Method and equipment for predicting biochemical recurrence risk after prostatic cancer radical operation

Abstract

The invention provides a method, a system, equipment, a medium and a program product for predicting a biochemical recurrence risk after a prostatic cancer radical operation, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring a numerical value of a prediction factor of a to-be-detected sample; predicting the biochemical recurrence risk after the prostatic cancer radical operation on the basis of the predictive factor; the method further includes calculating a risk value based on the predictor to predict a risk of predicting biochemical recurrence after the radical prostate cancer treatment. The BCR is predicted on the basis of the related parameters obtained through multi-parameter magnetic resonance imaging, and the problems that doctors are required to have a certain professional level when biochemical recurrence of the prostate cancer patient is predicted in the related technology is at least solved to a certain extent, and prediction is not accurate to a certain extent are solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical treatment, and more specifically, to a method, device, medium and program product for predicting the risk of biochemical recurrence after radical prostatectomy. Background Art

[0002] Prostate cancer (PCA) is one of the most common cancers in men worldwide. For patients with localized prostate cancer, surgical treatment (radical prostatectomy, RP) is still the standard treatment; however, approximately 20%-40% of patients who receive RP will experience biochemical recurrence (BCR) within 10 years. In the absence of secondary treatment, clinical progression will occur within 5-8 years after BCR, and 32-43% of patients will die from PCA within 15 years. Therefore, accurate prediction of BCR and identification of high-risk patients can guide more reasonable clinical treatment plans and the application of early individualized adjuvant therapy decisions after surgery to improve progression-free survival and overall survival. Specifically, for patients with a low predicted probability of biochemical recurrence, overtreatment can be avoided, and for patients with a high predicted probability of biochemical recurrence, more active treatment should be used as much as possible to delay disease progression. In the prior art, physicians generally use their own professional knowledge and experience to roughly estimate the probability of biochemical recurrence after surgery in patients. This method not only requires physicians to have a certain level of professionalism, but also the prediction is not necessarily accurate. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a method, device, medium and program product for predicting the risk of biochemical recurrence after radical prostatectomy; the method of the present invention predicts BCR based on relevant parameters obtained by multi-parameter magnetic resonance imaging, which at least to a certain extent overcomes the problem in the related art that predicting biochemical recurrence in prostate cancer patients requires physicians to have a certain level of professionalism and the prediction may not be accurate.

[0004] The first aspect of the present application discloses a method for predicting the risk of biochemical recurrence after radical prostatectomy for prostate cancer, the method comprising:

[0005] S1, obtain the value of the prediction factor of the sample to be tested;

[0006] S21, the prediction factors include the distance from the tumor to the membranous urethra; the risk of biochemical recurrence after radical prostatectomy is predicted based on the prediction factors; if the distance from the tumor to the membranous urethra is greater than a first threshold, a result is obtained that the risk of biochemical recurrence after surgery for the sample to be tested is low; if the distance from the tumor to the membranous urethra is less than or equal to the first threshold, a result is obtained that the risk of biochemical recurrence after surgery for the sample to be tested is high.

[0007] In some embodiments, S1 is executed and S21 is replaced by S22, wherein S22 includes: the predictive factor includes the capsule contact length (CCL); if the capsule contact length (CCL) is greater than a second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high; if the capsule contact length (CCL) is less than or equal to the second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low.

[0008] In some embodiments, the S1 is executed, and S21 is replaced by S23, wherein S23 includes: the prediction factor includes prostate volume; if the prostate volume is less than or equal to a third threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the prostate volume is greater than the third threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high;

[0009] Alternatively, S21 is replaced by S24, S24 includes: the prediction factor includes surgical experience; if the surgical experience is greater than a fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the surgical experience is less than or equal to the fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high.

[0010] In some embodiments, S1 is executed and S21 is replaced by S25, wherein S25 includes: the predictive factors include any two or more of the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), the prostate volume, and surgical experience, and the risk value of biochemical recurrence after radical prostatectomy is calculated based on the predictive factors.

[0011] In some embodiments, the risk value is obtained in the following manner: when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), the prostate volume, and the surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+prostate volume*c+surgical experience*d.

[0012] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and the capsule contact length (CCL), the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b;

[0013] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and the prostate volume, the risk value = the distance UD from the tumor to the membranous urethra*a+the prostate volume*c;

[0014] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+surgical experience*d.

[0015] In some embodiments, when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), and the prostate volume, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+prostate volume*c;

[0016] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), and surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+surgical experience*d;

[0017] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra, the prostate volume, and surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+the prostate volume*c+the surgical experience*d.

[0018] In some embodiments, the risk of postoperative biochemical recurrence includes the risk of any one year after surgery: 1 year, 2 years, or 3 years;

[0019] Optionally, the first threshold value and / or the second threshold value and / or the third threshold value are obtained by maximum selection test or ROC curve calculation of the software package "maxstat".

[0020] The second aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store a computer program; and the processor executes the computer program to implement the steps of the above method.

[0021] A third aspect of the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0022] A fourth aspect of the present application discloses a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0023] This application has the following beneficial effects:

[0024] 1. This application innovatively discloses a method for predicting the risk of biochemical recurrence after radical prostatectomy for prostate cancer. This method explores the relationship between preoperative pelvic anatomical structure and BCR for the first time, and uses UD as a predictor of BCRFS for the first time. It has better discrimination in predicting biochemical recurrence after radical prostatectomy. This method predicts BCR, at least to a certain extent, overcoming the problem in related technologies that predicting biochemical recurrence in prostate cancer patients requires physicians to have a certain level of professionalism, and the prediction is not necessarily accurate. Predicting BCR based on this method can significantly improve the accuracy of predicting biochemical recurrence of prostate cancer, help establish individualized and accurate diagnosis and treatment plans for patients, improve patient prognosis, and help reduce the medical burden on society.

[0025] 2. This application also innovatively combines UD and other MRI-related variables with common preoperative variables to calculate risk values ​​for predicting biochemical recurrence after radical prostatectomy, which makes up for the fact that there are no reports in the prior art on the relationship between preoperative pelvic anatomical structure and BCR. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the 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 work.

[0027] Figure 1 is a schematic diagram of a method flow chart provided by the first aspect of an embodiment of the present invention;

[0028] Figure 2 is a schematic diagram of a system for predicting the risk of biochemical recurrence after radical prostatectomy provided by the second aspect of an embodiment of the present invention;

[0029] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention;

[0030] Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by an embodiment of the present invention;

[0031] Figure 5 is a schematic diagram of a storage medium provided by an embodiment of the present invention;

[0032] Figure 6 is a flow chart of patient selection in a training set sample provided by an embodiment of the present invention;

[0033] Figure 7 is a Kaplan-Meier curve diagram of BCR-free survival drawn based on MRI features provided in an embodiment of the present invention; wherein, Figure 7 a is the KM curve of CCL, Figure 7 b is the KM curve of the maximum diameter MTD of prostate tumor, Figure 7 c is the KM curve of prostate volume, Figure 7 d is the KM curve of UD, Figure 7 e is the KM curve of the training set samples;

[0034] Figure 8 is a nomogram for predicting 3-year BCR-free survival after RP surgery provided by an embodiment of the present invention;

[0035] Fig. 9 is a performance index diagram of a new nomogram 3 years after RP surgery provided by an embodiment of the present invention; wherein, Fig. 9 a is the calibration diagram of the nomogram, Fig. 9 b is the event-dependent ROC curve of the new nomogram;

[0036] Fig.10 It is a Kaplan-Meier curve diagram of the BCR-free survival risk classification model provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0040] Figure 1 The present invention provides a method for predicting the risk of biochemical recurrence of prostate cancer after radical prostatectomy. Specifically, the method comprises the following steps:

[0041] S1: Get the value of the prediction factor of the sample to be tested;

[0042] In some embodiments, the term "subject" or "person to be tested" or "sample to be tested" as used herein refers to any animal (e.g., mammal), including but not limited to humans, non-human primates, rodents, etc., which will be the recipient of a specific treatment. Generally, the terms "subject" and "patient" are used interchangeably herein when referring to human subjects. Preferably, the subject is a human. In some embodiments, the sample to be tested is a patient clinically used to receive a prognostic assessment.

[0043] S21: The prediction factor includes the distance from the tumor to the membranous part of the urethra; the risk of biochemical recurrence after radical prostatectomy is predicted based on the prediction factor; if the distance from the tumor to the membranous part of the urethra is greater than a first threshold, a result is obtained that the risk of biochemical recurrence after surgery for the sample to be tested is low; if the distance from the tumor to the membranous part of the urethra is less than or equal to the first threshold, a result is obtained that the risk of biochemical recurrence after surgery for the sample to be tested is high; the distance from the tumor to the membranous part of the urethra is recorded as UD, UD>4 mm is a low-risk group, and UD≤4 mm is a high-risk group;

[0044] In some embodiments, the S1 is executed, and S21 is replaced by S22, and S22 includes: the predictive factor includes the capsular contact length (CCL); if the capsular contact length (CCL) is greater than the second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high; if the capsular contact length (CCL) is less than or equal to the second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low. Those with CCL ≤ 19.9 mm are in the low-risk group, and those with CCL > 19.9 mm are in the high-risk group;

[0045] In some embodiments, the S1 is executed, and S21 is replaced by S23, and S23 includes: the prediction factor includes prostate volume; if the prostate volume is less than or equal to a third threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the prostate volume is greater than the third threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high; those with a prostate volume ≤31 ml are in a low-risk group, and those with a prostate volume >31 ml are in a high-risk group;

[0046] Alternatively, S21 is replaced by S24, which includes: the predictive factor includes surgical experience; if the surgical experience is greater than a fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the surgical experience is less than or equal to the fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high. The fourth threshold of surgical experience is 100 times, but it is not limited to 100 times.

[0047] In some embodiments, S1 is executed and S21 is replaced by S25, wherein S25 includes: the predictive factors include any two or more of the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), the prostate volume, and surgical experience, and the risk value of biochemical recurrence after radical prostatectomy is calculated based on the predictive factors.

[0048] In some embodiments, the risk value is obtained in the following manner: when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), the prostate volume, and the surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+prostate volume*c+surgical experience*d.

[0049] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and the capsule contact length (CCL), the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b;

[0050] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and the prostate volume, the risk value = the distance UD from the tumor to the membranous urethra*a+the prostate volume*c;

[0051] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+surgical experience*d.

[0052] In some embodiments, when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), and the prostate volume, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+prostate volume*c;

[0053] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), and surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+surgical experience*d;

[0054] Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra, the prostate volume, and surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+the prostate volume*c+the surgical experience*d.

[0055] Specifically, the model coefficients obtained when selecting the training set samples are as follows: a is -0.952, b is 1.307, c is 1.547, and d is -0.929. The principle is as follows: The basic form of the Cox model is: ln(h(t,X) / h0(t))=β1X1+β2X2+…+βpXpln(h0 (t)h(t,X))=β1 X1 +β2

[0056] X2+…+βp Xp

[0057] Where: h(t,X)h(t,X) is the hazard function given the covariate XX at time tt. h0(t)h0(t) is the baseline hazard function, which represents the hazard function when all covariates are 0. β1,β2,…,βpβ1 ,β2,…,βp are model coefficients. X1,X2,…,XpX1 ,X2

[0058] ,…,Xp is the patient's predictor. The risk score (Risk Score) can be expressed as: Risk Score=β1X1+β2X2+…+βpXpRisk Score=β1 X1 +β2 X2+…+βp Xp.

[0059] In some embodiments, the risk of postoperative biochemical recurrence includes the risk of any one year after surgery: 1 year, 2 years, or 3 years;

[0060] Optionally, the first threshold value and / or the second threshold value and / or the third threshold value are obtained by the maximum selection test or ROC curve calculation of the software package "maxstat". Specifically, the first threshold value is optimally 4 mm; the second threshold value is optimally 19.9 mm; the third threshold value is optimally 31 ml; and the fourth threshold value is optimally 100 times. The distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), and the cutoff value of the prostate volume are derived from maxstat. The maxstat statistical package is a standard method for determining the optimal threshold value for distinguishing low and high risks of BCR. The fourth threshold value is not obtained by software, but is obtained based on the classification of doctors' surgical experience in previous literature.

[0061] In some embodiments, the risk value calculation formula is obtained by training the MRI images of the training set samples. Specifically, the training method includes:

[0062] 101, obtaining preoperative prostate MRI images of training set samples and clinical features corresponding to the samples;

[0063] 102, extracting MRI parameter features from the preoperative prostate MRI image;

[0064] 103, screening predictive factors from the MRI parameter characteristics and clinical characteristics based on univariate analysis and multivariate analysis;

[0065] 104. Construct a risk value prediction formula for the risk of biochemical recurrence after RP based on the prediction factors.

[0066] In some embodiments, the training set samples in 101 are pathologically confirmed PCa patients who underwent preoperative prostate mpMRI and subsequent RP at the institution between January 2015 and October 2022. BCR is defined as: persistent, detectable PSA (prostate-specific antigen) levels after RP, with two consecutive PSA values ​​≥ 0.2 ng / ml after a period of PSA normalization.

[0067] In some embodiments, the predictive factors include one or more of the following: the distance UD from the tumor to the membranous urethra, the prostate volume, the CCL, and surgical experience.

[0068] In some embodiments, the risk value prediction formula is used to predict BCRFS 3 years after RP.

[0069] In some embodiments, the univariate and multivariate analysis in 103 includes: extracting any one or more of the features including pelvic anatomical features, prostate morphological features and tumor-related risk factor features from the preoperative prostate MRI image; extracting the predictor from any one or more of the features; the pelvic anatomical features include any one or more of the following: prostate apex depth, anteroposterior diameter of pelvic inlet (API), pelvic depth, PCI, interspinous distance, symphysis angle, femoral bone width, and inferior conjugate of the pelvic midplane, and UD. The prostate morphological features include any one or more of the following: calculating prostate volume and prostate width using the conventional long ellipse formula; the tumor-related risk factor features include any one or more of the following: MTD, PI-RADS category of the index lesion, obvious EPE visible on MRI or invasion of adjacent anatomical structures, and capsule contact length (CCL) of the index lesion.

[0070] In the present invention, the term "prognosis" is recognized in the art and includes predictions about the likely course of a disease or disease development, particularly about the likelihood of disease remission, disease recurrence, tumor recurrence, metastasis, and death. "Good prognosis" means the likelihood that a patient with cancer, particularly pancreatic cancer, will remain disease-free (i.e., cancer-free). "Poor prognosis" means the likelihood of recurrence or recurrence of a potential cancer or tumor, metastasis, or death.

[0071] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention, such as Figure 3 As shown, the device may include: one or more processors, and one or more memories; wherein the memories store computer-readable codes, and when the computer-readable codes are run by the one or more processors, the method described above may be executed.

[0072] The processor in this embodiment can be an integrated circuit chip with signal processing capabilities. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, operations and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can be an X86 architecture or an ARM architecture.

[0073] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0074] For example, the method or device according to the embodiment of the present disclosure may also be implemented by Figure 4 The architecture of the computing device 3000 shown in FIG. Figure 4 As shown, the computing device 3000 may include a bus 3010, one or more CPUs 3020, a read-only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port 3050 connected to a network, an input / output component 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as ROM 3030 or hard disk 3070, may store various data or files used for processing and / or communication of the method provided by the present disclosure and program instructions executed by the CPU. The computing device 3000 may also include a user interface 3080. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of a computing device are shown.

[0075] The embodiment of the present invention also provides a computer-readable storage medium, such as Figure 5As shown, it is a schematic diagram of a storage medium provided by an embodiment of the present invention, and a computer readable instruction 4010 is stored on the computer storage medium 4020. When the computer readable instruction 4010 is executed by the processor, the method according to the embodiment of the present disclosure described with reference to the above figures can be executed. The computer readable storage medium in the embodiment of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory. It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0076] The embodiments of the present disclosure further provide a computer program product or system, including a computer program, which implements the steps of the above method when executed by a processor.

[0077] In some embodiments, this embodiment also discloses a system for predicting the risk of biochemical recurrence after radical prostatectomy. Figure 2 As shown, the system comprises:

[0078] An acquisition module 201 is used or configured to acquire a value of a prediction factor of a sample to be tested;

[0079] The first prediction module 2021 is used or configured such that the prediction factor includes the distance between the tumor and the membranous part of the urethra; based on the prediction factor, the risk of biochemical recurrence after radical prostatectomy is predicted; if the distance between the tumor and the membranous part of the urethra is greater than a first threshold, a result is obtained that the risk of biochemical recurrence after surgery of the sample to be tested is low; if the distance between the tumor and the membranous part of the urethra is less than or equal to the first threshold, a result is obtained that the risk of biochemical recurrence after surgery of the sample to be tested is high;

[0080] In some embodiments, the first prediction module 2021 in the system is replaced by a second prediction module 2022, and the second prediction module 2022 is used or configured such that the prediction factor includes a capsule contact length (CCL); if the capsule contact length (CCL) is greater than a second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high; if the capsule contact length (CCL) is less than or equal to the second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low:

[0081] In some embodiments, the first prediction module 2021 in the system is replaced by a third prediction module 2023, and the third prediction module 2023 is used or configured such that the prediction factor includes the prostate volume; if the prostate volume is less than or equal to a third threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the prostate volume is greater than the third threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high;

[0082] In some embodiments, the first prediction module 2021 in the system is replaced by a fourth prediction module 2024, and the fourth prediction module 2024 is used or configured such that the prediction factor includes surgical experience; if the surgical experience is greater than a fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the surgical experience is less than or equal to the fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high;

[0083] In some embodiments, the first prediction module 2021 in the system is replaced by a fifth prediction module 2025, and the fifth prediction module 2025 is used for or configured to include any two or more of the prediction factors including the distance UD from the tumor to the membranous urethra, the capsule contact length (CCL), the prostate volume, and surgical experience, and to calculate the risk value of biochemical recurrence after radical prostatectomy based on the prediction factors.

[0084] Example

[0085] 1. Materials and Methods

[0086] 1.1 Patients

[0087] We obtained institutional review board (IRB) approval for this retrospective study (IRB number I-22PJ1031). Patients with pathologically confirmed PCa who underwent preoperative prostate mpMRI and subsequent RP at our institution between January 2015 and October 2022 were retrospectively included. Exclusion criteria were as follows: (1) preoperative treatment (such as neoadjuvant chemotherapy and prostate-related surgery); (2) short-term hormonal therapy or radiotherapy after surgery; (3) the interval between MRI examination and surgery was more than 6 months; (4) incomplete clinical pathology and follow-up data required for evaluation. Data of 148 patients were finally available for analysis ( Figure 6 ). All preoperative clinicopathological variables and postoperative outcomes were extracted from medical and pathology reports. BCR was defined here as a sustained, detectable PSA level after RP, with two consecutive PSA values ​​≥ 0.2 ng / ml after a period of PSA normalization. Patients were followed up for at least 1 year in accordance with EAU guidelines, and if there was no disease recurrence, the follow-up period was determined by the last recorded PSA date. BCR-free survival was calculated as the interval between the RP date and the BCR date or the last follow-up date, whichever occurred first.

[0088] 1.2 Imaging Protocol and Analysis

[0089] All prostate mpMRI examinations were performed using a 3.0-T MRI scanner (GE750, GE Healthcare, Milwaukee, WI, USA). The mpMRI acquisition protocol followed PI-RADS recommendations and included T1-weighted imaging1 (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), dynamic contrast-enhanced (DCE) imaging, and apparent diffusion coefficient (ADC).

[0090] Three radiologists at the hospital with different levels of experience in interpreting prostate mpMRI (Radiologist 1: 10 years of experience, >5000 cases; Radiologist 2, 7 years of experience, >2000 cases; Radiologist 3, 5 years of experience, >1500 cases) evaluated the mpMRI images and determined the PI-RADS category of each lesion according to the PI-RADS version 2 or PI-RADS version 2.1 guidelines.

[0091] 1.3 Nuclear magnetic resonance measurements

[0092] MRI scans were reviewed by a single radiologist (2 years of experience, >1000 cases) who was blinded to the postoperative outcome. The radiologist assessed the following predictive factors based on the MRI images: (1) pelvic anatomy: prostate apex depth, anteroposterior diameter of pelvic inlet (API), pelvic depth, PCI, interspinous process distance, symphysis angle, femoral bone width, inferior conjugation of the pelvic midplane, and UD; (2) prostate morphology: prostate volume and prostate width were calculated using the conventional long ellipse formula; and (3) tumor-related risk factors: MTD, PI-RADS category of the index lesion, significant EPE or invasion of adjacent anatomical structures on MRI, and capsular contact length (CCL) of the index lesion.

[0093] All measurements in this study were performed using axial T2WI, combined with sagittal and coronal T2WI, reference high-b-value DWI images and corresponding ADC maps, and DCE images.

[0094] 1.4 Statistical analysis

[0095] Clinical, radiological, and histopathological characteristics were presented as descriptive statistics. Intergroup comparisons were performed using independent t-tests, chi-square tests, Mann-Whitney U tests, and Fisher's exact tests at a significance level of 0.05. The primary endpoint was BCR-free survival (BCRFS), calculated according to the final follow-up time of the patient's recurrence-free status. Survival functions were estimated using the Kaplan-Meier estimator and log-rank test. MRI-measured variables that met the p < 0.05 threshold were selected for subsequent regression model analysis. CCL was divided into ≤19.9 and >19.9 mm groups; MTD was divided into ≤23.9 mm and >23.9 mm groups; prostate volume was divided into ≤31 ml and >31 ml groups; and UD was divided into ≤4 mm and >4 mm groups. The above optimal cutoff values ​​for distinguishing low and high risk of BCR were calculated using the maximum selection test in the R package "maxstat".

[0096] Univariate and multivariate Cox proportional hazards ratio models were constructed to identify significant predictors of BCR, and a nomogram was constructed to predict BCRFS 3 years after RP. To validate the nomogram, we assessed discrimination and calibration for internal validation following a bootstrap approach (1000 bootstrap resamples). The Harrell concordance index (C-index) was used to assess discrimination. We constructed a calibration plot illustrating the relationship between the predicted probability of BCRFS and the actual observed events.

[0097] 2 Results

[0098] 2.1 Baseline characteristics

[0099] A total of 148 patients met the inclusion criteria of this study, with a mean age of 65.96 years and a median PSA of 8.76 ng / ml (IQR, 5.91-12.83) before RP. The MTD of MRI was 13.45 (IQR, 9.47–17.42); the distance from the tumor to the proximal urethral membranous part was 9.85 (IQR, 5.20-13.93). Most patients had ISUP grade 1 on biopsy (39.2%) and clinical T stage of T1-2c (83.8%). PSM was confirmed by pathology in 32 cases (21.6%). In this population, 26 patients (17.6%) had postoperative BCR, and the median follow-up time was 39.22 months (IQR, 21.58-61.05).

[0100] 2.2 Development and evaluation of a new BCR nomogram

[0101] Kaplan-Meier curves reflecting the BCRFS of the entire patient population in our study were also used to search for the optimal cutoff points for continuous variables measured by MRI ( Figure 7 The Kaplan-Meier curves of patients without BCR when CCL≤19.9mm, MTD≤23.9mm, prostate volume≤31ml, and UD>4mm were significantly different from those when CCL>19.9mm, MTD>23.9mm, prostate volume>31ml, and UD≤4mm (all log-rank p<0.05). According to some radiological characteristics (such as apical depth, API, pelvic depth, PCI, interspinous process distance, symphysis angle, and femoral width), the patients' BCR-free survival curves did not differ (all log-rank p>0.05), so the features with no differences were not included in the subsequent regression model analysis.

[0102] In univariate analysis, age, PSA level, cT, ISUP grade, prostate volume, MTD, CCL, UD, and surgical experience were significantly associated with BCR (all p < 0.05), and were therefore included in subsequent analysis. After multivariate Cox regression analysis, four independent predictors of BCR were finally obtained and used to establish a prediction model. The predictors included prostate volume (hazard ratio [HR], 3.91; 95% confidence interval [CI], 1.37-11.15; p = 0.011), UD (HR, 0.35; 0.95% CI: 0.15-0.83. p = 0.018), CCL (HR, 2.60; 95% CI, 0.99-6.82; p = 0.052), and surgical experience (HR, 0.34; 95% CI, 0.14-0.84. p = 0.020) (Table 1). The C index based on the simplified four-item multivariable Cox regression model was 0.82 (95% CI, 0.73-0.93). These variables were then incorporated into our nomogram to predict BCRFS at 3 years after RP ( Figure 8 ). The calibration diagram of the preoperative nomogram is as follows Fig. 9 As shown in a, it shows the acceptable prediction probability of BCRFS compared with the actual results. The AUC of this cohort was 0.85 (95% CI: 0.74-0.95) ( Fig. 9 b).

[0103] Table 1 Predictive factors for biochemical recurrence in univariate and multivariate Cox regression analysis

[0104]

[0105]

[0106]

[0107] Abbreviations: HR = hazard ratio, CI = confidence interval, PSA = prostate-specific antigen, PSAD = prostate-specific antigen density, ISUP = International Society of Urological Pathology, PPB = biopsy-positive rate, PI-RADS = Prostate Imaging Reporting and Data System, EPE = extraprostatic extension, UD = distance of tumor to proximal membranous urethra. Bold data indicate p < 0.05.

[0108] 2.3 BCR risk grading model based on the new nomogram

[0109] Based on the Cox regression coefficients, we identified two risk categories ( Fig.10)(The distribution and classification criteria of patients are shown in Table 2). In the survival analysis (KM curve), the classification was significantly associated with the risk of BCR (p<0.001). In the overall cohort, the 1-year, 2-year, and 3-year BCR-free survival rates were 97.3%, 97.3%, and 96.0%, respectively, in the low-risk group (n=75 in the overall cohort); and 89.0%, 82.2%, and 78.1%, respectively, in the high-risk group (n=73).

[0110] Preoperative pelvic anatomy is associated with oncological outcomes. Several studies have demonstrated that anthropometric measurements are associated with surgical difficulties and postoperative complications. UD (≤3.5 mm) has been reported to be an MRI predictor of PSM at the urethral apex with a sensitivity of 100% and a specificity of 95% (J = 0.946). In our cohort, UD (≤4 mm) was not associated with PSM but was associated with a higher postoperative pathological ISUP grade (P = 0.037), which is one of the factors that increase the incidence of BCR.

[0111] Table 2 Distribution and criteria of the risk classification of the newly developed model for predicting the change of BCR rate over time in 148 patients with mpMRI before RP

[0112]

[0113] Abbreviations: UD = distance to proximal membranous urethra, CCL = capsular contact length.

[0114] Definitions and abbreviations:

[0115] BCR, biochemical recurrence; BCRFS, BCR-free survival; RP, radical prostatectomy; PCA, prostate cancer; mpMRI, multiparameter magnetic resonance imaging; CCL, capsular contact length of the index lesion; MTD, maximum tumor diameter; UD, distance from tumor to proximal urethral membrane; PSM, positive surgical margin (positive incision margin means residual cancer cells, indicating that the cancer cells have not been completely removed and there is residual tumor after surgery; patients with positive surgical margins are prone to recurrence or further deterioration due to the presence of clear residual cancer cells in the body. The guidelines classify the risk of recurrence as high risk, which indicates incomplete surgery and poor prognosis).

[0116] The Kaplan-Meier curve, also known as the survival curve, is a common method of survival analysis. It mainly analyzes the impact of a single factor on survival time and is used to estimate patient survival rates and draw survival curves. The survival curve is a continuous step-shaped curve drawn with survival time as the horizontal axis and survival rate as the vertical axis to illustrate the relationship between survival time and survival rate. The endpoint of this study was biochemical recurrence of prostate cancer, and no patient deaths were found. If truncation occurs, it means that the patient was lost to follow-up during this period.

[0117] HR value, also called risk ratio, is mainly used in survival analysis. It is derived from the COX hazard ratio model and is used to estimate the multiple of the risk change of the outcome event due to the presence of a certain factor. It has important value in clinical therapeutic research and epidemiological cohort research.

[0118] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a part of a code, and the module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0119] In general, various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device. When various aspects of the disclosed embodiments are illustrated or described as block diagrams, flow charts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof as non-limiting examples.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. It should be understood by those skilled in the art that various modifications and combinations may be made to these embodiments or their features without departing from the principles and spirit of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A method for predicting the risk of biochemical recurrence after radical prostatectomy, characterized in that: The method comprises: S1, obtain the value of the prediction factor of the sample to be tested; S21, the prediction factors include the distance from the tumor to the membranous urethra; the risk of biochemical recurrence after radical prostatectomy is predicted based on the prediction factors; if the distance from the tumor to the membranous urethra is greater than a first threshold, a result is obtained that the risk of biochemical recurrence after surgery for the sample to be tested is low; if the distance from the tumor to the membranous urethra is less than or equal to the first threshold, a result is obtained that the risk of biochemical recurrence after surgery for the sample to be tested is high.

2. The method for predicting the risk of biochemical recurrence after radical prostatectomy according to claim 1, characterized in that: Execute S1 and replace S21 with S22, S22 includes: the prediction factor includes capsule contact length; if the capsule contact length is greater than a second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high; if the capsule contact length is less than or equal to the second threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low.

3. The method for predicting the risk of biochemical recurrence after radical prostatectomy according to claim 1, characterized in that: Execute S1, replace S21 with S23, S23 includes: the prediction factor includes prostate volume; if the prostate volume is less than or equal to a third threshold, a result that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the prostate volume is greater than the third threshold, a result that the risk of postoperative biochemical recurrence of the sample to be tested is high; Alternatively, S21 is replaced by S24, S24 includes: the prediction factor includes surgical experience; if the surgical experience is greater than a fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is low; if the surgical experience is less than or equal to the fourth threshold, a result is obtained that the risk of postoperative biochemical recurrence of the sample to be tested is high.

4. The method for predicting the risk of biochemical recurrence after radical prostatectomy according to claim 1, characterized in that: Execute S1 and replace S21 with S25, wherein S25 includes: the prediction factors include any two or more of the distance from the tumor to the membranous urethra, the capsule contact length, the prostate volume, and surgical experience, and the risk value of biochemical recurrence after radical prostatectomy is calculated based on the prediction factors.

5. The method for predicting the risk of biochemical recurrence after radical prostatectomy according to claim 4, characterized in that: The risk value is obtained in the following manner: when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length CCL, the prostate volume, and the surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+prostate volume*c+surgical experience*d; Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and the capsule contact length CCL, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b; Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and the prostate volume, the risk value = the distance UD from the tumor to the membranous urethra*a+the prostate volume*c; Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra and surgical experience, the risk value = the distance UD from the tumor to the membranous urethra*a+surgical experience*d.

6. The method for predicting the risk of biochemical recurrence after radical prostatectomy according to claim 4, characterized in that: When the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length CCL, and the prostate volume, the risk value = the distance UD from the tumor to the membranous urethra*a+CCL*b+prostate volume*c; Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra, the capsule contact length CCL, and surgical experience, the risk value = the distance from the tumor to the membranous urethra*a+CCL*b+surgical experience*d; Optionally, when the predictive factors include the distance UD from the tumor to the membranous urethra, the prostate volume, and surgical experience, the risk value = the distance from the tumor to the membranous urethra*a+prostate volume*c+surgical experience*d.

7. The method for predicting the risk of biochemical recurrence after radical prostatectomy according to claim 1, characterized in that: The risk of postoperative biochemical recurrence includes the risk in any one of 1 year, 2 years and 3 years after surgery; optionally, the first threshold and / or the second threshold and / or the third threshold are obtained by maximum selection test or ROC curve calculation of the software package "maxstat".

8. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images