion tracking system for automatic generation of a region of interest on a 3D surface of a patient positioned in a radiotherapy treatment room. More particularly, the disclosure relates to an assistive approach of a motion tracking system, by which a region of interest (ROI) is automatically generated on a generated 3D surface of the patient. Furthermore, a method for automatically generating a ROI on the 3D surface of the patient is described. In particular, all the embodiments refer to systems integrating methods for automatic ROI generation in a radiotherapy treatment setup.

Inventors

  • KERAUDREN, Kevin

Assignees

  • Vision RT Limited

Dates

Publication Date
20260506
Application Date
20200618

Claims (14)

  1. A patient motion tracking system for automatic generation of a region of interest on a 3D surface of a patient, the system comprising: a memory comprising stored region of interest (ROI) descriptive data; a 3D surface generation processor configured to utilize an input surface, and generate a 3D surface from said input surface; a ROI generation processor configured to utilize said stored ROI descriptive data and said 3D surface to output a ROI labelled 3D surface to a display and/or a motion tracking module, a quality module, configured to evaluate the quality of the ROI labelled 3D surface.
  2. System according to claim 1, wherein the quality module is configured to evaluate the quality of a ROI label forming part of the ROI labelled 3D surface.
  3. System according to claim 1 or 2, wherein the quality module is configured to estimate one or more geometric measurements of 3D data in said ROI labelled 3D surface and to compare said estimated geometric measurements with one or more set thresholds.
  4. System according to claim 3, wherein the geometric measurements are one of the following geometric measurements: - points or triangles in the ROI labelled 3D surface, - angle of the ROI labelled 3D surface, - curvatures of the ROI labelled 3D surface, - dimensions of the ROI labelled 3D surface, or - size of the ROI labelled 3D surface.
  5. System according to claim 3 or 4, wherein the quality module is configured to determine that the quality of the ROI labelled 3D surface is sufficient when the one or more estimated geometric measurements is lower than the one or more set thresholds.
  6. System according to claims 2 and 3-5, wherein the size of the one or more set thresholds is set on the basis of the amount of data contained within the ROI label of the ROI labelled 3D surface.
  7. System according to any one of claims 3-6, wherein the size of the one or more set thresholds is set based on a percentage measure between a reference data amount needed for the ROI labelled 3D surface to be used for motion tracking and the actual amount of data in the generated ROI labelled 3D surface.
  8. System according to any one of claims 1-7, wherein the system output an evaluation to a user, the evaluation being an indicator that the ROI labelled 3D surface is appropriate for motion tracking, or an indicator that the ROI labelled 3D surface should be adjusted to create a more appropriate 3D labelled 3D surface for motion tracking.
  9. System according to claim 8, wherein the ROI labelled 3D surface is input to the motion tracking module if the evaluation is the indicator that the ROI labelled 3D surface is appropriate for motion tracking.
  10. System according to any one of claims 1-9, wherein the patient is positioned in a radiotherapy treatment room, and wherein the system comprises a 3D scanning reconstruction system configured to be arranged in the radiotherapy treatment room and configured to generate said input surface.
  11. System according to any one of claims 1-10, wherein the 3D surface comprises at least a target area of the input surface, and the input surface is configured as a series of 2D image frames of at least said target area of said patient and said 3D surface generation processor is configured to generate from said 2D image frames said 3D surface.
  12. System according to claims 10 and 11, wherein the system furthermore comprises one or more cameras configured to be arranged in the radiotherapy treatment room and to obtain said series of 2D image frames of at least the target area of the patient.
  13. System according to any one of the previous claims, wherein said ROI labelled 3D surface is configured to be input to said display unit, wherein said display unit is configured to allow said user to adjust said region of interest via control inputs to the ROI generation processor, wherein the control inputs utilizes an adjustment of at least the borders of the ROI label of the ROI labelled 3D surface.
  14. System according to any one of the previous claims, wherein said ROI labelled 3D surface is utilized by the motion tracking module to track motion of patient during positioning and/or treatment of said patient in the treatment room.

Description

FIELD The present disclosure relates to a patient motion tracking system for automatic generation of a region of interest on a 3D surface of a patient positioned in a radiotherapy treatment room. More particularly, the disclosure relates to an assistive approach of a motion tracking system, by which a region of interest (ROI) is automatically generated on a generated 3D surface of the patient. Furthermore, a method for automatically generating a ROI on the 3D surface of the patient is described. In particular, all the embodiments refer to systems integrating methods for automatic ROI generation in a radiotherapy treatment setup. BACKGROUND Selecting a Region of Interest (ROI) is an important step in radiotherapy, especially in Surface Guided RadioTherapy (SGRT). The region of interest is the region of the patient's anatomy usually containing the target area for radiation. This ROI is often used for patient positioning and motion tracking monitoring of the patient during positioning and treatment of the patient, respectively. Thus, the region of interest should be clinically relevant, and should preferably be appropriately located with regards to the patient tumour, i.e. concentrated around the target area, which are to be treated with radiation therapy. In a radiation setup, the patient is normally immobilized by a restraining device, such as a head restrain, abdominal restrain, or similar device holding the patient in place on a couch in the treatment room. For the motion tracking to be fast and accurate, the region of interest should preferably exclude such immobilization devices, and thus only contain the target area of the patient. It should also be of appropriate size to ensure reliable surface registration and adequate framerate. Thus, the performance of the patient motion tracking system is dependent on how well a ROI is defined on the patient. The ROI is typically drawn on the patient surface in an imaging software, by the clinician treating the patient. In existing systems, the user denotes manually the area intended to cover the region of interest, for example with brush strokes or rectangular selections on a screen image of the patient. This manual process of denoting (i.e. drawing up) the ROI on each patient is a time-consuming process, which prolongs the treatment time of each patient undergoing radiotherapy. Further, the clinicians need to have some knowledge and practice in order to draw an optimal ROI for each anatomical site. Different anatomical sites may require different ROIs drawn up, and the ROI and clinicians therefore receive some training in order to know what kind of ROI to use for each anatomical site. Thus, there is a need to provide a simplified solution that addresses at least some of the above-mentioned problems and allows for an optimized process for identifying and marking the ROI of each patient undergoing radiotherapy. SUMMARY Accordingly, a simplified patient motion tracking system for automatic generation of a region of interest (ROI) in a 3D surface of a patient is disclosed. In more detail, the disclosure describes systems and methods for automatic generation of a ROI on a 3D surface in an imaging software, based on minimal user input. The patient motion tracking system described in different examples herein is generally configured to track at least a part of a patient during radiotherapy treatment. Especially, the part of the patient being tracked by the system is configured as a region of interest covering a target area (i.e. a cancerous tissue area) of the patient. An accurate estimation and generation of the ROI is important for the accuracy of the motion tracking system, which is why the disclosure more specifically focusses on a system enabling automatic generation of a region of interest on a generated 3D surface of a patient positioned in a radiotherapy treatment room. Accordingly, in one embodiment, the system comprises a memory comprising stored region of interest (ROI) descriptive data, a 3D surface generation processor configured to utilize an input surface, and to generate a 3D surface from the input surface. The 3D surface preferably comprises at least a target area of the input surface, where the target area is defined as a part of the patient surface where the cancer tissue is concentrated. The system furthermore comprises a ROI generation processor configured to utilize the stored ROI descriptive data and the 3D surface to output a ROI labelled 3D surface to a display and a motion tracking module, wherein the ROI labelled 3D surface is utilized by the motion tracking module to track motion of the patient during positioning and/or treatment of said patient in the treatment room. It should be understood that the "ROI labelled 3D surface" is the 3D surface of the patient having a ROI applied thereto. Thus, the 3D surface is generated by the 3D surface generation processor, then processed and output by the system as a ROI labelled version of the generated