A method and system for predicting prostate cancer in prostate biopsy

Abstract

The present disclosure provides a method and system for predicting prostate cancer in prostate biopsy patients, belonging to the technical field of prostate cancer prediction, including obtaining clinical data of prostate biopsy patients and determining the prostate health index of the patients; obtaining multi-parametric magnetic resonance imaging data of prostate biopsy patients; and obtaining a prostate cancer prediction probability based on the clinical data, prostate health index and multi-parametric magnetic resonance imaging data of prostate biopsy patients. The present disclosure can effectively improve the prediction efficacy of prostate cancer before biopsy, avoid more unnecessary biopsies without reducing the cancer detection rate.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of prostate cancer prediction, and particularly relates to a method and system for predicting prostate cancer in prostate biopsy patients. Background Art

[0002] Prostate cancer is the most common male malignant tumor in Western countries. The incidence of prostate cancer in China is also increasing year by year and currently ranks sixth among male malignant tumors, being the most common malignant tumor of the urinary system. Currently, domestic and foreign guidelines recommend serum prostate-specific antigen (PSA) as the first choice for prostate cancer screening. If a patient's serum PSA level is abnormally elevated, prostate biopsy is recommended for this part of patients to further confirm whether they have prostate cancer. However, PSA is not a specific serum marker for prostate cancer. Benign lesions of the prostate, such as benign prostatic hyperplasia, prostatitis, etc., can all cause abnormal elevation of serum PSA levels. Currently, domestic and foreign retrospective studies have shown that the positive rate of prostate biopsy is only about 40%. Moreover, prostate biopsy is an invasive examination, bringing unnecessary risks of complications to patients with negative biopsy results, such as bleeding, infection, pain, etc.

[0003] In existing prostate cancer prediction systems, prostate health index (PHI), prostate volume (PV), and age (Age) are usually used to predict prostate cancer (PCa). However, using only the above three indicators will limit the prediction efficiency for PCa. Since the popularization of multi-parametric magnetic resonance imaging of the prostate has not been promoted before, the role of multi-parametric magnetic resonance imaging of the prostate in PCa prediction has not been mentioned in previous technologies. Relying solely on the prostate health index, prostate volume, and age can improve the prediction efficiency for PCa, but the sensitivity and specificity need to be improved. Summary of the Invention

[0004] In view of the deficiencies or drawbacks in the prior art, the present disclosure provides a method and system for predicting prostate cancer in prostate biopsy patients, which can effectively improve the prediction efficiency of prostate cancer before biopsy and avoid more unnecessary biopsies without reducing the cancer detection rate.

[0005] To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:

[0006] In a first aspect, the present invention discloses a method for predicting prostate cancer in prostate biopsy, including:

[0007] Obtaining the clinical data of prostate biopsy patients and determining the prostate health index of the patients;

[0008] Obtain multi-parametric magnetic resonance imaging data of prostate biopsy patients;

[0009] Based on the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients, obtain the prostate cancer prediction probability.

[0010] In a second aspect, the present invention discloses a system for predicting prostate cancer in prostate biopsy patients, including:

[0011] A data acquisition module configured to: obtain the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients;

[0012] A data processing module configured to: based on the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients, obtain the prostate cancer prediction probability.

[0013] A result display module configured to: display the prostate cancer prediction probability results through multiple modes.

[0014] The above one or more technical solutions have the following beneficial effects:

[0015] The present disclosure increases the role of the imaging system in PCa prediction. Through the prostate health index, multi-parametric magnetic resonance, and other clinically predictive indicators for PCa, a comprehensive prediction of PCa is carried out in terms of anatomical structure (prostate multi-parametric magnetic resonance) and serology. Compared with the previous technology, more unnecessary biopsies can be avoided without reducing the cancer detection rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The specification drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention.

[0017] Figure 1 Schematic diagram of the interface of the prostate cancer prediction system for predicting prostate cancer and clinically significant prostate cancer;

[0018] Figure 2 Variable nomogram obtained by logistic regression analysis for predicting prostate cancer (A) and clinically significant prostate cancer (B);

[0019] Figure 3 ROC curve graph for predicting prostate cancer (A) and clinically significant prostate cancer (B). DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0021] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0022] In the case of no conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0023] Embodiment 1

[0024] An embodiment of the present disclosure discloses a method for predicting prostate cancer in prostate biopsy, and the method includes the following steps:

[0025] Step 1: Obtain the clinical data of the prostate biopsy patient and determine the prostate health index of the patient.

[0026] The clinical data of the prostate biopsy patient includes: patient age, total prostate specific antigen, free prostate specific antigen, and precursor prostate specific antigen.

[0027] Determining the prostate health index of the patient is specifically:

[0028] Based on the patient's total prostate specific antigen, free prostate specific antigen, and precursor prostate specific antigen, it is calculated using the prostate health index formula.

[0029] Among them, the prostate health index formula is:

[0030]

[0031] In the above formula, PHI is the prostate health index formula; -2[pro]PSA is the precursor prostate specific antigen; fPSA is the free prostate specific antigen; TPSA is the total prostate specific antigen.

[0032] Step 2: Obtain the multi-parametric magnetic resonance imaging data of the prostate biopsy patient.

[0033] The multi-parametric magnetic resonance imaging data of the prostate biopsy patient includes: prostate volume and PI-RADS score.

[0034] The prostate volume is calculated using the prostate volume formula based on the maximum anteroposterior diameter, maximum transverse diameter, and maximum longitudinal diameter of the prostate directly measured on the magnetic resonance image.

[0035] Among them, the prostate volume formula is:

[0036] PV = [Maximum anteroposterior diameter] × [Maximum transverse diameter] × [Maximum longitudinal diameter] × 0.52

[0037] In the above formula, PV is the prostate volume.

[0038] The PI-RADS score is derived from the Prostate Imaging and Reporting System, and the scoring criteria range from 1 to 5 points. PI-RADS 1 - Very low (CSPCa is extremely unlikely to be present); PI-RADS 2 - Low (CSPCa is unlikely to be present); PI-RADS 3 - Moderate (The presence of CSPCa is suspicious); PI-RADS 4 - High (CSPCa may be present); PI-RADS 5 - Very high (CSPCa is very likely to be present), where CSPCa is clinically significant prostate cancer.

[0039] The multi-parametric magnetic resonance examination of the prostate added in this disclosure comprehensively evaluates prostate cancer according to different scanning sequences, such as T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC), dynamic contrast-enhanced imaging (DCE), etc. Among them, T1WI is mainly used to evaluate regional lymph and skeletal structures and can detect biopsy-related bleeding that may mask or mimic cancer. T2WI can provide a highly defined anatomical image of the prostate zonal structure and has excellent soft tissue contrast. DWI quantifies the degree of movement of water molecules in tissues. In non-malignant prostate tissue, water molecules move relatively freely, but in cancerous prostate tissue, due to the increased volume of glandular epithelial tissue and high cellularity, the movement of water molecules is strongly inhibited, so it appears as bright spots surrounded by low-signal tissue on DWI. The ADC map reflects the ability of water molecules to move and is obtained by performing DWI with multiple magnet strengths (b values) and reducing the background signal from non-malignant prostate tissue. It has been proven to improve the sensitivity and accuracy of prostate detection. Therefore, the signal in the area affected by prostate cancer is lower than that of healthy tissue and appears as low signal. The purpose of the DCE sequence is to evaluate the status of tumor angiogenesis based on the differences in the speed and intensity of absorption and flushing of contrast agents in malignant prostate tissue. Early enhancement with increased intensity is a hallmark feature of cancer.

[0040] By adding multi-parametric magnetic resonance (mpMRI) examination, on the one hand, prostate cancer and non-prostate cancer tissues show differences in imaging scanning sequences. The information obtained from each sequence is integrated and scored according to the Prostate Imaging and Reporting System (PI-RADS v2.1), thereby increasing the predictive ability. Secondly, for the suspicious areas shown by mpMRI, the detection probability of cancer can be significantly increased by combining mpMRI-targeted biopsy and systematic puncture.

[0041] Step 3: Based on the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients, obtain the prostate cancer prediction probability.

[0042] Step 3.1: Use Logistic regression analysis to establish a prostate cancer prediction probability equation.

[0043] Randomly divide the patient population into a training set group and a validation set group in a ratio of 3:1, and ensure that the population baselines in the training set group and the validation set group are comparable, that is, there is no difference in the p-value statistically. In the training set population, use univariate Logistic regression analysis to determine the potential risk factors for prostate cancer and clinically significant prostate cancer. Risk factors with a p-value less than 0.05 in the univariate Logistic regression analysis or risk factors that are already recognized as prostate cancer risk factors clinically although there is no statistical difference are included in the multivariate Logistic regression analysis. Determine the risk factors with a p-value less than 0.05 in the multivariate Logistic regression analysis and finally include them in the multivariate Logistic regression analysis to obtain the coefficients and constants before each factor. By multiplying the coefficients of each variable, the prostate cancer prediction probability equation can be obtained:

[0044] P = 1 / {1 + exp[(0.058 × Age + 0.036 × PHI - 0.030 × PV + 1.077 × PI-RADS - 8.508)]}

[0045] For the prediction probability equation of clinically significant prostate cancer:

[0046] P = 1 / {1 + exp[(0.020 × Age + 0.032 × PHI + 0.850 × PI-RADS + 2.515 × Log

[0047] (PSAD) - 5.341)]}

[0048] In the formula, P is the prostate cancer prediction probability; Age is the patient's age; PHI is the prostate health index; PV is the prostate volume; PI-RADS is the PI-RADS score.

[0049] Step 3.2: Substitute the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients into the prostate cancer prediction probability equation to calculate the prostate cancer prediction probability.

[0050] For example, when Age is 69, the PI-RADS score is 3, PHI is 90, and PV = 45, the predicted probability of prostate cancer at this time is 0.645.

[0051] Example 2

[0052] The objective of this embodiment is to provide a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above method are implemented.

[0053] Embodiment III

[0054] The objective of this embodiment is to provide a computer-readable storage medium.

[0055] A computer-readable storage medium has a computer program stored thereon. When the program is executed by a processor, the steps of the above method are performed.

[0056] Embodiment IV

[0057] The objective of this embodiment is to provide a system for predicting prostate cancer in prostate biopsy, including:

[0058] A data acquisition module, configured to: acquire the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients;

[0059] A data processing module, configured to: obtain the prostate cancer prediction probability based on the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients.

[0060] A result display module, configured to: display the prostate cancer prediction probability results through multiple modes.

[0061] The steps involved in the devices in the above Embodiments II, III, and IV correspond to those in Method Embodiment I. For the specific implementation manners, reference can be made to the relevant description part of Embodiment I. The term "computer-readable storage medium" should be understood to include a single medium or multiple media containing one or more instruction sets; it should also be understood to include any medium that can store, encode, or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0062] Those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general computer device. Optionally, they can be implemented by program codes executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0063] Although the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, they are not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made without creative efforts on the basis of the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for predicting prostate cancer in prostate biopsy, characterized in that, it includes the following steps: Obtain the clinical data of prostate biopsy patients and determine the prostate health index of the patients; Obtain the multi-parametric magnetic resonance imaging data of prostate biopsy patients; Based on the clinical data, prostate health index and multi-parametric magnetic resonance imaging data of prostate biopsy patients, obtain the prostate cancer prediction probability; The multi-parametric magnetic resonance imaging data of the prostate biopsy patients includes prostate volume and PI-RADS score; the prostate volume is calculated using the prostate volume formula based on the maximum anteroposterior diameter, maximum transverse diameter and maximum longitudinal diameter of the prostate directly measured on the magnetic resonance image; the PI-RADS score is derived from the Prostate Imaging Reporting and Data System; According to the multi-parametric magnetic resonance imaging data obtained from prostate multi-parametric magnetic resonance examination, according to different scan sequences, the different scan sequences include: T1-weighted imaging T1WI, T2-weighted imaging T2WI, diffusion-weighted imaging DWI, apparent diffusion coefficient ADC, dynamic contrast-enhanced imaging DCE, that is, comprehensively evaluate prostate cancer in terms of both anatomical structure and serology; By adding multi-parametric magnetic resonance examination, prostate cancer and non-prostate cancer tissues show differences in the imaging scan sequence, integrate the information obtained from each sequence, and score according to the Prostate Imaging and Reporting System to increase the prediction ability; for the suspicious areas shown by multi-parametric magnetic resonance, increase the cancer detection probability by combining multi-parametric magnetic resonance targeted biopsy and systematic biopsy; The obtaining of the prostate cancer prediction probability includes: using univariate Logistic regression analysis to determine the potential risk factors for prostate cancer and clinically significant prostate cancer, incorporating the risk factors with p-values less than the set threshold in the univariate Logistic regression analysis or the risk factors that are clinically recognized as prostate cancer risk factors although there is no statistical difference into the multivariate Logistic regression analysis, establishing the risk factors with p-values less than the set threshold in the multivariate Logistic regression analysis and finally incorporating them into the multivariate Logistic regression analysis, the coefficient before each factor and the constant can be obtained, multiply the coefficients of each variable to establish the prostate cancer prediction probability equation, and calculate the prostate cancer prediction probability according to the prostate cancer prediction probability equation; The prostate cancer prediction probability equation is P = 1 / {1 + exp[(0.058×Age + 0.036×PHI - 0.030×PV + 1.077×PI-RADS - 8.508)]} In the formula, P is the prostate cancer prediction probability; Age is the patient's age; PHI is the prostate health index; PV is the prostate volume; PI-RADS is the PI-RADS score.

2. The method for predicting prostate cancer in prostate biopsy according to claim 1, characterized in that, the clinical data of the prostate biopsy patients includes the patient's age, total prostate-specific antigen, free prostate-specific antigen and precursor prostate-specific antigen.

3. A method for predicting prostate cancer in patients undergoing prostate biopsy, as described in claim 1, characterized in that, the prostate health index of the patient, specifically: It is calculated based on the total prostate-specific antigen, free prostate-specific antigen, and precursor prostate-specific antigen of the patient using the prostate health index formula.

4. A system for predicting prostate cancer in patients undergoing prostate biopsy, characterized in that, comprising: A data acquisition module, configured to: acquire the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients; A data processing module, configured to: obtain the prostate cancer prediction probability based on the clinical data, prostate health index, and multi-parametric magnetic resonance imaging data of prostate biopsy patients; A result display module, configured to: display the prostate cancer prediction probability results through multiple modes; The multi-parametric magnetic resonance imaging data of the prostate biopsy patient includes prostate volume and PI-RADS score; the prostate volume is calculated using the prostate volume formula based on the maximum anteroposterior diameter, maximum transverse diameter, and maximum longitudinal diameter of the prostate directly measured on the magnetic resonance image; the PI-RADS score is derived from the prostate imaging and reporting system; According to the multi-parametric magnetic resonance imaging data obtained from prostate multi-parametric magnetic resonance examination, according to different scan sequences, the different scan sequences include: T1-weighted imaging T1WI, T2-weighted imaging T2WI, diffusion-weighted imaging DWI, apparent diffusion coefficient ADC, dynamic contrast-enhanced imaging DCE, that is, a comprehensive evaluation of prostate cancer is carried out in terms of anatomical structure and serology; By adding multi-parametric magnetic resonance examination, prostate cancer and non-prostate cancer tissues show differences in the imaging scan sequence. The information obtained from each sequence is integrated and scored according to the prostate imaging and reporting system to increase the prediction ability; for suspicious areas shown by multi-parametric magnetic resonance, the cancer detection probability is increased by combining multi-parametric magnetic resonance targeted biopsy and systematic biopsy; The obtaining of the prostate cancer prediction probability includes: using univariate Logistic regression analysis to determine the potential risk factors for prostate cancer and clinically significant prostate cancer, incorporating the risk factors with a p-value less than the set threshold in the univariate Logistic regression analysis or the risk factors that are clinically recognized as prostate cancer risk factors although there is no statistical difference into the multivariate Logistic regression analysis, establishing the risk factors with a p-value less than the set threshold in the multivariate Logistic regression analysis and finally incorporating them into the multivariate Logistic regression analysis, the coefficient before each factor and the constant can be obtained, and by multiplying the coefficients of each variable, a prostate cancer prediction probability equation is established, and according to the prostate cancer prediction probability equation, the prostate cancer prediction probability is calculated; The prostate cancer prediction probability equation is P = 1 / {1 + exp[(0.058 × Age + 0.036 × PHI - 0.030 × PV + 1.077 × PI-RADS - 8.508)]} In the formula, P is the predicted probability of prostate cancer; Age is the patient's age; PHI is the prostate health index; PV is the prostate volume; PI-RADS is the PI-RADS score.

5. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, when the processor executes the program, the steps of the method according to any one of claims 1-3 are implemented.

6. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by the processor, the steps of the method according to any one of claims 1-3 are executed.

Images