Myeloma prognosis staging system based on image processing and processing method

Abstract

The invention provides a myeloma prognosis staging system based on image processing and a processing method, and belongs to the technical field of image processing and intelligent medical treatment. The staging system comprises a characteristic parameter input unit, an image import unit, a system self-checking unit, a staging processing unit, a result output unit and a database summarization unit; the database summarizing unit is used for summarizing and storing the physical sign parameters, the corresponding staging processing results and the actual prognosis results of the staging myeloma patients. The method is executed based on a prognosis staging system comprising a first subsystem and a second subsystem, and comprises the step of outputting a prognosis staging result of a to-be-staging myeloma patient based on a staging treatment result of a target staging myeloma patient, and / or an actual prognosis result and a focus area recognition result. According to the technical scheme, physical sign parameters and clinical difference parameters of different patients are considered, meanwhile, hardware and software environments of a clinical system are considered, and the accuracy and portability of the myeloma prognosis staging treatment process can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of image processing and intelligent medical technology, and in particular relates to a myeloma prognosis and staging system and processing method based on image processing, a computer-readable storage medium for implementing the method, a computer program product and an electronic device. Background Art

[0002] Multiple myeloma (MM) is the result of malignant clones of plasma cells, and its incidence is second only to lymphoma. The disease shows a variable, multi-step clinical course, progressing from undetermined or smoldering myeloma (SMM) to symptomatic MM and plasma cell leukemia. Some patients progress rapidly, while others have an overall survival of more than 10 years. It is obviously too simplistic to treat all patients in the same way. Medical clinical consensus believes that risk stratification and staging can ensure that patients receive treatment that optimizes results and minimizes toxic effects as much as possible. Specifically, it is crucial to establish an accurate prognostic assessment system, especially to identify high-risk MM patients at the initial diagnosis, and to develop individualized treatment methods "according to the individual" to achieve optimal management of the disease.

[0003] Existing studies have found that the amount of 8F-FDG retained in cells is roughly consistent with the amount of glucose consumed by cells. 18F tracing can reflect the distribution and uptake levels of glucose in organs, tissues and cells of the body. The bones and extramedullary lesions of MM are characterized by high metabolism, which is shown as high uptake in 18F-FDG PET / CT imaging. Therefore, 18F-FDG PET / CT can display the glucose metabolic load of the lesions. It can be seen that 18F-FDG PET / CT imaging can not only intuitively display the metabolic status of multiple myeloma lesions, but also evaluate the infiltration of organs and bones throughout the body through a single examination, thereby quickly displaying the location and number of lesions in a multi-faceted, comprehensive and comprehensive manner. Therefore, it has unique advantages in the diagnosis of multiple myeloma and the display of tumor load. Chinese invention patent application publication CN114219787A proposes a prognostic staging system for newly diagnosed multiple myeloma. By binarizing imaging staging characteristic parameters for the prognostic staging of newly diagnosed multiple myeloma, the beneficial effect of accurately staging newly diagnosed multiple myeloma can be achieved.

[0004] However, existing staging systems are usually designed only for imaging images of a specific format, and their image analysis process is relatively simple. At the same time, the hardware and software architecture used by the staging system is usually different from conventional medical equipment and is prone to malfunction. More importantly, existing prognostic staging judgments usually adopt a single pre-set threshold judgment mode, without considering the common references between the physical sign parameters of different patients and clinical difference parameters. The accuracy and portability of the staging system are still insufficient. Summary of the invention

[0005] To solve the above technical problems, the present invention proposes a myeloma prognosis and staging system and processing method based on image processing, a computer-readable storage medium, a computer program product and an electronic device for implementing the method.

[0006] In a first aspect of the present invention, a myeloma prognosis and staging system based on image processing is provided, wherein the staging system comprises a database aggregation unit, a characteristic parameter input unit, an image import unit, a system self-checking unit, a staging processing unit, and a result output unit; The database summary unit summarizes and stores the physical sign parameters of staged myeloma patients, the corresponding stage treatment results and the actual prognosis results; The characteristic parameter input unit is used to input the original physical sign parameters of the myeloma patient to be staged, and the original physical sign parameters include gender, height, age, blood type, weight, and blood pressure; The image importing unit is used to import the to-be-staged image of the to-be-staged myeloma patient; The system self-check unit is used to perform a system self-check operation, and the system self-check operation includes a hardware self-check and a software self-check; The staging processing unit is used to perform lesion area recognition on the to-be-staging image imported by the image importing unit; The result output unit outputs a staging result based on the result of the lesion area identification.

[0007] The staging system includes a first subsystem and a second subsystem; operating the first subsystem in a first operation phase of the staging system, and operating the second subsystem in a second operation phase after the first operation phase; The hardware self-check includes detecting whether there is a target field filled by the first subsystem at the target position every target duration; The software self-check includes, after the hardware self-check passes, detecting whether the second subsystem supports displaying the image to be staged.

[0008] The staging processing unit is used to perform lesion area recognition on the to-be-staged image imported by the image importing unit to obtain a lesion area recognition result, wherein the lesion area recognition result includes the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area.

[0009] The result output unit outputs the staging result based on the result of the lesion area identification, specifically including: The result output unit matches at least one target staged myeloma patient in the database aggregation unit, and obtains the staged treatment result and / or actual prognosis result of the target staged myeloma patient; Based on the staging treatment results of the target staged myeloma patient and / or the actual prognosis results, as well as the number of suspected lesion areas, the size of each suspected lesion area and the location of each suspected lesion area, the result output unit outputs the prognosis staging result of the myeloma patient to be staged.

[0010] After the result output unit outputs the prognosis staging result of the myeloma patient to be staged, the physical sign parameters of the myeloma patient to be staged, the image to be staged and the prognosis staging result are associated and stored in the database summary unit.

[0011] In a second aspect of the present invention, a method for myeloma prognosis and staging based on image processing is provided. The method is performed based on a prognosis and staging system comprising a first subsystem and a second subsystem, and the method comprises the following steps: S100: Inputting physical parameters of the myeloma patient to be staged, wherein the physical parameters include gender, height, age, blood type, weight, and blood pressure; S200: importing the image of the patient with myeloma to be staged; S300: performing lesion region recognition on the to-be-staged image of the to-be-staged myeloma patient to obtain the number of suspected lesion regions, the size of each suspected lesion region, and the position of each suspected lesion region; S400: Matching at least one target staged myeloma patient, and obtaining the staged treatment result and / or actual prognosis result of the target staged myeloma patient; S500: Based on the staging treatment result of the target staged myeloma patient and / or the actual prognosis result, as well as the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area, output the prognosis staging result of the myeloma patient to be staged; The first subsystem is operated in a first operation phase of the staging system, and the second subsystem is operated in a second operation phase after the first operation phase.

[0012] The step S400 matches at least one target staged myeloma patient from the cloud summary database; After step S500, the method further includes: The updated physical sign parameters and prognosis staging results of the myeloma patient to be staged are associated and stored in the cloud summary database.

[0013] After step S500, the method further includes: Updating the physical sign parameters of the myeloma patient to be staged; The updating includes: updating the lesion area recognition result of the to-be-staged image of the to-be-staged myeloma patient to the to-be-staged physical sign parameter; The lesion region recognition result of the to-be-staged image of the to-be-staged myeloma patient includes the number of suspected lesion regions, the size of each suspected lesion region, and the position of each suspected lesion region.

[0014] After step S500, the method further includes: The actual prognosis result of the patient with myeloma to be staged is obtained, and the updated physical sign parameters, prognosis staging result and actual prognosis result of the patient with myeloma to be staged are associated and stored in a cloud summary database.

[0015] Before step S100, the method further includes: A system self-checking step, wherein the system self-checking includes a hardware self-checking stage and a software self-checking stage; The hardware self-checking stage includes detecting whether there is a target field filled by the first subsystem at the target position every target time length; The software self-checking stage includes, after the hardware self-checking stage is passed, detecting whether the second subsystem supports displaying the image to be staged.

[0016] Part or all of the steps of the myeloma prognosis and staging method based on image processing described in the second aspect can be automatically implemented through various forms of electronic devices and computer program instructions; the computer program instructions can be stored in storage media of different forms and loaded into computer electronic devices for execution.

[0017] Therefore, in the third aspect of the present invention, a computer-readable storage medium is also provided for storing computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes a myeloma prognosis and staging processing method based on image processing as described in the second aspect.

[0018] In a fourth aspect of the present invention, an electronic device is also proposed, comprising a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the aforementioned myeloma prognosis and staging processing method based on image processing.

[0019] In a fifth aspect of the present invention, a computer program product is also proposed. The product includes a computer program. When the computer program is executed, the aforementioned myeloma prognosis and staging method based on image processing is implemented.

[0020] The technical solution of the present invention takes into account the hardware failures and software adaptation problems that may exist in the clinical myeloma prognosis and staging system. First, a system self-check unit is introduced to perform a system self-check operation, and the system self-check operation includes a hardware self-check and a software self-check. Secondly, different from the preset threshold staging judgment method commonly used in the prior art, the technical solution of the present invention is based on the staging treatment results of the target staged myeloma patient, and / or the actual prognosis results, as well as the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area, to output the prognosis and staging results of the myeloma patient to be staged, and also considers the actual staging results in the later stage, so as to continuously update the cloud summary database, consider the physical sign parameters and clinical difference parameters of different patients, and take into account the hardware and software environment of the clinical system, so as to improve the accuracy and portability of the myeloma prognosis and staging process.

[0021] Further advantages of the present invention will be further reflected in detail in the specific embodiments section in conjunction with the drawings of the specification. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 This is a schematic diagram of the functional units of a myeloma prognosis and staging system based on image processing according to an embodiment of the present invention; Figure 2 yes Figure 1 A schematic diagram of the working principle of the staging processing unit in the myeloma prognosis and staging system based on image processing; Figure 3 This is a main process step diagram of a myeloma prognosis and staging processing method based on image processing according to an embodiment of the present invention; Figure 4 yes Figure 3 A schematic diagram of a further preferred embodiment of the myeloma prognosis and staging method based on image processing. DETAILED DESCRIPTION

[0024] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments that are the same as the present application. Instead, they are only examples of devices and methods that are the same as some aspects of the present application as detailed in the attached claims.

[0025] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0026] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0027] Figure 1 The figure is a schematic diagram of the functional units of a myeloma prognosis and staging system based on image processing according to an embodiment of the present invention.

[0028] exist Figure 1 , it is shown that the prognosis and staging system includes a database aggregation unit, a characteristic parameter input unit, an image import unit, a system self-check unit, a staging processing unit and a result output unit.

[0029] Specifically, the functions performed by each functional unit are as follows: The characteristic parameter input unit is used to input the original physical sign parameters of the myeloma patient to be staged, and the original physical sign parameters include gender, height, age, blood type, weight, blood pressure, etc.; The process of inputting the original vital sign parameters of the myeloma patient to be staged involves user data. However, it is understandable that, according to the subsequent technical solution introduction, the data collected by the present invention are all unrelated to personal identity information (for example, vital sign parameters include gender, height, age, blood type, weight, blood pressure), and do not involve user identity identification; at the same time, before starting the relevant service, a prompt interface, pop-up window or output voice prompt information can be displayed, and the prompt interface, pop-up window or voice prompt information is used to prompt the user that the relevant data is currently being collected, so that the present application only starts to execute the relevant steps of obtaining the user's relevant data after obtaining the user's confirmation operation on the prompt interface or pop-up window, otherwise (that is, when the user's confirmation operation on the prompt interface or pop-up window is not obtained), the relevant steps of obtaining the user's relevant data are terminated, that is, the user's relevant data is not obtained, and the relevant service cannot be provided.

[0030] Therefore, in the specific implementation of this application, if user-related data is involved, when the embodiment of this application is applied to a specific product or technology, the user's permission or consent must be obtained, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0031] The image importing unit is used to import the to-be-staged image of the to-be-staged myeloma patient; As a specific example, the image to be staged is preferably a whole-body PET / CT image of a myeloma patient to be staged; Of course, in actual clinical applications, as an alternative or supplement, commonly used imaging examination methods for the diagnosis and treatment of multiple myeloma also include X-ray, CT, and MRI, and the corresponding imaging can also be used as the images to be staged in the embodiments of the present application.

[0032] The staging processing unit is used to perform lesion area recognition on the to-be-staging image imported by the image importing unit; The result output unit outputs a staging result based on the result of the lesion area identification.

[0033] exist Figure 1 Based on Figure 2 , Figure 2 yes Figure 1 A schematic diagram of the working principle of the staging processing unit in the myeloma prognosis and staging system based on image processing.

[0034] exist Figure 2 In the embodiment, the staging processing unit is used to perform lesion area recognition on the image to be staged imported by the image importing unit to obtain a lesion area recognition result, and the lesion area recognition result includes the number of suspected lesion areas, the size of each suspected lesion area and the position of each suspected lesion area.

[0035] The result output unit outputs the staging result based on the result of the lesion area identification, specifically including: The result output unit matches at least one target staged myeloma patient in the database aggregation unit, and obtains the staged treatment result and / or actual prognosis result of the target staged myeloma patient; Based on the staging treatment results of the target staged myeloma patient and / or the actual prognosis results, as well as the number of suspected lesion areas, the size of each suspected lesion area and the location of each suspected lesion area, the result output unit outputs the prognosis staging result of the myeloma patient to be staged.

[0036] The database summary unit summarizes and stores the physical sign parameters of staged myeloma patients and the corresponding stage treatment results and actual prognosis results.

[0037] After the result output unit outputs the prognosis staging result of the myeloma patient to be staged, the physical sign parameters of the myeloma patient to be staged, the image to be staged and the prognosis staging result are associated and stored in the database summary unit.

[0038] The system self-check unit is used to perform a system self-check operation, and the system self-check operation includes a hardware self-check and a software self-check; The staging system includes a first subsystem and a second subsystem; operating the first subsystem in a first operation phase of the staging system, and operating the second subsystem in a second operation phase after the first operation phase; The hardware self-check includes detecting whether there is a target field filled by the first subsystem at the target position every target duration; The software self-check includes, after the hardware self-check passes, detecting whether the second subsystem supports displaying the image to be staged.

[0039] Next, combine Figure 1-Figure 2 The system implementation scheme architecture is described below, with a specific example to illustrate the implementation process of the technical solution of the present application.

[0040] Assume that the myeloma patient to be staged is A, the original physical sign parameter sequence of the myeloma patient A to be staged is A1={sex, height, age, blood type, weight, blood pressure}; the image to be staged of the myeloma patient A to be staged is ImagA; First, perform a system self-test.

[0041] In clinical system applications, the terminal device currently operated by the user usually has two modes, corresponding to the first subsystem and the second subsystem respectively. The first subsystem is the daily working mode, which is usually used for simple data processing (such as prescription writing, etc.); the second subsystem is the prognosis staging mode, which requires the imported images to be staged to undergo a prognosis staging process.

[0042] It can be understood that the first subsystem is in master mode (master system) and the second subsystem is in slave mode (slave system). The first subsystem must be normal before switching to the second subsystem.

[0043] In clinical practice, the first subsystem usually has a high failure rate due to frequent use, and there may also be frequent switching operations (from the first subsystem to the second subsystem, and then back to the first subsystem), which may cause the software and hardware environment to be incompatible with the current actual data processing, resulting in system crashes, etc.

[0044] Therefore, the technical solution of the present invention introduces a system self-check unit, which is used to perform a system self-check operation, and the system self-check operation includes a hardware self-check and a software self-check; operating the first subsystem in a first operation phase of the staging system, and operating the second subsystem in a second operation phase after the first operation phase; The hardware self-check includes detecting whether there is a target field filled by the first subsystem at the target position every target duration; As a specific implementation, the system self-check can be implemented by an embedded controller (EC, Embedded Controller), specifically including: When the installment system is turned on, during the operation of the first subsystem, if it is in a normal working state and there is no fault or hang-up, it will fill a target field into the target position at every target duration, and the EC will detect whether there is a target field filled by the first subsystem at the target position at the same target duration; if the EC detects the target field at the target position, it means that the current first subsystem is in a normal working state; if the EC does not detect the target field at the target position, the EC can know that the current first subsystem may have a fault or hang-up, and may need to be restarted to fix the fault or release the hang-up state.

[0045] In order to save storage space and prevent the target field from being filled too many times at the target location, resulting in a large amount of space being occupied, the first subsystem can use the current timestamp as the target field when filling the target field at the target location. When filling it again after an interval of the target time, the current timestamp can be used to overwrite the last timestamp filled. The demand for storage space is reduced by continuously updating the timestamp filled at the target location.

[0046] If the number of times that the target field is not detected continuously exceeds a first threshold, the staging system is restarted.

[0047] The software self-check includes, after the hardware self-check passes, detecting whether the second subsystem supports displaying the image to be staged; if it does not support displaying the image to be staged, converting the format of the current image to be staged, or re-importing other images to be staged that support display.

[0048] This embodiment can enter the automatic repair mode. In the automatic repair mode, it is determined whether the electronic device has a fault or is in an idle state by detecting whether there is a target field filled by the first subsystem at the target location. If the number of consecutive times that the target field is not detected exceeds the first threshold, it is determined that a fault has occurred or the device is in an idle state. At this time, the installment system is restarted to enable it to self-repair certain faults by restarting, thereby avoiding the occurrence of system crashes due to the subsequent software and hardware environment being incompatible with the current actual data processing.

[0049] Next, we will move on to the actual image processing-based myeloma prognostic staging process: Step 1: Input the original physical sign parameter sequence A1={sex, height, age, blood type, weight, blood pressure} of the myeloma patient A to be staged through the characteristic parameter input unit; Step 2-obtaining the staging image ImagA of the myeloma patient A through the image importing unit; Step 3-The staging processing unit is used to perform lesion area recognition on the to-be-staged image imported by the image importing unit to obtain a lesion area recognition result Ar, wherein the lesion area recognition result Ar includes the number of suspected lesion areas Na, the size Ai of each suspected lesion area, and the position Lai of each suspected lesion area; Wherein, Ai represents the area size of the i-th suspected lesion area; Lai represents the position coordinates of the i-th suspected lesion area, i=1, 2, ...Na, Na≥2; Step 4-the result output unit matches at least one target staged myeloma patient B in the database aggregation unit; Among them, Step 4 specifically includes the following: Step 41: matching multiple target staged myeloma patients B in the database summary unit based on the original physical sign parameter sequence A1, wherein the original physical sign parameter sequence B1 of each target staged myeloma patient B is similar to the original physical sign parameter sequence A1; It can be understood that the database summary unit is continuously updated, and summarizes and stores the physical sign parameters of staged myeloma patients and the corresponding stage treatment results and actual prognosis results; Step 42: Obtain the staging processing result of each of the target staged myeloma patients B; the staging processing result includes the target lesion region recognition result Br of the staged image ImagB of the target staged myeloma patient B, and the lesion region recognition result Br includes the number Nb of suspected lesion regions, the size Bi of each suspected lesion region, and the position Lbi of each suspected lesion region; Step 43: If the similarity between the target lesion region recognition result Br and the target lesion region recognition result Ar is greater than a preset threshold, the staging treatment result and / or actual prognosis result of the target staged myeloma patient B is obtained; Step 5: Based on the staging treatment result of the target staged myeloma patient B and / or the actual prognosis result, and the target lesion area identification result Ar, the result output unit outputs the prognosis staging result of the myeloma patient to be staged.

[0050] In the embodiments of the present application, the staging treatment result refers to the clinical stage I, stage II, stage III, etc. standards, and the actual prognosis result refers to the actual survival rate (OS rate) of the relevant patients.

[0051] In a specific embodiment, the Step 5 further includes: If the target staged myeloma patient B also includes an actual prognosis result, the result output unit outputs the reference actual prognosis result of the to-be-staged myeloma patient.

[0052] In one embodiment, the staging treatment result and / or actual prognosis result of a target staged myeloma patient B is used as the staging treatment result and / or actual prognosis result of the to-be-staged myeloma patient A; In another embodiment, if there are multiple target staged myeloma patients B, the weighted result of the staging treatment results and / or the weighted result of the actual prognosis results of the target staged myeloma patients B are used as the staging treatment results and / or the actual prognosis results of the to-be-staged myeloma patient A; Preferably, the weighted weight used in the weighted result is determined based on the sum of the absolute values ​​of the differences between the corresponding items of the target lesion area identification result Br and the target lesion area identification result Ar (i.e., Na and Nb, Lai and Lbi (Euclidean distance), Ai and Bi) (|Na-Nb|+|Lai-Lbi|+|Ai-Bi|). The smaller the sum of the absolute values ​​of the differences, the greater the weighted weight.

[0053] After the weighted result is used as the staging result and / or the actual prognosis result of the myeloma patient A to be staged, the physical sign parameters, the image to be staged and the prognosis staging result of the myeloma patient to be staged are associated and stored in the database summary unit.

[0054] exist Figure 1-Figure 2 Based on the system implementation example, combined Figure 3-Figure 4 The method embodiment of the present invention is further described as follows: Figure 3 The main process step diagram of a myeloma prognosis and staging processing method based on image processing according to an embodiment of the present invention.

[0055] Figure 3 The method is performed based on a prognostic staging system comprising a first subsystem and a second subsystem, and the method comprises the following steps: S100: Inputting physical parameters of the myeloma patient to be staged, wherein the physical parameters include gender, height, age, blood type, weight, and blood pressure; S200: importing the image of the patient with myeloma to be staged; S300: performing lesion region recognition on the to-be-staged image of the to-be-staged myeloma patient to obtain the number of suspected lesion regions, the size of each suspected lesion region, and the position of each suspected lesion region; S400: Matching at least one target staged myeloma patient, and obtaining the staged treatment result and / or actual prognosis result of the target staged myeloma patient; S500: Based on the staging treatment result of the target staged myeloma patient and / or the actual prognosis result, as well as the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area, output the prognosis staging result of the myeloma patient to be staged; The first subsystem is operated in a first operation phase of the staging system, and the second subsystem is operated in a second operation phase after the first operation phase.

[0056] The step S400 matches at least one target staged myeloma patient from the cloud summary database; After step S500, the method further includes: The updated physical sign parameters and prognosis staging results of the myeloma patient to be staged are associated and stored in the cloud summary database.

[0057] After step S500, the method further includes: Updating the physical sign parameters of the myeloma patient to be staged; The updating includes: updating the lesion area recognition result of the to-be-staged image of the to-be-staged myeloma patient to the to-be-staged physical sign parameter; The lesion region recognition result of the to-be-staged image of the to-be-staged myeloma patient includes the number of suspected lesion regions, the size of each suspected lesion region, and the position of each suspected lesion region.

[0058] After step S500, the method further includes: The actual prognosis result of the patient with myeloma to be staged is obtained, and the updated physical sign parameters, prognosis staging result and actual prognosis result of the patient with myeloma to be staged are associated and stored in a cloud summary database.

[0059] A system self-checking step, wherein the system self-checking includes a hardware self-checking stage and a software self-checking stage; The hardware self-checking stage includes detecting whether there is a target field filled by the first subsystem at the target position every target time; the target field includes a timestamp of the current moment; The software self-checking stage includes, after the hardware self-checking stage is passed, detecting whether the second subsystem supports displaying the image to be staged.

[0060] Figure 4 yes Figure 3 A schematic diagram of a further preferred embodiment of the myeloma prognosis and staging method based on image processing.

[0061] For a more complete expression Figure 3-Figure 4 The whole process of the above embodiment of the present invention is implemented in a computer process language as follows: S000: system self-checking step, which includes a hardware self-checking stage and a software self-checking stage; The hardware self-checking stage includes detecting whether there is a target field filled by the first subsystem at the target position every target time; the target field includes a timestamp of the current moment; The software self-checking stage includes, after the hardware self-checking stage is passed, detecting whether the second subsystem supports displaying the current image to be staged; If the image to be divided is not supported for display, the format of the current image to be divided is converted, or other images to be divided that are supported for display are re-imported; S100: Inputting physical parameters of the myeloma patient to be staged, wherein the physical parameters include gender, height, age, blood type, weight, and blood pressure; S200: importing the image of the patient with myeloma to be staged; S300: performing lesion region recognition on the to-be-staged image of the to-be-staged myeloma patient to obtain the number of suspected lesion regions, the size of each suspected lesion region, and the position of each suspected lesion region; S400: Matching at least one target staged myeloma patient, and obtaining the staged treatment result and / or actual prognosis result of the target staged myeloma patient; S500: Based on the staging treatment result of the target staged myeloma patient and / or the actual prognosis result, as well as the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area, output the prognosis staging result of the myeloma patient to be staged; S600: updating the lesion region recognition result of the to-be-staged image of the to-be-staged myeloma patient to the physical sign parameter; S700: Obtaining the actual prognosis result of the myeloma patient to be staged; S800: The updated vital sign parameters, prognosis staging results and actual prognosis results of the myeloma patient to be staged are associated and stored in a cloud summary database, and the process returns to step S000.

[0062] The present invention provides multiple embodiments, each of which can constitute an independent technical solution and may contribute to the prior art and solve corresponding technical problems. However, it should be pointed out that different embodiments can be combined with each other without violating logic; at the same time, each embodiment can solve at least one technical problem, but it is not required that each individual embodiment solves multiple or all technical problems.

[0063] For other technologies, principles, algorithms or models not elaborated in detail in this application (such as performing lesion area identification on the staging image to obtain the number of suspected lesion areas, the size of each suspected lesion area and the location of each suspected lesion area), please refer to the prior art.

[0064] The technical solution of the present invention takes into account the hardware failures and software adaptation problems that may exist in the clinical myeloma prognosis and staging system. First, a system self-check unit is introduced to perform a system self-check operation, and the system self-check operation includes a hardware self-check and a software self-check. Secondly, different from the preset threshold staging judgment method commonly used in the prior art, the technical solution of the present invention is based on the staging treatment results of the target staged myeloma patient, and / or the actual prognosis results, as well as the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area, to output the prognosis and staging results of the myeloma patient to be staged, and also considers the actual staging results in the later stage, so as to continuously update the cloud summary database, consider the physical sign parameters and clinical difference parameters of different patients, and take into account the hardware and software environment of the clinical system, so as to improve the accuracy and portability of the myeloma prognosis and staging process.

[0065] The foregoing has shown and described the method embodiments and system of the present invention, but it is understandable to those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A myeloma prognosis and staging system based on image processing, the staging system comprising a characteristic parameter input unit, an image import unit, a system self-checking unit, a staging processing unit and a result output unit; Features: The system also includes a database aggregation unit; The database summary unit summarizes and stores the physical sign parameters of staged myeloma patients, the corresponding stage treatment results and the actual prognosis results; The characteristic parameter input unit is used to input the original physical sign parameters of the myeloma patient to be staged; The image importing unit is used to import the to-be-staged image of the to-be-staged myeloma patient; The system self-check unit is used to perform a system self-check operation, and the system self-check operation includes a hardware self-check and a software self-check; The staging processing unit is used to perform lesion area recognition on the to-be-staging image imported by the image importing unit; The result output unit outputs a staging result based on the result of the lesion area identification.

2. The myeloma prognosis and staging system based on image processing according to claim 1, characterized in that: The staging system includes a first subsystem and a second subsystem; operating the first subsystem in a first operation phase of the staging system, and operating the second subsystem in a second operation phase after the first operation phase; The hardware self-check includes detecting whether there is a target field filled by the first subsystem at the target position every target duration; The software self-check includes, after the hardware self-check passes, detecting whether the second subsystem supports displaying the image to be staged.

3. The myeloma prognosis and staging system based on image processing according to claim 1, characterized in that: The staging processing unit is used to perform lesion area recognition on the to-be-staged image imported by the image importing unit to obtain a lesion area recognition result, wherein the lesion area recognition result includes the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area.

4. The myeloma prognosis and staging system based on image processing as claimed in claim 3, characterized in that: The result output unit outputs the staging result based on the result of the lesion area identification, specifically including: The result output unit matches at least one target staged myeloma patient in the database aggregation unit, and obtains the staged treatment result and / or actual prognosis result of the target staged myeloma patient; Based on the staging treatment results of the target staged myeloma patient and / or the actual prognosis results, as well as the number of suspected lesion areas, the size of each suspected lesion area and the location of each suspected lesion area, the result output unit outputs the prognosis staging result of the myeloma patient to be staged.

5. The myeloma prognosis and staging system based on image processing as claimed in claim 3, characterized in that: After the result output unit outputs the prognosis staging result of the myeloma patient to be staged, the physical sign parameters of the myeloma patient to be staged, the image to be staged and the prognosis staging result are associated and stored in the database summary unit.

6. A method for myeloma prognosis and staging based on image processing, the method being performed based on a prognosis and staging system comprising a first subsystem and a second subsystem, characterized in that: The method comprises the following steps: S100: Input the physical parameters of the myeloma patient to be staged; S200: importing the staging image of the myeloma patient to be staged; S300: performing lesion region recognition on the to-be-staged image of the to-be-staged myeloma patient to obtain the number of suspected lesion regions, the size of each suspected lesion region, and the position of each suspected lesion region; S400: Matching at least one target staged myeloma patient, and obtaining the staged treatment result and / or actual prognosis result of the target staged myeloma patient; S500: Based on the staging treatment result of the target staged myeloma patient and / or the actual prognosis result, as well as the number of suspected lesion areas, the size of each suspected lesion area, and the position of each suspected lesion area, output the prognosis staging result of the myeloma patient to be staged; The first subsystem is operated in a first operation phase of the staging system, and the second subsystem is operated in a second operation phase after the first operation phase.

7. The method for myeloma prognosis and staging based on image processing according to claim 6, characterized in that: The step S400 matches at least one target staged myeloma patient from the cloud summary database; After step S500, the method further includes: The updated physical sign parameters and prognosis staging results of the myeloma patient to be staged are associated and stored in the cloud summary database.

8. The method for myeloma prognosis and staging based on image processing according to claim 6, characterized in that: After step S500, the method further includes: Updating the physical sign parameters of the myeloma patient to be staged; The updating includes: updating the lesion area recognition result of the to-be-staged image of the to-be-staged myeloma patient to the to-be-staged physical sign parameter; The lesion region recognition result of the to-be-staged image of the to-be-staged myeloma patient includes the number of suspected lesion regions, the size of each suspected lesion region, and the position of each suspected lesion region.

9. The method for myeloma prognosis and staging based on image processing according to claim 6, characterized in that: After step S500, the method further includes: The actual prognosis result of the patient with myeloma to be staged is obtained, and the updated physical sign parameters, prognosis staging result and actual prognosis result of the patient with myeloma to be staged are associated and stored in a cloud summary database.

10. The method for myeloma prognosis and staging based on image processing according to claim 6, characterized in that: Before step S100, the method further includes: A system self-checking step, wherein the system self-checking includes a hardware self-checking stage and a software self-checking stage; The hardware self-checking stage includes detecting whether there is a target field filled by the first subsystem at the target position every target time length; The software self-checking stage includes, after the hardware self-checking stage is passed, detecting whether the second subsystem supports displaying the image to be staged.

Images