A tumor cell risk assessment method, device, equipment and storage medium

Abstract

The application discloses a tumor cell risk assessment method, device, equipment and storage medium. The method comprises the following steps: acquiring a target marker detection image corresponding to a circulating tumor cell of a target patient; determining a first marker color difference and a second marker color difference corresponding to the target marker detection image based on the target marker detection image; inputting the first marker color difference and the second marker color difference into a tumor cell concentration detection model for cell concentration detection; and determining a target risk assessment result corresponding to the target marker detection image based on an output result of the tumor cell concentration detection model. The application can realize automatic risk assessment of circulating tumor cells, greatly reduce labor costs, improve tumor cell risk assessment efficiency, and thus ensure the stability and repeatability of the risk assessment result.

Description

Technical Field

[0001] This invention relates to the field of medical image analysis technology, and in particular to a method, apparatus, device, and storage medium for tumor cell risk assessment. Background Technology

[0002] The detection and risk assessment of circulating tumor cells is a key step in the field of liquid tumor biopsy. Their quantity and molecular phenotypic information can reflect tumor burden, metastasis risk and treatment response to a certain extent, and have important clinical significance for early warning of cancer, efficacy evaluation, recurrence monitoring and prognosis.

[0003] Currently, traditional methods for assessing tumor cell risk mainly rely on manual image interpretation or identification based on a single biomarker. However, these methods are highly subjective, labor-intensive, and inefficient, failing to guarantee the stability and reproducibility of the assessment results, thus hindering their application in clinical monitoring and large-scale sample analysis. Summary of the Invention

[0004] This invention provides a method, device, equipment, and storage medium for tumor cell risk assessment, enabling automated risk assessment of circulating tumor cells. This significantly reduces labor costs and the subjectivity of assessment results, improves the efficiency of tumor cell risk assessment, and ensures the stability and repeatability of risk assessment results, thus facilitating its application in clinical monitoring and large-scale sample analysis.

[0005] According to one aspect of the present invention, a method for assessing tumor cell risk is provided, the method comprising: Acquire images of target biomarkers corresponding to circulating tumor cells in the target patient; Based on the target marker detection image, determine the first marker color difference and the second marker color difference corresponding to the target marker detection image; The color difference of the first biomarker and the color difference of the second biomarker are input into the tumor cell concentration detection model for cell concentration detection. Based on the output of the tumor cell concentration detection model, the target risk assessment result corresponding to the target biomarker detection image is determined.

[0006] According to another aspect of the present invention, a tumor cell risk assessment device is provided, the device comprising: The image acquisition module is used to acquire images of target biomarkers corresponding to circulating tumor cells in the target patient. A color difference determination module is used to determine the first color difference and the second color difference of the target marker detection image based on the target marker detection image. The risk assessment module is used to input the color difference of the first marker and the color difference of the second marker into the tumor cell concentration detection model for cell concentration detection, and to determine the target risk assessment result corresponding to the target marker detection image based on the output result of the tumor cell concentration detection model.

[0007] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the tumor cell risk assessment method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the tumor cell risk assessment method according to any embodiment of the present invention.

[0009] The technical solution of this invention provides a data foundation for subsequent analysis by acquiring target biomarker detection images corresponding to circulating tumor cells of a target patient. Based on the target biomarker detection images, determining the color difference of a first biomarker and a second biomarker corresponding to the target biomarker detection images can effectively eliminate background interference and provide accurate and reliable input data for subsequent model analysis. The first and second biomarker color differences are input into a tumor cell concentration detection model for cell concentration detection. Based on the output of the tumor cell concentration detection model, the target risk assessment result corresponding to the target biomarker detection image is determined, avoiding the subjectivity and limitations of a single judgment standard and greatly improving assessment efficiency and accuracy. This invention, by performing dual biomarker detection on circulating tumor cells, and performing color difference analysis based on the target biomarker detection images, as well as tumor cell detection and risk assessment based on the color differences, can achieve automated and efficient circulating tumor cell risk assessment, greatly reducing manual costs, ensuring the stability and repeatability of risk assessment results, and facilitating applications in clinical monitoring and large-scale sample analysis.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a tumor cell risk assessment method provided in Embodiment 1 of the present invention; Figure 2 This is an example image of a target marker detection image according to Embodiment 1 of the present invention; Figure 3 This is a flowchart of a tumor cell risk assessment method provided in Embodiment 2 of the present invention; Figure 4 This is a schematic diagram of the structure of a tumor cell risk assessment device provided in Embodiment 3 of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device that implements the tumor cell risk assessment method of this invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Example 1 Figure 1This is a flowchart illustrating a tumor cell risk assessment method according to Embodiment 1 of the present invention. This embodiment is applicable to situations involving circulating tumor cell detection and risk assessment in patients. The method can be executed by a tumor cell risk assessment device, which can be implemented in hardware and / or software. This tumor cell risk assessment device can be configured in an electronic device. Figure 1 As shown, the method includes: S110. Obtain images of target biomarkers corresponding to circulating tumor cells of the target patient.

[0016] The target patient can refer to a specific cancer patient who requires circulating tumor cell (CTC) detection and risk assessment. Circulating tumor cells (CTCs) are tumor cells that detach from the primary tumor lesion and enter the bloodstream. The target biomarker detection image can refer to an experimental image containing dual biomarker signals obtained by detecting CTCs in a sample from the target patient.

[0017] Specifically, CTC detection technology can be used to perform circulating tumor cell detection experiments on target patients based on dual biomarker signals, and obtain images of the target biomarkers. This can avoid the limitations caused by a single biomarker, enrich the detection dimensions, and provide a comprehensive data foundation for subsequent analysis.

[0018] For example, S110 may include: in response to a dual-marker detection operation on circulating tumor cells of a target patient, acquiring a target marker detection image corresponding to the target patient, wherein the dual markers include: epithelial cell adhesion molecules and matrix metalloproteinases.

[0019] Epithelial cell adhesion molecule (EpCAM) can refer to a transmembrane glycoprotein widely expressed on the surface of normal epithelial cells and most epithelial-derived tumor cells. Matrix metalloproteinase 9 (MMP9) can refer to a proteolytic enzyme capable of degrading the extracellular matrix (such as collagen).

[0020] Specifically, epithelial cell adhesion molecules and matrix metalloproteinases can be used as dual biomarker signals to detect circulating tumor cells in blood samples from target patients. The experimental samples can be photographed to generate images of the target biomarkers, providing a comprehensive and multi-dimensional data foundation for subsequent analysis.

[0021] S120. Based on the target marker detection image, determine the first marker color difference and the second marker color difference corresponding to the target marker detection image.

[0022] The first marker color difference can refer to the RGB difference between different apertures corresponding to the first marker in the target marker detection image. The second marker color difference can refer to the RGB difference between different apertures corresponding to the second marker in the target marker detection image.

[0023] Specifically, based on the target marker detection image, the RGB difference between different apertures corresponding to the first marker and the RGB difference between different apertures corresponding to the second marker can be calculated to obtain the color difference between the first marker and the second marker. This can effectively eliminate background interference and provide accurate and reliable input data for subsequent model analysis.

[0024] For example, S120 may include: determining a first marker detection region and a second marker detection region based on the target marker detection image; performing color difference analysis on the first marker detection region and the second marker detection region respectively to determine the first marker color difference and the second marker color difference corresponding to the target marker detection image.

[0025] The first marker detection region can refer to the area in the target marker detection image that contains the hole location corresponding to the first marker signal (such as EpCAM). The second marker detection region can refer to the area in the target marker detection image that contains the hole location corresponding to the second marker signal (such as MMP9).

[0026] Specifically, the target marker detection image can be segmented based on the first marker signal and the second marker signal to determine the first marker detection area and the second marker detection area; and color difference analysis can be performed between different apertures in the first marker detection area and the second marker detection area to determine the first marker color difference and the second marker color difference corresponding to the target marker detection image, thereby eliminating background interference and greatly improving the accuracy and reliability of the data.

[0027] For example, determining a first marker detection region and a second marker detection region based on a target marker detection image includes: segmenting the first marker hole position in the target marker detection image to determine the first marker detection region, wherein the first marker detection region includes: a first blank region and a first detection region; segmenting the second marker hole position in the target marker detection image to determine the second marker detection region, wherein the second marker detection region includes: a second blank region and a second detection region.

[0028] The first blank area can refer to the region in the target biomarker detection image where wells containing only the first biomarker signal are annotated. The first detection region can refer to the region in the target biomarker detection image where wells containing both the first biomarker signal and circulating tumor cells are annotated. The second blank area can refer to the region in the target biomarker detection image where wells containing only the second biomarker signal are annotated. The second detection region can refer to the region in the target biomarker detection image where wells containing both the second biomarker signal and circulating tumor cells are annotated.

[0029] Specifically, wells in the target biomarker detection image containing only the first biomarker signal are annotated (the annotation size can be dynamically adjusted according to analysis needs) to determine the first blank region. Wells in the target biomarker detection image containing both the first biomarker signal and circulating tumor cells are annotated to determine the first detection region. Wells in the target biomarker detection image containing only the second biomarker signal are annotated to determine the second blank region. Wells in the target biomarker detection image containing both the second biomarker signal and circulating tumor cells are annotated to determine the second detection region. Through independent region segmentation, it can be ensured that the final obtained color difference of the first and second biomarkers is a true reflection of the characteristics of their respective well locations, avoiding mutual contamination between signals.

[0030] For example, a target marker detection image can be as follows: Figure 2 As shown, the first and second biomarker signals can be the CTC surface epithelial cell adhesion molecule EpCAM and matrix metalloproteinase MMP9, respectively. Figure 2 The four circular areas at the top center are the four wells, labeled a, b, c, and d from left to right. The function and purpose of each well are as follows: Well a: Uses Epcam protein as a marker to identify tumor cells; this is a blank control well. Well b: Uses MMP9 protein as a marker to identify tumor cells; this is a blank control well. Well c: Also uses Epcam protein as a marker to identify tumor cells; this is a sample well. Well d: Also uses MMP9 protein as a marker to identify tumor cells; this is a sample well. The blank control wells contain only the marker, while the sample wells contain both the marker and tumor cells. Well a in the image can be circled to define the first blank area; well c in the image can be circled to define the first detection area; well b in the target marker detection image can be circled to define the second blank area; and well d in the target marker detection image can be circled to define the second detection area.

[0031] For example, color difference analysis is performed on the first marker detection area and the second marker detection area respectively to determine the first marker color difference and the second marker color difference corresponding to the target marker detection image, including: determining the first color intensity value corresponding to the first blank area and the second color intensity value corresponding to the first detection area, and determining the first marker color difference corresponding to the target marker detection image based on the first color intensity value and the second color intensity value; determining the third color intensity value corresponding to the second blank area and the fourth color intensity value corresponding to the second detection area, and determining the second marker color difference corresponding to the target marker detection image based on the third color intensity value and the fourth color intensity value.

[0032] Wherein, the first color intensity can refer to the average RGB value within the first blank area. The second color intensity can refer to the average RGB value within the first detection area. The third color intensity can refer to the average RGB value within the second blank area. The fourth color intensity can refer to the average RGB value within the second detection area.

[0033] Specifically, such as Figure 2 As shown in the figure, the background color of the four wells can be unified during the experiment, such as by unifying it to green, so that the color of each well is the same but the color depth is different, which facilitates color difference analysis. Within the segmented first blank region (i.e., the area within well a), the average RGB value of all pixels in the region is automatically calculated, which is the first color intensity value. Within the segmented first detection region (i.e., the area within well c), the average RGB value of all pixels in the region is automatically calculated, which is the second color intensity value. The difference between the second color intensity value and the first color intensity value is the first marker color difference corresponding to the target marker detection image. Within the segmented second blank region (i.e., the area within well b), the average RGB value of all pixels in the region is automatically calculated, which is the third color intensity value. Within the segmented second detection region (i.e., the area within well d), the average RGB value of all pixels in the region is automatically calculated, which is the fourth color intensity value. The difference between the fourth color intensity value and the third color intensity value is the second marker color difference corresponding to the target marker detection image. This enables accurate quantification of tumor cell characteristics under different markers, providing a solid and reliable data foundation for subsequent cell concentration detection and risk assessment.

[0034] S130. Input the color difference of the first marker and the color difference of the second marker into the tumor cell concentration detection model to detect cell concentration. Based on the output of the tumor cell concentration detection model, determine the target risk assessment result corresponding to the target marker detection image.

[0035] The tumor cell concentration detection model can refer to a trained machine learning regression model used to predict the concentration of circulating tumor cells based on color difference. The target risk assessment result can refer to the outcome reflecting a patient's tumor risk level and can be used to guide clinical decision-making.

[0036] Specifically, the obtained color difference of the first and second markers can be directly input into a pre-trained tumor cell concentration detection model for cell concentration detection. Based on the tumor cell concentrations corresponding to different markers output by the tumor cell concentration detection model, the patient's tumor risk can be analyzed to determine the target risk assessment result corresponding to the target marker detection image. This avoids the subjectivity of manual interpretation and the limitations of a single threshold rule, ensuring the reliability of the assessment results.

[0037] In this embodiment, by acquiring target biomarker detection images corresponding to circulating tumor cells of the target patient, a data foundation is provided for subsequent analysis. Based on the target biomarker detection images, the color difference of the first biomarker and the color difference of the second biomarker corresponding to the target biomarker detection images can effectively eliminate background interference and provide accurate and reliable input data for subsequent model analysis. The color difference of the first biomarker and the color difference of the second biomarker are input into the tumor cell concentration detection model for cell concentration detection. Based on the output results of the tumor cell concentration detection model, the target risk assessment result corresponding to the target biomarker detection image is determined, which can avoid the subjectivity and limitations of a single judgment standard and greatly improve the assessment efficiency and accuracy. This invention, by performing dual biomarker detection on circulating tumor cells, and performing color difference analysis based on the target biomarker detection images, as well as tumor cell detection and risk assessment based on the color differences, can achieve automated and efficient circulating tumor cell risk assessment, greatly reducing manual costs, ensuring the stability and repeatability of risk assessment results, and facilitating its application in clinical monitoring and large-scale sample analysis.

[0038] Example 2 Figure 3 This is a flowchart of a tumor cell risk assessment method provided in Embodiment 2 of the present invention. Based on the above embodiments, this embodiment optimizes the step "determining the target risk assessment result corresponding to the target biomarker detection image based on the output result of the tumor cell concentration detection model". Explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.

[0039] See Figure 3 Another tumor cell risk assessment method provided in this embodiment specifically includes the following steps: S210. Obtain images of target biomarkers corresponding to circulating tumor cells of the target patient.

[0040] S220. Based on the target marker detection image, determine the first marker color difference and the second marker color difference corresponding to the target marker detection image.

[0041] S230. Input the color difference of the first marker and the color difference of the second marker into the tumor cell concentration detection model to detect cell concentration. Based on the output of the tumor cell concentration detection model, determine the first cell concentration value and the second cell concentration value corresponding to the target marker detection image.

[0042] The first cell concentration value can refer to the estimated concentration of circulating tumor cells (CTCs) in the blood sample, as predicted by the tumor cell concentration detection model, reflecting the number of circulating tumor cells (CTCs) in the blood sample, which is the first biomarker. The second cell concentration value can refer to the estimated concentration of circulating tumor cells (CTCs) in the blood sample, as predicted by the tumor cell concentration detection model, reflecting the number of circulating tumor cells (CTCs) in the second biomarker.

[0043] Specifically, the tumor cell concentration detection model can be derived by training multiple models, including but not limited to Random Forest, Extremely Randomized Trees, Gradient Boosting Decision Tree, Ridge Regression, and Artificial Neural Network Regression (MLPRegressor algorithm), and then visually comparing the predictive capabilities of different models based on the training results. The model with the best CTC concentration prediction ability is then used to predict tumor cell concentration based on color difference. It should be noted that the tumor cell concentration detection model is learned from the relationship between color difference and cell concentration during a large number of tumor cell concentration detection experiments; color difference is directly proportional to tumor cell concentration. By inputting the color difference of the first and second markers into the tumor cell concentration detection model, the model can predict the tumor cell concentration under different markers based on the proportional relationship between color difference and cell concentration, obtaining the first and second cell concentration values ​​corresponding to the target marker detection image. This automatically converts the color difference obtained from image analysis into a cell concentration value, greatly improving the detection efficiency and accuracy of tumor cell concentration.

[0044] S240. Based on the first cell concentration value and the second cell concentration value, determine the target risk assessment result.

[0045] Specifically, based on the first and second cell concentration values, a potential risk analysis is performed on the circulating tumor cells in the target patient to determine the target risk assessment results, providing key data support for the subsequent clinical diagnosis of the patient.

[0046] For example, S240 may include: determining a target risk ratio corresponding to the target marker detection image based on a first cell concentration value and a second cell concentration value; comparing the target risk ratio with a preset risk threshold to determine the target risk assessment result.

[0047] The target hazard ratio can be a quantitative value used to reflect the potential risk level of CTCs in the blood sample of a target patient. The preset risk threshold can be a pre-set threshold used to define the risk level of circulating tumor cells.

[0048] Specifically, the ratio between the second cell concentration value and the first cell concentration value can be directly determined as the target risk ratio corresponding to the target biomarker detection image, i.e., target risk ratio = second cell concentration value / first cell concentration value. If the target risk ratio is greater than a preset risk threshold, the target risk assessment result is determined to be high risk, and the tumor cells are in a metastatic phase. If the target risk ratio is less than or equal to the preset risk threshold, the target risk assessment result is determined to be low risk, and the tumor cells are in a stable phase. It should be noted that after generating the first and second cell concentration values, the first and second cell concentration values ​​can be visualized, facilitating comparative analysis by users (such as medical personnel). Experimental data can also be saved to update the model training data for continuous optimization of the tumor cell concentration detection model. Furthermore, the preset risk threshold can be automatically updated based on the updated model training data.

[0049] The technical solution of this embodiment determines the first and second cell concentration values ​​corresponding to the target biomarker detection image based on the output results of a tumor cell concentration detection model, avoiding the subjectivity of manual analysis and improving detection accuracy. Based on the first and second cell concentration values, the target risk assessment result is determined, ensuring the accuracy of the assessment results. This invention automatically converts the color difference obtained from image analysis into cell concentration under dual biomarkers through a model, and performs risk assessment based on the cell concentration of the dual biomarkers. This enables a comprehensive representation of the quantity information and biological functional status of circulating tumor cells, avoiding the limitations of a single biomarker, improving the efficiency and accuracy of tumor cell quantitative analysis, and providing reliable data support for subsequent clinical diagnosis.

[0050] Example 3 Figure 4 This is a schematic diagram of a tumor cell risk assessment device provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: an image acquisition module 310, a color difference determination module 320, and a risk assessment module 330; The image acquisition module 310 is used to acquire images of target biomarkers corresponding to circulating tumor cells of the target patient. The color difference determination module 320 is used to determine the first color difference and the second color difference of the target marker detection image based on the target marker detection image; The risk assessment module 330 is used to input the color difference of the first marker and the color difference of the second marker into the tumor cell concentration detection model for cell concentration detection, and to determine the target risk assessment result corresponding to the target marker detection image based on the output result of the tumor cell concentration detection model.

[0051] In this embodiment, by acquiring target biomarker detection images corresponding to circulating tumor cells of the target patient, a data foundation is provided for subsequent analysis. Based on the target biomarker detection images, the color difference of the first biomarker and the color difference of the second biomarker corresponding to the target biomarker detection images are determined, which can effectively eliminate background interference and provide accurate and reliable input data for subsequent model analysis. The color difference of the first biomarker and the color difference of the second biomarker are input into the tumor cell concentration detection model for cell concentration detection. Based on the output results of the tumor cell concentration detection model, the target risk assessment result corresponding to the target biomarker detection image is determined, which can avoid the subjectivity and limitations of a single judgment standard and greatly improve the assessment efficiency and accuracy. This invention, by performing dual biomarker detection on circulating tumor cells, and performing color difference analysis based on the target biomarker detection images, as well as tumor cell detection and risk assessment based on the color differences, can achieve automatic and efficient circulating tumor cell risk assessment, greatly reducing labor costs, ensuring the stability and repeatability of risk assessment results, and facilitating its application in clinical monitoring and large-scale sample analysis.

[0052] Optionally, the image acquisition module 310 is specifically used to: in response to the dual-marker detection operation of circulating tumor cells of the target patient, acquire the target marker detection image corresponding to the target patient, wherein the dual markers include: epithelial cell adhesion molecules and matrix metalloproteinases.

[0053] Optionally, the color difference determination module 320 may include: The detection area determination unit is used to determine a first marker detection area and a second marker detection area based on the target marker detection image; The color difference determination unit is used to perform color difference analysis on the first marker detection area and the second marker detection area respectively, and determine the first marker color difference and the second marker color difference corresponding to the target marker detection image.

[0054] Optionally, the detection area determination unit is specifically used to: segment the first marker hole position in the target marker detection image to determine the first marker detection area, wherein the first marker detection area includes: a first blank area and a first detection area; segment the second marker hole position in the target marker detection image to determine the second marker detection area, wherein the second marker detection area includes: a second blank area and a second detection area.

[0055] Optionally, the color difference determination unit is specifically used to: determine a first color intensity value corresponding to the first blank area and a second color intensity value corresponding to the first detection area, and determine a first marker color difference corresponding to the target marker detection image based on the first color intensity value and the second color intensity value; determine a third color intensity value corresponding to the second blank area and a fourth color intensity value corresponding to the second detection area, and determine a second marker color difference corresponding to the target marker detection image based on the third color intensity value and the fourth color intensity value.

[0056] Optionally, the risk assessment module 330 may include: The cell concentration determination unit is used to determine the first cell concentration value and the second cell concentration value corresponding to the target marker detection image based on the output of the tumor cell concentration detection model. A risk assessment unit is used to determine the target risk assessment result based on the first cell concentration value and the second cell concentration value.

[0057] Optionally, the risk assessment unit is specifically used to: determine the target risk ratio corresponding to the target biomarker detection image based on the first cell concentration value and the second cell concentration value; and compare the target risk ratio with a preset risk threshold to determine the target risk assessment result.

[0058] The above-described device can execute the tumor cell risk assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the tumor cell risk assessment method.

[0059] Example 4 Figure 5This is a schematic diagram of an electronic device implementing the tumor cell risk assessment method of this invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0060] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0061] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0062] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as tumor cell risk assessment methods.

[0063] In some embodiments, the tumor cell risk assessment method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the tumor cell risk assessment method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the tumor cell risk assessment method by any other suitable means (e.g., by means of firmware).

[0064] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0065] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0066] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0067] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0068] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0069] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0070] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0071] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0072] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for assessing tumor cell risk, characterized in that, include: Acquire images of target biomarkers corresponding to circulating tumor cells in the target patient; Based on the target marker detection image, determine the first marker color difference and the second marker color difference corresponding to the target marker detection image; The color difference of the first biomarker and the color difference of the second biomarker are input into the tumor cell concentration detection model for cell concentration detection. Based on the output of the tumor cell concentration detection model, the target risk assessment result corresponding to the target biomarker detection image is determined.

2. The method according to claim 1, characterized in that, The acquisition of the target marker detection image includes: In response to the dual biomarker detection operation on circulating tumor cells of a target patient, an image of the target biomarker corresponding to the target patient is acquired, wherein the dual biomarkers include: epithelial cell adhesion molecules and matrix metalloproteinases.

3. The method according to claim 1, characterized in that, The step of determining the first marker color difference and the second marker color difference corresponding to the target marker detection image based on the target marker detection image includes: Based on the target marker detection image, a first marker detection region and a second marker detection region are determined; Color difference analysis is performed on the first marker detection area and the second marker detection area respectively to determine the first marker color difference and the second marker color difference corresponding to the target marker detection image.

4. The method according to claim 3, characterized in that, The step of determining the first marker detection region and the second marker detection region based on the target marker detection image includes: The first marker hole position in the target marker detection image is segmented to determine the first marker detection area, wherein the first marker detection area includes: a first blank area and a first detection area; The second marker hole position in the target marker detection image is segmented to determine the second marker detection area, wherein the second marker detection area includes: a second blank area and a second detection area.

5. The method according to claim 4, characterized in that, The step of performing color difference analysis on the first marker detection region and the second marker detection region respectively to determine the first marker color difference and the second marker color difference corresponding to the target marker detection image includes: Determine the first color intensity value corresponding to the first blank area and the second color intensity value corresponding to the first detection area, and based on the first color intensity value and the second color intensity value, determine the first marker color difference corresponding to the target marker detection image; The third color intensity value corresponding to the second blank area and the fourth color intensity value corresponding to the second detection area are determined, and based on the third color intensity value and the fourth color intensity value, the second marker color difference corresponding to the target marker detection image is determined.

6. The method according to claim 1, characterized in that, The determination of the target risk assessment result corresponding to the target biomarker detection image based on the output of the tumor cell concentration detection model includes: Based on the output of the tumor cell concentration detection model, the first cell concentration value and the second cell concentration value corresponding to the target marker detection image are determined. Based on the first cell concentration value and the second cell concentration value, the target risk assessment result is determined.

7. The method according to claim 6, characterized in that, The determination of the target risk assessment result based on the first cell concentration value and the second cell concentration value includes: Based on the first cell concentration value and the second cell concentration value, the target risk ratio corresponding to the target marker detection image is determined; The target risk ratio is compared with a preset risk threshold to determine the target risk assessment result.

8. A tumor cell risk assessment device, characterized in that, include: The image acquisition module is used to acquire images of target biomarkers corresponding to circulating tumor cells in the target patient. A color difference determination module is used to determine the first color difference and the second color difference of the target marker detection image based on the target marker detection image. The risk assessment module is used to input the color difference of the first marker and the color difference of the second marker into the tumor cell concentration detection model for cell concentration detection, and to determine the target risk assessment result corresponding to the target marker detection image based on the output result of the tumor cell concentration detection model.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the tumor cell risk assessment method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the tumor cell risk assessment method according to any one of claims 1-7.

Images