Follow-up information determination method, device, equipment and readable storage medium

Abstract

The application discloses a follow-up information determination method, device and equipment and a readable storage medium. The follow-up information determination method comprises the following steps: acquiring ultrasonic imaging data and elastic imaging data of an ex vivo target tissue; extracting component information of the ex vivo target tissue at different positions from the ultrasonic imaging data to obtain component distribution information of the ex vivo target tissue, and extracting elastic information of the ex vivo target tissue at different positions from the elastic imaging data to obtain elastic distribution information of the ex vivo target tissue; and inputting the component distribution information and the elastic distribution information into a fusion model, and outputting follow-up information corresponding to the ex vivo target tissue from the fusion model. The acquisition efficiency and accuracy of the follow-up information can be improved.

Description

Technical Field

[0001] This invention relates to the field of biomedicine, and more specifically to a method, apparatus, device, and readable storage medium for determining follow-up information. Background Technology

[0002] Treatment methods for human tissues (such as tumor tissue, benign lesions, etc.) can include excision and drug therapy. Typically, after performing an excision or drug therapy, medical staff will arrange follow-up appointments for patients to continue monitoring the treatment's effectiveness and changes in their condition. The specific follow-up information varies depending on the individual patient's situation, such as the duration of follow-up. For example, some patients require follow-up within one week after the excision, some within three months, and some monthly for up to six months.

[0003] Currently, the follow-up time after human tissue excision is determined manually by medical staff based on an analysis of the patient's actual condition, which is inefficient. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, device, and computer-readable storage medium for determining follow-up information, which can improve the efficiency and accuracy of obtaining follow-up information.

[0005] This invention provides a method for determining follow-up information, the method comprising:

[0006] Acquire ultrasound and elastography data of isolated target tissues;

[0007] From the ultrasound imaging data, the composition information of the isolated target tissue at different locations is obtained, and the composition distribution information of the isolated target tissue is obtained.

[0008] From the elastic imaging data, the elasticity information of the isolated target tissue at different locations is obtained, thus obtaining the elasticity distribution information of the isolated target tissue; and

[0009] The component distribution information and the elasticity distribution information are input into the fusion model, and the fusion model outputs follow-up information corresponding to the ex vivo target tissue.

[0010] In some embodiments, the follow-up information includes at least the follow-up time.

[0011] In some embodiments, the output of follow-up information corresponding to the ex vivo target tissue includes:

[0012] Follow-up information is output according to multiple different operational dimensions, with each operational dimension corresponding to a follow-up information. The operational dimension is used to represent the type of operation for the target tissue, which is the tissue in which the ex vivo target tissue was located before it was ex vivo.

[0013] In some embodiments, the follow-up information output by the fusion model corresponding to the ex vivo target tissue includes:

[0014] Based on the respective weights of the component distribution information and the elasticity distribution information, the fusion model performs a fusion calculation on the component distribution information and the elasticity distribution information to obtain follow-up information corresponding to the ex vivo target tissue.

[0015] In some embodiments, the weights of the component distribution information and the elasticity distribution information are obtained based on the following method:

[0016] The training data and its label information are input into the fusion model, which then learns the weights of the component distribution information and the elasticity distribution information.

[0017] In some embodiments, acquiring the ultrasound imaging data and elastography data of the ex vivo target tissue includes:

[0018] Under the condition that the ambient temperature of the isolated target tissue does not exceed the temperature threshold, ultrasound imaging data and elastography data of the isolated target tissue are acquired.

[0019] In some embodiments, acquiring the ultrasound imaging data and elastography data of the ex vivo target tissue includes:

[0020] The ambient temperature of the ex vivo target tissue is controlled to not exceed a temperature threshold.

[0021] The ex vivo target tissue is fixed in a tissue carrier, and ultrasound imaging data and elastography data of the fixed ex vivo target tissue are obtained.

[0022] In some embodiments, obtaining elastic information of the isolated target tissue at different locations from the elastic imaging data to obtain elastic distribution information of the isolated target tissue includes:

[0023] From the elastic imaging data, obtain the absolute elasticity information of the ex vivo target tissue at different locations;

[0024] From the elasticity imaging data, obtain the relative elasticity information and absolute elasticity information of the ex vivo target tissue at different locations;

[0025] For each location, the relative elasticity information and absolute elasticity information of the isolated target tissue at that location are fused to obtain the elasticity distribution information of the isolated target tissue.

[0026] In some embodiments, the follow-up information output by the fusion model corresponding to the ex vivo target tissue includes:

[0027] The tissue properties of the ex vivo target tissue are obtained by fusing the component distribution information and the elasticity distribution information.

[0028] Based on the correspondence between the tissue nature and follow-up information, the follow-up information corresponding to the ex vivo target tissue is output.

[0029] In another aspect, the present invention provides a follow-up information determination device, the device comprising:

[0030] The data acquisition module is used to acquire ultrasound imaging data and elastography data of isolated target tissues;

[0031] The first data analysis module is used to obtain the composition information of the isolated target tissue at different locations from the ultrasound imaging data, and to obtain the composition distribution information of the isolated target tissue.

[0032] The second data analysis module is used to obtain elastic information of the isolated target tissue at different locations from the elastic imaging data, thereby obtaining elastic distribution information of the isolated target tissue; and

[0033] The follow-up information determination module is used to input the component distribution information and the elasticity distribution information into the fusion model, and the fusion model outputs follow-up information corresponding to the ex vivo target tissue.

[0034] In another aspect, the present invention provides a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the method described above.

[0035] In another aspect, the present invention provides an electronic device comprising a processor and a memory, the memory being used to store a computer program which, when executed by the processor, implements the method described above.

[0036] In some embodiments of this application, the components of the isolated target tissue at different locations are extracted from ultrasound imaging data, and the elasticity of the isolated target tissue at different locations is extracted from elastography data, thus obtaining component distribution information and elasticity distribution information of the isolated target tissue. A fusion model then outputs follow-up information corresponding to the isolated target tissue based on the component distribution information and elasticity distribution information. In this way, medical personnel no longer need to spend time manually determining follow-up information, thereby improving the efficiency and accuracy of follow-up information acquisition. Attached Figure Description

[0037] The features and advantages of the invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the invention in any way. In the drawings:

[0038] Figure 1 A flowchart illustrating a method for determining follow-up information according to an embodiment of this application is shown;

[0039] Figure 2 A schematic diagram of an ex vivo target tissue provided in one embodiment of this application is shown;

[0040] Figure 3 A schematic diagram of the functional modules of a follow-up information determination device provided in one embodiment of this application is shown;

[0041] Figure 4 A schematic diagram of the structure of an electronic device provided in one embodiment of this application is shown. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Please see Figure 1 This is a schematic flowchart illustrating a method for determining follow-up information according to an embodiment of this application. The method for determining follow-up information can be applied to electronic devices. Electronic devices include, but are not limited to, medical devices. Figure 1 In China, the method for determining follow-up information includes the following steps:

[0044] Step S11: Acquire ultrasound imaging data and elastography data of the isolated target tissue.

[0045] In this embodiment, the ex vivo target tissue includes, but is not limited to, ex vivo tumor tissue, ex vivo nodules, and ex vivo benign lesion tissue. The ex vivo target tissue can be obtained by rotary cutting with a rotary cutting device, by surgical resection, or by other methods. This application does not limit the specific method of obtaining the ex vivo target tissue.

[0046] In some embodiments, ultrasound imaging and elastography data of the isolated target tissue can be acquired when the ambient temperature does not exceed a temperature threshold. Maintaining an ambient temperature below the temperature threshold ensures that the isolated target tissue does not denature and retains its original properties. In this embodiment, the temperature threshold is 50 degrees Celsius.

[0047] In some embodiments, the ambient temperature of the isolated target tissue can be controlled to not exceed a temperature threshold, and the isolated target tissue can be fixed in a tissue carrier to obtain ultrasound imaging data and elastography data of the fixed isolated target tissue.

[0048] For isolated target tissues (i.e., after they have become isolated target tissues), the temperature of the environment in which the isolated target tissues are located is kept below the temperature threshold before, during and after fixation, in order to ensure that the isolated target tissues do not denature and retain their original properties.

[0049] In some embodiments, the tissue carrier includes, but is not limited to, agar and gelatin. Fixing isolated target tissue with agar or gelatin not only achieves effective fixation of the isolated target tissue, but also ensures that subsequent ultrasound imaging data and elastography data can be easily and stably acquired.

[0050] In this embodiment, the ultrasound imaging data can be B-mode ultrasound imaging data of the isolated target tissue, specifically including but not limited to the scattering coefficient, attenuation, and scatterer distribution characteristic parameters of the isolated target tissue. The elastic imaging data can be quasi-static elastic imaging data and shear wave elastic imaging data of the isolated target tissue, specifically including but not limited to the elastic modulus, elastic distribution parameters, viscoelastic parameters, and dispersion curves of the isolated target tissue. Those skilled in the art can obtain B-mode ultrasound imaging data, quasi-static elastic imaging data, and shear wave elastic imaging data using various techniques, which will not be elaborated upon here.

[0051] Step S12: Obtain the composition information of the isolated target tissue at different locations from the ultrasound imaging data to obtain the composition distribution information of the isolated target tissue.

[0052] In some embodiments, component distribution information is used to characterize the composition of the target tissue at different locations. The components may include the constituent substances of the isolated target tissue and their concentrations. Constituent substances include, but are not limited to, water, fat, and protein. The concentration of each constituent substance may be the percentage of each constituent substance in the target tissue. The constituent substances and their concentrations can be collectively referred to as the composition of the isolated target tissue. Different locations within the isolated target tissue may have corresponding compositions. Component distribution information is used to characterize the composition at different locations within the isolated target tissue. For example, please refer to... Figure 2 This is a schematic diagram of an ex vivo target tissue provided in one embodiment of this application. Figure 2 In this study, the isolated target tissue was divided into five regions: A, B, C, D, and E. Taking protein content as an example, the protein content of tissue in region A might be 30%, that in region B might be 50%, and that in regions C, D, and E might be 10%.

[0053] Step S13: Obtain elastic information of the isolated target tissue at different locations from the elastic imaging data to obtain the elastic distribution information of the isolated target tissue.

[0054] In some embodiments, similar to the constituent components, different locations within the isolated target tissue may also exhibit corresponding elasticity. Elasticity distribution information is used to characterize the elasticity at different locations within the isolated target tissue.

[0055] In some embodiments, absolute and relative elasticity information of the isolated target tissue at different locations can be obtained from elasticity imaging data. For each location, the relative and absolute elasticity information of the isolated target tissue at that location are fused to obtain the elasticity distribution information of the isolated target tissue. For any location of the target tissue, relative elasticity can refer to the elastic characteristics of that location relative to the elasticity of other locations. For example, the elasticity at that location is better or worse than the elasticity at other locations. Absolute elasticity can refer to the elastic modulus at various locations of the target tissue.

[0056] Specifically, the elasticity imaging data of the target tissue can include shear wave elastography data and quasi-static elastography data. Shear wave elastography data is obtained by performing shear wave elastography on the target tissue, while quasi-static elastography data is obtained by performing quasi-static elastography on the target tissue. The absolute elasticity of the target tissue at different locations can be obtained from the shear wave elastography data, and the relative elasticity of the target tissue at different locations can be obtained from the quasi-static elastography data.

[0057] Step S14: Input the component distribution information and elasticity distribution information into the fusion model, and the fusion model outputs the follow-up information corresponding to the ex vivo target tissue.

[0058] The follow-up information for the isolated target tissue is the same as the follow-up information for the corresponding organism. The component distribution and elasticity distribution information of the isolated target tissue can both be used for pathological analysis. For example, Figure 2 In the study, region B had the highest protein content, indicating faster tissue metabolism in region B and potential issues with abnormal cell replication. The isolated target tissue in this region might be malignant. For example, Figure 2 In this context, assuming that the elasticity of tissue region B is lower than that of tissue region A, it can be assumed that tissue region B is harder than tissue region A, and the degree of fibrosis in tissue region B may be more severe than that in tissue region A.

[0059] In some embodiments, the follow-up information includes at least the follow-up time, which may refer to the time of the first follow-up or the time of each follow-up when multiple follow-ups are conducted. Preferably, in addition to the follow-up time, the follow-up information may also include the follow-up frequency, the number of follow-ups, etc.

[0060] In some embodiments, the fusion model is pre-trained and can perform fusion calculations on component distribution information and elasticity distribution information to obtain follow-up information. Fusion calculation refers to the comprehensive evaluation of the component distribution information and elasticity distribution information of the ex vivo target tissue to obtain follow-up information corresponding to the ex vivo target tissue. For example, if the comprehensive evaluation of the component distribution information and elasticity distribution information of the ex vivo target tissue determines that the tissue is benign, then the follow-up frequency in the corresponding follow-up information can be lower, i.e., fewer follow-up visits. However, if the comprehensive evaluation of the component distribution information and elasticity distribution information of the ex vivo target tissue determines that the tissue is malignant, then the follow-up frequency in the corresponding follow-up information can be higher, i.e., more follow-up visits.

[0061] If the target tissue is an ex vivo nodule or benign lesion, the follow-up frequency will be relatively lower and the follow-up interval will be relatively longer compared with that of an ex vivo tumor tissue.

[0062] In some embodiments, considering the different impacts of component distribution information and elasticity distribution information on follow-up information, their influence can be characterized by weights. Distribution information with a greater impact on follow-up information can have a larger weight, while distribution information with a smaller impact can have a smaller weight. For example, assuming that component distribution information has the greatest impact on follow-up information, and elasticity distribution information has a relatively smaller impact, then the weight corresponding to component distribution information can be the largest, and the weight corresponding to elasticity distribution information can be relatively small. Based on the respective weights of component distribution information and elasticity distribution information, the fusion model performs a fusion calculation on the component distribution information and elasticity distribution information to obtain the follow-up information corresponding to the ex vivo target tissue.

[0063] In this embodiment, the fusion model can be trained using machine learning methods. Training data and its label information can be input into the fusion model, which then learns the weights assigned to the component distribution information and the elasticity distribution information, respectively.

[0064] In some other embodiments, the fusion model can be trained using linear regression. The weights assigned to component distribution information and elasticity distribution information can be obtained by performing linear regression on the training data of the fusion model.

[0065] In some embodiments, the fusion model obtains the tissue properties of the ex vivo target tissue by fusing component distribution information and elasticity distribution information; and outputs follow-up information corresponding to the ex vivo target tissue based on the correspondence between tissue properties and follow-up information.

[0066] Specifically, tissue properties can characterize the benign or deteriorated state of an isolated target tissue. Tissue properties can be divided into multiple levels, each with corresponding follow-up information. The follow-up information for each level can be pre-specified.

[0067] Of course, for some machine learning-based fusion models, the fusion model can also directly output corresponding follow-up information based on the characteristics of component distribution information and elasticity distribution information. That is, it is not necessary to first obtain the organizational properties of the target organization and then output follow-up information based on the correspondence between organizational properties and follow-up information.

[0068] In some embodiments, the fusion model can output follow-up information according to multiple different operational dimensions, with each operational dimension corresponding to a follow-up information. The operational dimension is used to represent the type of operation for the target tissue, which is the tissue in which the target tissue was located before it was removed from the body.

[0069] Specifically, the target tissue originates from an organism (such as the human body), and includes, but is not limited to, tumor tissue, nodules, and benign lesion tissue. Ex vivo target tissue refers to part or all of the target tissue that has been removed from the organism. For example, if a tumor grows on the breast, the tumor is the target tissue. If a portion of the tumor tissue is removed from the breast, that portion of the tumor tissue is the ex vivo target tissue.

[0070] In this embodiment, the fusion model can output corresponding follow-up information from two operational dimensions: rotary cutting and drug treatment. The follow-up information output from the rotary cutting dimension represents the follow-up information after rotary cutting treatment of the isolated target tissue. The follow-up information output from the drug treatment dimension represents the follow-up information after drug treatment of the isolated target tissue. Thus, medical personnel can obtain the corresponding follow-up information according to the actual treatment plan, or select the actual treatment plan based on the follow-up information from the two treatment plans. This demonstrates good practicality and adaptability.

[0071] In some embodiments of this application, the components of the isolated target tissue at different locations are extracted from ultrasound imaging data, and the elasticity information at different locations of the isolated target tissue is extracted from elastography data, resulting in component distribution information and elasticity distribution information of the isolated target tissue. Then, a fusion model outputs follow-up information corresponding to the isolated target tissue based on the component distribution information and elasticity distribution information. In this way, medical personnel no longer need to spend time manually determining follow-up information, thereby improving the efficiency of obtaining follow-up information. Furthermore, in the process of determining follow-up information in this embodiment, the influence of elastic factors characterizing tissue hardness and tissue composition factors is fully considered, thus obtaining more accurate follow-up information.

[0072] Please see Figure 3 This is a functional module diagram of a follow-up information determination device provided in one embodiment of this application. The follow-up information determination device includes:

[0073] The data acquisition module is used to acquire ultrasound imaging data and elastography data of the excised target tissue obtained by rotary cutting.

[0074] The first data analysis module is used to obtain the composition information of the isolated target tissue at different locations from the ultrasound imaging data, and to obtain the composition distribution information of the isolated target tissue.

[0075] The second data analysis module is used to obtain elastic information of the isolated target tissue at different locations from the elastic imaging data, thereby obtaining elastic distribution information of the isolated target tissue; and

[0076] The follow-up information determination module is used to input the component distribution information and the elasticity distribution information into the trained fusion model, and the fusion model outputs follow-up information corresponding to the ex vivo target tissue.

[0077] Please see Figure 4 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. The electronic device includes a processor and a memory. The memory stores a computer program, which, when executed by the processor, implements the aforementioned follow-up information determination method.

[0078] The processor can be a central processing unit (CPU). It can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.

[0079] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the embodiments of this invention. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the methods described in the above embodiments.

[0080] The memory may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor, etc. Furthermore, the memory may include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, which can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0081] One embodiment of this application also provides a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the above-described follow-up time determination method.

[0082] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for determining follow-up information, characterized in that, The method includes: Acquire ultrasound and elastography data of isolated target tissues; From the ultrasound imaging data, the composition information of the isolated target tissue at different locations is obtained, and the composition distribution information of the isolated target tissue is obtained. From the elastic imaging data, the elasticity information of the isolated target tissue at different locations is obtained, thus obtaining the elasticity distribution information of the isolated target tissue; and The component distribution information and the elasticity distribution information are input into the fusion model, and the fusion model outputs follow-up information corresponding to the ex vivo target tissue. Specifically, obtaining elasticity information of the isolated target tissue at different locations from the elasticity imaging data to obtain elasticity distribution information of the isolated target tissue includes: From the elasticity imaging data, obtain the relative elasticity information and absolute elasticity information of the ex vivo target tissue at different locations; For each location, the relative elasticity information and absolute elasticity information of the isolated target tissue at that location are fused to obtain the elasticity distribution information of the isolated target tissue.

2. The method as described in claim 1, characterized in that, The follow-up information includes at least the follow-up time.

3. The method as described in claim 1, characterized in that, The output of follow-up information corresponding to the ex vivo target tissue includes: Follow-up information is output according to multiple different operational dimensions, with each operational dimension corresponding to one follow-up information. The operational dimension is used to represent the type of operation for the target tissue, which is the tissue in which the ex vivo target tissue was located before it was ex vivo.

4. The method as described in claim 1, characterized in that, The follow-up information corresponding to the ex vivo target tissue output by the fusion model includes: Based on the respective weights of the component distribution information and the elasticity distribution information, the fusion model performs a fusion calculation on the component distribution information and the elasticity distribution information to obtain follow-up information corresponding to the ex vivo target tissue.

5. The method as described in claim 4, characterized in that, The weights assigned to the component distribution information and the elasticity distribution information are obtained based on the following method: The training data and its label information are input into the fusion model, which then learns the weights of the component distribution information and the elasticity distribution information.

6. The method as described in claim 1, characterized in that, The acquisition of ultrasound imaging data and elastography data of the ex vivo target tissue includes: Under the condition that the ambient temperature of the isolated target tissue does not exceed the temperature threshold, ultrasound imaging data and elastography data of the isolated target tissue are acquired.

7. The method as described in claim 1, characterized in that, The acquisition of ultrasound imaging data and elastography data of the ex vivo target tissue includes: The ambient temperature of the ex vivo target tissue is controlled to not exceed a temperature threshold. The ex vivo target tissue is fixed in a tissue carrier, and ultrasound imaging data and elastography data of the fixed ex vivo target tissue are obtained.

8. The method as described in claim 1, characterized in that, The follow-up information output by the fusion model corresponding to the ex vivo target tissue includes: The tissue properties of the ex vivo target tissue are obtained by fusing the component distribution information and the elasticity distribution information. Based on the correspondence between the tissue nature and follow-up information, the follow-up information corresponding to the ex vivo target tissue is output.

9. A follow-up information determination device, characterized in that, The device includes: The data acquisition module is used to acquire ultrasound imaging data and elastography data of ex vivo target tissues; The first data analysis module is used to obtain the composition information of the isolated target tissue at different locations from the ultrasound imaging data, and to obtain the composition distribution information of the isolated target tissue. The second data analysis module is used to obtain elastic information of the isolated target tissue at different locations from the elastic imaging data, thereby obtaining elastic distribution information of the isolated target tissue; and The follow-up information determination module is used to input the component distribution information and the elasticity distribution information into the fusion model, and the fusion model outputs follow-up information corresponding to the ex vivo target tissue. Specifically, the second data analysis module is used to obtain the relative elasticity information and absolute elasticity information of the ex vivo target tissue at different locations from the elastic imaging data. For each location, the relative elasticity information and absolute elasticity information of the isolated target tissue at that location are fused to obtain the elasticity distribution information of the isolated target tissue.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program that, when executed by a processor, implements the method as described in any one of claims 1 to 8.

11. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory being used to store a computer program that, when executed by the processor, implements the method as described in any one of claims 1 to 8.

Images