Early diagnosis system for cervical cancer lesion caused by HPVE6 / E7 and application

Abstract

The invention discloses an HPVE6 / E7-caused cervical cancer lesion early diagnosis system and application, and relates to the technical field of medical treatment, the system comprises an HPVE6 / E7 protein detection module used for quantitatively detecting the HPVE6 / E7 protein level in cervical exfoliated cells of a target object to obtain a detection result of the HPVE6 / E7 protein level; the telomerase activity detection module is used for detecting the activity of single-cell telomerase in the cervical exfoliated cells to obtain a detection result of the activity of the single-cell telomerase; the diagnosis threshold determination module is used for determining a diagnosis threshold of the HPVE6 / E7 protein level and a diagnosis threshold of the single cell telomerase activity based on the first correlation analysis result, the second correlation analysis result and the third correlation analysis result; the combined diagnosis module is used for carrying out early diagnosis on the precancerous lesion of the cervical cancer on the target object; and the risk assessment module is used for assessing the progress risk of the cervical lesion of the target object and the possibility of relapse after treatment according to the early diagnosis result of the cervical precancerous lesion.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to an early diagnosis system and application of cervical cancer lesions caused by HPVE6 / E7. Background Art

[0002] Globally, cervical cancer ranks fourth among female malignancies. The cause of cervical cancer has been clearly identified as persistent infection with high-risk HPV. With the continuous advancement of HPV testing methods, the wider use of preventive HPV vaccines, and the maturation of corresponding screening strategies, cervical cancer prevention has become highly effective. Screening for precancerous lesions allows for timely intervention to prevent progression to cancer, and screening for early-stage cancers allows for timely treatment and cure.

[0003] Cervical cancer is a malignant tumor suitable for screening and is highly effective. A three-step screening strategy is currently employed: initial screening with 1) HPV testing and cervical cytology; 2) HPV typing and cytology triage; and 3) cytology and HPV testing triage. Abnormal results from the initial screening result are referred for colposcopy, where a biopsy of the lesion is obtained to assist in diagnosis. Histopathology is the gold standard for diagnosis.

[0004] However, the current challenge is that implementing vaccines and screening strategies requires enormous human, material, and financial resources, making them prohibitively expensive and burdensome for resource-poor regions. For cervical cancer, a disease with a clear etiology, the enormous costs of prevention and control reflect the incomplete understanding of existing technologies, necessitating the development of simpler methods tailored to the needs of resource-poor regions. Summary of the Invention

[0005] The embodiments of the present application provide a system and application for early diagnosis of cervical cancer lesions caused by HPV E6 / E7 to solve the above technical problems.

[0006] The present application provides an early diagnosis system for cervical cancer lesions caused by HPVE6 / E7, comprising: an HPVE6 / E7 protein detection module for quantitatively detecting the HPVE6 / E7 protein level in the cervical exfoliated cells of the target object to obtain the detection result of the HPVE6 / E7 protein level; a telomerase activity detection module for detecting the single-cell telomerase activity in the cervical exfoliated cells to obtain the detection result of the single-cell telomerase activity; a data analysis module for analyzing the correlation between the HPVE6 / E7 protein level and the degree of cervical lesions to obtain a first correlation analysis result; analyzing the correlation between the single-cell telomerase activity and the degree of cervical lesions to obtain a second correlation analysis result; and analyzing the correlation between the HPVE6 / E7 protein level and the single-cell telomerase activity. a diagnostic threshold determination module for determining the diagnostic threshold of the HPVE6 / E7 protein level and the diagnostic threshold of the single-cell telomerase activity based on the first correlation analysis result, the second correlation analysis result and the third correlation analysis result; a combined diagnosis module for performing an early diagnosis of cervical precancerous lesions on the target object according to the detection results of the HPVE6 / E7 protein level and the detection results of the single-cell telomerase activity, combined with the diagnostic threshold of the HPVE6 / E7 protein level and the diagnostic threshold of the single-cell telomerase activity; and a risk assessment module for assessing the progression risk of cervical lesions and the possibility of recurrence after treatment of the target object according to the results of the early diagnosis of cervical precancerous lesions.

[0007] The present application provides an application of an early diagnosis system for cervical cancer lesions caused by HPVE6 / E7, including: inputting a cervical exfoliated cell sample from a patient into the early diagnosis system for cervical cancer lesions caused by HPVE6 / E7; the early diagnosis system for cervical cancer lesions caused by HPVE6 / E7 outputs the results of early diagnosis of cervical precancerous lesions of the target object and the risk of progression of the patient's cervical lesions and the possibility of recurrence after treatment.

[0008] Based on the embodiments provided herein, the combined use of an HPV E6 / E7 protein detection module and a telomerase activity detection module enables early diagnosis of cervical precancerous lesions at the molecular level. This is more direct than traditional cytological examinations and HPV DNA testing, and helps improve diagnostic accuracy. The data analysis module can analyze the correlation between HPV E6 / E7 protein levels and the severity of cervical lesions, as well as the correlation between single-cell telomerase activity and the severity of cervical lesions. This multi-dimensional correlation analysis helps to more comprehensively understand the pathological process. The combined diagnosis module combines the test results and diagnostic thresholds to perform early diagnosis of cervical precancerous lesions in target subjects, thereby providing the possibility of early intervention, which is crucial for preventing lesions from developing into cervical cancer. The risk assessment module can assess the risk of progression of cervical lesions and the possibility of recurrence after treatment based on the results of early diagnosis, which is of great significance for formulating personalized treatment plans and preventive measures. The system provides a simple method for early diagnosis of cervical precancerous lesions, adapted to the needs of resource-poor areas, and helps alleviate the huge human, material, and financial pressures required to implement vaccine and screening strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0010] Figure 1 This is a structural diagram of an optional system for early diagnosis of cervical cancer lesions caused by HPV E6 / E7 according to an embodiment of the present application;

[0011] Figure 2 This is a flowchart of an optional method for determining a third correlation analysis result according to an embodiment of the present application.

[0012] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0014] Alternatively, as Figure 1 As shown, the present application provides an early diagnosis system for cervical cancer lesions caused by HPV E6 / E7, comprising:

[0015] HPVE6 / E7 protein detection module 101 is used to quantitatively detect the HPVE6 / E7 protein level in the cervical exfoliated cells of the target subject and obtain the detection result of the HPVE6 / E7 protein level;

[0016] The telomerase activity detection module 102 is used to detect the single-cell telomerase activity in the cervical exfoliated cells and obtain the detection result of the single-cell telomerase activity;

[0017] Data analysis module 103 is used to analyze the correlation between HPV E6 / E7 protein levels and the severity of cervical lesions to obtain a first correlation analysis result; analyze the correlation between single-cell telomerase activity and the severity of cervical lesions to obtain a second correlation analysis result; and analyze the correlation between HPV E6 / E7 protein levels and single-cell telomerase activity to obtain a third correlation analysis result;

[0018] a diagnostic threshold determination module 104 for determining a diagnostic threshold for HPV E6 / E7 protein levels and a diagnostic threshold for single-cell telomerase activity based on the first correlation analysis result, the second correlation analysis result, and the third correlation analysis result;

[0019] a combined diagnosis module 105 for performing early diagnosis of cervical precancerous lesions on a target subject based on the detection results of the HPVE6 / E7 protein levels and the detection results of the single-cell telomerase activity, combined with the diagnostic thresholds of the HPVE6 / E7 protein levels and the diagnostic thresholds of the single-cell telomerase activity;

[0020] The risk assessment module 106 is used to assess the risk of progression of cervical lesions of the target subject and the possibility of recurrence after treatment based on the results of early diagnosis of cervical precancerous lesions.

[0021] Based on the embodiments provided herein, the combined use of an HPV E6 / E7 protein detection module and a telomerase activity detection module enables early diagnosis of cervical precancerous lesions at the molecular level. This is more direct and sensitive than traditional cytological examinations and HPV DNA testing, helping to improve diagnostic accuracy. The data analysis module can analyze the correlation between HPV E6 / E7 protein levels and the severity of cervical lesions, as well as the correlation between single-cell telomerase activity and the severity of cervical lesions. This multi-dimensional correlation analysis helps to more comprehensively understand the pathological process. The combined diagnosis module combines the test results and diagnostic thresholds to perform early diagnosis of cervical precancerous lesions in target subjects, thereby providing the possibility of early intervention, which is crucial for preventing lesions from developing into cervical cancer. The risk assessment module can assess the risk of progression of cervical lesions and the possibility of recurrence after treatment based on the results of early diagnosis, which is of great significance for formulating personalized treatment plans and preventive measures. The system provides a simple method for early diagnosis of cervical precancerous lesions, adapted to the needs of resource-poor areas, and helps to alleviate the huge human, material, and financial pressures required to implement vaccine and screening strategies.

[0022] Furthermore, the correlation between the HPVE6 / E7 protein level and the degree of cervical lesions was analyzed, and the first correlation analysis result was obtained, which was configured as follows:

[0023] Preprocessing the data of HPVE6 / E7 protein levels, including normalization and removal of outliers;

[0024] The pre-processed data of HPVE6 / E7 protein levels were expanded using the Hermite series to convert the pre-processed data of HPVE6 / E7 protein levels into a series of high-order moments and cumulants;

[0025] Select the distribution characteristics from the Hermite series expansion terms;

[0026] The distribution characteristics extracted by the Hermite series were rank transformed together with the pre-processed data of HPVE6 / E7 protein levels;

[0027] The distribution characteristics after rank transformation are integrated with the data of cervical lesion severity after rank transformation to form an enhanced data set;

[0028] For each pair of observations in the enhanced data set, the rank difference of the pair of observations in the enhanced data set is calculated; wherein each pair of observations includes the HPVE6 / E7 protein level observation and the cervical lesion degree observation;

[0029] Based on the rank difference of each pair of observations, the first Spearman rank correlation coefficient is determined;

[0030] According to the first Spearman rank correlation coefficient, the correlation between HPVE6 / E7 protein level and the degree of cervical lesions was analyzed to obtain the first correlation analysis results.

[0031] The Hermite series can capture higher-order statistical properties of the data, which may complement the first- and second-order statistical properties considered in Spearman correlation analysis. Feature selection: Key features are selected from the Hermite series expansion. These features can best reflect the distribution characteristics of the data and provide richer information for subsequent correlation analysis.

[0032] First-order statistical properties manifested in Spearman correlation analysis: Rank assignment: In Spearman correlation analysis, first-order statistical properties primarily reflect the central tendency of the data, that is, the average level of the data. First, we performed rank assignment on the data on HPVE6 / E7 protein levels and the severity of cervical lesions. This step is actually a first-order transformation of the data, converting the raw data values ​​to their relative positions in the dataset. This ignores the actual magnitude of the values ​​and only retains the order of the data.

[0033] Second-order statistical characteristics are reflected in Spearman correlation analysis: rank difference and sum of squares of differences:

[0034] Second-order statistics focus on the variability or dispersion of the data. In Spearman analysis, we calculate the difference between the corresponding ranks of the two variables. These differences reflect the relative position of each observation in the two variables and are a way to measure variability.

[0035] The distribution characteristics extracted from the Hermite series were rank-transformed together with the ranking data of HPVE6 / E7 protein levels. These transformed features were then integrated with the ranking data of cervical lesion severity to form an enhanced dataset. This approach not only considers the first- and second-order statistical properties of the data, but also incorporates higher-order statistical properties, providing a more comprehensive perspective on the correlation between HPVE6 / E7 protein levels and cervical lesion severity.

[0036] By calculating the Spearman rank correlation coefficient on the augmented dataset, we were able to assess the correlation between HPVE6 / E7 protein levels and the severity of cervical lesions, while taking into account the central tendency, variability, and shape of the distribution. This approach not only reveals the monotonic relationship between the two variables but also captures nonlinear relationships and higher-order statistical properties in the data, resulting in a more comprehensive and in-depth first-order correlation analysis.

[0037] Furthermore, the first Spearman rank correlation coefficient is determined based on the rank difference of each pair of observations based on the following formula:

[0038] in, is the first Spearman rank correlation coefficient; is the number of observation pairs in the augmented dataset; It is Rank difference of observations; and They are the differential entropy of HPVE6 / E7 protein level and the differential entropy of cervical lesion degree, respectively.

[0039] Furthermore, if Figure 2 As shown, the correlation between HPVE6 / E7 protein levels and single-cell telomerase activity was analyzed, and the third correlation analysis result was obtained, which was configured as follows:

[0040] S201, performing rank transformation on the data of HPVE6 / E7 protein levels and the data of single-cell telomerase activity, respectively, to generate a first rank sequence and a second rank sequence;

[0041] S202, calculating the mutual information between the first ranked sequence and the second ranked sequence;

[0042] S203, calculating a second Spearman rank correlation coefficient based on the mutual information between the first ranked sequence and the second ranked sequence;

[0043] S204. Analyze the correlation between the HPVE6 / E7 protein level and the single-cell telomerase activity based on the second Spearman rank correlation coefficient to obtain a third correlation analysis result.

[0044] Furthermore, the diagnostic threshold determination module determines the diagnostic threshold of the HPV E6 / E7 protein level and the diagnostic threshold of the single-cell telomerase activity based on the first correlation analysis result, the second correlation analysis result, and the third correlation analysis result, and is configured as follows:

[0045] Construct a deep belief network consisting of multiple restricted Boltzmann machine layers; each layer of the deep belief network includes multiple neuron nodes;

[0046] The first correlation analysis result, the second correlation analysis result, and the third correlation analysis result are used as input features of the deep belief network;

[0047] Constructing a hidden Markov model; wherein each state of the hidden Markov model corresponds to a different degree of cervical lesions;

[0048] Initialize the transition probability matrix and emission probability matrix of the hidden Markov model;

[0049] The output of the deep belief network is used as the observation sequence of the hidden Markov model, and the state sequence of the hidden Markov model is used as the hidden state of the deep belief network for joint fine-tuning:

[0050] Based on the jointly fine-tuned deep belief network and hidden Markov model, the results of the first, second and third correlation analyses, the diagnostic thresholds of HPVE6 / E7 protein levels and single-cell telomerase activity were determined.

[0051] Among them, the deep belief network, namely DBN, is the full name of DeepBeliefNetwork; the hidden Markov model, namely HMM, is the full name of HiddenMarkovModel.

[0052] Furthermore, the output of the deep belief network is used as the observation sequence of the hidden Markov model, and the state sequence of the hidden Markov model is used as the hidden state of the deep belief network for joint fine-tuning, which is configured as follows:

[0053] Construct a loss function; wherein the loss function includes the reconstruction error of the deep belief network and the log-likelihood of the hidden Markov model; the reconstruction error of the deep belief network is calculated based on the mean square error; the log-likelihood of the hidden Markov model is calculated based on the forward algorithm;

[0054] The first, second, and third correlation analysis results are forward propagated through a deep belief network to obtain a representation of the hidden layer; the output of the deep belief network is used as the observation sequence of the hidden Markov model, and the probability of each state is calculated through the forward algorithm of the hidden Markov model;

[0055] According to the loss of the deep belief network, the backpropagation algorithm is used to calculate the gradient and update the weights and biases of the deep belief network; according to the loss of the hidden Markov model, the expectation maximization algorithm is used to update the transition probability matrix and emission probability matrix of the hidden Markov model until the loss function converges.

[0056] The following is an example of a joint fine-tuning process:

[0057] DBN forward propagation: The first correlation analysis results, the second correlation analysis results, and the third correlation analysis results are forward propagated through DBN to obtain the representation of the hidden layer. ;in, It is The activation value of the layer, and They are The weights and biases of the layers, is the activation function.

[0058] HMM forward algorithm: Use the output of DBN as the observation sequence of the hidden Markov model and calculate the probability of each state through the forward algorithm of HMM.

[0059] Loss function construction: Construct loss function , including the reconstruction error of DBN and the log-likelihood of HMM. ;in, is the reconstruction error of DBN; is the log-likelihood of the HMM, is the weight used to balance the two loss terms.

[0060] Parameter update: Based on the loss function, the weights and biases of DBN are updated using the backpropagation algorithm.

[0061] Expectation-Maximization (EM) algorithm: Use the expectation-maximization algorithm to update the transition probability matrix and emission probability matrix of the HMM.

[0062] Through the above process, we can combine the correlation analysis results of HPVE6 / E7 protein levels and single-cell telomerase activity, and use DBN and HMM for joint fine-tuning to determine the threshold for early diagnosis of cervical cancer lesions.

[0063] Furthermore, the transition probability matrix represents the transition probability between different degrees of cervical lesions; the emission probability matrix represents the probability of observing the detection results of a certain diagnostic threshold of HPVE6 / E7 protein level and the detection results of single-cell telomerase activity at a certain degree of cervical lesion.

[0064] Furthermore, the HPVE6 / E7 protein detection module uses magnetic particle chemiluminescence to perform quantitative detection of HPVE6 / E7 protein.

[0065] Furthermore, the telomerase activity detection module uses real-time fluorescence quantitative PCR to detect single-cell telomerase activity.

[0066] Alternatively, as Figure 2 As shown, the present application provides an application of an early diagnosis system for cervical cancer lesions caused by HPV E6 / E7, comprising:

[0067] Entering cervical exfoliated cell samples from patients into the HPVE6 / E7 system leads to an early diagnosis system for cervical cancer lesions;

[0068] HPVE6 / E7 causes the cervical cancer lesion early diagnosis system to output the results of early diagnosis of cervical precancerous lesions for the target subject, as well as the patient's risk of progression of cervical lesions and the possibility of recurrence after treatment.

[0069] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An early diagnosis system for cervical cancer caused by HPV E6 / E7, characterized in that: include: HPVE6 / E7 protein detection module, used for quantitatively detecting the HPVE6 / E7 protein level in the cervical exfoliated cells of the target subject to obtain the detection result of the HPVE6 / E7 protein level; A telomerase activity detection module, used to detect the single-cell telomerase activity in the cervical exfoliated cells and obtain the detection result of the single-cell telomerase activity; A data analysis module, configured to analyze the correlation between the HPVE6 / E7 protein level and the degree of cervical lesions to obtain a first correlation analysis result; Analyzing the correlation between the single-cell telomerase activity and the degree of cervical lesions to obtain a second correlation analysis result; and analyzing the correlation between the HPVE6 / E7 protein level and the single-cell telomerase activity to obtain a third correlation analysis result; a diagnostic threshold determination module, configured to determine the diagnostic threshold of the HPV E6 / E7 protein level and the diagnostic threshold of the single-cell telomerase activity based on the first correlation analysis result, the second correlation analysis result, and the third correlation analysis result; a combined diagnosis module for performing early diagnosis of cervical precancerous lesions on the target subject based on the detection results of the HPVE6 / E7 protein levels and the detection results of the single-cell telomerase activity, in combination with the diagnostic thresholds of the HPVE6 / E7 protein levels and the diagnostic thresholds of the single-cell telomerase activity; The risk assessment module is used to assess the risk of progression of cervical lesions of the target subject and the possibility of recurrence after treatment based on the results of early diagnosis of cervical precancerous lesions.

2. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 1, characterized in that: The analysis of the correlation between the HPVE6 / E7 protein level and the degree of cervical lesions to obtain a first correlation analysis result is configured as follows: Preprocessing the data of HPVE6 / E7 protein levels; wherein the preprocessing includes normalization and removal of outliers; The pre-processed data of HPVE6 / E7 protein levels were expanded using the Hermite series to convert the pre-processed data of HPVE6 / E7 protein levels into a series of high-order moments and cumulants; Select the distribution characteristics from the Hermite series expansion terms; The distribution characteristics extracted by the Hermite series were rank transformed together with the pre-processed data of HPVE6 / E7 protein levels; The distribution characteristics after rank transformation are integrated with the data of cervical lesion severity after rank transformation to form an enhanced data set; For each pair of observations in the enhanced data set, calculating the rank difference of the pair of observations in the enhanced data set; wherein each pair of observations includes an HPVE6 / E7 protein level observation and a cervical lesion severity observation; Based on the rank difference of each pair of observations, the first Spearman rank correlation coefficient is determined; According to the first Spearman rank correlation coefficient, the correlation between the HPVE6 / E7 protein level and the degree of cervical lesions is analyzed to obtain the first correlation analysis result.

3. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 2, characterized in that: The first Spearman rank correlation coefficient is determined based on the rank difference of each pair of observations based on the following formula: ; in, is the first Spearman rank correlation coefficient; is the number of observation pairs in the augmented dataset; It is Rank difference of observations; and They are the differential entropy of HPVE6 / E7 protein level and the differential entropy of cervical lesion degree, respectively.

4. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 2, characterized in that: The correlation between the HPV E6 / E7 protein level and the single cell telomerase activity is analyzed to obtain a third correlation analysis result, which is configured as follows: The data of HPVE6 / E7 protein levels and single-cell telomerase activity were rank transformed to generate the first rank sequence and the second rank sequence respectively; Calculating mutual information between the first rank sequence and the second rank sequence; Calculating a second Spearman rank correlation coefficient based on the mutual information between the first ranked sequence and the second ranked sequence; The correlation between the HPVE6 / E7 protein level and the single-cell telomerase activity was analyzed based on the second Spearman rank correlation coefficient to obtain the third correlation analysis result.

5. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 4, characterized in that: The diagnostic threshold determination module determines the diagnostic threshold of the HPV E6 / E7 protein level and the diagnostic threshold of the single-cell telomerase activity based on the first correlation analysis result, the second correlation analysis result, and the third correlation analysis result, and is configured as follows: Constructing a deep belief network consisting of multiple restricted Boltzmann machine layers; wherein each layer of the deep belief network includes multiple neuron nodes; Using the first correlation analysis result, the second correlation analysis result, and the third correlation analysis result as input features of the deep belief network; Constructing a hidden Markov model; wherein each state of the hidden Markov model corresponds to a different degree of cervical lesions; Initializing the transition probability matrix and the emission probability matrix of the hidden Markov model; The output of the deep belief network is used as the observation sequence of the hidden Markov model, and the state sequence of the hidden Markov model is used as the hidden state of the deep belief network for joint fine-tuning: Based on the jointly fine-tuned deep belief network and hidden Markov model, the first correlation analysis result, the second correlation analysis result and the third correlation analysis result, the diagnostic threshold of the HPVE6 / E7 protein level and the diagnostic threshold of the single-cell telomerase activity are determined.

6. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 5, characterized in that: The output of the deep belief network is used as the observation sequence of the hidden Markov model, and the state sequence of the hidden Markov model is used as the hidden state of the deep belief network for joint fine-tuning, which is configured as follows: Constructing a loss function; wherein the loss function includes a reconstruction error of the deep belief network and a log-likelihood of the hidden Markov model; the reconstruction error of the deep belief network is calculated based on a mean square error; and the log-likelihood of the hidden Markov model is calculated based on a forward algorithm; Performing forward propagation of the first correlation analysis result, the second correlation analysis result, and the third correlation analysis result through the deep belief network to obtain a representation of the hidden layer; using the output of the deep belief network as an observation sequence of the hidden Markov model, and calculating the probability of each state through the forward algorithm of the hidden Markov model; According to the loss of the deep belief network, the gradient is calculated using the backpropagation algorithm, and the weights and biases of the deep belief network are updated; according to the loss of the hidden Markov model, the transition probability matrix and the emission probability matrix of the hidden Markov model are updated using the expectation maximization algorithm until the loss function converges.

7. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 5, characterized in that: The transition probability matrix represents the transition probability between different degrees of cervical lesions; the emission probability matrix represents the probability of observing the detection result of a diagnostic threshold of a certain HPVE6 / E7 protein level and the detection result of the single-cell telomerase activity at a certain degree of cervical lesion.

8. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 1, characterized in that: The HPVE6 / E7 protein detection module uses magnetic particle chemiluminescence to perform quantitative detection of HPVE6 / E7 protein.

9. The system for early diagnosis of cervical cancer caused by HPV E6 / E7 according to claim 1, characterized in that: The telomerase activity detection module uses real-time fluorescence quantitative PCR to detect single-cell telomerase activity.

10. An application of an early diagnosis system for cervical cancer caused by HPV E6 / E7, based on the early diagnosis system for cervical cancer caused by HPV E6 / E7 according to claim 1, characterized in that: include: Entering cervical exfoliated cell samples from patients into the HPVE6 / E7 system leads to an early diagnosis system for cervical cancer lesions; The HPVE6 / E7 causes the cervical cancer lesion early diagnosis system to output the results of the early diagnosis of cervical precancerous lesions for the target object, as well as the patient's risk of progression of cervical lesions and the possibility of recurrence after treatment.

Images