Automatic qualitative description of anatomical change in radiotherapy

An automated system using qualitative spatial reasoning algorithms addresses the inaccuracies in manual monitoring of anatomical changes during radiation therapy, providing rapid and consistent qualitative descriptions through a graphical interface.

JP2024161515AInactive Publication Date: 2024-11-19ELEKTA INK
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
JP2024137472
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2018-12-14
Filing Date
2024-08-17
Publication Date
2024-11-19
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Current methods for monitoring anatomical changes during radiation therapy are prone to errors and inconsistencies due to manual visual assessment and interpretation of quantitative data, leading to potential misinterpretation of spatial relationships and varying qualitative descriptions.

Method used

An automated system for monitoring anatomical changes using qualitative spatial reasoning algorithms, such as RCC-8 and Cardinal spatial reasoning, to identify and classify changes in anatomical images, providing a consistent and qualitative description of these changes through a graphical user interface.

Benefits of technology

The system enables faster, more accurate, and consistent monitoring of anatomical changes during radiation therapy, allowing for quicker identification and reporting of changes in a format understandable by clinicians and patients alike, reducing the need for extensive data explanation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024161515000001_ABST
    Figure 2024161515000001_ABST
Patent Text Reader

Abstract

To provide a system and a method for monitoring an anatomical change in a subject under radiotherapy, an arrangement for medical imaging and analysis, and a computer program for executing the method.SOLUTION: The undermentioned processes are executed for monitoring an anatomical change in a subject under radiotherapy. First anatomical image data and subsequent anatomical image data on the subject are received. The first anatomical image data and the subsequent anatomical image data are analyzed. The analysis includes registration of the subsequent anatomical image data in the first anatomical data. A change between the first anatomical image data and the subsequent anatomical image data is identified as a change state, and the identified change state is caused to coincide with corresponding qualitative descriptions. A monitoring report is provided, which includes the qualitative descriptions of the identified change.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates generally to monitoring anatomical changes, and specifically, but not exclusively, the present invention relates to monitoring anatomical changes in a subject during radiation therapy. [Background technology]

[0002] In radiation therapy, a target structure in a patient's body, such as a tumor, is treated with radiation, which may be in the form of external radiation, such as photons, or particles, such as protons, e.g., in external beam radiation therapy (EBRT). The treatment is delivered in such a way that the radiation dose delivered to the target structure (TS) is as high as possible, while at the same time delivering the lowest possible radiation dose to the surrounding healthy tissues and structures, usually referred to as organs at risk (OAR).

[0003] The treatment typically involves exposing patients to radiation in multiple doses with recovery periods between each dose, a method known as "fractionated radiation therapy," with each session referred to as a "fraction." The rationale for this approach is that TS tumor tissue is believed to recover less well from a dose fraction than healthy tissue, including OARs.

[0004] Fractions are often given over the course of a day, resulting in treatments that are distributed over time. During this time, the patient may undergo anatomical changes, such as organ movement and deformations that occur naturally in the body. Also, each fraction of treatment delivered to the patient may have anatomical effects. In particular, during radiation treatment, it is expected that the target structure, such as the tumor, will shrink. In this context, "during radiation treatment" does not mean the specific time at which the patient is actually exposed to radiation, but the entire time that irradiation is taking place in all treatment fractions, including recovery periods. "During" or "in" radiation treatment refers to a situation in which anatomical changes occur, but the monitoring of the changes is done before or after the delivery of a treatment fraction, not during the actual delivery of the fraction. Anatomical changes occurring in the patient during treatment need to be monitored and evaluated to ensure that the treatment is being delivered appropriately and that modifications or additional measures can be taken if necessary.

[0005] In modern radiotherapy clinical practice, anatomical changes occurring in patients during radiotherapy are monitored and documented in the treatment record. Qualitative descriptions are used to describe, communicate and record the changes, as well as quantitative measurements. Generally, the changes are assessed visually and recorded manually. Visual inspection usually involves manual processing of quantitative measurements and comparison of treatment planning images, such as CT scans, with images acquired in the laboratory, such as cone-beam computed tomography (CBCT) images, planar x-ray images or separately recorded MRI images. The in-lab images are usually taken immediately prior to treatment and are used for both symptom monitoring and patient setup. Summary of the Invention [Problem to be solved by the invention]

[0006] Based on this visual assessment and analysis of the quantitative data, clinicians qualitatively interpret and describe the types of anatomical changes. However, visual assessment, manual processing, and interpretation are error-prone and time-consuming. Such errors occur when clinicians overlook relevant anatomical changes or misinterpret the spatial relationships between objects in different images. Moreover, handwritten input of qualitative descriptions can lead to variability and inconsistencies in the description of similar situations. Furthermore, interpretation of anatomical changes requires analysis of large amounts of data and specialized skills. [Means for solving the problem]

[0007] The present invention aims to provide an automated method for monitoring anatomical changes in a subject undergoing radiation therapy. The present invention further addresses the need for a consistent, qualitative description of anatomical changes in a subject during treatment.

[0008] A system and method for monitoring anatomical changes in a subject during radiation therapy, as well as an arrangement for medical imaging and analysis and a computer program for carrying out the method, are provided. The system for monitoring anatomical changes in a subject during radiation therapy includes an analysis unit with an input configured to receive first anatomical image data and subsequent anatomical image data of the subject, the analysis unit being configured to register at least the subsequent anatomical data to the first anatomical data. The system further includes a change state identification unit configured to identify changes between the first anatomical image data and the subsequent anatomical image data as change states, and a qualitative translator configured to match the identified change states to corresponding qualitative descriptions. Change states are specific classifications in which changes are grouped according to their characteristics. The change states are identified by assigning a classification that best corresponds to the characteristics of the changes between the first anatomical image data and the subsequent anatomical image data. Preferably, the qualitative description is indicative of the characteristics of the change state. More preferably, the qualitative description reflects how a physician would describe the characteristics of the change when monitoring a patient during treatment. The system further comprises a reporting unit configured to provide a monitoring report including a qualitative description of the identified altered state, the corresponding qualitative description being, for example, a natural language description and / or a graphic image, preferably a pictogram, which has the advantage that it is easy to understand not only for clinicians but also for patients and physicians of other disciplines.

[0009] In an embodiment of the system, the change state identification unit includes at least one qualitative spatial reasoning algorithm, the qualitative spatial reasoning algorithm preferably being: RCC -8 computation (calculation) algorithm and / or the Cardinal Spatial Reasoning Algorithm.

[0010] Preferably, the analysis unit of the system further comprises an input configured to receive dose distribution data of a treatment plan for the subject, and the change state identification unit is further or alternatively configured to identify a change between the dose distribution data and subsequent anatomical image data as a change state. Possibly, including this optional input allows the system to further or alternatively monitor anatomical changes of the subject in comparison to the planned dose distribution.

[0011] Preferably, the qualitative translator is configured to match the identified change states to the corresponding qualitative descriptions using a look-up table.

[0012] Preferably, the reporting unit comprises a display adapted to visually display the monitoring report. This is particularly preferred when the monitoring report is a pictorial report. In particular, the display is advantageously adapted to visually display the monitoring report in the form of a graphical user interface. The advantage of presenting the report in the form of a user interface is that depending on the situation, a version of the report can be selected and displayed that is optimal for the situation. Furthermore, it has the advantage that additional data, e.g. patient images, dose information, quantitative data of the analysis results, etc., are available in the background and can be selected and displayed as required. The main report screen is simplified and easier to understand, since no information is displayed if not selected. Preferably, the graphical user interface comprises at least one control for selecting information to be displayed as part of the monitoring report, making optimal use of said options.

[0013] A method for monitoring anatomical changes in a subject undergoing radiation therapy includes receiving first and subsequent anatomical image data of the subject, and analyzing the first and subsequent anatomical image data, the analysis including registering the subsequent anatomical data to the first anatomical data. The method further includes identifying changes between the first and subsequent anatomical image data as change conditions, and matching the identified change conditions to corresponding qualitative descriptions. The method also includes providing a monitoring report including the qualitative descriptions of the identified changes. The method is preferably , executed on a computer.

[0014] In a preferred embodiment of the method, identifying the alteration comprises providing the first anatomical image data and the subsequent anatomical image data to at least one qualitative spatial reasoning algorithm, wherein the qualitative spatial reasoning algorithm preferably comprises: The RCC-8 computation algorithm and / or the Cardinal Spatial Reasoning algorithm.

[0015] Preferably, the step of receiving the first and subsequent anatomical image data of the subject further includes a step of receiving dose distribution data of a treatment plan for the subject, and the step of identifying the change further or alternatively includes a step of identifying a change between the dose distribution data and the subsequent anatomical image data as a change condition.

[0016] In other preferred embodiments, which may be combined in other embodiments or in any suitable combination, analyzing the anatomical image data further comprises acquiring quantitative image data, wherein the image data preferably comprises at least one of the following: a size of the region of interest, a change in size of the region of interest, a distance the region of interest has shifted, and a total radiation dose received by the region of interest. If quantitative image data is acquired, the monitoring report preferably also comprises at least one quantitative description of at least one of the identified changes.

[0017] The medical image processing and analysis arrangement comprises one or more imaging devices configured to provide images of a subject being treated, a contouring tool configured to provide anatomical image data based on images provided by the one or more imaging devices; and the above-mentioned system for monitoring anatomical changes during radiation therapy for monitoring anatomical changes in the subject during radiation therapy. Effect of the Invention

[0018] An advantage of the present invention is that anatomical changes in patients undergoing radiation therapy may be monitored more quickly and more accurately. Identification of the changes as changes allows the changes to be consistently classified. The automated analysis of the first and subsequent images, combined with the automated identification of the changes, is faster and more accurate than manual comparison of the images by a clinician.

[0019] Another advantage of the present invention is that it allows for a more consistent monitoring of anatomical changes in patients undergoing radiation therapy. By identifying the changes as change states, the changes can be consistently classified. Each change state is also matched with a corresponding qualitative description. As a result, changes belonging to the same classification have the same qualitative description. This has the added advantage of making it easier for doctors and clinicians to find similar cases in a database. Another advantage is that the dataset can be used as input for machine learning algorithms.

[0020] A further advantage is that monitoring reports are presented that allow changes to be noted directly without the need for further analysis, and the changes are reported in a qualitative manner, e.g., using language similar to that used by physicians to describe patients' symptoms, so that the reports can be read or viewed by the patient or consulting physician to provide information without extensive explanation of the data.

[0021] Further advantages from the described invention will also be apparent to those skilled in the art. [Brief description of the drawings]

[0022] [Figure 1] FIG. 1 shows a schematic and exemplary diagram of a system for monitoring anatomical changes in a subject during radiation therapy and further elements of an arrangement for medical imaging and analysis. [Diagram 2] 2a and 2b are schematic and exemplary diagrams illustrating the retrieval of states by a qualitative spatial reasoning algorithm. [Diagram 3] FIG. 3 is a schematic and exemplary diagram illustrating an example of a method for monitoring anatomical changes during radiation therapy. [Figure 4] FIG. 4 is a schematic and exemplary diagram illustrating another example of a method for monitoring anatomical changes during radiation therapy. [Diagram 5] FIG. 5 is a schematic and exemplary illustration of an example of a report of monitoring anatomical changes in a subject in the form of a pictographic report. [Figure 6] FIG. 6 is a schematic and exemplary diagram illustrating another example of a report of monitoring anatomical changes in a subject in the form of a graphical user interface. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] 1 illustrates a system 110 for monitoring anatomical changes in a subject during radiation therapy. In this example, the system is illustrated as part of a medical imaging and analysis setup 100.

[0024] In the medical imaging and analysis arrangement 100, a planning image 101 of the subject to be treated is acquired by an imaging device 102. This image may be a computed tomography image (CT), a magnetic resonance image (MR), a positron emission tomography (PET) or other medical image, or a composite image such as a combined PET / CT or PET / MR image. In FIG. 1, a PET / CT imaging device 102 is illustrated as an example. In this first image, a contouring tool 103 is used to define a region of interest (ROI) to provide first anatomical image data 104. The ROI in the subject will include at least one target structure (TS), typically a tumor or one or more organs at risk (OARs). The contouring tool typically interacts with a user, who may be, for example, a trained medical imaging technician or a radiologist, to define the contours of the ROI. This process can be fully manual or partially or fully automated.

[0025] During the course of treatment, at least one subsequent image 105 of the subject is acquired. This image can be acquired using the same imaging device 102 as the planning image, but can also be acquired using one or more alternative imaging devices 106. Such alternative imaging devices can be CT, MR or other medical imaging devices. In a preferred embodiment, the subsequent images are acquired using a second medical imaging device 106, either a cone beam CT (CBCT) or a planar X-ray imager, configured to image the subject in the treatment room. An advantage of this setup is that the images can be used to monitor anatomical changes in the subject and to set up the subject for delivery of radiotherapy treatment fractions.

[0026] In the subsequent image 105, the ROI is also defined using a contouring tool 103 to provide subsequent anatomical image data 107. Contouring can be done from scratch as in the planning image, manually, automatically, or semi-automatically with user interaction. Contouring of the subsequent image can also be done by automatically propagating contours from the planning image 101 to the subsequent image 105 using a process of deformable image registration. When using this process, the user preferably has the option to accept and / or manually correct the automatically propagated contours.

[0027] The anatomical image data 104 and 107 are then analyzed to monitor anatomical changes of the subject. This is done using a system for monitoring anatomical changes during radiation therapy 110. The system includes an analysis unit 111, a change state identification unit 112, a qualitative translator 113 and a reporting unit 114. The analysis unit 111 comprises an input configured to receive the first anatomical image data 104 and the subsequent anatomical image data 107 of the subject.

[0028] The analysis unit 111 is configured to at least register the subsequent anatomical image data 107 to the first anatomical image data 104. As mentioned above, the first planning image 101 may be acquired using an imaging device 102 different from the device 106 used to acquire the subsequent image 105. Also, the subject's position in the imaging device changes slightly for each image acquisition. As a result, the frame of reference of the anatomical image data may differ from image to image, as may the scale. However, for accurate and reliable comparison, it is desirable that the reference frames of the first anatomical image 104 data and the subsequent anatomical image data 107 are the same. It is desirable that the images are of the same scale and have the same coordinate system, so that changes due to changes in the subject's anatomical structure, rather than the circumstances under which the images were acquired, are detected. Therefore, it is necessary to match the scale and reference frame of the subsequent image and its anatomical image data to those of the first anatomical image and its anatomical image data. This matching operation is called "registration". The registration of the subsequent anatomical image data to the first anatomical image data can be performed by identifying and matching anatomical landmarks. Anatomical landmarks are anatomical structures of the subject that are known to change little within the time frame of radiation therapy, such as bone structures. The anatomical landmarks can be part of the anatomical image data in the form of contours, such as contours of bony structures that are part of the image. The subsequent anatomical image data is then scaled, translated, and rotated until the size and position of the anatomical landmarks correspond as closely as possible to the size and position of the anatomical landmarks in the first anatomical image data. Preferably, the registration is automated.

[0029] The analysis unit 111 may further be configured to quantify the anatomical changes between the first anatomical image data and the second anatomical image data. This quantification may be absolute, e.g., the magnitude of the shift of the OAR in millimeters. The quantification may also be relative, e.g., the ratio by which the TS has been reduced. In particular, the analysis unit 111 may be further configured to perform any additional analysis method steps described below with reference to FIG. 4.

[0030] The change state identification unit 112 is configured to identify changes between the first anatomical image data 104 and the subsequent anatomical image data 107 as change states. A change state is a number of predefined categories in which changes are grouped according to their characteristics. A change state is identified by assigning a category that best corresponds to the characteristics of the change between the first anatomical image data and the subsequent anatomical image data. The change state may be based on a category with characteristics predefined by a user, or on a spatial model or a size model. A spatial model defines a change state according to possible relations between two regions. The number and nature of change states of the model depend on the characteristics of interest. The model, or the model used to identify the change state, may be based on a spatial model, a size ... , can be selected accordingly.

[0031] For example, a shift in the ROI may be a characteristic of interest. In this case, the change is classified or modeled according to the magnitude and direction of the shift. A well-known model of direction is the compass direction, which defines four change states: north, south, east, and west. The size of the shift may be classified using a user-defined range, for example, defining three change states (small, medium, and large). In another example, the overlap of the ROI with its original position is of interest. A simple overlap model defines four change states (full overlap, partial overlap, touching, and no overlap). In yet another example, the change in size of the ROI may be a characteristic of interest. In this example, a simple model defines three change states (growth, shrinkage, and no change).

[0032] The qualitative translator 113 is configured to match the change states identified by the change state identification unit 112 to corresponding qualitative descriptions. Preferably, the qualitative descriptions provide an indication of the characteristics of the change state. For example, "OAR shifts to the left" or "TS shrinks". More preferably, the qualitative descriptions reflect how a physician would describe the characteristics of the change when monitoring a patient in treatment. The qualitative translator 113 is preferably configured to match the identified change states to corresponding qualitative descriptions using a look-up table. The look-up table provides a convenient way to consistently use the same qualitative description for each change state when a change state is detected.

[0033] The reporting unit 114 is configured to provide a monitoring report including a qualitative description of the identified change conditions. In the example of Fig. 1, the reporting unit comprises a display 115 for visually displaying the monitoring report. In a preferred embodiment, the monitoring report is displayed in the form of a graphical user interface, for example as illustrated in Fig. 6.

[0034] In the exemplary embodiment illustrated in Fig. 1, the analysis unit 111 of the system for monitoring anatomical variations 110 further comprises an input for receiving dose distribution data 108 of the subject's treatment plan, which may be the same input arranged for receiving the anatomical image data or another input. The dose distribution data preferably comprises a demarcated dose area, for example in the form of isodose contours.

[0035] The fractionated dose area can be used by the system for monitoring anatomical changes in the subject with respect to the planned dose instead of the first anatomical image data 104. To this end, the change state identification unit 112 is preferably further configured to identify changes between the dose distribution data 108 and the subsequent anatomical image data 107 as change states. By including this option, the system can additionally or alternatively monitor anatomical changes in the subject in comparison to the planned dose distribution.

[0036] In one embodiment of the monitoring system 110, the change state identification unit 112 includes at least one qualitative spatial reasoning algorithm, which is preferably an RCC-8 computation algorithm and / or a cardinal spatial reasoning algorithm. Qualitative spatial reasoning is a branch of artificial intelligence that deals with the problem of generating qualitative descriptions that summarize similar quantitative measurements.

[0037] 2a and 2b show a schematic and exemplary depiction of the detection of change states by a qualitative spatial reasoning algorithm.

[0038] FIG. 2a illustrates the detection of a change in the form of a cardinal directional relationship between two objects. The illustration is for 2D cardinal spatial reasoning, but this form of modeling can also be used in 3D. 3D cardinal qualitative spatial reasoning is particularly suitable for detecting and qualitatively describing shifts in ROIs.

[0039] As shown on the left side of Fig. 2a, the ROI 201 forming the basis of the comparison is fitted to a bounding box around which a directional grid is defined, which forms a model of the possible shift states, which for 2D are top, bottom, left and right and have nine change states: SL for top and left, L for left, IL for bottom and left, S for top, 0 for top, I for bottom, SR for top and right, R for right and IR for bottom and right.

[0040] The right side of Fig. 2a illustrates the detection of a change state of an ROI. The ROI in the first anatomical image data 202 is shown with a dotted outline and grid, and the same ROI is shown with a solid outline and bounding box in the subsequent anatomical image data 203. The identified change state is a qualitative description "SL" which corresponds to a form of natural language "ROI has shifted upward and to the left".

[0041] Figure 2(b) shows the change states identified by the RCC-8 calculation. The RCC-8 calculation is a type of region coupling calculation. The RCC-8 calculation models the relationship between two regions into eight possible spatial relationships to form the change states. Although the RCC-8 calculation can be used to describe the change in a single ROI, it is particularly suited to describe the high-dose regions of the dose distribution in a treatment plan and the location and overlap of TSs and OARs. The RCC-8 calculation is also useful for describing the change when TSs and OARs overlap or are in close proximity.

[0042] The changing states of the RCC-8 computational model are, from top to bottom and left to right in Fig. 2b, namely, non-contact DC, partial overlap PO, external contact EC, equivalent EQ, tangent proper part TPP, tangent proper inverse part TPPi, non-tangent proper part NTPP, and non-tangent proper part NTPPi.

[0043] FIG. 2(b) illustrates the change states of ROI A and ROI B. These may be the same ROI, with the first anatomical image data as A and the subsequent anatomical image data as B. For example, if the change state “A NTPpi B” is identified, there may be a corresponding qualitative description in the form of natural language “ROI has shrunk”. Alternatively, for example, if the change state “A DC B” is identified, the natural language of the ROI may be “ROI has completely moved out of its original position”. Alternatively, the ROI may be a dose planning data and ROI B may be an ROI of a subsequent image. For example, if the change state “A NTTPi B” is identified, the natural language may be “ROI enters the high dose treatment region”. Furthermore, A and B may be two different ROIs in the same anatomical image data. For example, if the change state “A PO B” is detected, the corresponding natural language may be “OAR overlaps with TS”.

[0044] A change condition is also identified when there is no change in the subject's anatomical structure and one or more ROIs are substantially identical in the first anatomical image data and the subsequent anatomical image data. An example qualitative description consistent with this condition is "no change in ROIs," which is indicated by "O" in FIG. 2a. , which is detected as “EQ” in Figure 2b.

[0045] 3 illustrates diagrammatically the steps of a method for monitoring anatomical changes in a subject during radiation therapy 300. The method for monitoring anatomical changes in a subject is preceded by the steps of obtaining first anatomical image data 301 and subsequent anatomical data 302. This anatomical image data may be obtained in a similar manner as described above with respect to the medical image analysis arrangement 100 shown in FIG.

[0046] A method 300 for monitoring anatomical changes of a subject during radiation therapy according to the present invention includes receiving 310 first and subsequent anatomical image data of the subject, and analyzing 320 the first and subsequent anatomical image data, including registering the subsequent anatomical data to the first anatomical data. The method further includes identifying 330 changes between the first and subsequent anatomical image data as change conditions, and matching 340 the identified change conditions to corresponding qualitative descriptions. The method also includes providing 350 a monitoring report including the qualitative descriptions of the identified changes.

[0047] Figure 4 illustrates in a schematic manner the steps of another example of a method 400 for monitoring anatomical changes in a subject during radiation therapy. The method 400 of Figure 4 includes method steps 410, 420, 440, and 450 that are similar to steps 310, 320, 340, and 350 of the method 300 shown in Figure 3. However, the method steps of Figure 4 include several additional options compared to the method 300 of Figure 3, which represent advantageous additional options that can be used separately, in subcombinations, or in full combination, as illustrated in Figure 4.

[0048] Advantageously, the system 110 for monitoring anatomical changes illustrated in FIG. 1 may be further configured to perform any or all of these additional steps.

[0049] The method of monitoring anatomical changes in a subject is preceded by obtaining first anatomical image data 301 and subsequent anatomical data 302. The method is also preceded by determining a treatment plan for the subject, including dose distribution data 401.

[0050] A method 400 for monitoring anatomical changes in a subject during radiation therapy according to the present invention includes receiving 410 data, including receiving first and subsequent anatomical image data of the subject, and further including receiving dose distribution data of a treatment plan for the subject.

[0051] The method then includes analyzing 420 the received data. The data analyzing step includes registering 421 subsequent anatomical data to the first anatomical data. In the exemplary embodiment shown in FIG. 4, analyzing the anatomical image data further includes obtaining quantitative image data. Obtaining the quantitative data may include one or more of a measurement of a size or volume of the ROI 422, a change in size or volume of the ROI 423, a distance the ROI has shifted 424, and / or a radiation dose of the ROI 425. The ROI may be one or more OARs and / or one or more TSs. If quantitative data is obtained about the change in the ROI, it may be expressed in absolute values ​​of the change, but it may also be expressed in relative values, for example, in percentages.

[0052] The method further includes identifying changes in the received data as change conditions 430. Changes are identified between the first anatomical image data and the subsequent anatomical image data 431, and also or alternatively between the dose distribution data and the subsequent anatomical image data 432. In both steps, either the first anatomical image data or the dose distribution data and the subsequent anatomical image data are preferably provided to one or more spatial reasoning algorithms.

[0053] The monitoring method of the exemplary embodiment of Fig. 4 includes an optional step of determining the patient's risk factors 426. Quantitative information regarding the dose received by the ROI is preferably calculated and stored for further reference after the delivery of each fraction of the treatment. Such information may include a dose volume histogram, a dose distribution within the ROI, or an average or total dose received by the entire region of the ROI. Calculating and storing this quantitative dose information has the advantage that the dose received by the ROI so far can be combined with the expected dose that will be delivered in the next fraction based on subsequent image data. In clinical practice, the ROI predefines the acceptable limits of one or more statistical descriptors of the received radiation that are considered safe. These statistical descriptors may be, among others, a dose volume histogram, a minimum dose for the entire ROI region, a maximum dose for the entire ROI region, a maximum dose for the hottest subregion of the ROI, an average dose, or an average maximum or minimum dose. The appropriate statistical descriptor is determined by the nature of the ROI. For example, in the case of TS, at least a minimum dose is prescribed to be administered to the entire TS region. Also, for example, in the case of OARs, it may be prescribed that the mean dose should not exceed a certain threshold. If the value of one or more statistical descriptors calculated for the ROI is within a predefined tolerance limit, the risk factor is determined to be low. If the value of one or more statistical descriptors is below the tolerance limit but close to this value, the risk is determined to be medium. If the value of a statistical descriptor of an ROI exceeds the tolerance level of the next fraction, the risk is deemed to be high.

[0054] In step 440 of the method, quantitative data obtained from the analysis and the identified alterations and the identified risk factors are collected and combined. The identified alterations are matched with corresponding descriptions. This step includes matching the identified alterations with corresponding qualitative descriptions 441. The qualitative descriptions can be supplemented, if applicable, by quantitative data 442 and the identified risk factors 443. Preferably, the quantitative data is used to supplement the qualitative natural language description of the identified alterations, e.g. "Tumor TS has shrunk by 10%" or "Organ OAR has shifted 5 mm to the left into high dose areas", and the risk factors measured in 426 can be separately indicated, e.g., as "high", "medium", "low", but preferably are qualitative descriptions in the form of pictorials, e.g., red for high, yellow for medium and green for low. The quantitative data can also be used to supplement the pictorial information, e.g., to indicate the relative magnitude of the pictorial elements.

[0055] In step 444, the collected and combined data is further used to identify whether the current patient's condition requires physician review and follow-up. For example, if the TS is significantly outside the high dose region of the treatment plan, a modification of the treatment plan may be necessary. In other instances, the OAR may have shrunk to the point that additional measures are needed to stabilize the patient and / or mitigate adverse side effects of the treatment.

[0056] The method also includes step 450 of providing a monitoring report that includes a qualitative description of the identified changes. In this embodiment, quantitative information is included in any follow-up and reporting identified in step 444 to alert a physician for review.

[0057] FIG. 5 illustrates diagrammatically an example of a monitoring report 500 of anatomical changes in a subject in the form of a pictorial report. The report is preferably presented on a display. However, a hard copy printout is also possible, which allows easy distribution of the information to the patient undergoing treatment. In this example, the monitoring report 500 is presented in the form of a table. The rows of the table are the regions of interest monitored. In this example, the regions of interest are two OARs, OAR1 and OAR2, located in the treatment area, and a TS in the form of a tumor GTV. The regions of interest can be, for example, the left parotid gland as an OAR and a TS in the form of a tumor located in close proximity to the left parotid gland. The columns represent the patient's condition before the delivery of the fractions of treatment. The F1 column is fraction 1, F2 fraction 2, etc. The illustrated report is provided up to F5 fraction 5. The anatomical changes in the example are analyzed and reported in terms of the dose distribution of the treatment plan. The dose distribution data consists of the contour of the planned target volume PTV. This is the information shown in the title line of the report ROI-PTV.

[0058] The pictogram report shows the change status determined using the RCC-8 calculation. The PTV is represented in each pictogram as a circle with a dotted outline and each ROI is represented as a circle with a solid outline. Quantitative data is added in the form of relative size and distance. The pictograms are further enhanced with risk indicators in the form of shading. Low risk ROIs are unshaded, medium risk ROIs are hatched, and high risk ROIs are medium shading. Alternatively, green, orange, and red colors may be used as risk "signals." This color scheme is familiar and easily recognized.

[0059] The pictorial reports in FIG. 5 can be easily understood not only by the clinician himself, but also by, for example, the patient or a consulting physician in a different medical field. For example, OAR 2 is "OAR 2 is outside the high dose treatment area, low risk". For example, OAR 1 is "OAR 1 is shrinking, moving towards the high dose treatment area, high risk". An example of TS is "The tumor is shrinking, but the shifter is also moving towards the edge of the high dose treatment area" before the delivery of fraction 2.

[0060] In the example of Figure 5, fractions F3-F4 were delivered according to the original treatment plan. However, as a possible alternative strategy, the physician could decide to acquire new planning images and modify the patient's treatment plan instead of proceeding with the delivery, based on the report provided during the pre-delivery setup of fraction 3. The availability of rapidly provided and easily readable automated reports means that setup images acquired from the patient in the treatment room just before delivery can be used for these evaluations. Additional image processing for this purpose can be omitted.

[0061] 6 illustrates, in a schematic manner, another example of a report of monitoring anatomical changes in a subject in the form of a graphical user interface (GUI) 600. The report is preferably presented on a display, such as a desktop computer display, a presentation screen, or a wireless display device. An advantage of displaying the report in a user interface format is that the version of the report most appropriate for the situation can be selected for display. A further advantage is that additional data, such as patient images, dosimetry information, or quantitative data obtained from further analysis, can be available in the background and accessed and displayed as appropriate or required.

[0062] In the example of FIG. 6, the main screen 610 of the GUI is a pictorial report similar to the report 500 shown in FIG. 5, with the same advantages. The rows of the table are also for the regions of interest to be monitored. In this example, the regions of interest are the TS in the form of two OARs, OAR1 and OAR2, again located in the treatment area, and the tumor GTV. The columns represent the patient's condition before the delivery of the fractions of treatment. The F1 column is fraction 1, F2 is fraction 2, etc. An example report is provided up to F5 for fraction 5. Again, the pictorial report shows the changing conditions determined using the RCC-8 calculations and supplemented with quantitative data. Anatomical image data for one image is represented in each pictogram as a circle with a dotted outline, and subsequent images are represented by circles with a solid outline. Quantitative data was added in the form of relative size and distance, and the pictograms were further enhanced by a risk indicator in shading.

[0063] The anatomical changes in this example GUI are analyzed and reported with respect to the initial image data used in the treatment plan and the dose distribution of the treatment plan. The GUI has a screen selector in the form of a drop down menu 611 that allows the user to select either a report of a comparison of the subsequent anatomical image data with the dose distribution data, shown as ROI-PTV in Figure 5, or a comparison of the subsequent anatomical image data with the first anatomical image data, shown as ROI-CT in Figure 6. The main screen, Figure 6, shows the option to compare the subsequent anatomical image data of each fraction with the first anatomical image data obtained from the planning CT image.

[0064] In addition to the example drop-down menu 611, the GUI 600 of FIG. 6 has more controls to select the information to be displayed as part of the monitoring report. Each pictorial representation of the data table in the main screen 610 allows access to further data available for the transition state, thereby providing individual controls for each transition state. The data can be accessed, for example, by clicking on the pictorial representation with a mouse or via arrow key navigation within the table. In the GUI of FIG. 6, when a state is selected, a new additional screen 620 is opened. In this example, additional information is shown regarding the transition state of OAR1 compared to the planning CT before delivering fraction 4 for radiation therapy.

[0065] The additional screen 620 shows a natural language description 621 of the change state supplemented with additional quantitative information. In this example, "GTV increases by 15% and shifts right by 5", which provides an easy and consistent understanding of the pictorial visual display. The natural language description can be used by the doctor or clinician when explaining the pictorial report to a patient or a colleague. The additional screen 620 also provides further access to more detailed information. In this example, access is provided via three controls in the form of three buttons 622, 623, and 624, although more or less buttons are also possible, as are alternative access options such as drop-down menus.

[0066] Button 622 is a "View Image" button configured to open an additional screen showing subsequent images of the subject. Preferably, the images also display anatomical image data in the form of OAR and TS contours. A particularly advantageous option of this screen is to display subsequent images together with the first anatomical image data, side-by-side with the first anatomical image data, allowing the user to visually inspect and compare.

[0067] Button 623 is a "Dose Report" button that is configured to open an additional screen that displays the dose report. The dose report can be shown in an image, a table, or a dose volume histogram. The dose report can also be interactive to allow the user to explore and view multiple forms of dose information.

[0068] Button 624 is a "Change Report" button configured to open an additional screen 630 showing a change report. The change report provides additional quantitative data regarding the changes in the subsequent anatomical image data. In the example shown in FIG. 6, the additional screen shows a report title 631 and the change report in the form of a data table 632.

[0069] Any of the method steps disclosed herein may be recorded in the form of a computer program containing instructions that, when executed on a processor, cause the processor to perform such method steps. Such instructions may be stored in a computer program product. The computer program product may be provided by dedicated hardware as well as hardware capable of executing software in association with appropriate software. When provided by a processor, the functionality may be provided by a single dedicated processor, by a single shared processor, or by multiple individual processors, some of which may be shared. Furthermore, embodiments of the invention may be in the form of a computer program product accessible from a computer-enabled or computer-readable storage medium that provides program code for use by or in connection with a computer or any instruction execution system. For purposes of this description, a computer-enabled or computer-readable storage medium may be any device that can contain, store, communicate, propagate, or transport a program for use in connection with or by an instruction execution system, device, or the like. The medium may be an electronic, magnetic, optical, electromagnetic, infrared, semiconductor system, apparatus, device, or propagation medium. Examples of computer-readable media include semiconductor or solid state memory, magnetic tape, removable computer diskettes, random access memory "RAM", read only memory "ROM", rigid magnetic disks, and optical disks. Recent examples of optical disks include compact disk-read only memory "CD-ROM", compact disk-read / write "CD-R / W", Blu-Ray™, and DVD. An example of a propagation medium is the Internet or other wired or wireless communication systems.

[0070] Variations of the disclosed embodiments can be understood and implemented by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. It should be noted that the various embodiments can be combined to achieve further advantageous effects.

[0071] The word "comprising" in the claims does not exclude other elements or steps, and the indefinite article "a" or "an" (original) does not exclude a plurality.

[0072] A single unit or device may fulfill the functions of certain items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0073] Any reference signs in the claims shall not be construed as limiting their scope.

Claims

1. A system for monitoring anatomical changes in a subject during radiation therapy, comprising: - an analysis unit, comprising an input configured to receive first anatomical image data and subsequent anatomical image data of said subject, said analysis unit being configured to register at least said subsequent anatomical data to said first anatomical data; a change state identification unit configured to identify a change between said first anatomical image data and said subsequent anatomical image data as a change state; - a qualitative translator configured to match the identified change states to corresponding qualitative descriptions; - a reporting unit configured to provide a monitoring report including a qualitative description of the identified altered conditions.

2. The system of claim 1, wherein the change state identification unit comprises at least one qualitative spatial reasoning algorithm, the qualitative spatial reasoning algorithm being preferably an RCC-8 computation algorithm and / or a Cardinal Spatial Reasoning Algorithm.

3. 3. The system of claim 1 or 2, wherein the analysis unit further comprises an input configured to receive dose distribution data of a treatment plan for the subject; and the change state identification unit is further or alternatively configured to identify a change between the dose distribution data and subsequent anatomical image data as a change state.

4. The system of any one of claims 1 to 3, wherein the qualitative translator is configured to match the identified change states to the corresponding qualitative descriptions using a look-up table.

5. The system according to any one of claims 1 to 4, wherein the corresponding qualitative description is a natural language description and / or a graphic image, preferably a pictogram.

6. The system according to any one of claims 1 to 5, wherein the reporting unit comprises a display configured to visually display the monitoring report.

7. The system of claim 6 , wherein the display is configured to visually display the monitoring report in the form of a graphical user interface.

8. The system of claim 7 , wherein the graphical user interface comprises at least one control for selecting information to be displayed as part of the monitoring report.

9. 1. A method for monitoring anatomical changes in a subject undergoing radiation therapy, comprising: : - receiving first and subsequent anatomical image data of the subject; - analyzing the first anatomical image data and the subsequent anatomical image data, the analysis including registering the subsequent anatomical data to the first anatomical data; - identifying a change between the first anatomical image data and the subsequent anatomical image data as a change state; - matching the identified change states to corresponding qualitative descriptions; and - providing a monitoring report comprising a qualitative description of the identified changes.

10. 10. The method of claim 9, wherein identifying the change comprises feeding the first anatomical image data and the subsequent anatomical image data to at least one qualitative spatial reasoning algorithm, wherein the qualitative spatial reasoning algorithm is preferably an RCC-8 computational algorithm and / or a Cardinal Spatial Reasoning Algorithm.

11. 11. The method of claim 9 or 10, wherein receiving the first and subsequent anatomical image data of the subject further comprises receiving dose distribution data of a treatment plan for the subject; and wherein identifying the change further or alternatively comprises identifying a change between the dose distribution data and the subsequent anatomical image data as a change condition.

12. 12. The method of any one of claims 9 to 11, wherein analysing the anatomical image data further comprises acquiring quantitative image data, wherein the image data preferably comprises at least one of the following: size of the region of interest, size change of the region of interest, distance the region of interest has shifted, and total radiation dose received by the region of interest.

13. The method of claim 12 , wherein the monitoring report further comprises at least one quantitative description of at least one of the identified changes.

14. 1. An arrangement for medical image processing and analysis, comprising: - one or more imaging devices configured to provide images of a subject to be treated; - a contouring tool configured to provide anatomical image data based on images provided by said one or more imaging devices; - a system according to claim 1 for monitoring anatomical changes in a subject during radiation therapy.

15. A computer program comprising instructions which, when executed by a processor, cause the processor to carry out a method according to any of claims 9 to 13.

Citation Information

Patent Citations

  • Ultrasonic diagnostic equipment

    JP1999299791A

  • Radiotherapy system and control method for the same

    JP2012024145A

  • Image processing system, image processing device, image processing method, and medical image diagnostic device

    JP2013039360A

  • Radiation therapy information generating device

    JP2013059576A

  • Radiotherapy treatment apparatus, system and method

    JP2015083068A