Method, equipment and medium for identifying high-grade and low-grade bladder cancer based on ASL image

Abstract

The invention belongs to the field of intelligent medical treatment, and particularly relates to a method, equipment and medium for identifying high-grade and low-grade bladder cancer based on an ASL image, and the method comprises the following steps: S101, obtaining an ASL image of a bladder cancer patient; s102, extracting the ASL image to obtain the bladder blood flow, wherein the bladder blood flow is the bladder blood flow of the maximum focus; s103, judging whether the bladder cancer patient is high-grade bladder cancer or low-grade bladder cancer based on the bladder blood flow, judging that the bladder cancer patient is high-grade bladder cancer when the bladder blood flow is greater than a threshold value, and judging that the bladder cancer patient is low-grade bladder cancer if not. According to the application, key elements in the ASL-MRI image, which can be used for diagnosis of high-level and low-level bladder cancer, are found, so that diagnosis of bladder cancer patients inapplicable to contrast agents can be realized, and judgment can be quickly and effectively realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medicine, and more particularly, to a method, device, medium and program product for differentiating high-grade and low-grade urothelial carcinoma based on ASL images. Background Art

[0002] Bladder cancer (BCa) is the most common malignant tumor of the urinary tract and one of the most common cancers globally. According to histological differences, BCa is divided into low-grade or high-grade tumors. Differentiating between low-grade and high-grade bladder cancer is crucial for the diagnosis and treatment decisions of each individual. High-grade BCa has a higher recurrence rate and is more likely to progress to muscle invasion. Patients with low-grade BCa can choose prophylactic chemotherapy after transurethral resection. High-grade BCa is usually treated with radical cystectomy and requires additional intravenous injection of Bacillus Calmette-Guérin for 1-3 years.

[0003] Various contemporary techniques for detecting BCa include imaging techniques such as ultrasound (US), CT, MRI, positron emission tomography-CT (PET / CT), as well as cystoscopy, biopsy, and cytology. The treatment of BCa depends largely on the pathological grade, but cystoscopy and biopsy sometimes lead to misjudgment. CT is currently still the preferred imaging examination method for suspected BCa due to its short scanning time, relatively low contraindications, and cost-effectiveness. Multiparametric MRI is also widely used for the diagnosis and follow-up of BCa due to its high soft tissue resolution. Dynamic contrast-enhanced (DCE)-MRI can evaluate the tumor enhancement and perfusion patterns. However, both CT and MRI require contrast agents when evaluating BCa, which may not be applicable to some patients. For example, BCa mainly occurs in elderly patients, and due to poor renal function, some elderly patients are prohibited from using contrast agents.

[0004] Arterial spin labeling (ASL) is a non-invasive MRI technique that can provide quantitative perfusion values without exogenous contrast agents. ASL has been widely used in brain MRI and is gradually being used in other organs. So far, there have been few studies on the application of ASL technology in BCa, and we hope to explore a diagnostic method for BCa in elderly patients who are prohibited from using contrast agents. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method for differentiating high-grade and low-grade bladder cancer based on ASL images, which uses the quantitative bladder blood flow in ASL images to differentiate the grade of bladder cancer.

[0006] This application (the first aspect) discloses a method for differentiating high-grade and low-grade bladder cancer based on ASL images, including:

[0007] S101: Obtain the ASL image of a bladder cancer patient; S102: Extract the bladder blood flow from the ASL image, where the bladder blood flow is the bladder blood flow of the largest lesion; S103: Based on the bladder blood flow, determine whether the bladder cancer patient has high-grade bladder cancer or low-grade bladder cancer. If the bladder blood flow is greater than the threshold, it is determined as high-grade bladder cancer; otherwise, it is determined as low-grade bladder cancer.

[0008] Further, the method for obtaining the bladder blood flow is as follows: Obtain the axial ASL image and the coronal ASL image of the bladder cancer patient respectively, extract the bladder blood flow of the axial ASL image of the largest lesion and the bladder blood flow of the coronal ASL image respectively, and calculate the average value to obtain the bladder blood flow.

[0009] Further, the threshold is the value corresponding to the optimal balance point selected from the ROC curve for judging high-grade bladder cancer and low-grade bladder cancer based on the bladder blood flow as the threshold.

[0010] Further, S103 is replaced by S103': Input the bladder blood flow into a classifier for classification, and judge whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier.

[0011] Further, the classifier includes one or more of the following: logistic regression, random forest, support vector machine, XGboost, decision tree, extreme learning machine.

[0012] Further, the method further includes: Obtain the DCE-MRI image of the bladder cancer patient, and extract from the DCE-MRI image and input the bladder blood flow and into a classifier for classification, and judge whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier.

[0013] Further, the method further includes: Obtain the clinical characteristics of the bladder cancer patient, where the clinical characteristics include one or more of the following: whether there is muscle invasion, Ki-67, Her-2 type. Input the bladder blood flow and the clinical characteristics into a classifier for classification, and judge whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier.

[0014] This application also discloses a method for differentiating high-grade and low-grade bladder cancer based on DCE-MRI images, which is characterized in that the method includes: Obtain the DCE-MRI image of the bladder cancer patient; Extract from the DCE-MRI image ; Based on Determine whether the bladder cancer patient has high-grade bladder cancer or low-grade bladder cancer. If the blood flow of the bladder is greater than the threshold, it is determined as high-grade bladder cancer; otherwise, it is determined as low-grade bladder cancer.

[0015] Furthermore, the method further includes: simultaneously acquiring the ASL image of the bladder cancer patient; extracting the blood flow of the bladder from the ASL image, where the blood flow of the bladder is the blood flow of the largest lesion; and inputting the blood flow of the bladder and into a classifier for classification, and determining whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier.

[0016] The second aspect of the present application discloses a system for differentiating high-grade and low-grade bladder cancer based on ASL images, including:

[0017] An acquisition module: used to acquire the ASL image of the bladder cancer patient; an extraction module: used to extract the blood flow of the bladder from the ASL image, where the blood flow of the bladder is the blood flow of the largest lesion; a decision module: used to determine whether the bladder cancer patient has high-grade bladder cancer or low-grade bladder cancer based on the blood flow of the bladder. If the blood flow of the bladder is greater than the threshold, it is determined as high-grade bladder cancer; otherwise, it is determined as low-grade bladder cancer.

[0018] The third aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the above method.

[0019] The fourth aspect of the present application discloses a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it realizes the steps of the above method.

[0020] The fifth aspect of the present application discloses a computer program product, including a computer program, and when the computer program is executed by a processor, it realizes the steps of the above method.

[0021] The present application has the following beneficial effects: (1) The present application discovers the key elements in ASL-MRI images that can be used for the diagnosis of high-grade and low-grade bladder cancer, thereby realizing the rapid and effective determination of the diagnosis of bladder cancer patients who are not suitable for contrast agents;

[0022] (2) In the present application, by averaging the BBF of ASL in two directions, more accurate diagnosis is achieved. Description of the Drawings

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0024] Figure 1 It is a schematic flowchart of the method provided in the first aspect of the embodiments of the present invention;

[0025] Figure 2 It is a schematic diagram of the program product provided in the second aspect of the embodiments of the present invention;

[0026] Figure 3 It is a schematic diagram of the computer device provided in the embodiments of the present invention;

[0027] Figure 4 It is a schematic diagram of the architecture of the exemplary computing device provided in the embodiments of the present invention;

[0028] Figure 5 It is a schematic diagram of the storage medium provided in the embodiments of the present invention;

[0029] Figure 6 It is a schematic diagram of the T2W1 image and the corresponding ASL-MRI image provided in the embodiments of the present invention. Among them, Figure A is the T2W1 image of high-grade Bca with muscle invasion, and Figure D is the ASL-MRI image of the corresponding patient; Figure B is the T2W1 image of high-grade BCa without muscle invasion, and Figure E is the ASL-MRI image of the corresponding patient; Figure C is the T2W1 image of low-grade Bca without muscle invasion, and Figure F is the ASL-MRI image of the corresponding patient;

[0030] Figure 7 It is the correlation schematic diagram of BBF and in the present invention;

[0031] Figure 8 It is a schematic diagram of the axial and coronal T2W1 images and the corresponding ASL-MRI images of an image provided in the embodiments of the present invention;

[0032] Figure 9 It is a schematic diagram of the axial and coronal T2W1 images and the corresponding ASL-MRI images of another image provided in the embodiments of the present invention; Detailed implementation manners

[0033] To enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention.

[0034] In some of the processes described in the specification, claims, and above-mentioned drawings of the present invention, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as S101, S102, 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 such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are different types.

[0035] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0036] Figure 1 is a schematic flow chart of a method based on evaluating PATENTNAME provided by an embodiment of the present invention. Specifically, the method includes the following steps:

[0037] S101: Obtain the ASL image of a bladder cancer patient;

[0038] S102: Extract the bladder blood flow from the ASL image, and the bladder blood flow is the bladder blood flow of the largest lesion;

[0039] S103: Based on the bladder blood flow, determine whether the bladder cancer patient has high-grade bladder cancer or low-grade bladder cancer. If the bladder blood flow is greater than the threshold, it is determined as high-grade bladder cancer, otherwise it is determined as low-grade bladder cancer.

[0040] In some embodiments, 29 patients (20 males, mean age: 68 ± 9 years [range: 50 - 83 years]) were consecutively recruited in this prospective study. The inclusion criteria were BCa patients with a first diagnosis or recurrence after TURBT and a lesion diameter > 1 cm. The exclusion criteria were patients with a lesion diameter < 1 cm. A total of 20 patients received bladder DCE-MRI within 1 week before the study. All patients underwent bladder ASL scans on a 3T MRI system (MAGNETOM Vida, Siemens Healthineers, Erlangen, Germany). Patients were required to empty their bladders 30 - 60 minutes before the examination and then drink approximately 500 ml of water. Axial and coronal T2-weighted reference images were obtained (Figure 8 , Figure 9 as shown in Figure 9 , and then ASL-MRI was performed on the target lesion on two planes. A three-dimensional TGSE research sequence with a pseudo-continuous ASL protocol was used to obtain ASL data with the following parameters: TR / TE, 5000.00 ms / 25.80 ms; post-labeling delay, 1500 ms; TI, 3000 ms; field of view, 300×150 mm 2 ; voxel size, 2.3×2.3×4.0 mm 3 ; T1 blood, 1200 ms; The acquisition time was 5 minutes and 5 seconds. After data acquisition, a quantitative bladder blood flow (BBF) map was generated online.

[0041] The ASL data in both directions of all patients were tissue- and randomized. A radiologist with 3 years of experience and unaware of the sequence information independently delineated each region of interest and measured the BBF at the maximum lesion level. Each sequence was measured twice and the average value was taken. The final BBF value for BCa in each patient was the average BBF in both directions.

[0042] For 20 patients with DCE sequences, the quantitative parameters of DCE-MRI were measured using GenIQ software , and the pathological and immunohistochemical results of the patients were collected. Spearman correlation analysis was used to evaluate the correlation between BBF and the correlation between.

[0043] The Mann-Whitney U test was used to analyze whether there were differences in BBF values between the pathological group and the immunohistochemical group (high grade / low grade, with / without muscle invasion, Ki-67 [cut-off value, 25%] and Her-2 type). A two-sided P<0.05 was considered significant.

[0044] Results: Among 29 patients, 26 had focal bladder lesions and 3 had diffuse thickening of the bladder wall. Pathological results were available for 27 patients: 14 had muscle invasion; 13 had non-muscle invasion; 15 had high-grade urothelial carcinoma and 8 had low-grade urothelial carcinoma, among which Figure 6 showed schematic images of some patients: among which Figure 6 A and 6D were the T2W1 image and ASL image of a high-grade urothelial tumor with muscle invasion (BBF = 189.00 mL / [100 mL*min]), respectively; Figure 6 B and Figure 6E is the T2W1 image and ASL image of high-grade urothelial tumors without muscle invasion (BBF = 40.08 (mL / [100mL*min]); Figure 6 C and Figure 6 F are the T2W1 image and ASL image of low-grade urothelial tumors without muscle invasion (BBF = 29.60 (mL / [100 mL*min]).

[0045] BBF is moderately positively correlated with (r = 0.632, P = 0.003) ( Figure 7 as shown). The BBF values in the high-grade urothelial carcinoma, muscle invasion, and Ki-67>25% groups were significantly higher than those in the low-grade urothelial carcinoma, non-muscle invasion, and Ki-67≤25% groups (P = 0.004, 0.001, and 0.048, respectively). The BBF values varied according to Her-2 type (0 / 1+ vs. 2+ / 3+ and 0 / 1+ / 2+ vs. 3+; P = 0.161 and 0.930, respectively). Table 1 lists the detailed results.

[0046] Table 1. Results of the analysis of BBF differences between subgroups

[0047]

[0048] BBF numbers are median (interquartile range).

[0049] Discussion and conclusion: We prospectively investigated the value of ASL in the evaluation of BCa. BBF and are moderately positively correlated. Our results suggest that the BBF parameter of ASL can be used to evaluate BCa because it provides a reproducible and quantitative measurement of tumor perfusion and is correlated with pathological and immunohistochemical indices. In addition, ASL reduces the need for contrast agents, additional equipment, and personnel, potentially making ASL an equivalent and more cost-effective alternative to DCE-MRI.

[0050] Based on the above research results, the present application established the following prediction model:

[0051] In some embodiments, a predictive ROC curve was obtained based on the predictive relationship between BBF and high- and low-grade bladder cancer, with an AUC value of 0.833, a sensitivity of 0.83, a specificity of 0.73, and a cutoff value of 40.

[0052] In some embodiments, based on The predictive ROC curve was obtained for the predictive relationship with high- and low-grade bladder cancer, with an AUC value of 0.867, a sensitivity of 0.80, a specificity of 0.875, and a cutoff value of 0.95.

[0053] In some embodiments, the input features of the machine learning model are the patient's BBF, , and the label is the high or low grade of the patient's bladder cancer. After training, a second classifier is obtained (AUC: 0.975; sensitivity: 0.87; specificity: 1). The BBF of a new bladder cancer patient, is input into the second classifier to obtain the grade of the patient's bladder cancer.

[0054] In some embodiments, the input features of the machine learning model are the patient's BBF, , Ki-67, and the label is the high or low grade of the patient's bladder cancer. After training, a third classifier is obtained (accuracy AUC: 1; sensitivity: 1; specificity: 1). The BBF of a new bladder cancer patient, is input into the third classifier to obtain the grade of the patient's bladder cancer.

[0055] In some embodiments, the input features of the machine learning model are the patient's BBF, , Ki-67, Her-2 type, and whether there is muscle invasion, and the label is the high or low grade of the patient's bladder cancer. After training, a fourth classifier is obtained. The BBF of a new bladder cancer patient, is input into the fourth classifier to obtain the grade of the patient's bladder cancer.

[0056] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention. As Figure 3 shown, the device 2000 may include: one or more processors 2010 and one or more memories 2020; wherein, computer-readable code is stored in the memory, and when the computer-readable code is run by the one or more processors, the methods described above can be executed.

[0057] The processor in this embodiment may be an integrated circuit chip with signal processing capabilities. The above processor may 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 gate or transistor logic devices, discrete hardware components. The various methods, operations, and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., and may be of the X86 architecture or the ARM architecture.

[0058] In general, the various example embodiments of the present disclosure may be implemented in hardware or dedicated circuits, software, firmware, logic, or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device. When aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein may be implemented as non-limiting examples in hardware, software, firmware, dedicated circuits or logic, general hardware or a controller or other computing device, or some combination thereof.

[0059] For example, the method or apparatus according to the embodiments of the present disclosure may also be implemented by means of Figure 4 the architecture of the computing device 3000 shown. As Figure 4 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, input / output components 3060, a hard disk 3070, etc. The storage device in the computing device 3000, such as the ROM 3030 or the hard disk 3070, may store various data or files used for the processing and / or communication of the method provided by the present disclosure and the 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 when implementing different devices, one or more components shown in the Figure 4 computing device may be omitted according to actual needs.

[0060] The embodiments of the present invention also provide a computer-readable storage medium, such as Figure 5As shown, it is a schematic diagram of a storage medium 4000 provided by an embodiment of the present invention. Computer-readable instructions 4010 are stored on the computer storage medium 4020. When the computer-readable instructions 4010 are run by a processor, the methods according to the embodiments of the present disclosure described with reference to the above figures can be executed. The computer-readable storage medium in the embodiments 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 but 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 (DDR SDRAM), 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 memories for the methods described herein are intended to include, but are not limited to, these and any other suitable types of memories. It should be noted that the memories for the methods described herein are intended to include, but are not limited to, these and any other suitable types of memories.

[0061] The embodiments of the present disclosure also provide a computer program product or a computer program. When the computer program is executed by a processor, the steps of the above method are implemented, as Figure 2 shown. The computer program product or the computer program includes: an acquisition module 201: configured to acquire ASL images of bladder cancer patients;

[0062] an extraction module 202: configured to extract the bladder blood flow from the ASL images, where the bladder blood flow is the bladder blood flow of the largest lesion;

[0063] a decision module 203: configured to determine whether the bladder cancer patient has high-grade bladder cancer or low-grade bladder cancer based on the bladder blood flow. When the bladder blood flow is greater than a threshold, it is determined as high-grade bladder cancer; otherwise, it is determined as low-grade bladder cancer.

[0064] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of 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 blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0065] In general, the various example embodiments of the present disclosure can be implemented in hardware or a dedicated circuit, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software that can be executed by a controller, a microprocessor, or other computing devices. When aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it will be understood that the blocks, devices, systems, techniques, or methods described herein can be implemented as non-limiting examples in hardware, software, firmware, a dedicated circuit or logic, general hardware or a controller or other computing devices, or some combination thereof.

[0066] 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 foregoing method embodiments, and will not be elaborated herein.

[0067] 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 merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, 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 couplings or direct couplings or communication connections shown or discussed with each other can be indirect couplings or communication connections through some interfaces, devices, or units, and can be in electrical, mechanical, or other forms.

[0068] The unit described as a separation component may or may not be physically separated. The component presented as a unit may or may not be a physical unit, that is, it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0069] In addition, in each embodiment of the present invention, each functional unit may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0070] The exemplary embodiments of the present disclosure described in detail above are merely illustrative and not restrictive. Those skilled in the art should understand that various modifications and combinations can 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 differentiating high - grade and low - grade bladder cancer based on ASL images, characterized in that, The method includes: S101: Obtain the ASL image of a bladder cancer patient; S102: Extract the bladder blood flow from the ASL image, where the bladder blood flow is the bladder blood flow of the largest lesion; S103: Based on the bladder blood flow, determine whether the bladder cancer patient has high-grade bladder cancer or low-grade bladder cancer. If the bladder blood flow is greater than the threshold, it is determined as high-grade bladder cancer; otherwise, it is determined as low-grade bladder cancer.

2. The method for differentiating high-grade and low-grade bladder cancer based on ASL images according to claim 1, wherein The method for obtaining the bladder blood flow is as follows: Obtain the ASL images of a bladder cancer patient in at least two orientations. Based on the ASL images in the at least two orientations, extract the bladder blood flows of the largest lesions in the at least two orientations respectively, and calculate the average value of the bladder blood flows of the largest lesions in the at least two orientations to obtain the bladder blood flow. The orientation is any one of the following: axial, sagittal, and coronal; Optionally, obtain the axial ASL image and the coronal ASL image of a bladder cancer patient, extract the bladder blood flow of the axial ASL image of the largest lesion and the bladder blood flow of the coronal ASL image of the largest lesion respectively, and calculate the average value to obtain the bladder blood flow.

3. The method for differentiating high-grade and low-grade bladder cancer based on ASL images according to claim 1, wherein The threshold is the value corresponding to the optimal balance point selected by the ROC curve for judging high-grade bladder cancer and low-grade bladder cancer based on the bladder blood flow.

4. The method for differentiating high-grade and low-grade bladder cancer based on ASL images according to claim 1, wherein S103 is replaced with S103': Input the bladder blood flow into a classifier for classification, and determine whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier; Optionally, the classifier includes one or more of the following: logistic regression, random forest, support vector machine, XGboost, decision tree, extreme learning machine; Optionally, the method further includes: obtaining a DCE-MRI image of a bladder cancer patient, and extracting from the DCE-MRI image , and inputting the bladder blood flow and into a classifier for classification, and judging whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier.

5. The method for differentiating high-grade and low-grade bladder cancer based on ASL images according to claim 4, wherein, The method further includes: Obtain the clinical features of a bladder cancer patient. The clinical features include one or more of the following: whether there is muscle invasion, Ki-67, Her-2 type. Input the bladder blood flow and the clinical features into a classifier for classification, and determine whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier.

6. A method for differentiating high-grade and low-grade bladder cancer based on DCE-MRI images, characterized in that, The method includes: Obtain the DCE-MRI image of a bladder cancer patient; The DCE-MRI images are extracted to obtain ; Based on Determine whether the bladder cancer patient has high-grade bladder cancer or low-grade bladder cancer. If the blood flow in the bladder is greater than the threshold, it is determined as high-grade bladder cancer; otherwise, it is determined as low-grade bladder cancer.

7. The method for differentiating high-grade and low-grade bladder cancer based on DCE-MRI images according to claim 6, wherein, The method further includes: simultaneously acquiring the ASL image of a bladder cancer patient; extracting the bladder blood flow from the ASL image, where the bladder blood flow is the bladder blood flow of the largest lesion; and inputting the bladder blood flow into a classifier for classification, and judging whether the patient has high-grade bladder cancer or low-grade bladder cancer according to the output of the classifier.

8. A computer device, characterized in that, The device includes: 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 1-7.

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, it implements the steps of the method according to any one of claims 1-7.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images