Generation method for surgical resection-type sufficient radiation therapy dose plan for large hepatocellular carcinoma

Abstract

The present invention provides a generation method for a surgical resection-type sufficient radiation therapy dose plan for a large hepatocellular carcinoma. Assuming the principles of liver segmentectomy or hemihepatectomy principles when surgical liver resection is used to resect a liver tumor, a radiation therapy plan is generated using a liver region volume remaining after the assumed surgical resection as a target. The method specifically comprises: step 1, obtaining an original medical image; step 2, identifying a target region, a maximal dose region, and a remaining liver region from the original medical image, and obtaining a region identification result; step 3, obtaining a remaining liver region volume, and determining whether the remaining liver region volume is within a preset range; if the remaining liver region volume is not within the preset range, ending; otherwise, executing step 4; step 4, performing radiation therapy plan design on the basis of the region identification result and the original medical image, and obtaining a radiation therapy plan result. The maximum value of the preset range is 700 ml, and the minimum value is 300 ml. The present method can automatically implement radiation therapy plan generation.

Description

A method for generating adequate radiation therapy plans for surgical resection of large liver cancer Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method for generating a sufficient dose radiotherapy plan for surgical resection of large liver cancer. Background Art

[0002] Radiation therapy is one of the most important cancer treatments. For inoperable liver cancer, it is the most effective local treatment. The implementation of radiation therapy relies on the radiation plan, specifically the planning of the radiation area and dose. The rationality of the radiation plan is crucial for both treatment effectiveness and safety. Currently, radiation plan design relies on forward parameter setting by physicists or inverse radiation plan design using commercial software.

[0003] When the forward design method is used, the design of the radiotherapy plan is easily influenced by subjectivity and has low efficiency. When commercial software is used for reverse radiotherapy plan design, although subjective influences can be avoided to a certain extent, in actual application, the dose distribution cannot meet the requirements, and it is impossible to design a radiotherapy plan that meets the requirements for specific types of cancer, resulting in low application efficiency.

[0004] To ensure treatment safety, current international guidelines recommend that radiotherapy be considered for large liver cancers only when the normal liver volume is greater than 700 ml. However, large liver cancers less than 700 ml are common in clinical practice (see Figure 1). These patients are ineligible for radical surgery. Without liver radiotherapy, they lose the opportunity for excellent control and prolonged survival through localized radiotherapy, a treatment option with an 80% efficacy rate. For these patients, if new treatment planning principles are not proposed and only the average dose to the normal remaining liver volume is considered, neither forward planning nor conventional reverse planning using commercial software will meet actual treatment needs. Summary of the Invention

[0005] To address the aforementioned limitations, the present invention leverages the strategy of preserving the remaining liver during radical liver cancer surgery to propose a method for generating adequate radiotherapy plans for surgical resection of large liver cancers. This method, based on concepts similar to segmentectomy and hemihepatectomy during surgical liver resection, assumes that the remaining liver volume after surgical tumor resection is used as the target. Through automated identification of key areas in the original medical images, radiotherapy plans are automatically generated, enabling large liver cancers less than 700 ml to tolerate doses of 50 Gy or more.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for generating a sufficient-dose radiotherapy plan for surgical resection of large liver cancer, the method comprising:

[0008] Step 1: Obtain original medical images;

[0009] Step 2: Identify the target area, the highest dose area, and the remaining liver area from the original medical image to obtain a region recognition result;

[0010] The highest dose area is an area where a preset highest radiation dose is applied;

[0011] Step 3: Obtain the volume of the remaining liver region and determine whether the volume of the remaining liver region is within a preset range; if the volume of the remaining liver region is not within the preset range, then the process ends; otherwise, proceed to step 4;

[0012] The residual liver area volume is the liver volume remaining after the tumor is surgically removed;

[0013] Step 4: Design a radiotherapy plan based on the region recognition results and the original medical image to obtain a radiotherapy plan result;

[0014] The radiotherapy plan result is composed of a number of regional radiation dose results; the regional radiation dose results include regional coordinates and radiation doses.

[0015] Furthermore, the following conditions must be met for radiotherapy planning:

[0016] The irradiation dose of the highest dose area is 50 Gy or more;

[0017] The radiation dose of the remaining liver area is no higher than 500 cGy, and the volume of the remaining liver area is at least 300 ml.

[0018] Furthermore, the maximum value of the preset range is 700 ml and the minimum value is 300 ml.

[0019] Compared with the prior art, the present invention has the following advantages:

[0020] (1) The radiotherapy plan for large liver cancer can be automatically generated based on image recognition technology. The generated radiotherapy plan is of high quality and fast, which improves the work efficiency of doctors.

[0021] (2) The parameter of the residual liver area volume below 500 cGy is proposed. By limiting this parameter to greater than 300 ml, the problem of being unable to generate radiotherapy plans when the residual liver volume is less than 700 ml can be solved, meeting the needs of the actual medical environment.

[0022] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following preferred embodiments are specifically cited and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] FIG1 is a schematic diagram of a large liver cancer with a residual liver area volume of less than 700 ml provided by an embodiment of the present invention.

[0024] FIG2 is a flow chart of a method for generating a surgical resection radiotherapy plan for large liver cancer, provided by an embodiment of the present invention.

[0025] FIG3 is a schematic diagram of a quasi-surgical resection radiotherapy plan result provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following specific embodiments illustrate the embodiments of the present invention. Those skilled in the art can easily understand the other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. In order to further understand the present invention, the present invention is further described in detail below in conjunction with the best embodiment.

[0027] The present invention provides a method for generating a sufficient-dose radiotherapy plan for surgical resection of large liver cancer. Referring to FIG2 , the method comprises the following steps:

[0028] Step 1: Obtain original medical images;

[0029] The original medical image is a liver CT image or MRI image;

[0030] The original medical image must include the complete target area, which is the complete liver area consisting of the tumor area and the remaining liver area; the remaining liver area is the normal liver area;

[0031] Step 2: Identify the target area, the highest dose area, and the remaining liver area from the original medical image to obtain a region recognition result;

[0032] The highest dose area is an area where a preset highest radiation dose is applied;

[0033] Step 3: Obtain the volume of the remaining liver region and determine whether the volume of the remaining liver region is within a preset range; if the volume of the remaining liver region is not within the preset range, then the process ends; otherwise, proceed to step 4;

[0034] The residual liver area volume is the liver volume remaining after the tumor is surgically removed;

[0035] Step 4: Design a radiotherapy plan based on the region recognition results and the original medical image to obtain a radiotherapy plan result;

[0036] 3 , the radiotherapy plan result is composed of several regional radiation dose results; the regional radiation dose results include regional coordinates and radiation doses.

[0037] Furthermore, the following conditions must be met for radiotherapy planning:

[0038] The irradiation dose of the highest dose area is 50 Gy or more;

[0039] The radiation dose of the remaining liver area is no higher than 500 cGy, and the volume of the remaining liver area is at least 300 ml.

[0040] Furthermore, the maximum value of the preset range is 700 ml and the minimum value is 300 ml.

[0041] As an embodiment, the region recognition result is obtained in step 2 by:

[0042] Step 21: performing image preprocessing on the original medical image to obtain a target recognition image;

[0043] Step 22: Identify the target area from the target recognition image using a target recognition algorithm to obtain a first image recognition result;

[0044] Step 23: Based on the first image recognition result, segment the target area in the target recognition image into the remaining liver area and the tumor area using an image segmentation algorithm to obtain a second image recognition result;

[0045] Step 24: Identify the lesion core area from the tumor area of ​​the target identification image using the core area recognition model to obtain a third image recognition result. The lesion core area is the highest dose area, and the dose in this area is more than 50 Gy.

[0046] Furthermore, the target recognition algorithm is implemented using U-Net.

[0047] Furthermore, the image segmentation algorithm is implemented using a semantic segmentation algorithm based on deep learning.

[0048] Furthermore, the core area recognition model is a recognition model trained based on a deep learning algorithm.

[0049] As an example, in step 3, the volume of the remaining liver region can be obtained by estimating and inputting a value.

[0050] As an embodiment, in step 3, the volume of the remaining liver region can also be calculated by obtaining the input target region volume and using the region recognition result; the specific calculation method is:

[0051] Among them, v n is the volume of the remaining liver area, N is the number of image pixels of the remaining liver area, N0 is the number of image pixels of the target area, v0 is the volume of the target area, and α is the preset remaining liver volume correction coefficient.

[0052] As an example, the volume of the remaining liver region in step 3 can also be calculated by the following method: n =v0-v c

[0053] Among them, v n is the volume of the remaining liver area, v0 is the volume of the target area, v c is the volume of the tumor area; the volume of the tumor area is obtained by:

[0054] Among them, N c is the number of image pixels of the tumor area, N0 is the number of image pixels of the target area, v0 is the volume of the target area, and β is the preset tumor volume correction coefficient.

[0055] As an embodiment, performing radiotherapy planning in step 4 specifically includes:

[0056] Step 41: Initialize the radiotherapy plan result, specifically including:

[0057] Setting the region coordinates of the first element of the radiotherapy plan result to the region boundary coordinates of the highest dose region, and setting the radiation dose of the first element of the radiotherapy plan result to the preset highest irradiation dose;

[0058] The preset maximum radiation dose is not less than 50Gy;

[0059] Setting the region coordinates of the last element of the radiotherapy plan result to the region boundary coordinates of the remaining liver region, and setting the radiation dose of the last element of the radiotherapy plan result to 500 cGy;

[0060] Step 42: Calculate the radiation area and radiation dose one by one from the highest dose area to the remaining liver area, and save them in the radiation therapy plan result.

[0061] Step 42 specifically includes:

[0062] Step 421: Set the current region boundary coordinate list as the region boundary coordinate of the highest dose region, and set the radiation dose of the current region to the preset highest radiation dose;

[0063] Step 422: For each boundary point in the current region boundary coordinate list, obtain the corresponding outer point according to the outer point search rule, and combine all outer points to obtain the outer region coordinates;

[0064] Step 423: determine whether the coordinates of all outer points exceed the remaining liver area; if not, execute step 424; otherwise, end;

[0065] Step 424: Subtract the interval radiation dose from the current region radiation dose to obtain the outer layer radiation dose;

[0066] Step 425: Save the outer region coordinates and outer radiation dose at this time to the radiotherapy plan result; at the same time, update the current region boundary coordinate list to the outer region coordinates, and update the current region radiation dose to the outer radiation dose; return to step 422 to continue execution.

[0067] Furthermore, the outer point search rule is calculated as follows:

[0068] (1) Obtain the image feature value f1 of the current boundary point;

[0069] (2) finding the boundary point of the remaining liver region closest to the current boundary point from the boundary of the remaining liver region, and obtaining the image feature value f2 of the point;

[0070] (3) Calculate the image feature gradient value f0, the calculation method is:

[0071] Wherein, M is the preset dose level number, i.e. the level number of radiation dose;

[0072] (4) Select the point on the line connecting the current boundary point and the corresponding boundary point of the remaining liver area that is farthest from the current boundary point and whose image eigenvalue satisfies f1+f0+fb as the outer layer point corresponding to the current boundary point; fb is the preset image eigenvalue deviation.

[0073] Furthermore, the interval radiation dose is calculated as follows:

[0074] Where D0 is the interval radiation dose; D max The preset maximum radiation dose; D min is the preset minimum irradiation dose; M is the preset dose level number.

[0075] As an embodiment, the method of the present invention may be implemented in software and / or a combination of software and hardware, for example, by using an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device.

[0076] The method of the present invention can be implemented in the form of a software program that can be executed by a processor to perform the steps or functions described above. Similarly, the software program (including related data structures) can be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive, a floppy disk, or the like.

[0077] In addition, some steps or functions of the method of the present invention may be implemented using hardware, for example, as a circuit that cooperates with a processor to execute each step or function.

[0078] In addition, a portion of the method described in the present invention may be implemented as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the method and / or technical solution according to the present application through the operation of the computer. The program instructions for invoking the method described in the present invention may be stored in a fixed or removable recording medium, and / or transmitted via a data stream in a broadcast or other signal-carrying medium, and / or stored in a working memory of a computer device that operates according to the program instructions.

[0079] As an embodiment, the present invention also provides a device comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the device is triggered to run the methods and / or technical solutions based on the aforementioned multiple embodiments.

[0080] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all optional embodiments, and the actions and modules involved are not necessarily required by this application.

[0081] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0082] In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that ordinary technicians in this field can implement them. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0083] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as a preferred embodiment, it is not intended to limit the present invention. Any technician familiar with the present profession can make slight changes or modifications to equivalent embodiments using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for generating a sufficient radiotherapy plan for large liver cancer resection surgery, characterized in that the method comprises the following steps: Step 1, obtain the original medical image; Step 2, identify the target area, the highest dose area and the remaining liver area from the original medical image to obtain the area recognition result; The highest dose area is the area where the preset highest irradiation dose is applied; Step 3, obtain the volume of the remaining liver area, and determine whether the volume of the remaining liver area is within the preset range; if the volume of the remaining liver area is not within the preset range, end; otherwise, execute Step 4; The volume of the remaining liver area is the volume of the liver remaining after assuming tumor resection by surgery; Step 4, design a radiotherapy plan based on the area recognition result and the original medical image to obtain the radiotherapy plan result; The radiotherapy plan result consists of several regional radiotherapy dose results; the regional radiotherapy dose result includes the regional coordinates and the radiotherapy dose.

2. The method according to claim 1, characterized in that the original medical image is a liver CT image or an MRI image; The original medical image needs to contain the complete target area, the target area is the complete liver area, and the target area is composed of the tumor area and the remaining liver area.

3. The method according to claim 1, characterized in that the irradiation dose of the highest dose area is above 50 Gy.

4. The method according to claim 1, characterized in that the radiotherapy dose of the remaining liver area is not higher than 500 cGy, and the volume of the remaining liver area reaches at least 300 ml.

5. The method according to claim 1, characterized in that the maximum value of the preset range is 700 ml, and the minimum value is 300 ml.

6. The method according to claim 1, characterized in that in Step 2, obtaining the area recognition result is specifically achieved through the following method: Step 21, perform image preprocessing on the original medical image to obtain the target recognition image; Step 22, identify the target area from the target recognition image by means of the target recognition algorithm to obtain the first image recognition result; Step 23, based on the first image recognition result, segment the target area in the target recognition image into the remaining liver area and the tumor area by means of the image segmentation algorithm to obtain the second image recognition result; Step 24, identify the lesion core area from the tumor area of the target recognition image through the core area recognition model to obtain the third image recognition result, and the lesion core area is the highest dose area.

7. The method according to claim 1, characterized in that in Step 3, the volume of the remaining liver area is calculated by obtaining the volume of the input target area and then using the area recognition result; The specific calculation method for the remaining liver region volume is as follows: where v n is the remaining liver region volume, N is the number of image pixels of the remaining liver region, N0 is the number of image pixels of the target region, v0 is the target region volume, and α is a preset correction coefficient.

8. The method according to claim 1, characterized in that in Step 4, the radiotherapy plan specifically includes: Step 41, initialize the radiotherapy plan result, specifically including: Set the regional coordinates of the first element of the radiotherapy plan result to the regional boundary coordinates of the highest dose area, and set the radiotherapy dose of the first element of the radiotherapy plan result to the preset highest irradiation dose; Set the regional coordinates of the last element of the radiotherapy plan result as the regional boundary coordinates of the remaining liver region, and set the radiation dose of the last element of the radiotherapy plan result as 500 cGy; Step 42: Starting from the highest-dose region, calculate the radiation region and radiation dose one by one for the remaining liver region, and save them to the radiotherapy plan result.

9. The method according to claim 8, wherein Step 42 specifically includes: Step 421: Set the current regional boundary coordinate list as the regional boundary coordinates of the highest-dose region, and at the same time set the current regional radiation dose as the preset maximum irradiation dose; Step 422: For each boundary point in the current regional boundary coordinate list, obtain the corresponding outer point according to the outer point search rule, and the combination of all outer points obtains the outer regional coordinates; Step 423: Determine whether the coordinates of all outer points exceed the remaining liver region; if they do not exceed the remaining liver region, execute Step 424; otherwise, end; Step 424: Subtract the interval radiation dose from the current regional radiation dose to obtain the outer radiation dose; Step 425: Save the outer regional coordinates and the outer radiation dose at this time to the radiotherapy plan result; at the same time, update the current regional boundary coordinate list to the outer regional coordinates, and update the current regional radiation dose to the outer radiation dose; return to Step 422 to continue execution.

10. The method according to claim 8, wherein The outer point search rule is counted as: (1) Obtain the image feature value f1 of the current boundary point; (2) Search for the boundary point of the remaining liver region that is closest to the current boundary point from the regional boundary of the remaining liver region, and obtain the image feature value f2 of this point; (3) Calculate the image feature gradient value f0, and the calculation method is as follows: where M is the preset dose level number, that is, the number of levels of radiation dose; (4) Select the point that is farthest from the current boundary point and whose image feature value satisfies f1 + f0 + fb on the line connecting the current boundary point and the corresponding boundary point of the remaining liver region as the outer point corresponding to the current boundary point; fb is the preset image feature value deviation.

Images