Qualitative assessment and data scoring system for predicting prostate cancer in PSA gray zone

Abstract

Provided in the present invention is a qualitative assessment and data scoring system for predicting prostate cancer in a PSA gray zone. The system comprises a magnetic resonance device, wherein a port thereof is electrically connected to a data temporary storage module, the data temporary storage module sends data to an imaging detection module by means of a network connection module, the imaging detection module is connected to a background system, and the background system comprises a scoring module and a PC unit; the scoring module acquires the value of the volume ratio of central gland prostate to total prostate on the basis of magnetic resonance imaging, so as to obtain a scoring result; and the scoring module is connected to an association result output module and a storage module, the storage module is used for storing the scoring result, and the association result output module is used for matching the scoring result with a disease risk, and outputting a matching result. The present invention can improve the accuracy of tumor detection, thereby reducing unnecessary prostate puncturing.

Description

Qualitative and statistical scoring systems for predicting PSA gray zone prostate cancer Technical Field

[0001] The present invention relates to the technical field of prostate cancer prediction, and in particular, to a qualitative and data scoring system for predicting PSA gray zone prostate cancer, and especially to a qualitative and data scoring system for predicting PSA gray zone prostate cancer through magnetic resonance imaging. Background Art

[0002] Prostate cancer is the most common male malignancy in Western countries. Its incidence in China has also been increasing annually, currently ranking sixth among male malignancies and the most common urological malignancy. Early diagnosis of prostate cancer is crucial. Prostate-specific antigen (PSA), the most important tumor marker for prostate cancer, is associated with a prostate cancer incidence rate of only 25% when its value is between 4 and 10 ng / mL (the PSA gray zone). Therefore, research on factors associated with prostate biopsy positivity in the gray zone is crucial. Currently, free PSA / total PSA (f% PSA) and PSA density (PSAD) are the most commonly used indicators influencing prostate biopsy positivity, but these indicators still have inconsistent predictive results in clinical practice. It is currently believed that prostate tumors tend to arise in the peripheral zone of the prostate, while benign prostatic hyperplasia (BPH) lesions are more commonly located in the central gland. Therefore, we observed through magnetic resonance imaging that the volume ratio of central gland prostate to total prostate (PVc / PV), a new predictive indicator, was significantly different between prostate cancer and benign prostatic hyperplasia.

[0003] Patent publication number CN104424386A discloses a computer-aided prostate cancer identification system and method based on multi-parameter magnetic resonance imaging. The system comprises an image preprocessing module, a parameter processing module, and a prediction and evaluation module. The system utilizes the features of T2-weighted images, diffusion-weighted images, and dynamic contrast-enhanced images, employing an artificial neural network architecture to identify prostate cancer lesions. Testing showed that the system achieved an area under the ROC (receiver operating characteristic) curve of 0.931 in the peripheral zone of the prostate, with an identification accuracy of 0.887. The area under the ROC curve for the central gland was 0.909, with an identification accuracy of 0.915.

[0004] Patent publication number CN115831362A discloses a method and system for predicting prostate cancer risk in patients undergoing prostate biopsy. This method and system, encompassing the technical field of prostate cancer prediction, involves obtaining clinical data from prostate biopsy patients and determining the patient's prostate health index (PHI); obtaining multi-parameter magnetic resonance imaging (MRI) data from prostate biopsy patients; and deriving a predicted probability of prostate cancer based on the clinical data, PHI, and multi-parameter MRI data. These existing prostate cancer prediction technologies all require the integration of multiple MRI parameters, resulting in complex calculations.

[0005] Summary of the Invention

[0006] In view of the deficiencies in the prior art, the present invention provides a qualitative and numerical scoring system for predicting prostate cancer based on magnetic resonance imaging (MRI).

[0007] According to the present invention, a qualitative and numerical scoring system for predicting prostate cancer by magnetic resonance imaging is provided, wherein:

[0008] A qualitative and data scoring system for predicting prostate cancer based on magnetic resonance imaging (MRI) performance, the system comprising: a magnetic resonance device; a data storage module electrically connected to a port of the magnetic resonance device, the data storage module being used to convert electrical signals from the magnetic resonance device and temporarily store data;

[0009] The data temporary storage module sends the data to the imaging detection module through the network connection module, and the imaging detection module is used to display the imaging of the magnetic resonance device;

[0010] The imaging detection module is connected to a background system, which includes a scoring module and a PC unit;

[0011] The scoring module obtains the volume ratio value of the central prostate gland and the total prostate gland based on magnetic resonance imaging and the detection value based on prostate specific antigen PSA, obtains a scoring result, matches the scoring result with the disease risk and outputs it.

[0012] Preferably, the magnetic resonance device comprises: a main magnet, a gradient magnetic field, a radio frequency coil, a computer system and other auxiliary equipment;

[0013] Wherein, the main magnet: generates a magnetic field to provide an environment for imaging;

[0014] The gradient magnetic field: applying a gradient magnetic field to add spatial coordinate information to each magnetic resonance signal, and the gradient magnetic field can also provide support for related sequences including gradient echo;

[0015] The radio frequency coil transmits radio frequency pulses and collects magnetic resonance signals;

[0016] Computer system: responsible for controlling, receiving and issuing relevant instructions, filling the K space of the collected magnetic resonance signals, and then outputting them as magnetic resonance images through Fourier transform; other auxiliary equipment provides auxiliary support for the normal operation of the equipment.

[0017] Preferably, the scoring module includes: a calculation model input module, the calculation model input module is used to input the evaluation calculation formula, and the port of the calculation model input module is connected to the calculation model analysis module;

[0018] The calculation model prostate puncture positive probability analysis module is used to evaluate the value calculated by the logistics regression prediction model. The calculation model probability analysis module port is connected to the judgment module, and the judgment module is used to judge the prostate puncture positive probability.

[0019] Preferably, the scoring module is connected to a correlation result output module and a storage module, the storage module is used to store the prediction results, and the correlation result output module is used to match the score with the disease risk and output the result.

[0020] Preferably, the scoring module comprises: calculating the prostate central gland volume PVc and the total gland volume PV based on magnetic resonance imaging, wherein the prostate central gland volume PVc and the total gland volume PV are calculated as: Π / 6×anteroposterior diameter×lateral diameter×superior diameter (ml);

[0021] Specifically including: 1) based on the patient's age; 2) based on the detection value of total prostate-specific antigen PSA; 3) based on the ratio of the detection value of free prostate-specific antigen fPSA to total prostate-specific antigen PSA: %fPSA; 4) based on the ratio of total prostate-specific antigen density PSAD = total prostate-specific antigen PSA / prostate volume PV; 5) based on the ratio of PVc / PV volume ratio Vratio;

[0022] In the modeling group, univariate and multivariate logistic regression analysis was performed on the patients' clinical indicators: age, tPSA, f%PSA, PSAD and PVc / PV volume ratio Vratio. The results of multivariate analysis showed that age, PSAD and PVc / PV volume ratio Vratio were independent predictors of prostate cancer.

[0023] Preferably, the scoring module further includes: using a multivariate logistics regression model to analyze the calculation formula:

[0024] The probability of a positive prostate biopsy result = e[-0.3524+0.0129×(age)+0.9399×(PSAD)-0.8213×(Vratio) / (1+e[-0.3524+0.0129×(age)+0.9399×(PSAD)-0.8213×(Vratio)].

[0025] Preferably, the magnetic resonance device, data temporary storage module, imaging detection module and background system are all electrically connected to a power supply device, and the power supply device plays a role of power supply.

[0026] Preferably, the power supply device includes a microcontroller, a current acquisition module electrically connected to the microcontroller, a voltage acquisition module, a time recording module, an alarm module and a battery pack. The current acquisition module is used to detect the circuit current, the voltage acquisition module is used to detect the circuit voltage, the time recording module is used to record the working time, and the alarm module is used to alarm when the current and voltage are abnormal.

[0027] Preferably, the network connection module includes a WIFI module and an I / O connection module, which are used to provide two data transmission modes: wireless and wired.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. A qualitative and statistical scoring system for predicting prostate cancer using the central prostate gland volume ratio based on magnetic resonance imaging, thereby improving the accuracy of tumor detection and reducing unnecessary prostate biopsies;

[0030] 2. There is no need to combine multiple magnetic resonance imaging parameters. The calculation method is simple. Only the patient's age, prostate-specific antigen density (PSAD), and prostate central gland volume ratio (Vration) need to be input to predict the risk of gray zone prostate cancer.

[0031] Other beneficial effects of the present invention will be explained through the introduction of specific technical features and technical solutions in the specific implementation methods. Those skilled in the art should be able to understand the beneficial technical effects brought about by the introduction of these technical features and technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0033] Figure 1 is a diagram of the system components and the power supply module;

[0034] Figure 2 is a table of multivariate logistics regression analysis results;

[0035] Figure 3 is a table of multivariate logistics regression analysis results;

[0036] Figure 4 is a schematic diagram of a power supply module;

[0037] Figure 5 shows the ROC curve. DETAILED DESCRIPTION

[0038] The present invention will be described in detail below with reference to specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those skilled in the art, several changes and improvements can be made without departing from the scope of the present invention. These all fall within the scope of protection of the present invention.

[0039] An embodiment of the present invention provides a qualitative and data scoring system for predicting prostate cancer through magnetic resonance imaging (MRI) manifestations, the system comprising: a magnetic resonance device; a port of the magnetic resonance device electrically connected to a data storage module, the data storage module being used to convert electrical signals from the magnetic resonance device and temporarily store data; the data storage module sending data to an imaging detection module via a network connection module, the imaging detection module being used to display imaging from the magnetic resonance device; the imaging detection module being connected to a background system, the background system comprising a scoring module and a PC unit.

[0040] The scoring module obtains the volume ratio value of the central prostate gland and the total prostate gland based on magnetic resonance imaging and the detection value based on prostate-specific antigen PSA to obtain a scoring result; the scoring module is connected to the associated result output module and the storage module, the storage module is used to store the prediction results, and the associated result output module is used to match the score with the disease risk and output it.

[0041] The magnetic resonance device includes: a main magnet, a gradient magnetic field, a radio frequency coil, a computer system and other auxiliary equipment; wherein, the main magnet generates a magnetic field to provide an environment for imaging.

[0042] Gradient magnetic field: This applies a gradient magnetic field to attach spatial coordinate information to each MRI signal. The gradient magnetic field also supports related sequences, including gradient echoes. Radiofrequency coil: This transmits RF pulses and acquires MRI signals. Computer system: This controls, receives, and issues relevant instructions, while also filling the K-space of the acquired MRI signals and outputting them as MRI images through Fourier transform. Other auxiliary equipment supports the normal operation of the equipment.

[0043] The scoring module includes: a calculation model input module, which is used to input the evaluation calculation formula, and the port of the calculation model input module is connected to the calculation model analysis module; a calculation model prostate puncture positive probability analysis module is used to evaluate the value calculated by the logistics regression prediction model, and the port of the calculation model probability analysis module is connected to the judgment module, and the judgment module is used to judge the probability of prostate puncture positivity.

[0044] The scoring module includes: calculating the prostate central gland volume PVc and the total gland volume PV based on magnetic resonance imaging, wherein the prostate central gland volume PVc and the total gland volume PV are calculated as: Π / 6×anteroposterior diameter×lateral diameter×superior diameter (ml);

[0045] Specifically including: 1) based on the patient's age; 2) based on the detection value of total prostate-specific antigen PSA; 3) based on the ratio of the detection value of free prostate-specific antigen fPSA to total prostate-specific antigen PSA: %fPSA; 4) based on the ratio of total prostate-specific antigen density PSAD = total prostate-specific antigen PSA / prostate volume PV; 5) based on the ratio of PVc / PV volume ratio Vratio;

[0046] In the modeling group, univariate and multivariate logistic regression analyses were performed on the patients' clinical indicators: age, tPSA, f%PSA, PSAD, and PVc / PV volume ratio Vratio. The results of the multivariate analysis showed that age, PSAD, and PVc / PV volume ratio Vratio were all independent predictors of prostate cancer. Figure 2 shows the results of the multivariate logistic regression analysis.

[0047] The scoring module also includes: using the multivariate logistics regression model to analyze the calculation formula:

[0048] Probability of a positive prostate biopsy result = e[-0.3524 + 0.0129 × (age) + 0.9399 × (PSAD) - 0.8213 × (Vratio) / (1 + e[-0.3524 + 0.0129 × (age) + 0.9399 × (PSAD) - 0.8213 × (Vratio)]]. Figure 3 shows the results of a multivariate logistics regression analysis (including only independent predictors of prostate cancer).

[0049] As shown in Figure 4 , the MRI device, data storage module, imaging detection module, and backend system are all electrically connected to a power supply. This power supply comprises a microcontroller, a current acquisition module electrically connected to the microcontroller, a voltage acquisition module, a time recording module, an alarm module, and a battery pack. The current acquisition module detects circuit current, the voltage acquisition module detects circuit voltage, the time recording module records operating hours, and the alarm module generates an alarm if current or voltage is abnormal.

[0050] The network connection module includes a WIFI module and an I / O wiring module, which are used to provide both wireless and wired data transmission methods.

[0051] Next, the present invention will be described in more detail.

[0052] 1 , the system provided by the present invention includes: a magnetic resonance device, which includes: a main magnet, a gradient magnetic field, a radio frequency coil, a computer system and other auxiliary equipment.

[0053] Among them, the main magnet generates a magnetic field to provide an environment for imaging; the gradient magnetic field applies a gradient magnetic field to add spatial coordinate information to each magnetic resonance signal. In addition, the gradient magnetic field can also provide support for related sequences including gradient echo.

[0054] Radio frequency coil: emits radio frequency pulses and collects MR signals (magnetic resonance signals); computer system: is responsible for controlling, receiving and issuing relevant instructions, while filling the K space of the collected magnetic resonance signals, and then outputting them as magnetic resonance images through Fourier transform; other auxiliary equipment provides auxiliary support for the normal operation of the equipment.

[0055] The port of the magnetic resonance device is electrically connected to a data storage module, which is used to convert the electrical signals of the magnetic resonance device and temporarily store data; the data storage module sends data to the imaging detection module through the network connection module, and the imaging detection module is used to display the imaging of the magnetic resonance device; the imaging detection module is connected to a background system, which includes a scoring module and a PC unit.

[0056] The scoring module includes a calculation model input module, which is used to input the evaluation calculation formula, and the port of the calculation model input module is connected to the calculation model prediction analysis module; the calculation model analysis module uses the logistics regression model to analyze the calculated value, and the port of the calculation model analysis module is connected to the judgment module, which is used to judge whether the predicted risk meets the standard, and the judgment module includes a threshold setting module.

[0057] The scoring module is connected to the associated result output module and the storage module. The storage module is used to store the scoring results, and the associated result output module is used to match the scoring results with the disease risk and output them.

[0058] Univariate and multivariate logistic regression analyses were performed for the PSA 4-10 ng / mL group during the modeling phase, using prostate cancer and non-prostate cancer outcomes as the two main variables. Age, PSA, f%PSA, PSAD, and the ratio of the central prostate gland to the total prostate volume were considered numeric variables. The study showed that age, f / t PSA, PSAD, and the ratio of the central prostate gland to the total prostate volume were significant. A logistic regression model was derived, assuming RAM.PeaR (risk of risk assessment model for prostate cancer) as the probability of prostate cancer development, ranging from 0 to 1. PSA: total prostate-specific antigen; f%PSA: ratio of free prostate-specific antigen to total prostate-specific antigen; PSAD: prostate-specific antigen density; and PVc / PV: ratio of the central prostate gland to the total prostate volume.

[0059] Each patient was assessed for PSA, f%PSA, PSAD, and PVc / PV ratio. Prostate biopsy was performed after prostate cancer risk was estimated using a logistic regression model. fPSA and tPSA were measured 48 hours after digital rectal examination, cystoscopy, catheterization, and one week after prostate massage.

[0060] The total prostate volume PV and the central prostate gland volume PVc: The volume of the prostate and central gland V = Π / 6 × anterior-posterior diameter × left-right diameter × superior-inferior diameter (ml).

[0061] PSAD = serum PSA / prostate volume.

[0062] The qualitative and statistical scoring system for predicting prostate cancer based on MRI findings also includes a scoring module that uses a multivariate logistics regression model to analyze and calculate the following formula: Probability of a positive prostate biopsy result = e[-0.3524 + 0.0129 × (age) + 0.9399 × (PSAD) - 0.8213 × (Vratio) / (1 + e[-0.3524 + 0.0129 × (age) + 0.9399 × (PSAD) - 0.8213 × (Vratio)]]. Figure 3 shows the results of the multivariate logistics regression analysis (including only independent predictors of prostate cancer). The area under the receiver operating characteristic (ROC) curve (AUC) showed that PSAD (AUC value 0.732) and Vratio (AUC value 0.865) had high diagnostic value, as shown in Figure 5.

[0063] The patient's age, PSAD, and volume ratio (Vratio) are entered into the input module. The probability of a positive prostate cancer result is calculated using the logistic regression prediction model formula. The probability partitions are: low risk <0.25, intermediate risk 0.25-0.5, high risk 0.5-0.8, and very high risk >0.8. This guides the necessity of biopsy.

[0064] Embodiments of the present invention provide a qualitative and data scoring system for predicting gray zone prostate cancer based on magnetic resonance imaging manifestations. By using the prostate central gland volume ratio of magnetic resonance imaging to predict prostate cancer, the qualitative and data scoring system can improve the accuracy of tumor detection and reduce unnecessary prostate punctures.

[0065] Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, and units provided by the present invention in purely computer-readable program code, it is entirely possible to implement the same functions of the system and its various devices, modules, and units provided by the present invention in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; the devices, modules, and units for implementing various functions can also be considered as both software modules implementing the method and structures within the hardware component.

[0066] The above describes specific embodiments of the present invention. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art may make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. The embodiments of this application and the features in the embodiments may be combined with each other in any manner unless there is a conflict.

Claims

1. A qualitative and statistical scoring system for predicting PSA gray zone prostate cancer, characterized in that: include: Magnetic resonance equipment; The port of the magnetic resonance device is electrically connected to a data temporary storage module, and the data temporary storage module is used to convert the electrical signal of the magnetic resonance device and perform data temporary storage; The data temporary storage module sends the data to the imaging detection module through the network connection module, and the imaging detection module is used to display the imaging of the magnetic resonance device; The imaging detection module is connected to a background system, and the background system includes a scoring module and a PC unit; The scoring module obtains the volume ratio value of the central prostate gland and the total prostate gland based on magnetic resonance imaging and the detection value based on prostate specific antigen PSA, obtains a scoring result, matches the scoring result with the disease risk and outputs it.

2. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 1, characterized in that: The magnetic resonance device includes: a main magnet, a gradient magnetic field, a radio frequency coil, a computer system and other auxiliary equipment; Wherein, the main magnet: generates a magnetic field to provide an environment for imaging; The gradient magnetic field: applying a gradient magnetic field to add spatial coordinate information to each magnetic resonance signal, and the gradient magnetic field can also provide support for related sequences including gradient echo; The radio frequency coil is used to transmit radio frequency pulses and collect magnetic resonance signals; Computer system: responsible for controlling, receiving and issuing relevant instructions, filling the K space of the collected magnetic resonance signals, and then outputting them as magnetic resonance images through Fourier transform; other auxiliary equipment provides auxiliary support for the normal operation of the equipment.

3. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 1, characterized in that: The scoring module includes: a calculation model input module, the calculation model input module is used to input the evaluation calculation formula, and the port of the calculation model input module is connected to the calculation model analysis module; The calculation model prostate puncture positive probability analysis module is used to evaluate the value calculated by the logistics regression prediction model. The calculation model probability analysis module port is connected to the judgment module, and the judgment module is used to judge the prostate puncture positive probability.

4. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 1, characterized in that: The scoring module is connected to an associated result output module and a storage module, the storage module is used to store the prediction results, and the associated result output module is used to match the score with the disease risk and output it.

5. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 1, characterized in that: The scoring module includes: calculating the prostate central gland volume PVc and the total gland volume PV based on magnetic resonance imaging, wherein the prostate central gland volume PVc and the total gland volume PV are calculated as: Π / 6×anteroposterior diameter×left-right diameter×upper-lower diameter (ml); Specifically including: 1) based on the patient's age; 2) based on the detection value of total prostate-specific antigen PSA; 3) based on the ratio of the detection value of free prostate-specific antigen fPSA to total prostate-specific antigen PSA: %fPSA; 4) based on the ratio of total prostate-specific antigen density PSAD = total prostate-specific antigen PSA / prostate volume PV; 5) based on the ratio Vratio of PVc / PV volume ratio; In the modeling group, univariate and multivariate logistic regression analysis was performed on the patients' clinical indicators: age, tPSA, f%PSA, PSAD and PVc / PV volume ratio Vratio. The results of multivariate analysis showed that age, PSAD and PVc / PV volume ratio Vratio were independent predictive indicators of prostate cancer.

6. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 5, characterized in that: The scoring module also includes: using the multivariate logistics regression model to analyze the calculation formula: Probability of a positive prostate puncture result = e[-0.3524+0.0129×(age)+0.9399×(PSAD)-0.8213×(Vratio) / (1+e[-0.3524+0.0129×(age)+0.9399×(PSAD)-0.8213×(Vratio)).

7. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 1, characterized in that: The magnetic resonance device, data temporary storage module, imaging detection module and background system are all electrically connected to a power supply device, and the power supply device plays a role of power supply.

8. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 7, characterized in that: The power supply device includes a microcontroller, a current acquisition module electrically connected to the microcontroller, a voltage acquisition module, a time recording module, an alarm module and a battery pack. The current acquisition module is used to detect the circuit current, the voltage acquisition module is used to detect the circuit voltage, the time recording module is used to record the working time, and the alarm module is used to alarm when the current and voltage are abnormal.

9. The qualitative and statistical scoring system for predicting PSA gray zone prostate cancer according to claim 1, characterized in that: The network connection module includes a WIFI module and an I / O wiring module, which are used to provide two data transmission modes: wireless and wired.

Images