A method and system for predicting risk of thyroid papillary carcinoma

Abstract

This application relates to the field of otolaryngology technology, specifically a method and system for predicting the risk of papillary thyroid carcinoma. By combining multiple sets of clinical indicators and multiple imaging feature data, this application can effectively assess and predict the risk of papillary thyroid carcinoma. The scoring data provides a more intuitive determination of the severity of papillary thyroid carcinoma, thereby enabling the differentiation between atypical subacute thyroiditis and papillary thyroid carcinoma. Compared to existing technologies, the discrimination results of the embodiments in this application are more accurate.

Description

Technical Field

[0001] This application relates to the field of otolaryngology technology, specifically to a method and system for predicting the risk of papillary thyroid carcinoma. Background Technology

[0002] Thyroid cancer is the most common malignant tumor of the head and neck. There are several histological types of thyroid cancer, the most common being papillary thyroid carcinoma, which has the best prognosis among malignant thyroid tumors. It typically grows slowly and has a low degree of malignancy. Typical clinical manifestations include single or multiple painless nodules in the thyroid gland, which are hard in texture and have poor mobility. Some patients may be diagnosed due to symptoms such as hoarseness, choking when drinking, and difficulty swallowing caused by tumor invasion of surrounding tissues, nerves, or metastasis to cervical lymph nodes.

[0003] In current technologies, ultrasound imaging is primarily used for preliminary diagnosis. While traditional imaging plays an important role in assessing the risk of thyroid nodules, its subjectivity and ambiguity often lead to difficulties in clinical decision-making. Summary of the Invention

[0004] To address the technical problems existing in the prior art, this application provides an auxiliary diagnostic method and system for thyroid diseases that combines computer medical images with multiple clinical indicators. By acquiring CT images of the thyroid region and extracting radiographic features from the CT images, the extracted features are combined with clinical data to achieve risk identification based on a predictive model.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0006] In a first aspect, a method for predicting the risk of papillary thyroid carcinoma is provided. The method includes: acquiring clinical data of a patient to be diagnosed and imaging feature data of a target region of the patient; the imaging feature data includes CT image feature data, and the clinical data is biophysical and chemical data, including free thyroxine content, free triiodothyronine content, thyroid-stimulating hormone content, thyroglobulin content, thyroglobulin antibody content, and thyroid peroxidase antibody content; inputting the clinical data and the imaging feature data into a risk prediction model to calculate a risk value; the risk prediction model is a nomogram model.

[0007] Furthermore, the image group feature data includes the number of original mask voxels, multiple gray-level region size matrix features, neighborhood gray-level difference matrix features, multiple gray-level dependency matrix features, and gray-level co-occurrence matrix.

[0008] Furthermore, the plurality of grayscale region size matrix features include a plurality of two-dimensional grayscale region size matrix features and a plurality of three-dimensional grayscale region size matrix features.

[0009] Furthermore, the multiple features of the two-dimensional gray-scale region size matrix include large-area emphasis of the gray-scale region size matrix under wavelet HLH filtering, regional variance of the gray-scale region size matrix under wavelet HLH filtering, and regional percentage of the gray-scale region size matrix under wavelet LHH filtering.

[0010] Furthermore, the multiple three-dimensional grayscale region size matrix features are obtained by using a three-dimensional Laplacian Gaussian filter, including low grayscale region emphasis of the grayscale region size matrix processed by a 5mm scale three-dimensional Laplacian Gaussian filter, and small area emphasis of the grayscale region size matrix processed by a 5mm scale three-dimensional Laplacian Gaussian filter.

[0011] Furthermore, the neighborhood gray-level difference matrix features include the roughness of the neighborhood gray-level difference matrix obtained by wavelet HLH filtering.

[0012] Furthermore, the gray-level dependency matrix features include small dependency low gray-level emphasis in the gray-level dependency matrix of square filtering and large dependency emphasis in the gray-level dependency matrix of three-dimensional local binary mode filtering.

[0013] Furthermore, the gray-level co-occurrence matrix includes a linear correlation metric 1 of the gray-level co-occurrence matrix obtained by wavelet LHH filtering.

[0014] Furthermore, the step of inputting the clinical data and the imaging feature data into the risk prediction model to calculate the risk value includes: obtaining, based on the nomogram, the first score, second score, third score, fourth score, fifth score, sixth score, and seventh score corresponding to the free thyroxine content, free triiodothyronine content, thyroid-stimulating hormone content, thyroglobulin content, thyroglobulin antibody content, and thyroid peroxidase antibody content and the imaging feature data, as well as the corresponding total score.

[0015] Secondly, a risk prediction system for papillary thyroid carcinoma is provided. The system includes: a data acquisition unit for acquiring clinical data of a patient to be diagnosed and imaging feature data of a target region of the patient; the imaging feature data includes CT image feature data, and the clinical data is biophysical and chemical data, including free thyroxine content, free triiodothyronine content, thyroid-stimulating hormone content, thyroglobulin content, thyroglobulin antibody content, and thyroid peroxidase antibody content; and a risk prediction unit for inputting the clinical data and the imaging feature data into a risk prediction model to calculate a risk value; the risk prediction model is a nomogram model.

[0016] The technical solution provided in this application combines multiple sets of clinical indicators and multiple imaging feature data to effectively assess and predict the risk of papillary thyroid carcinoma. This scoring data provides a more intuitive determination of the severity of papillary thyroid carcinoma, thereby enabling the differentiation between atypical subacute thyroiditis and papillary thyroid carcinoma. Compared to existing technologies, the discrimination results of this application are more accurate. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] The methods, systems, and / or procedures shown in the accompanying drawings will be further described with reference to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example figures represent similar mechanisms in the various views of the drawings.

[0019] Figure 1 This is a schematic flowchart of the method for predicting the risk of papillary thyroid carcinoma provided in the embodiments of this application.

[0020] Figure 2 This is a schematic diagram of the line graph model in the embodiments of this application.

[0021] Figure 3 This is a schematic diagram of the system structure provided in the embodiments of this application.

[0022] Figure 4 This is a schematic diagram of the terminal device structure provided in the embodiments of this application. Detailed Implementation

[0023] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0024] In the detailed description below, numerous specific details are illustrated with examples to provide a comprehensive understanding of the relevant guidance. However, it will be apparent to those skilled in the art that this application can be practiced without these details. In other instances, well-known methods, procedures, systems, components, and / or circuits have been described at a relatively high level without detail to avoid unnecessarily obscuring aspects of this application.

[0025] This application uses flowcharts to illustrate the execution process performed by a system according to embodiments of this application. It should be clearly understood that the execution processes in the flowcharts may not be executed sequentially. Instead, these execution processes may be executed in reverse order or simultaneously. Additionally, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0026] Before providing a further detailed description of the embodiments of the present invention, the nouns and terms involved in the embodiments of the present invention will be explained, and the nouns and terms involved in the embodiments of the present invention shall be interpreted as follows.

[0027] (1) In response to, used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which the operation is performed are met, one or more operations may be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations are performed.

[0028] (2) Based on, used to indicate the conditions or states on which the operation is performed depends. When the conditions or states on which it depends are met, one or more operations can be performed in real time or with a set delay. Unless otherwise specified, there is no restriction on the order of execution of the multiple operations.

[0029] This application provides a method for predicting the risk of papillary thyroid carcinoma, and more particularly, a method for differentiating between atypical subacute thyroiditis and papillary thyroid carcinoma. The thyroid gland is an important gland in the human endocrine system, located in the anterior midline of the neck. Its function is to synthesize and secrete thyroid hormones, which are crucial for maintaining the normal function of the human body's metabolism, growth and development, nervous system, and cardiovascular system. Subacute thyroiditis is a self-limiting inflammatory disease, and a small percentage of patients present with ultrasound findings similar to papillary thyroid carcinoma, often leading to unnecessary fine-needle aspiration biopsy or even surgical treatment. Ultrasound imaging examination combines the advantages of immediacy, non-invasiveness, and cost-effectiveness, and is the preferred method for screening and preliminary diagnosis of thyroid nodules. It can accurately capture key imaging features such as nodule size, shape, margin characteristics, internal echogenicity, calcification type, and blood flow distribution, and is a commonly used imaging technique in the prior art. However, in actual clinical use, the ultrasound images are not stable, with blurred or irregular lesion boundaries and features similar to papillary thyroid carcinoma, such as reactive lymph node enlargement, which makes the identification of subacute thyroiditis and papillary thyroid carcinoma inaccurate.

[0030] Therefore, in order to solve the above-mentioned technical problems, this application provides a method for predicting the risk of papillary thyroid carcinoma. This method combines clinical indicators with radiographic feature data from CT images to identify papillary thyroid carcinoma. For more information on this method, please refer to [link to relevant documentation]. Figure 1 This includes the following steps:

[0031] Step S11. Obtain the clinical data of the patient to be diagnosed and the image group feature data of the target region of the patient to be diagnosed.

[0032] In this embodiment, the method uses a joint prediction approach to assess the risk of papillary thyroid carcinoma. The logic of the joint prediction approach is to obtain the score corresponding to each indicator based on the nomogram through the prediction model, and then obtain the total score. The total score is used to determine the risk level of stroke, especially the risk level of papillary thyroid carcinoma.

[0033] The clinical data in this embodiment are biophysical and chemical data, including the content of free thyroxine, free triiodothyronine, thyroid-stimulating hormone, thyroglobulin, thyroglobulin antibody, and thyroid peroxidase antibody.

[0034] To acquire the image group feature data, the patient's CT images were first obtained, and then features were extracted from the CT images using PyRadiomics software. In the preprocessing stage, the CT data were first resampled to a voxel size of [1, 1, 3] using the BSpline interpolation method, and then normalized and discretized to ensure data consistency and stability. To comprehensively reflect the multi-scale information of the images, in addition to the original images, various image types such as LoG filtering, Wavelet, wavelet transform, square, square root, logarithmic, exponential, gradient, and LBP3D were used to generate different processing results, thereby extracting shape, first-order statistical, and texture features. The extracted features were then filtered to obtain features highly correlated with risk prediction. The Z-score method was used to standardize the data for feature filtering. Variance filtering was used to remove low-variability features with variance less than 0.01, thereby eliminating redundant noise. Subsequently, using the Mann-Whitney U test combined with FDR correction, features exhibiting significant differences among different groups were selected, and the top n candidate features with the smallest corrected p-values ​​were chosen. To further reduce the impact of multicollinearity, correlation analysis was performed on the candidate features, eliminating redundant features with correlation coefficients exceeding r. Next, a Lasso-based stability selection method was used to evaluate the robustness of each feature, retaining those with high stability. Finally, ElasticNetCV was used for cross-validation to further optimize the feature subset, and the final selected features served as input variables for subsequent data balancing and classification modeling.

[0035] The embodiments of this application filter the dataset based on the above processing method, retaining significant features including the number of original mask voxels, multiple gray-level region size matrix features, neighborhood gray-level difference matrix features, multiple gray-level dependency matrix features, and gray-level co-occurrence matrix.

[0036] Specifically, the multiple grayscale region size matrix features include multiple two-dimensional grayscale region size matrix features and multiple three-dimensional grayscale region size matrix features. The multiple two-dimensional grayscale region size matrix features include large-area emphasis of the grayscale region size matrix obtained by wavelet HLH filtering, regional variance of the grayscale region size matrix obtained by wavelet HLH filtering, and regional percentage of the grayscale region size matrix obtained by wavelet LHH filtering. The multiple three-dimensional grayscale region size matrix features are obtained by using a three-dimensional Laplacian Gaussian filter, including low-grayscale region emphasis and small-area emphasis of the grayscale region size matrix processed by a 5mm scale three-dimensional Laplacian Gaussian filter.

[0037] Specifically, the neighborhood gray-level difference matrix features include the roughness of the neighborhood gray-level difference matrix obtained by wavelet HLH filtering.

[0038] Specifically, multiple gray-level dependency matrix features include low gray-level emphasis on small dependencies in the gray-level dependency matrix of square filtering, and high gray-level emphasis on large dependencies in the gray-level dependency matrix of three-dimensional local binary mode filtering. The gray-level co-occurrence matrix includes the linear correlation measure of the gray-level co-occurrence matrix of wavelet LHH filtering.

[0039] Step S12. Input the clinical data and the imaging group feature data into the risk prediction model to calculate the risk value.

[0040] In this embodiment, the risk prediction model is a nomogram model. The nomogram model obtains the total score by mapping the scores corresponding to the multiple biophysical and chemical data and image group feature data obtained in step S11, and based on the score corresponding to each indicator and image group feature data. This total score is the risk value in this embodiment, which is used to characterize the risk level corresponding to papillary thyroid carcinoma.

[0041] Specifically, based on the nomogram, the free thyroxine ratio, thyroid-stimulating hormone content, thyroglobulin content, thyroglobulin antibody content, and thyroid peroxidase antibody content are obtained, along with the first, second, third, fourth, fifth, and sixth scores corresponding to the image group feature data, and the corresponding total score.

[0042] The free thyroxine ratio is the ratio of free thyroxine content to free triiodothyronine content. An elevated free thyroxine ratio is considered an independent risk factor for differentiated thyroid cancer, and thyroid-stimulating technology is...

[0043] For the calculation results of this nomogram model, please refer to [link / reference]. Figure 2Radscore is the overall calculated score of the image group feature data, i.e., the sixth score value. The Radscore score is calculated based on the following formula: Radscore = (Number of original mask voxels * 0.6221539) + (Large area emphasis of the gray-level region size matrix after wavelet HLH filtering * 0.159806297562722) + (Regional variance of the gray-level region size matrix after wavelet HLH filtering * -0.3186641) + (Regional percentage of the gray-level region size matrix after wavelet LHH filtering * -0.198138164) + (Low gray-level region emphasis of the gray-level region size matrix processed by the 5mm scale 3D Laplacian Gaussian filter * 0.489) The following parameters are used to evaluate the grayscale region size matrix processed by the 009+5mm scale 3D Laplacian Gaussian filter: small area emphasis * -0.075704273 + large area low grayscale emphasis by wavelet LHH * -0.0316045 + roughness of the neighborhood grayscale difference matrix of wavelet HLH filter * 0.301852 + small dependency low grayscale emphasis of the grayscale dependency matrix of square filter * 0.530769 + large dependency emphasis of the grayscale dependency matrix of 3D local binary mode filter * 0.136077 + linear correlation measure of the grayscale co-occurrence matrix of wavelet LHH filter 1 * 1.37838.

[0044] For the specific calculation process of the nodal graph in this embodiment, please refer directly to [the relevant documentation / reference]. Figure 2 As shown, the calculation logic of the nodal chart can be used to achieve this, and will not be elaborated further in this embodiment.

[0045] In summary, this embodiment combines multiple sets of clinical indicators and multiple imaging feature data to effectively assess and predict the risk of papillary thyroid carcinoma. This scoring data provides a more intuitive way to determine the severity of papillary thyroid carcinoma, thereby enabling the differentiation between atypical subacute thyroiditis and papillary thyroid carcinoma.

[0046] See Figure 3 In addition to the method provided in steps S11-S12, this embodiment also provides a prediction system 30, which includes:

[0047] Data acquisition unit 31 is used to acquire clinical data of the patient to be diagnosed and image group feature data of the target area of ​​the patient to be diagnosed;

[0048] The risk prediction unit 32 is used to input the clinical data and the imaging group feature data into the risk prediction model to calculate the risk value.

[0049] In this embodiment, the risk prediction model is a nomogram model.

[0050] See Figure 4The above methods can also be integrated into the provided terminal device 40. Since the device may vary significantly due to differences in configuration or performance, it may include one or more processors 401 and memories 402. The memories 402 may store one or more application programs or data. The memories 402 can be temporary or persistent storage. The application programs stored in the memories 402 may include one or more modules (not shown in the figure), each module may include a series of computer-executable instructions from the terminal device. Furthermore, the processor 401 may be configured to communicate with the memories 402, and the terminal device may execute the series of computer-executable instructions stored in the memories 402. The terminal device may also include one or more power supplies 403, one or more wired or wireless network interfaces 404, one or more input / output interfaces 405, one or more keyboards 406, etc.

[0051] In one specific embodiment, the terminal device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for use in the terminal device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0052] Acquire clinical data of the patient to be diagnosed and radiographic feature data of the target region of the patient to be diagnosed;

[0053] The clinical data and the imaging feature data are input into the risk prediction model to calculate the risk value.

[0054] The following is a detailed introduction to each component of the processor:

[0055] In this embodiment, the processor is an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0056] Optionally, the processor can perform various functions, such as the above-mentioned functions, by running or executing software programs stored in memory and by calling data stored in memory. Figure 1 The method shown.

[0057] In a specific implementation, as one example, the processor may include one or more microprocessors.

[0058] The memory is used to store the software program that executes the solution of this application, and the execution is controlled by the processor. The specific implementation method can be referred to the above method embodiment, which will not be repeated here.

[0059] Optionally, the memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory can be integrated with the processor or exist independently and coupled to the processing unit through the processor's interface circuitry; this application embodiment does not specifically limit this.

[0060] It should be noted that the processor structure shown in this embodiment does not constitute a limitation on the device. The actual device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0061] Furthermore, the technical effects of the processor can be referred to the technical effects of the methods described in the above-described method embodiments, and will not be repeated here.

[0062] It should be understood that the processor in the embodiments of this application may 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, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0063] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0064] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0065] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0066] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0067] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0068] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0070] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0072] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for predicting the risk of papillary thyroid carcinoma, characterized in that, The method includes: Acquire clinical data of the patient to be diagnosed and imaging feature data of the target region of the patient to be diagnosed; the imaging feature data includes CT image feature data, and the clinical data is biophysical and chemical data, including free thyroxine ratio, thyroid-stimulating hormone content, thyroglobulin content, thyroglobulin antibody content, and thyroid peroxidase antibody content; The clinical data and the imaging feature data are input into a risk prediction model to calculate the risk value; the risk prediction model is a nomogram model.

2. The method for predicting the risk of papillary thyroid carcinoma according to claim 1, characterized in that, The image group feature data includes the number of original mask voxels, multiple gray-level region size matrix features, neighborhood gray-level difference matrix features, multiple gray-level dependency matrix features, and gray-level co-occurrence matrix.

3. The method for predicting the risk of papillary thyroid carcinoma according to claim 2, characterized in that, The multiple grayscale region size matrix features include multiple two-dimensional grayscale region size matrix features and multiple three-dimensional grayscale region size matrix features.

4. The method for predicting the risk of papillary thyroid carcinoma according to claim 3, characterized in that, The features of the two-dimensional gray-scale region size matrix include large-area emphasis of the gray-scale region size matrix under wavelet HLH filtering, regional variance of the gray-scale region size matrix under wavelet HLH filtering, and regional percentage of the gray-scale region size matrix under wavelet LHH filtering.

5. The method for predicting the risk of papillary thyroid carcinoma according to claim 3, characterized in that, Multiple three-dimensional grayscale region size matrix features are obtained by using a three-dimensional Laplacian Gaussian filter, including low grayscale region emphasis of the grayscale region size matrix processed by a 5mm scale three-dimensional Laplacian Gaussian filter, and small area emphasis of the grayscale region size matrix processed by a 5mm scale three-dimensional Laplacian Gaussian filter.

6. The method for predicting the risk of papillary thyroid carcinoma according to claim 2, characterized in that, The neighborhood gray-level difference matrix features include the roughness of the neighborhood gray-level difference matrix obtained by wavelet HLH filtering.

7. The method for predicting the risk of papillary thyroid carcinoma according to claim 2, characterized in that, The gray-level dependency matrix features include small dependency and low gray-level emphasis in the gray-level dependency matrix of square filtering, and large dependency and emphasis in the gray-level dependency matrix of three-dimensional local binary mode filtering.

8. The method for predicting the risk of papillary thyroid carcinoma according to claim 2, characterized in that, The gray-level co-occurrence matrix includes the linear correlation metric of the gray-level co-occurrence matrix obtained by wavelet LHH filtering.

9. The method for predicting the risk of papillary thyroid carcinoma according to claim 1, characterized in that, The free thyroxine ratio is the ratio of free thyroxine content to free triiodothyronine content. The step of inputting the clinical data and the imaging feature data into the risk prediction model to calculate the risk value includes: obtaining the first score, second score, third score, fourth score, fifth score, and sixth score corresponding to the free thyroxine ratio, the thyroid-stimulating hormone content, the thyroglobulin content, the thyroglobulin antibody content, the thyroid peroxidase antibody content, and the imaging feature data, as well as the corresponding total score, based on the nomogram.

10. A risk prediction system for papillary thyroid carcinoma, characterized in that, The system includes: The data acquisition unit acquires clinical data of the patient to be diagnosed and imaging feature data of the target area of ​​the patient to be diagnosed; the imaging feature data includes CT image feature data, and the clinical data is biophysical and chemical data, including free thyroxine content, free triiodothyronine content, thyroid-stimulating hormone content, thyroglobulin content, thyroglobulin antibody content, and thyroid peroxidase antibody content. The risk prediction unit inputs the clinical data and the imaging feature data into the risk prediction model to calculate the risk value; the risk prediction model is a nomogram model.

Images