Prostate tumor onset risk prediction method and system

Abstract

The invention relates to the technical field of urinary system disease diagnosis, in particular to a prostate tumor onset risk prediction method and system. By combining multiple groups of indexes and image group feature data, the prostate diseases, especially the prostate tumors, can be effectively evaluated, score data reflecting the state of the prostate tumors can be obtained, and the incidence probability and the staging result degree of the endometrial diseases can be more intuitively determined through the score data. Therefore, the overall automatic prediction of the prostate disease is realized.

Description

Technical Field

[0001] The present application relates to the technical field of urinary system disease diagnosis, and specifically to a method and system for predicting the risk of prostate tumor incidence. Background Art

[0002] Early screening and diagnosis of prostate cancer are crucial in clinical diagnosis and treatment. Common diagnostic methods currently include digital rectal examination (DRE), serum prostate-specific antigen (PSA) levels, multi-parameter magnetic resonance imaging (MRI) of the prostate, and biopsy. In clinical practice, the DRE is a common examination procedure in which a physician inserts a gloved finger into the patient's rectum to examine the prostate for abnormalities. If a nodule or lump is palpated, the patient is highly suspected of having a prostate cancer. However, a limitation of the DRE is that if a lump is palpated, the patient may already be in the advanced stage of prostate cancer. Currently, PSA testing is also used for early screening. PSA is a glycoprotein secreted by prostate epithelial cells and commonly found in semen and blood. PSA testing requires collecting a blood sample to measure the PSA level. Generally, if a patient's PSA level is above 4 ng / mL, further testing is indicated. Patients with PSA levels between 4 ng / mL and 10 ng / mL have an approximately 25% chance of having PCa. When the PSA exceeds 10 ng / mL, the likelihood of having PCa exceeds 50%. However, it is important to note that elevated PSA levels can occur in some conditions, such as benign prostatic hyperplasia, prostatitis, trauma, and recent instrumental examinations, leading to the risk of false positives. To address this issue, several PSA-related indices have been explored to help predict clinically significant disease. These indices include free PSA, protein-bound PSA, and PSA density. However, definitive evidence regarding the utility of these methods is lacking. Summary of the Invention

[0003] In order to solve the technical problems existing in the prior art, the embodiment of the present application provides an auxiliary diagnosis method and system for the diagnosis of prostate diseases by combining computer medical images and multiple clinical indicators. By extracting imaging group features from images, the extracted features and clinical data are combined to realize automated risk assessment based on a predictive model.

[0004] In order to achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows: In a first aspect, a method for predicting the risk of prostate tumor incidence is provided, the method comprising: obtaining clinical data of a patient to be diagnosed and imaging group characteristic data of a target area of ​​the patient to be diagnosed; the imaging group characteristic data comprises MRI image characteristic data, and the clinical data comprises age, total prostate-specific antigen data, free prostate-specific antigen data, alkaline phosphatase data and fibrinogen data; inputting the clinical data and the imaging group characteristic data into a risk prediction model to calculate a risk value; the risk prediction model is a nomogram model.

[0005] Furthermore, the image group feature data includes multiple first-order features, multiple gray-level co-occurrence matrix features, multiple gray-level run matrix features, and multiple gray-level size area matrix features.

[0006] Furthermore, the plurality of first-order features include the first-order skewness of the original sequence, the first-order median of the LHL sequence, the first-order mean of the LHL sequence, the first-order ninetieth percentile of the LLL sequence, and the first-order median of the LLH sequence.

[0007] Furthermore, the multiple gray-level co-occurrence matrix features include LLL sequence gray-level co-occurrence matrix correlation, LHH sequence gray-level co-occurrence matrix cluster trend, LLH sequence gray-level co-occurrence matrix and average, original sequence gray-level co-occurrence matrix related information measure 1 and LLL sequence gray-level co-occurrence matrix related information measure 1.

[0008] Furthermore, the plurality of grayscale run matrix features include LLH sequence grayscale run matrix low grayscale run emphasis, original sequence grayscale run matrix run percentage, LLL sequence grayscale run matrix long run low grayscale emphasis and original sequence grayscale run matrix long run low grayscale emphasis.

[0009] Furthermore, the multiple grayscale size area matrix features include the normalized area size unevenness of the original sequence grayscale size area matrix, the high grayscale emphasis of the small area of ​​the LLH sequence grayscale size area matrix, the high grayscale area emphasis of the LHL sequence grayscale size area matrix, the low grayscale area emphasis of the LHL sequence grayscale size area matrix, the area entropy of the LHH sequence grayscale size area matrix and the grayscale unevenness of the original sequence grayscale size area matrix.

[0010] Furthermore, the clinical data and the imaging group characteristic data are input into the risk prediction model to calculate the risk value, including: obtaining the first score, second score, third score, fourth score, fifth score and sixth score corresponding to the age, total prostate-specific antigen data, free prostate-specific antigen data, alkaline phosphatase data and fibrinogen data and the imaging group characteristic data based on the nomogram model, as well as the corresponding total score.

[0011] Furthermore, the sixth score corresponding to the characteristic data of the image group is obtained, including: respectively obtaining the first-order skewness of the original sequence, the first-order median of the LHL sequence, the first-order mean of the LHL sequence, the first-order ninetieth percentile of the LLL sequence, the first-order median of the LLH sequence, the correlation of the gray-level co-occurrence matrix of the LLL sequence, the cluster trend of the gray-level co-occurrence matrix of the LHH sequence, the sum average of the gray-level co-occurrence matrix of the LLH sequence, the related information measure 1 of the gray-level co-occurrence matrix of the original sequence, the related information measure 1 of the gray-level co-occurrence matrix of the LLL sequence, the low gray-level stroke emphasis of the gray-level stroke matrix of the LLH sequence, and the stroke percentage of the gray-level stroke matrix of the original sequence , the sub-scores corresponding to the long-run low-grayscale emphasis of the LLL sequence grayscale run matrix, the long-run low-grayscale emphasis of the original sequence grayscale run matrix, the normalized regional size unevenness of the original sequence grayscale size region matrix, the small-region high-grayscale emphasis of the LLH sequence grayscale size region matrix, the high-grayscale region emphasis of the LHL sequence grayscale size region matrix, the low-grayscale region emphasis of the LHL sequence grayscale size region matrix, the regional entropy of the LHH sequence grayscale size region matrix and the grayscale unevenness of the original sequence grayscale size region matrix, and the sub-scores are updated according to the calculated weights corresponding to the above data and then weighted to obtain the seventh score.

[0012] In a second aspect, a prostate tumor incidence risk prediction system is provided, which includes: a data acquisition unit for acquiring clinical data of a patient to be diagnosed and imaging group characteristic data of a target area of ​​the patient to be diagnosed; a risk prediction unit for inputting the clinical data and the imaging group characteristic data into a risk prediction model to calculate a risk value; the risk prediction model is a nomogram model.

[0013] Furthermore, the risk prediction module includes a first score calculation unit, a second score calculation unit, a third score calculation unit, a fourth score calculation unit, a fifth score calculation unit and a sixth score calculation unit.

[0014] In the technical solution provided in the embodiments of the present application, by combining multiple groups of indicators and imaging group feature data, prostate diseases, especially prostate tumors, can be effectively evaluated, and score data reflecting the status of prostate tumors can be obtained. Through this score data, the probability of endometrial disease and the degree of staging results can be more intuitively determined, thereby realizing an overall automated prediction of the incidence of prostate diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0016] The methods, systems, and / or programs in the accompanying drawings will be further described according 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 numerals represent similar structures in the various views of the drawings.

[0017] Figure 1 This is a flow chart of the method for predicting the incidence of prostate tumors provided in an embodiment of the present application.

[0018] Figure 2 Schematic diagram of the segmentation result provided in an embodiment of the present application.

[0019] Figure 3 It is a schematic diagram of the nomogram model in the embodiment of the present application.

[0020] Figure 4 It is a schematic diagram of the system structure provided in an embodiment of the present application.

[0021] Figure 5 This is a schematic diagram of the terminal device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to better understand the above technical solution, the technical solution of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0023] In the following detailed description, numerous specific details are set forth by way of example in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to one skilled in the art that the present application can be practiced without these details. In other instances, well-known methods, procedures, systems, compositions, and / or circuits have been described at a relatively high level, without detail, to avoid unnecessarily obscuring aspects of the present application.

[0024] Flowcharts are used in this application to illustrate the execution processes performed by the system according to the embodiments of the present application. It should be clearly understood that the execution processes of the flowcharts may not be executed in sequence. Instead, these execution processes may be executed in reverse order or simultaneously. In addition, at least one additional execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0025] Before further explaining the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are explained. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations.

[0026] (1) In response to, it is used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0027] (2) Based on, used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0028] An embodiment of the present application provides a method for predicting the risk of prostate tumor incidence, which comprises obtaining an MRI image by performing magnetic resonance imaging on a target area of ​​a patient, extracting and screening image group features in the MRI image, obtaining multiple image group feature data, and processing the multiple image group feature data and multiple clinical data based on a joint scoring model to obtain a risk prediction score for the risk of prostate disease, especially for the incidence of prostate tumors.

[0029] This embodiment provides an automated method for predicting the risk of prostate disease, which uses MRI images and multiple clinical indicators to establish a joint evaluation model. Based on this joint evaluation model, the prostate membrane tumor is predicted and the corresponding degree is judged, with a high detection rate and accuracy.

[0030] For more information on this forecasting method, see Figure 1 , including the following steps: Step S11: Acquire clinical data of the patient to be diagnosed and image group feature data of the target area of ​​the patient to be diagnosed.

[0031] In this embodiment, this method adopts a combined prediction method to predict prostate diseases, especially prostate tumors, and especially to judge and determine the extent of prostate tumors. The logic of the combined prediction method 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 possibility and extent of prostate tumors.

[0032] The indicators in this embodiment include clinical data and MRI image group feature data, wherein the image group feature data is MRI image feature data in multiple sequences and multiple frequency bands, and the risk prediction model is a nomogram model.

[0033] Specifically, the clinical data included in the indicators include age, total prostate-specific antigen (PSA), free PSA, alkaline phosphatase (ALP), and fibrinogen. The acquisition of imaging feature data begins with image segmentation and region of interest (ROI) extraction from the MRI images. Image segmentation is typically performed manually in existing technologies, which relies heavily on physician judgment, is time-consuming, and, because it relies on physician experience, can negatively impact the segmentation results.

[0034] In order to solve this problem, in this embodiment, computer technology is used to segment the MRI image, and the segmentation of the regional image is achieved through automated segmentation means.

[0035] Specifically, in this embodiment, a segmentation model is configured, and the segmentation of the tumor area in the MRI image is completed based on this segmentation model. Among them, the 3D segmentation network constructed based on the U-Net network for this segmentation model includes an encoder and a decoder, and the encoder and the decoder are connected in a jump connection manner. Among them, in the encoder module, the downsampling extraction of image features is realized by a convolution module with a residual connection block, the feature map is normalized by combining the batch normalization layer, and the maximum pooling is used to reduce the volume of the feature map. A pyramid connection module is configured in the decoder to perform multi-receptive field and multi-depth feature extraction on low-dimensional features to better obtain the dimensional feature information of the image; and the gate attention module is introduced to realize the effective fusion of high-dimensional features and low-dimensional features, with the aim of using the global semantic information of high-dimensional features to guide low-dimensional features. The decoding layer is consistent with the encoding layer, and the fusion residual connection block is introduced into each decoding layer, and the trilinear difference is used to expand the upsampling feature.

[0036] Specifically, during the compression phase, the model first performs global mean pooling to obtain global image feature information. The cascaded pyramid convolution module achieves multi-scale feature extraction by adjusting the receptive field and depth of the convolution. Taking into account the size of the feature map in the decoder, the parallel convolution kernels in the pyramid convolution module are configured with three sizes: 3×3×3, 5×5×5, and 9×9×9. After the input features are convolved with a kernel of 1×1×1 to obtain the original input features of the cascaded pyramid convolution module, a 3×3×3 convolution is first performed to obtain the output component y1. Next, the output component y1 is fused with the original features through a 5×5×5 convolution to obtain the output component y2. Finally, the component y2 is fused with the original features through a 9×9×9 convolution to obtain the output component y3. To ensure consistent output feature scales across different convolution kernel sizes, padding is set to 1×1×1, 2×2×2, and 4×4×4, respectively, with a stride of 1. The final output y is the sum of all output components.

[0037] MRI has anisotropy in spatial resolution, which makes it difficult to effectively extract space using isotropic 3D convolution. Therefore, the embodiment of the present application designs residual connection blocks with various anisotropies in each convolution layer to extract multi-directional features and optimize the training process. Anisotropic rather than uniform 3D convolution kernels are used. The specific setting strategy is: the convolution kernel is set to 3×3×1, and for cross-layer feature acquisition, the convolution kernel is set to 1×1×3.

[0038] The encoder and decoder are connected via skip connections, which employ a gated attention mechanism. The two inputs of the skip connection receive the high-dimensional features of the encoding layer and the low-dimensional features of the decoding layer, respectively. These features are then added together after a 1x1x1 convolution of the same parameter size to produce the intermediate features. Finally, the compressed features, activated by a sigmoid function, are dot-multiplied with the original high-dimensional features to produce the module's final output.

[0039] In this embodiment, the convolutional layer uses custom convolution kernel weights to extract low-dimensional image features to separately extract the edges of the prostate gland and tumor. Furthermore, considering that image edge contours are low-dimensional features, the image edge extraction module is placed on top of the decoding layer, and two output ports are provided on the output layer to output the segmentation results and edge contours, respectively. When using convolution for edge detection, this embodiment uses a grouped convolution method to batch process the input segmentation results, ensuring consistency with the segmentation network system.

[0040] The above segmentation model can be used to segment tumors in MRI images. The segmentation results can be found in Figure 2 The results shown in the figure show that in order to obtain the radiomic features of the segmented images, the radiomics toolkit was used to extract the radiomic features of multiple sequences corresponding to each image. LASSO regression was used to reduce the dimensionality of the features and eliminate radiomic features with a weight of 0 to reduce overfitting caused by high-dimensional data.

[0041] Through the above process, a total of 20 imaging omics features were screened out, including multiple first-order features, multiple gray-level co-occurrence matrix features, multiple gray-level travel matrix features, and multiple gray-level size area matrix features.

[0042] Among them, the first-order features include the first-order skewness of the original sequence, the first-order median of the LHL sequence, the first-order mean of the LHL sequence, the first-order 90th percentile of the LLL sequence and the first-order median of the LLH sequence; the gray-level co-occurrence matrix features include the gray-level co-occurrence matrix correlation of the LLL sequence, the cluster trend of the gray-level co-occurrence matrix of the LHH sequence, the gray-level co-occurrence matrix and the average, the gray-level co-occurrence matrix related information measure 1 of the original sequence and the gray-level co-occurrence matrix related information measure 1 of the LLL sequence; the gray-level trip matrix features include the low gray-level trip emphasis of the LLH sequence gray-level trip matrix, the original The features of the grayscale area matrix include the normalized area size unevenness of the original sequence grayscale area matrix, the high grayscale emphasis of the small area of ​​the LLH sequence grayscale area matrix, the high grayscale area emphasis of the LHL sequence grayscale area matrix, the low grayscale area emphasis of the LHL sequence grayscale area matrix, the area entropy of the LHH sequence grayscale area matrix and the grayscale unevenness of the original sequence grayscale area matrix.

[0043] Step S12: Input the clinical data and the imaging group characteristic data into a risk prediction model to calculate the risk value.

[0044] In this embodiment, the risk prediction model is a nomogram model. The nomogram model obtains the mapping scores corresponding to the multiple clinical data and imaging group characteristic data obtained in step S11, and obtains a total score based on the scores corresponding to each indicator and imaging group characteristic data. This total score is the risk value in this embodiment, which is used to characterize the grade corresponding to the risk of prostate tumor incidence and the degree of risk of incidence.

[0045] Specifically, the first score, second score, third score, fourth score, fifth score and sixth score corresponding to age, total prostate-specific antigen data, free prostate-specific antigen data, alkaline phosphatase data and fibrinogen data and the imaging group characteristic data, as well as the corresponding total score are obtained respectively.

[0046] For the calculation results of this nomogram model, please refer to Figure 3, where radsocre is the overall calculated score of the imaging group feature data, that is, the sixth score value. The calculation of the radsocre score is based on the following formula: Radscore = -0.007301*original sequence first-order skewness + 0.058207*LHL sequence first-order median + 0.019232*LHL sequence first-order mean -0.021387*LLL sequence first-order 90th percentile + 0.0011265*LLH sequence first-order median + 0.002902*LLL sequence gray level co-occurrence matrix correlation + 0.001029*LHH sequence gray level co-occurrence matrix cluster trend + 0.008970*LLH sequence gray level co-occurrence matrix and average -0.0017543*original sequence gray level co-occurrence matrix related information measure 1 + 0.031006*LLL sequence gray level co-occurrence matrix related information measure 1 + 0.026483*LLH sequence gray level Stroke matrix low grayscale stroke emphasis -0.026497*original sequence grayscale stroke matrix stroke percentage +0.028647*LLL sequence grayscale stroke matrix long stroke low grayscale emphasis +0.013129*original sequence grayscale stroke matrix long stroke low grayscale emphasis +0.00000001*original sequence grayscale size region matrix normalized region size unevenness +0.052583*LLH sequence grayscale size region matrix small region high grayscale emphasis +0.0075627*LHL sequence grayscale size region matrix high grayscale region emphasis +0.051764*LHL sequence grayscale size region matrix low grayscale region emphasis +0.031647*LHH sequence grayscale size region matrix region entropy -0.160765*original sequence grayscale size region matrix grayscale unevenness

[0047] The specific calculation process of the nomogram in this embodiment can be directly referred to Figure 3 As shown, this can be achieved by using the calculation logic of the nomogram, which will not be described in detail in this embodiment.

[0048] In summary, in this embodiment, by combining the above-mentioned multiple groups of indicators, the possibility and severity of prostate tumors can be effectively evaluated in advance, and the probability and severity of prostate tumors can be determined more intuitively through this score data, thereby realizing the overall automated prediction of prostate tumors.

[0049] See Figure 4 With respect to the method provided in step S11-step S12, a prediction system 40 is further provided in this embodiment, and the system includes: A data acquisition unit 41 is used to acquire clinical data of a patient to be diagnosed and image group feature data of a target area of ​​the patient to be diagnosed; The risk prediction unit 42 is configured to input the clinical data and the imaging group feature data into a risk prediction model to calculate a risk value.

[0050] In this embodiment, the risk prediction model is a nomogram model.

[0051] See Figure 5 The above method can also be integrated into the provided terminal device 50. In view of the fact that the device may have relatively large differences due to different configurations or performance, it can include one or more processors 501 and memory 502. The memory 502 can store one or more applications or data. The memory 502 can be a temporary storage or a persistent storage. The application stored in the memory 402 can include one or more modules (not shown in the figure), each of which can include a series of computer-executable instructions in the terminal device. Furthermore, the processor 501 can be configured to communicate with the memory 502, and the terminal device can execute the series of computer-executable instructions in the memory 502. The terminal device can also include one or more power supplies 403, one or more wired or wireless network interfaces 504, one or more input / output interfaces 505, one or more keyboards 506, etc.

[0052] In a 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 in the terminal device, and the one or more programs are configured to be executed by one or more processors, including computer-executable instructions for performing the following: Acquiring clinical data of a patient to be diagnosed and imaging feature data of a target area of ​​the patient to be diagnosed; The clinical data and the imaging group characteristic data are input into a risk prediction model to calculate the risk value; the risk prediction model is a nomogram model.

[0053] The following is a detailed introduction to the various components of the processor: In this embodiment, the processor is an application specific integrated circuit (ASIC), or is configured to implement one or more integrated circuits of the embodiments of the present application, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0054] Optionally, the processor can execute various functions by running or executing the software program stored in the memory and calling the data stored in the memory, such as executing the above Figure 1 The method shown.

[0055] In a specific implementation, as an embodiment, the processor may include one or more microprocessors.

[0056] The memory is used to store the software program for executing the solution of the present application, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0057] Alternatively, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and be coupled to the processing unit through the processor's interface circuit, and this is not specifically limited in the embodiments of the present application.

[0058] It should be noted that the structure of the processor shown in this embodiment does not constitute a limitation on the device. The actual device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0059] In addition, the technical effects of the processor can refer to the technical effects of the method described in the above method embodiment, and will not be repeated here.

[0060] It should be understood that the processor in the embodiments of the present 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.

[0061] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0062] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially 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 means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0063] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural 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 single or plural.

[0064] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean 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 the present application.

[0065] Those skilled in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel 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.

[0066] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0067] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0068] The units described as separate components may or may not be physically separate, and 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 these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0069] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0070] If the functions are implemented in the form of 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 the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0071] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for predicting the risk of prostate tumor incidence, characterized in that: The method comprises: Acquiring clinical data of a patient to be diagnosed and imaging group characteristic data of a target area of ​​the patient to be diagnosed; the imaging group characteristic data includes MRI image characteristic data, and the clinical data includes age, total prostate-specific antigen data, free prostate-specific antigen data, alkaline phosphatase data, and fibrinogen data; The clinical data and the imaging group characteristic 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 prostate tumors according to claim 1, wherein: The image group feature data includes multiple first-order features, multiple grayscale co-occurrence matrix features, multiple grayscale run matrix features, and multiple grayscale size area matrix features.

3. The method for predicting the risk of prostate tumors according to claim 2, wherein: The plurality of first-order features include the first-order skewness of the original sequence, the first-order median of the LHL sequence, the first-order mean of the LHL sequence, the first-order ninetieth percentile of the LLL sequence, and the first-order median of the LLH sequence.

4. The method for predicting the risk of prostate tumor incidence according to claim 3, wherein: The multiple gray-level co-occurrence matrix features include LLL sequence gray-level co-occurrence matrix correlation, LHH sequence gray-level co-occurrence matrix cluster trend, LLH sequence gray-level co-occurrence matrix and average, original sequence gray-level co-occurrence matrix related information measure 1 and LLL sequence gray-level co-occurrence matrix related information measure 1.

5. The method for predicting the risk of prostate tumors according to claim 4, wherein: The plurality of grayscale run matrix features include LLH sequence grayscale run matrix low grayscale run emphasis, original sequence grayscale run matrix run percentage, LLL sequence grayscale run matrix long run low grayscale emphasis and original sequence grayscale run matrix long run low grayscale emphasis.

6. The method for predicting the risk of prostate tumors according to claim 5, wherein: The multiple grayscale size area matrix features include the normalized area size unevenness of the original sequence grayscale size area matrix, the high grayscale emphasis of the small area of ​​the LLH sequence grayscale size area matrix, the high grayscale area emphasis of the LHL sequence grayscale size area matrix, the low grayscale area emphasis of the LHL sequence grayscale size area matrix, the area entropy of the LHH sequence grayscale size area matrix and the grayscale unevenness of the original sequence grayscale size area matrix.

7. The method for predicting the risk of prostate tumors according to claim 6, wherein: The step of inputting the clinical data and the imaging group characteristic 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 age, total prostate-specific antigen data, free prostate-specific antigen data, alkaline phosphatase data and fibrinogen data and the imaging group characteristic data based on the nomogram model, as well as the corresponding total score.

8. The method for predicting the risk of prostate tumor incidence according to claim 7, wherein: The obtaining of the sixth score corresponding to the characteristic data of the image group includes: respectively obtaining the first-order skewness of the original sequence, the first-order median of the LHL sequence, the first-order mean of the LHL sequence, the first-order ninetieth percentile of the LLL sequence, the first-order median of the LLH sequence, the correlation of the gray-level co-occurrence matrix of the LLL sequence, the cluster trend of the gray-level co-occurrence matrix of the LHH sequence, the gray-level co-occurrence matrix and the average of the LLH sequence, the related information measure 1 of the gray-level co-occurrence matrix of the original sequence, the related information measure 1 of the gray-level co-occurrence matrix of the LLL sequence, the low gray-level stroke emphasis of the gray-level stroke matrix of the LLH sequence, the stroke percentage of the gray-level stroke matrix of the original sequence, and the gray-level co-occurrence matrix of the LLL sequence. The sub-scores corresponding to the long-run low-grayscale emphasis of the L-sequence grayscale run matrix, the long-run low-grayscale emphasis of the original sequence grayscale run matrix, the normalized regional size unevenness of the original sequence grayscale size region matrix, the small-region high-grayscale emphasis of the LLH sequence grayscale size region matrix, the high-grayscale region emphasis of the LHL sequence grayscale size region matrix, the low-grayscale region emphasis of the LHL sequence grayscale size region matrix, the regional entropy of the LHH sequence grayscale size region matrix and the grayscale unevenness of the original sequence grayscale size region matrix are updated according to the calculated weights corresponding to the above data, and then weighted to obtain the seventh score.

9. A prostate tumor risk prediction system, characterized in that: The system comprises: A data acquisition unit, configured to acquire clinical data of a patient to be diagnosed and imaging feature data of a target area of ​​the patient to be diagnosed; The risk prediction unit is used to input the clinical data and the imaging group characteristic data into a risk prediction model to calculate the risk value; the risk prediction model is a nomogram model.

10. The prostate tumor risk prediction system according to claim 8, characterized in that: The risk prediction module includes a first score calculation unit, a second score calculation unit, a third score calculation unit, a fourth score calculation unit, a fifth score calculation unit, and a sixth score calculation unit.

Images