Bladder cancer recurrence prediction method and system, storage medium and program product

Abstract

The invention provides a bladder cancer recurrence prediction method and system, a storage medium and a program product. The method comprises the following steps: acquiring bladder cancer recurrence prediction data and a corresponding recurrence label; the bladder cancer recurrence prediction data comprises CT image data, conventional blood detection data and biochemical inspection data which correspond to one another; respectively establishing a CT image training data set, a conventional blood detection training data set and a biochemical examination training data set; inputting the CT image training data set, the conventional blood detection training data set and the biochemical examination training data set into a preset neural network, and performing parameter adjustment on the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model; and when the current bladder cancer recurrence prediction data is obtained, classifying the current bladder cancer recurrence prediction data according to recurrence labels based on the bladder cancer recurrence prediction model. The accuracy and efficiency of bladder cancer recurrence risk prediction can be improved.

Description

Background Art

[0002] Bladder cancer refers to a malignant tumor that occurs on the bladder mucosa. It is the most common malignant tumor of the urinary system and one of the top ten common tumors in the body. After treatment, bladder cancer may still recur. The risk of bladder cancer recurrence varies significantly depending on the patient's disease stage. The recurrence rate of patients with non-invasive bladder cancer is about 65%, while the recurrence rate of patients in higher stages of the disease can reach 73%. In the process of reducing the risk of recurrence, providing appropriate adjuvant treatment according to the patient's recurrence risk level is a key link. Therefore, accurately predicting the patient's risk of recurrence is of great significance for formulating a reasonable adjuvant treatment plan.

[0003] In recent years, machine learning technology has been widely used in cancer prediction and prognosis assessment due to its excellent discriminative ability. However, there are still few studies that attempt to use machine learning to predict the risk of bladder cancer recurrence. Some studies focus on using morphological features manually extracted from pathology sections and electronic health records to predict recurrence. At the same time, deep learning technology has also been used to automatically extract features from pathology sections and predict recurrence.

[0004] Existing technologies mainly rely on the analysis of pathological sections to predict the risk of bladder cancer recurrence. Although this method is effective to a certain extent, it has some obvious limitations and shortcomings. First, although pathological sections can provide important information about the morphology of cancer cells, they cannot capture the three-dimensional structure and microscopic image characteristics of the bladder and tumor tissue. These image features are crucial for accurately assessing the aggressiveness of the tumor and the risk of recurrence in patients, but they are often ignored in current prediction models. Secondly, existing technologies often fail to fully consider the patient's inflammation level and overall health status when analyzing the risk of recurrence. Inflammation levels and overall health status have been shown to be closely related to the progression and recurrence risk of cancer. Therefore, ignoring these indicators will lead to lower accuracy in predicting bladder cancer recurrence.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] In view of this, the present invention provides a bladder cancer recurrence prediction method, system, storage medium and program product to at least solve the above-mentioned problem of low accuracy in bladder cancer recurrence prediction.

[0007] One aspect of an embodiment of the present invention provides a method for predicting bladder cancer recurrence, comprising the following steps:

[0008] Acquire bladder cancer recurrence prediction data and a recurrence label corresponding to each of the bladder cancer recurrence prediction data; wherein the bladder cancer recurrence prediction data includes mutually corresponding CT image data, routine blood test data and biochemical test data;

[0009] According to the plurality of bladder cancer recurrence prediction data, a CT image training data set, a conventional blood test training data set and a biochemical examination training data set are respectively established;

[0010] Inputting the CT image training data set, the conventional blood test training data set, and the biochemical examination training data set into a preset neural network, and adjusting parameters of the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model;

[0011] When the current bladder cancer recurrence prediction data is acquired, the current bladder cancer recurrence prediction data is classified according to the recurrence label based on the bladder cancer recurrence prediction model.

[0012] In some embodiments, the CT image data is a three-dimensional image;

[0013] The routine blood test data include: eosinophil percentage, monocyte percentage, mean corpuscular hemoglobin concentration, platelet count and hematocrit;

[0014] The biochemical examination data include: lipoprotein concentration, alanine aminotransferase concentration, blood glucose concentration, creatinine concentration and α-hydroxybutyrate dehydrogenase concentration.

[0015] In some embodiments, the relative weight ratios of eosinophil percentage, monocyte percentage, mean corpuscular hemoglobin concentration, platelet count, and hematocrit are: 1: 0.982252: 0.949399: 0.917071: 0.880628;

[0016] The relative weight ratios of lipoprotein concentration, alanine aminotransferase concentration, blood glucose concentration, creatinine concentration and α-hydroxybutyrate dehydrogenase concentration were: 1:0.992169:0.985879:0.940291:0.932662.

[0017] In some embodiments, the preset neural network is a multi-input neural network, including a first neural network, a second neural network, and a third neural network;

[0018] The preset neural network processes the CT image data through the first neural network; wherein the first neural network is a 3D neural network;

[0019] The preset neural network processes the conventional blood test data through the second neural network;

[0020] The preset neural network processes the biochemical examination data through the third neural network.

[0021] In some embodiments, the first neural network is: a convolutional neural network, a fully connected neural network, a recurrent neural network, or a Transformer model;

[0022] The second neural network and the third neural network are respectively: a convolutional neural network, a fully connected neural network, a support vector machine or a decision tree.

[0023] In some embodiments, the recurrence signature includes: low risk, medium risk, and high risk.

[0024] In some embodiments, after acquiring the bladder cancer recurrence prediction data and the recurrence label corresponding to each of the bladder cancer recurrence prediction data, and before establishing the CT image training data set, the conventional blood test training data set, and the biochemical examination training data set according to the plurality of bladder cancer recurrence prediction data, the following steps are also included:

[0025] The CT image data is preprocessed to highlight the three-dimensional structure and microscopic image features of the bladder and the tumor in the CT image data; wherein the preprocessing at least includes: segmentation, noise reduction and contrast enhancement.

[0026] Another aspect of the embodiments of the present invention further provides a bladder cancer recurrence prediction system, which is used to implement the bladder cancer recurrence prediction method, comprising:

[0027] A data acquisition module, which acquires bladder cancer recurrence prediction data and a recurrence label corresponding to each of the bladder cancer recurrence prediction data; wherein the bladder cancer recurrence prediction data includes mutually corresponding CT image data, routine blood test data and biochemical test data;

[0028] A data establishment module, which establishes a CT image training data set, a conventional blood test training data set, and a biochemical examination training data set according to the plurality of bladder cancer recurrence prediction data;

[0029] A model training module, inputting the CT image training data set, the conventional blood test training data set and the biochemical examination training data set into a preset neural network, and adjusting parameters of the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model;

[0030] The model prediction module, when acquiring the current bladder cancer recurrence prediction data, classifies the current bladder cancer recurrence prediction data according to the recurrence label based on the bladder cancer recurrence prediction model.

[0031] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium for storing a program, wherein the program implements the steps of the bladder cancer recurrence prediction method when executed by a processor.

[0032] Another aspect of the embodiments of the present invention further provides a computer program product, including a computer program, which implements the steps of the bladder cancer recurrence prediction method when executed.

[0033] The bladder cancer recurrence prediction method, system, storage medium and program product of the present invention construct a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, and comprehensively consider the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, which can improve the accuracy and efficiency of bladder cancer recurrence risk prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present invention, and together with the specification are used to explain the principles of the present invention. Obviously, the accompanying drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0035] Figure 1 A flowchart showing the steps of a method for predicting bladder cancer recurrence according to an embodiment of the present invention;

[0036] Figure 2 Show Figure 1 Schematic diagram of the process of predicting bladder cancer recurrence;

[0037] Figure 3 A flowchart showing the steps of another method for predicting bladder cancer recurrence according to an embodiment of the present invention;

[0038] Figure 4 A schematic diagram showing a module of a bladder cancer recurrence prediction system according to an embodiment of the present invention;

[0039] Figure 5 A schematic diagram showing the structure of a bladder cancer recurrence prediction device according to an embodiment of the present invention;

[0040] Figure 6 A schematic diagram showing the structure of a computer-readable storage medium according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0041] In order to make the advantages, spirit and features of the present invention easier and clearer to understand, the following will be described and discussed in detail with reference to the accompanying drawings using specific embodiments. It is worth noting that these specific embodiments are only representative embodiments of the present invention, and the specific methods, devices, conditions, materials, etc. exemplified therein are not intended to limit the present invention or the corresponding specific embodiments. In addition, the devices in the figures are only used to express their relative positions and are not drawn according to their actual proportions, so it is necessary to explain this first.

[0042] In the description of this specification, the description with reference to the terms "a specific embodiment", "another specific embodiment" or "part of a specific embodiment" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments in a suitable manner.

[0043] In various embodiments of the present invention, the expression "or" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" may include A, may include B, or may include both A and B. In addition, the indefinite articles "a", "a", and "an" before the device or element of the present invention have no restrictions on the quantity requirements (i.e., the number of occurrences) of the device or element. Therefore, "a" should be interpreted as including one or at least one, and the device or element in the singular form also includes the plural form, unless the number clearly refers to the singular form.

[0044] The inventor of this case has provided a solution to the problems existing in the prior art through careful and in-depth research. The present invention discloses a bladder cancer recurrence prediction method, system, storage medium and program product. Among them, the bladder cancer recurrence prediction method includes the following steps: obtaining bladder cancer recurrence prediction data and corresponding recurrence labels; the bladder cancer recurrence prediction data includes mutually corresponding CT image data, routine blood test data and biochemical examination data; establishing a CT image training data set, a routine blood test training data set and a biochemical examination training data set respectively; inputting the CT image training data set, the routine blood test training data set and the biochemical examination training data set into a preset neural network, and adjusting the parameters of the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model; when obtaining the current bladder cancer recurrence prediction data, based on the bladder cancer recurrence prediction model, the current bladder cancer recurrence prediction data is classified according to the recurrence label. The bladder cancer recurrence prediction method, system, storage medium and program product of the present invention construct a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, and comprehensively consider the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, which can improve the accuracy and efficiency of bladder cancer recurrence risk prediction.

[0045] The specific implementation modes of the present invention are further described in detail below with reference to the accompanying drawings.

[0046] like Figure 1 As shown, one aspect of the present invention provides a method for predicting bladder cancer recurrence, comprising the following steps:

[0047] S110, obtaining bladder cancer recurrence prediction data and a recurrence label corresponding to each bladder cancer recurrence prediction data; wherein the bladder cancer recurrence prediction data includes mutually corresponding CT image data, routine blood test data, and biochemical test data;

[0048] S120, establishing a CT image training data set, a conventional blood test training data set, and a biochemical examination training data set respectively according to the plurality of bladder cancer recurrence prediction data;

[0049] S130, inputting the CT image training data set, the conventional blood test training data set, and the biochemical examination training data set into a preset neural network, and adjusting the parameters of the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model;

[0050] S140 . When the current bladder cancer recurrence prediction data is obtained, the current bladder cancer recurrence prediction data is classified according to the recurrence label based on the bladder cancer recurrence prediction model.

[0051] It is worth noting that the above S110 to S140 are merely step numbers, which are used to facilitate reference and avoid text duplication, rather than to limit the order of implementation of the various steps of the method. In other embodiments, the above steps of the method can also be written and implemented in an interchangeable order, and are not limited thereto. The subsequent step numbers in the present invention all have the same meaning and function, and the repeated parts will not be repeated.

[0052] In some embodiments, the CT (Computed Tomography) image data is a three-dimensional image, but is not limited thereto. Using three-dimensional CT image data as training data for a bladder cancer recurrence prediction model can capture the three-dimensional structure and microscopic image features of the bladder and tumor tissue, and can improve the accuracy of bladder cancer recurrence prediction.

[0053] In some embodiments, routine blood test data include: eosinophil percentage, monocyte percentage, mean corpuscular hemoglobin concentration, platelet count and hematocrit, but are not limited thereto. Specifically, in the eosinophil percentage (EO%), eosinophils are a type of white blood cell involved in immune response. Studies have shown that abnormal increase or decrease in eosinophils may be associated with the development and recurrence of certain cancers. This may be because they play a role in inflammation and immune surveillance, thereby affecting tumor growth and metastasis. In the monocyte percentage (MONO%), monocytes are an important immune cell that can be transformed into macrophages and dendritic cells and participate in phagocytosis and antigen presentation. Changes in the proportion of monocytes may reflect the state of the immune system, which plays a key role in identifying and clearing cancer cells. Therefore, changes in monocytes may be related to the risk of cancer recurrence. In the mean corpuscular hemoglobin concentration (MCHC), MCHC represents the concentration of hemoglobin in red blood cells. Anemia or abnormal red blood cell function in cancer patients may reflect the impact of cancer on the body and the side effects of treatment. Changes in MCHC may indirectly reflect the health status and recurrence risk of bladder cancer patients. In platelet count (PLT), platelets play an important role in hemostasis and wound healing and are closely related to tumor growth and metastasis. High platelet counts (thrombocytosis) are common in many types of cancer and have been shown to be associated with poor prognosis and cancer recurrence. In hematocrit (HCT), hematocrit refers to the volume percentage of red blood cells in the blood. Changes in HCT can reflect the patient's blood status. Symptoms such as anemia or dehydration may affect the overall health and treatment effect of cancer patients. Therefore, abnormalities in HCT may be related to the risk of recurrence of bladder cancer. Therefore, routine blood test data such as eosinophil percentage, monocyte percentage, mean corpuscular hemoglobin concentration, platelet count and hematocrit, as training data for the bladder cancer recurrence prediction model, can reflect the patient's inflammation level and overall health status, and can improve the accuracy of bladder cancer recurrence prediction.

[0054] Furthermore, the relative weight ratios of eosinophil percentage, monocyte percentage, mean corpuscular hemoglobin concentration, platelet count and hematocrit are: 1:0.982252:0.949399:0.917071:0.880628. Specifically, the relative weight ratio of the above data is the weight ratio of the influence of these data on the final prediction result during model training. The above data are used to train the bladder cancer recurrence prediction model with the above weight ratio, which can improve the accuracy of bladder cancer recurrence prediction.

[0055] In some embodiments, the biochemical test data include: lipoprotein concentration, alanine aminotransferase concentration, blood glucose concentration, creatinine concentration and alpha-hydroxybutyrate dehydrogenase concentration, but are not limited thereto. Specifically, lipoprotein (A) is a complex that transports lipids in the blood. Abnormal lipoprotein levels may reflect metabolic disorders, which are associated with the development and recurrence of various cancers. An imbalance in the ratio of high-density lipoprotein (HDL) and low-density lipoprotein (LDL) may affect the stability of cell membranes and signal transduction, thereby promoting the growth and metastasis of cancer cells. Alanine aminotransferase (ALT) is a liver enzyme that is mainly present in the liver. Elevated ALT levels usually indicate liver cell damage. Bladder cancer patients may have increased liver burden due to tumor spread or treatment, resulting in abnormal ALT levels. Abnormal liver function may affect the body's overall metabolism and immune function, leading to the recurrence of cancer. Abnormal blood glucose (GLU) levels, especially long-term hyperglycemia (diabetes), are closely related to the occurrence and recurrence of cancer. Hyperglycemia may promote the growth and spread of tumor cells, while affecting the function of the immune system, and the body's ability to monitor and eliminate cancer cells decreases. Creatinine (CREA) is a product of muscle metabolism and is excreted through the kidneys. Serum creatinine levels can reflect renal function. Bladder cancer patients may suffer from impaired renal function due to tumor compression or side effects of treatment, which in turn affects creatinine levels. Abnormal renal function may affect drug metabolism and excretion, causing the risk of cancer recurrence. α-Hydroxybutyrate dehydrogenase (HBDH) is an enzyme related to energy metabolism. Increased HBDH levels may reflect tissue damage or abnormal changes in cellular metabolism. Increased HBDH in bladder cancer patients may be related to increased tumor burden or side effects of treatment, all of which may cause cancer recurrence. Therefore, biochemical examination data such as lipoprotein, alanine aminotransferase, blood sugar, creatinine and α-Hydroxybutyrate dehydrogenase index data, as training data for the bladder cancer recurrence prediction model, can further reflect the patient's inflammation level and overall health status, and can improve the accuracy of bladder cancer recurrence prediction.

[0056] In some embodiments, the relative weight ratio of lipoprotein concentration, alanine aminotransferase concentration, blood glucose concentration, creatinine concentration and α-hydroxybutyrate dehydrogenase concentration is: 1: 0.992169: 0.985879: 0.940291: 0.932662. Specifically, the relative weight ratio of the above data is the weight ratio of the influence of these data on the final prediction result during model training. The above data is used to train the bladder cancer recurrence prediction model with the above weight ratio, which can improve the accuracy of bladder cancer recurrence prediction.

[0057] like Figure 2As shown, in some embodiments, the preset neural network can be a multi-input neural network, which can include a first neural network, a second neural network, and a third neural network. The preset neural network processes CT image data through the first neural network; wherein the first neural network is a 3D neural network. The preset neural network processes conventional blood test data through the second neural network. The preset neural network processes biochemical examination data through the third neural network. wherein the first neural network, the second neural network, and the third neural network can be trained and processed in parallel.

[0058] Specifically, the first neural network can be: a convolutional neural network, a fully connected neural network, a recurrent neural network or a Transformer model. The second neural network and the third neural network can be: a convolutional neural network, a fully connected neural network, a support vector machine or a decision tree, respectively. The present application can improve the accuracy and efficiency of bladder cancer recurrence prediction by selecting the above neural network models.

[0059] Exemplarily, the present application can process CT image data through a 3D convolutional neural network (3D-CNN), extract high-level features from the CT image data, and output it as a 512-dimensional feature vector. Conventional blood test data is processed by a convolutional neural network (CNN), features are extracted from the conventional blood test data, and output as a 32-dimensional feature vector. Biochemical examination data is processed by another convolutional neural network (CNN), features are extracted from the biochemical examination data, and output as a 32-dimensional feature vector. The Concatenate layer of the preset preset neural network splices the above three feature vectors into a 576-dimensional vector. The preset preset neural network processes the spliced ​​feature vector through multiple fully connected layers (Dense), and finally outputs the predicted recurrence label.

[0060] In some embodiments, the recurrence label may include: low risk, medium risk and high risk, but is not limited thereto. Specifically, the low risk of the actual recurrence label may be that no recurrence is found in 5 years of follow-up; the medium risk may be that recurrence is found in 5 years of follow-up, and the recurrence occurs 12 months after the operation; the high risk may be that recurrence is found in 5 years of follow-up, and the recurrence occurs within 12 months of the operation. That is, when the bladder cancer recurrence prediction model of the present application is implemented, the acquired CT image data, routine blood test data and biochemical examination data are classified according to the low risk, medium risk and high risk in the predicted recurrence label to assist doctors in predicting the recurrence risk of the corresponding user.

[0061] like Figure 3As shown, in some embodiments, after step S110 and before step S120, the following steps may be further included: preprocessing the CT image data to highlight the three-dimensional structure and microscopic image features of the bladder and tumor in the CT image data; wherein the preprocessing includes at least segmentation, noise reduction, and contrast enhancement. Preprocessing the CT image data can improve the accuracy and efficiency of bladder cancer recurrence prediction.

[0062] The bladder cancer recurrence prediction method of the present invention constructs a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, and comprehensively considers the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, which can improve the accuracy and efficiency of bladder cancer recurrence risk prediction.

[0063] like Figure 4 As shown, based on the same inventive concept, another aspect of the present invention provides a bladder cancer recurrence prediction system 50, which is used to implement the above-mentioned bladder cancer recurrence prediction method, specifically comprising:

[0064] The data acquisition module 51 acquires bladder cancer recurrence prediction data and a recurrence label corresponding to each bladder cancer recurrence prediction data; wherein the bladder cancer recurrence prediction data includes mutually corresponding CT image data, routine blood test data and biochemical test data;

[0065] A data establishment module 52, which establishes a CT image training data set, a conventional blood test training data set, and a biochemical examination training data set according to a plurality of bladder cancer recurrence prediction data;

[0066] The model training module 53 inputs the CT image training data set, the conventional blood test training data set and the biochemical test training data set into a preset neural network, and adjusts the parameters of the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model;

[0067] The model prediction module 54, when acquiring the current bladder cancer recurrence prediction data, classifies the current bladder cancer recurrence prediction data according to the recurrence label based on the bladder cancer recurrence prediction model.

[0068] In some embodiments, the bladder cancer recurrence prediction system 50 further includes:

[0069] The data processing module pre-processes the CT image data to highlight the three-dimensional structure and microscopic image features of the bladder and tumor in the CT image data; wherein the pre-processing at least includes: segmentation, noise reduction and contrast enhancement.

[0070] The bladder cancer recurrence prediction system of the present invention constructs a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, and comprehensively considers the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, which can improve the accuracy and efficiency of bladder cancer recurrence risk prediction.

[0071] like Figure 5 As shown, based on the same inventive concept, another aspect of the present invention further provides a bladder cancer recurrence prediction device, comprising: a processor; a memory, wherein executable instructions of the processor are stored. The processor is configured to execute the steps of the bladder cancer recurrence prediction method by executing the executable instructions.

[0072] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0073] Refer to the following Figure 5 The electronic device 600 according to this embodiment of the present invention is described. Figure 5 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0074] like Figure 5 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0075] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0076] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0077] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0078] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0079] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0080] The bladder cancer recurrence prediction device of the present invention constructs a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, and comprehensively considers the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, which can improve the accuracy and efficiency of bladder cancer recurrence risk prediction.

[0081] like Figure 6 As shown, based on the same inventive concept, another aspect of the present invention further provides a computer-readable storage medium for storing a program, which implements the steps of the bladder cancer recurrence prediction method when the program is executed. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present invention described in the above-mentioned electronic prescription circulation processing method part of this specification.

[0082] like Figure 6 As shown, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0083] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0084] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program codes contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0085] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0086] The computer-readable storage medium of the present invention constructs a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, comprehensively considering the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, which can improve the accuracy and efficiency of bladder cancer recurrence risk prediction.

[0087] Based on the same inventive concept, another aspect of the present invention further provides a computer program product, including a computer program, and when the computer program is executed, the steps of the above-mentioned bladder cancer recurrence prediction method are performed. The computer program product of the embodiment of the present invention can be in the form of software, and the computer program included therein can refer to the embodiment of the computer-readable storage medium, and the repeated parts will not be repeated.

[0088] The computer program product of the present invention constructs a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, comprehensively considering the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, and can improve the accuracy and efficiency of bladder cancer recurrence risk prediction.

[0089] The bladder cancer recurrence prediction method, system, storage medium and program product of the present invention construct a multi-input bladder cancer recurrence prediction model through CT image data, routine blood test data and biochemical examination data, and comprehensively consider the three-dimensional structure and microscopic image characteristics of the patient's bladder and tumor tissue, as well as the patient's inflammation level and overall health status, which can improve the accuracy and efficiency of bladder cancer recurrence risk prediction.

[0090] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A method for predicting bladder cancer recurrence, characterized in that: The following steps are involved: Acquire bladder cancer recurrence prediction data and a recurrence label corresponding to each of the bladder cancer recurrence prediction data; wherein the bladder cancer recurrence prediction data includes mutually corresponding CT image data, routine blood test data and biochemical test data; According to the plurality of bladder cancer recurrence prediction data, a CT image training data set, a conventional blood test training data set and a biochemical examination training data set are respectively established; Inputting the CT image training data set, the conventional blood test training data set, and the biochemical examination training data set into a preset neural network, and adjusting parameters of the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model; When the current bladder cancer recurrence prediction data is acquired, the current bladder cancer recurrence prediction data is classified according to the recurrence label based on the bladder cancer recurrence prediction model.

2. The method for predicting bladder cancer recurrence according to claim 1, characterized in that: The CT image data is a three-dimensional image; The routine blood test data include: eosinophil percentage, monocyte percentage, mean corpuscular hemoglobin concentration, platelet count and hematocrit; The biochemical examination data include: lipoprotein concentration, alanine aminotransferase concentration, blood glucose concentration, creatinine concentration and α-hydroxybutyrate dehydrogenase concentration.

3. The method for predicting bladder cancer recurrence according to claim 2, characterized in that: The relative weight ratios of eosinophil percentage, monocyte percentage, mean corpuscular hemoglobin concentration, platelet count, and hematocrit were: 1:0.982252:0.949399:0.917071:0.880628; The relative weight ratios of lipoprotein concentration, alanine aminotransferase concentration, blood glucose concentration, creatinine concentration and α-hydroxybutyrate dehydrogenase concentration were: 1:0.992169:0.985879:0.940291:0.932662.

4. The method for predicting bladder cancer recurrence according to claim 2, characterized in that: The preset neural network is a multi-input neural network, including a first neural network, a second neural network and a third neural network; The preset neural network processes the CT image data through the first neural network; wherein the first neural network is a 3D neural network; The preset neural network processes the conventional blood test data through the second neural network; The preset neural network processes the biochemical examination data through the third neural network.

5. The method for predicting bladder cancer recurrence according to claim 4, characterized in that: The first neural network is: a convolutional neural network, a fully connected neural network, a recurrent neural network or a Transformer model; The second neural network and the third neural network are respectively: a convolutional neural network, a fully connected neural network, a support vector machine or a decision tree.

6. The method for predicting bladder cancer recurrence according to claim 1, characterized in that: The recurrence labels include: low risk, medium risk and high risk.

7. The method for predicting bladder cancer recurrence according to claim 1, characterized in that: After acquiring the bladder cancer recurrence prediction data and the recurrence labels corresponding to each of the bladder cancer recurrence prediction data, and before establishing the CT image training data set, the conventional blood test training data set, and the biochemical examination training data set according to the plurality of bladder cancer recurrence prediction data, the following steps are also included: The CT image data is preprocessed to highlight the three-dimensional structure and microscopic image features of the bladder and the tumor in the CT image data; wherein the preprocessing at least includes: segmentation, noise reduction and contrast enhancement.

8. A bladder cancer recurrence prediction system, used to implement the bladder cancer recurrence prediction method according to claim 1, characterized in that: include: A data acquisition module, which acquires bladder cancer recurrence prediction data and a recurrence label corresponding to each of the bladder cancer recurrence prediction data; wherein the bladder cancer recurrence prediction data includes mutually corresponding CT image data, routine blood test data and biochemical test data; A data establishment module, which establishes a CT image training data set, a conventional blood test training data set, and a biochemical examination training data set according to the plurality of bladder cancer recurrence prediction data; A model training module, inputting the CT image training data set, the conventional blood test training data set and the biochemical examination training data set into a preset neural network, and adjusting parameters of the preset neural network according to the recurrence label until the preset neural network converges to obtain a bladder cancer recurrence prediction model; The model prediction module, when acquiring the current bladder cancer recurrence prediction data, classifies the current bladder cancer recurrence prediction data according to the recurrence label based on the bladder cancer recurrence prediction model.

9. A computer-readable storage medium for storing a program, characterized in that: When the program is executed by a processor, the steps of the bladder cancer recurrence prediction method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed, the steps of the method for predicting bladder cancer recurrence according to any one of claims 1 to 7 are implemented.

Images