Microcirculation resistance value obtaining method and device and operation planning method

Abstract

The invention relates to a microcirculation resistance value obtaining method and device and an operation planning method. The method comprises the following steps: acquiring first medical image data and portal vein circulation models of one or more training objects; iterating the microcirculation resistance value in the portal vein circulation model until the similarity between the portal vein circulation model and the portal vein of the training object meets a preset condition, and obtaining a first microcirculation resistance value of the training object; according to the first microcirculation resistance value and the corresponding first medical image data, training to obtain a mapping relation between the microcirculation resistance value and the medical image data; and obtaining a second microcirculation resistance value of the target object based on the mapping relation and the second medical image data of the target object. By adopting the method, an accurate microcirculation resistance value can be obtained, so that the TIPS surgical planning precision is improved.

Description

Technical Field

[0001] This application relates to the field of medical measurement, and in particular to methods, devices, and surgical planning methods for obtaining microcirculation resistance values. Background Technology

[0002] Portal hypertension (Portosystemic hypertension) is one of the most serious syndromes caused by chronic liver disease and a significant manifestation of cirrhosis. It can be treated with TIPS (Transjugular Intrahepatic Portosystemic Shut). In TIPS, the internal jugular vein is used as the puncture site. A catheter is inserted through the superior vena cava, right atrium, and inferior vena cava into the hepatic vein. Under X-ray guidance, the catheter is punctured into the intrahepatic vein. After dilating the liver parenchyma between the two veins, a stent is implanted to create an artificial shunt between the hepatic vein and the portal vein, allowing portal vein blood flow to be directly diverted to the inferior vena cava. This reduces portal vein pressure and treats conditions such as variceal bleeding and refractory ascites associated with portal hypertension. The choice of puncture path and stent size in TIPS affects postoperative portal blood pressure and shunt flow; therefore, the puncture path and stent size must be planned based on the portal hypertension level before performing the procedure.

[0003] The relevant technology employs deep learning algorithms to identify imaging changes that occur after a period of time due to portal hypertension, such as portal vein dilation and imaging features related to gastric fundus varices, and derives portal vein pressure based on these image features. However, the direct cause of portal hypertension is increased hepatic microcirculatory resistance. Specifically, liver fibrosis and cirrhosis cause endothelial dysfunction, leading to intrahepatic vasoconstriction and thrombosis in the portal vein and hepatic vein microcirculation, resulting in increased microcirculatory resistance and thus triggering portal hypertension.

[0004] While related technologies determine portal vein pressure based on image features, they fail to consider the crucial role of microcirculatory resistance, resulting in low accuracy in preoperative planning for TIPS procedures. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, and surgical planning method for obtaining microcirculation resistance values ​​that can solve the problem of low preoperative planning accuracy in TIPS surgery, in order to address the aforementioned technical issues.

[0006] Firstly, this embodiment provides a method for obtaining microcirculation resistance values, the method comprising:

[0007] Acquire first medical imaging data and portal vein circulation models for one or more training subjects;

[0008] Iterate the microcirculation resistance value in the portal vein circulation model until the similarity between the portal vein circulation model and the vein of the training object meets the preset condition, and obtain the first microcirculation resistance value of the training object;

[0009] Based on the first microcirculation resistance value and the corresponding first medical image data, a mapping relationship between the microcirculation resistance value and the medical image data is trained.

[0010] Based on the mapping relationship and the second medical imaging data of the target object, the second microcirculation resistance value of the target object is obtained.

[0011] In some embodiments, iterating over the microcirculatory resistance values ​​in the portal vein circulation model includes:

[0012] The portal vein circulation model is coupled and connected to the resistor unit and the capacitor unit;

[0013] Iterate over the resistance value of the resistor unit and / or the capacitance value of the capacitor unit.

[0014] In some embodiments, each branch of the target vein in the portal vein circulation model is connected to different resistive and capacitive units, and the portal vein circulation model is coupled with the resistive and capacitive units to form a closed loop.

[0015] In some embodiments, iterating over the microcirculatory resistance values ​​in the portal vein circulation model includes:

[0016] Obtain the portal vein blood flow characteristic values ​​of the training object;

[0017] With the portal vein blood flow characteristic value used as the solution condition for the portal vein circulation model, the microcirculation resistance value in the portal vein circulation model is iterated.

[0018] In some embodiments, obtaining portal vein blood flow feature values ​​of the training object includes:

[0019] Acquire the mapping relationship between medical imaging data and / or preset physiological indicators and venous blood flow characteristics;

[0020] Based on the mapping relationship, portal vein blood flow feature values ​​corresponding to the preset physiological indicators of the first medical imaging data and / or the training object are obtained.

[0021] Secondly, this embodiment provides a surgical planning method, the method comprising:

[0022] A portal vein circulation model of the target object is obtained, wherein the microcirculation resistance value of the portal vein circulation model of the target object is calculated according to the microcirculation resistance value acquisition method described in the first aspect above;

[0023] Based on the portal vein circulation model, simulations of various surgical procedures were performed to obtain the venous blood pressure and venous blood shunt flow rate of the portal vein circulation model after the surgery. Among them, there are one or more distinguishing features between different surgical procedures: the puncture site, puncture path, and stent type of the portal vein circulation model.

[0024] Based on the venous blood pressure and the venous blood shunt flow rate, the target surgical method is selected from the multiple surgical methods.

[0025] In some embodiments, a target surgical approach is selected from the multiple surgical approaches based on the venous blood pressure and the venous blood shunt flow rate, including:

[0026] When the venous blood pressure and the venous blood shunt flow rate meet the set thresholds, the current surgical procedure is taken as the target surgical procedure.

[0027] Thirdly, this embodiment provides a microcirculation resistance value acquisition device, the device comprising:

[0028] The acquisition module is used to acquire the first medical image data and portal vein circulation model of one or more training subjects;

[0029] An iterative module is used to iterate the microcirculation resistance value in the portal vein circulation model until the similarity between the portal vein circulation model and the portal vein of the training object meets a preset condition, thereby obtaining the first microcirculation resistance value of the training object.

[0030] The training module is used to train a mapping relationship between the microcirculation resistance value and the corresponding medical image data based on the first microcirculation resistance value and the first medical image data.

[0031] The calculation module is used to obtain the second microcirculation resistance value of the target object based on the mapping relationship and the second medical imaging data of the target object.

[0032] Fourthly, this embodiment provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the microcirculation resistance value acquisition method described in the first aspect above.

[0033] Fifthly, this embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the microcirculation resistance value acquisition method described in the first aspect above.

[0034] The aforementioned method, device, and surgical planning method for obtaining microcirculatory resistance values, through iterative portal vein circulation modeling, obtains an accurate first microcirculatory resistance value. Using this first microcirculatory resistance value as the gold standard, a mapping relationship between microcirculatory resistance and medical imaging data is trained. Based on this mapping relationship and the target subject's second medical imaging data, a personalized and accurate second microcirculatory resistance value can be obtained for the target subject. Since microcirculatory resistance is the direct cause of portal hypertension, accurate microcirculatory resistance values ​​can accurately assess the target subject's portal hypertension symptoms, thereby improving the planning accuracy of TIPS surgery for treating portal hypertension. Attached Figure Description

[0035] Figure 1 This is an application environment diagram of a method for obtaining microcirculation resistance values ​​in one embodiment;

[0036] Figure 2 This is a flowchart illustrating a method for obtaining microcirculation resistance values ​​in one embodiment;

[0037] Figure 3 This is a schematic diagram of the portal vein circulation model in one embodiment;

[0038] Figure 4 This is a flowchart illustrating a surgical planning method in one embodiment;

[0039] Figure 5 This is a flowchart illustrating the TIPS surgical planning method in one embodiment;

[0040] Figure 6 This is a structural block diagram of a microcirculation resistance value acquisition device in one embodiment;

[0041] Figure 7 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0043] To achieve precise planning for TIPS (Transient Intra-Intended Procedural Procedure), portal vein pressure measurement is necessary. Currently, most methods for assessing portal hypertension involve invasive procedures. These invasive methods, based on interventional consumables, are difficult to apply to patients suspected of having portal hypertension, preventing early-stage TIPS planning. The mainstream non-invasive assessment of portal hypertension primarily employs deep learning algorithms, directly training HVPG (Hepatic Venous Pressure Gradient) regression or classification models based on medical images. Deep learning algorithms often identify imaging features that result from changes in portal hypertension over time, such as portal vein dilation and gastric varices. However, these features are not present in some early-stage patients, leading to inaccurate measurements and consequently, low precision in TIPS planning.

[0044] This embodiment provides a method for obtaining microcirculatory resistance values. Since increased microcirculatory resistance is a direct cause of portal hypertension, accurate microcirculatory resistance values ​​allow for precise planning of TIP (Transurethral Incision Procedure) surgery.

[0045] The method for obtaining microcirculation resistance values ​​provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located on a cloud or other network server. The data storage system can be used to store data such as first medical image data, second medical image data, and the mapping relationship between microcirculation resistance values ​​and medical image data. Based on terminal 102, or the interaction between terminal 102 and server 104, the data stored in the data storage system is obtained, and the microcirculation resistance value acquisition method in this embodiment is executed. Terminal 102 can be, but is not limited to, various personal computers, laptops, and tablets. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0046] In one embodiment, such as Figure 2 As shown, a method for obtaining microcirculation resistance values ​​is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0047] Step S202: Obtain first medical image data and portal vein circulation model of one or more training subjects.

[0048] The training subjects included patients with symptoms of portal hypertension, and the first medical imaging data included data on the venous regions of each subject with portal hypertension. The venous region data in the first medical imaging data corresponded to the portal venous circulation model.

[0049] The portal vein circulation model includes the structures of the portal vein and hepatic portal vein, used to simulate the real-world conditions of the portal vein and hepatic portal vein in the training subjects. Optionally, multiple patients with different symptoms of portal hypertension are selected as training subjects. Medical images of the venous regions with portal hypertension in each training subject are obtained through ultrasound, magnetic resonance imaging, etc., to obtain the first medical imaging data and establish the portal vein circulation model.

[0050] Step S204: Iterate the microcirculation resistance value in the portal vein circulation model until the similarity between the portal vein circulation model and the vein of the training object meets the preset condition, and obtain the first microcirculation resistance value of the training object.

[0051] The preset conditions are used to indicate that the portal hypertension symptoms of the iterated portal vein circulation model are similar to those of the training subjects, and that the first microcirculatory resistance value in the iterated portal vein circulation model tends to be consistent with the actual microcirculatory resistance value of the training subjects. Optionally, iterating the microcirculatory resistance value in the portal vein circulation model includes: iterating the microcirculatory resistance value in the portal vein circulation model by modifying the parameters in the portal vein circulation model; or, coupling the portal vein circulation model with a circuit model, and assisting the portal vein circulation model in iterating the microcirculatory resistance value by modifying the parameters in the circuit model.

[0052] Optionally, the veins of the portal vein circulation model and the veins of the training object are compared. If the relative error between the veins of the portal vein circulation model and the veins of the training object is less than a specified threshold, the similarity between the veins of the portal vein circulation model and the veins of the training object is determined to meet a preset condition. The specified threshold can be set based on application requirements; a smaller threshold indicates higher calculation accuracy, and vice versa.

[0053] Optionally, medical image data of the veins of the training object and / or vein features of the training object are obtained. If the similarity between the image data presented by the portal vein circulation model and the medical image data of the training object is greater than a specified threshold, and / or if the similarity between one or more vein features in the portal vein circulation model and one or more real vein features of the training object is greater than a specified threshold, it is determined that the similarity between the veins of the portal vein circulation model and the training object meets the preset conditions.

[0054] Step S206: Based on the first microcirculation resistance value and the corresponding first medical image data, train to obtain the mapping relationship between the microcirculation resistance value and the medical image data.

[0055] Optionally, the first microcirculation resistance value can be used as the gold standard to train a pre-defined function or model, enabling the function or model to accurately output the corresponding medical image data based on the microcirculation resistance value. Alternatively, image features such as signal intensity and texture can be extracted from MR images to establish a multiple linear or nonlinear regression model for predicting microcirculation resistance, and this regression model can be used as a pre-defined model for prediction. Alternatively, machine learning regression algorithms such as support vector regression can be used for prediction to obtain the corresponding medical image data. Furthermore, MR images can be used as input to train a deep learning-based regression prediction model, which then outputs medical image data corresponding to the microcirculation resistance.

[0056] Step S208: Based on the mapping relationship and the second medical imaging data of the target object, the second microcirculation resistance value of the target object is obtained.

[0057] The target population consists of patients requiring TIPS surgery planning. The second medical imaging data includes venous areas in the target population with portal hypertension, which can be obtained through ultrasound, MRI, or other methods. Optionally, based on a mapping relationship, the microcirculatory resistance value associated with the target population's second medical imaging data is obtained, thus yielding the target population's second microcirculatory resistance value.

[0058] In the aforementioned method for obtaining microcirculatory resistance values, the microcirculatory resistance values ​​of the portal vein circulation model are iterated. Since elevated portal vein pressure is mainly caused by an increase in microcirculatory resistance, when the portal vein circulation model and the veins of the training subject are similar, the portal hypertension symptoms in the portal vein circulation model are similar to the actual portal hypertension symptoms of the training subject. At this point, the first microcirculatory resistance value of the portal vein circulation model can be inferred to be an accurate microcirculatory resistance value. Based on the accurate first microcirculatory resistance, an accurate mapping relationship between microcirculatory resistance and medical imaging data can be trained, allowing for a more accurate second microcirculatory resistance value to be obtained based on the mapping relationship and the second medical imaging data of the target subject. With an accurate second microcirculatory resistance value obtained, the portal hypertension symptoms of the target subject can be accurately determined, thereby achieving precise planning of TIP surgery and solving the problem of low accuracy in TIP surgery planning.

[0059] Furthermore, related technologies often rely on interventional consumables for invasive measurement of portal vein pressure. Invasive measurement methods are difficult to apply to early-stage suspected portal hypertension patients, making it difficult to detect and intervene in portal hypertension in its early stages. Many patients with portal hypertension only receive intervention after a considerable period of illness. In this embodiment, after training to obtain the mapping relationship between microcirculatory resistance values ​​and medical imaging data, only a second set of medical imaging data of the target subject with portal hypertension symptoms is needed to non-invasively obtain the target subject's microcirculatory resistance value. This method is applicable to patients with portal hypertension in the early, middle, and late stages simultaneously.

[0060] In one embodiment, iterating the microcirculatory resistance value in the portal vein circulation model includes: coupling the portal vein circulation model to resistive and capacitive units; and iterating the resistance value of the resistive unit and / or the capacitance value of the capacitive unit. The capacitive unit is a collection of one or more capacitors; the resistive unit is a collection of one or more resistors. The capacitive and resistive units are used to simulate microcirculatory resistance. The portal vein circulation model is a hemodynamic model used to simulate the portal vein and hepatic portal vein of the training subject. Optionally, the portal vein circulation model includes a mutually coupled portal vein circulation model, a hepatic portal vein circulation model, and a microcirculatory model composed of resistive and capacitive units.

[0061] Optionally, in the portal vein circulation model, each branch of the target vein is connected to different resistive and capacitive units, thus coupling the portal vein circulation model with the resistive and capacitive units to form a closed loop. The target vein is the vein associated with portal hypertension.

[0062] Optionally, constructing the portal vein circulation model includes: obtaining a portal vein circulation model and a hepatic portal vein circulation model based on the first medical imaging data; acquiring a microcirculation model composed of resistive and capacitive units; the resistance and capacitance values ​​of the corresponding resistive and capacitive units are determined by the actual microcirculation resistance of the training object and the size of the portal vein branches; acquiring the resistance and capacitance values ​​includes: changing the resistance and / or capacitance values, and, if the similarity between the portal vein circulation model and the veins of the training object meets preset conditions, determining that the microcirculation resistance simulated by the circuits containing the resistive and capacitive units matches the actual microcirculation resistance of the training object, and stopping the adjustment of the capacitive and resistive units; and coupling the three models—the portal vein circulation model, the hepatic portal vein circulation model, and the microcirculation model composed of resistive and capacitive units—to obtain the portal vein circulation model.

[0063] Figure 3 This is a schematic diagram of a portal vein circulation model in this embodiment, as shown below. Figure 3As shown, in the portal vein circulation model, each branch of the target vein is connected to different resistor and capacitor units, thus coupling the portal vein circulation model with the resistor and capacitor units. Specifically, any end of a branch of the target vein is connected to the first end of the corresponding resistor unit and the first end of the corresponding capacitor unit, and the second end of each resistor unit and the second end of the capacitor unit are grounded. The resistor unit includes a resistor R_m, and the capacitor unit includes a capacitor C.

[0064] In this embodiment, by changing the resistance value of the resistor unit and / or the capacitance value of the capacitor unit, the microcirculation resistance value in the portal vein circulation model coupled with the resistor unit and the capacitor unit is iterated, so that the adjustment of the microcirculation resistance value is controllable, and the effect of accurately obtaining the first microcirculation resistance value can be achieved.

[0065] In order to improve the similarity between the portal vein circulation model and the veins of the training object through iteration, in one embodiment, iterating the microcirculation resistance value in the portal vein circulation model includes: obtaining the portal vein blood flow feature value of the training object; and iterating the microcirculation resistance value in the portal vein circulation model when the portal vein blood flow feature value is used as the solution condition of the portal vein circulation model.

[0066] The portal vein blood flow features of the training subjects include, but are not limited to, features such as the blood flow velocity and blood volume in the main venous trunk. Using these portal vein blood flow features as solution conditions for the portal vein circulation model means using them as initial parameters for iterating the model.

[0067] In this embodiment, by using the portal vein blood flow feature value as the solution condition for the portal vein circulation model, the portal vein blood flow feature value simulated by the portal vein circulation model during the iteration process is consistent with the actual blood flow feature value of the training object, so as to ensure that the iterated portal vein circulation model is similar to the real vein.

[0068] Optionally, obtaining portal vein blood flow feature values ​​of the training object includes: obtaining the mapping relationship between medical imaging data and / or preset physiological indicators and venous blood flow features; and obtaining portal vein blood flow feature values ​​corresponding to the first medical imaging data and / or preset physiological indicators of the training object based on the mapping relationship.

[0069] Medical imaging data includes, but is not limited to, venous data measured using methods such as PCMR (Phase Contrast Cine Magnetic Resonance) or ultrasound. Preset physiological indicators include those associated with venous blood flow characteristics, such as vein diameter and blood flow spectrum. By establishing a mapping relationship between medical imaging data and venous blood flow characteristics, or between preset physiological indicators and venous blood flow characteristics, or between medical imaging data and preset physiological indicators and venous blood flow characteristics, non-invasive acquisition of portal vein blood flow characteristic values ​​in training subjects can be achieved, reducing the damage caused by acquiring microcirculatory resistance values.

[0070] In one embodiment, obtaining a portal vein circulation model includes: performing image segmentation on first medical image data; and establishing a portal vein circulation model based on the image segmentation results of the first medical image data. Optionally, the first medical image data may be preprocessed first, and then a three-dimensional model may be constructed based on the image segmentation results of the first medical image data to obtain the portal vein circulation model.

[0071] Based on the same inventive concept, this application also provides a surgical planning method based on the microcirculation resistance value acquisition method mentioned above. Figure 4 A flowchart illustrating the surgical planning method, such as... Figure 4 As shown, the surgical planning methods include:

[0072] Step S402: Obtain the portal vein circulation model of the target object, wherein the microcirculation resistance value of the portal vein circulation model of the target object is calculated according to any of the above-described microcirculation resistance value acquisition method embodiments.

[0073] The portal vein circulation model of the target object is a model of the veins in which the target object has or is suspected of having portal hypertension. Optionally, second medical imaging data of the target object is acquired, and the portal vein circulation model of the target object is constructed based on the second medical imaging data.

[0074] Step S404: Simulate various surgical procedures based on the portal vein circulation model to obtain the venous blood pressure and venous blood shunt flow rate of the portal vein circulation model after the surgery. Among them, there are one or more distinguishing features between different surgical procedures: puncture site, puncture path, and stent type of the portal vein circulation model.

[0075] In each surgical procedure, the choice of puncture site, puncture path, and stent type all affect postoperative portal blood pressure and shunt flow. Insufficient shunt flow will prevent portal blood pressure from falling below a safe level, while excessive shunt flow may lead to hepatic encephalopathy. Therefore, venous blood pressure and venous shunt flow in the portal vein circulation model can be adjusted by modifying one or more of the characteristics of the puncture site, puncture path, and stent type in the surgical procedure.

[0076] Step S406: Based on venous blood pressure and venous blood shunt flow rate, select the target surgical method from multiple surgical options. The target surgical method is the surgical plan with the lowest shunt flow rate that can reduce the target patient's portal blood pressure to a safe level.

[0077] Optionally, based on venous blood pressure and venous blood shunt flow rate, a target surgical procedure can be selected from multiple surgical methods, including: when venous blood pressure and venous blood shunt flow rate meet a set threshold, the current surgical procedure is selected as the target surgical procedure. The set threshold can be modified according to actual application needs.

[0078] In one embodiment, another TIPS surgical planning method is provided. Figure 5 This is a flowchart illustrating the TIPS surgical planning method in this embodiment, as shown below. Figure 5 As shown, it includes the following steps:

[0079] Step S501: Assess hepatic microcirculatory resistance in a large number of patients.

[0080] Optionally, the patient's venous pressure characteristics are measured, and the patient's portal vein blood flow characteristics are measured using non-invasive methods such as PCMR or ultrasound. Venous pressure characteristics include, but are not limited to, portal blood pressure, hepatic venous pressure, and hepatic venous pressure gradient. Portal vein blood flow characteristics include, but are not limited to, portal vein trunk blood flow velocity or blood flow rate. The patient's venous pressure characteristics can be measured using invasive pressure guidewires or catheters, or they can be obtained through non-invasive measurements. Non-invasive measurement of the patient's venous pressure characteristics includes: acquiring medical imaging data, and / or, specified physiological indicators associated with the venous pressure characteristics. A non-invasive assessment model is obtained based on the mapping relationship between the medical imaging data and the specified physiological indicators. Based on the non-invasive assessment model, the portal vein blood flow characteristics corresponding to the patient's medical imaging data and / or specified physiological indicators are obtained.

[0081] Acquire enhanced CT (Computed Tomography) or MR (Magnetic Resonance) images of the patient's blood vessels. Based on the image segmentation results, establish a three-dimensional hemodynamic model including the patient's portal vein and hepatic vein structures. Couple the three-dimensional hemodynamic model with a zero-dimensional circuit model to obtain a coupled model, namely the portal vein circulation model in the above embodiment. The zero-dimensional circuit model includes at least one capacitor unit and at least one resistor unit.

[0082] The coupling model uses the patient's portal vein flow rate as the inlet boundary condition. By changing the resistance and / or capacitance values ​​in the circuit model, it iterates the microcirculatory resistance of the coupling model until the similarity between the portal vein circulation model and the veins of the training object meets a preset condition. At this point, the microcirculatory resistance value of the portal vein circulation model is the accurate microcirculatory resistance value of the patient. Specifically, iterating the microcirculatory resistance value in the portal vein circulation model of the training object until the similarity between the portal vein circulation model and the veins of the training object meets the preset condition includes: using the portal vein blood flow feature value as the inlet boundary condition of the portal vein circulation model, iterating the microcirculatory resistance value until the similarity between the venous pressure feature value of the portal vein circulation model and the venous pressure feature value of the training object reaches a preset value. For example, the inlet boundary condition is the portal vein flow rate, and the venous pressure feature value is HVPG.

[0083] The above method for obtaining microcirculation resistance values ​​was repeated on a large number of patients to obtain multiple microcirculation resistance values ​​and corresponding medical imaging data.

[0084] Step S502: An artificial intelligence model is trained based on a large number of patients' liver microcirculation resistance and image data, and the liver microcirculation resistance of a specified patient is assessed based on the artificial intelligence model.

[0085] A relevant artificial intelligence network model was designed, using the aforementioned accurate value of microcirculatory resistance as the gold standard. This model was trained based on liver MR images or ultrasound liver elastography to obtain a regression model that can quantitatively predict microcirculatory resistance values ​​based on image data related to the degree of liver fibrosis or cirrhosis. Liver MR images or ultrasound liver elastography data reflecting the degree of liver fibrosis or cirrhosis were collected from specified patients. Based on the trained regression model and the liver MR images or ultrasound liver elastography data reflecting the degree of liver fibrosis or cirrhosis from specified patients, the liver microcirculatory resistance value for the specified patients was obtained.

[0086] Step S503: Plan TIPS surgery based on the individualized liver microcirculation resistance of the specified patient.

[0087] Based on the regression model trained in step S502 and the data from a specified patient reflecting the degree of liver fibrosis or cirrhosis, the hepatic microcirculatory resistance value for that patient is obtained. A coupled model for the specified patient is constructed using the same method as in step S501. The hepatic microcirculatory resistance value of the specified patient is used as the microcirculatory resistance parameter in the coupled model. Based on the coupled model of the specified patient, virtual surgical models are created at different puncture sites and pathways, and shunt stents of different sizes are placed. Simulation calculations are performed on different virtual surgical models to obtain predicted values ​​of postoperative portal blood pressure and shunt volume for different surgical procedures. The optimal puncture site, pathway, and stent size are selected based on the prediction results.

[0088] In this embodiment, the patient's hepatic microcirculatory resistance value is accurately assessed based on HVPG pressure measurement and portal vein flow data, providing a possibility for obtaining the gold standard for microcirculatory resistance. Based on this gold standard, an artificial intelligence model is trained that can extract liver fibrosis or cirrhosis features from image data related to the degree of liver fibrosis or cirrhosis, and non-invasively assess microcirculatory resistance based on these features. Since increased liver fibrosis and cirrhosis directly affect hepatic microcirculatory resistance, the trained AI model can more accurately and non-invasively assess hepatic microcirculatory resistance by extracting liver fibrosis or cirrhosis features from medical images. Based on the patient's individualized hepatic microcirculatory resistance, more accurate preoperative planning of the puncture path, site, and stent size for personalized TIPS surgery can be achieved, resulting in more accurate preoperative planning results.

[0089] Based on the same inventive concept, this application also provides a microcirculation resistance value acquisition device for implementing the microcirculation resistance value acquisition method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the microcirculation resistance value acquisition device provided below can be found in the limitations of the microcirculation resistance value acquisition method described above, and will not be repeated here.

[0090] In one embodiment, such as Figure 6 As shown, a microcirculation resistance value acquisition device is provided, comprising: an acquisition module, an iteration module, a training module, and a calculation module, wherein:

[0091] The acquisition module is used to acquire the first medical image data and portal vein circulation model of one or more training subjects;

[0092] The iteration module is used to iterate the microcirculation resistance value in the portal vein circulation model until the similarity between the portal vein circulation model and the portal vein of the training object meets the preset conditions, and obtains the first microcirculation resistance value of the training object.

[0093] The training module is used to train the mapping relationship between the first microcirculation resistance value and the corresponding first medical image data based on the first microcirculation resistance value and the corresponding first medical image data.

[0094] The calculation module is used to obtain the second microcirculation resistance value of the target object based on the mapping relationship and the second medical image data of the target object.

[0095] In one embodiment, iterating the microcirculation resistance value in the portal vein circulation model includes: coupling the portal vein circulation model to resistive units and capacitive units; and iterating the resistance value of the resistive units and / or the capacitance value of the capacitive units. Optionally, each branch of the target vein in the portal vein circulation model is connected to different resistive units and capacitive units, and the portal vein circulation model is coupled to the resistive units and capacitive units to form a closed loop.

[0096] Optionally, the iterative process of the microcirculatory resistance value in the portal vein circulation model further includes: obtaining the portal vein blood flow feature value of the training object; and iterating the microcirculatory resistance value in the portal vein circulation model when the portal vein blood flow feature value is used as the solution condition for the portal vein circulation model.

[0097] In one embodiment, obtaining portal vein blood flow feature values ​​of a training subject includes: obtaining the mapping relationship between medical imaging data and / or preset physiological indicators and venous blood flow features; and based on the mapping relationship, obtaining portal vein blood flow feature values ​​corresponding to the first medical imaging data and / or preset physiological indicators of the training subject.

[0098] Each module in the aforementioned microcirculation resistance value acquisition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0099] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for obtaining microcirculation resistance values. The display unit is used to form a visually visible image and can be a display screen or a projection device. The display screen can be an LCD screen, and the input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0100] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0101] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the steps in the embodiments of the methods for obtaining microcirculation resistance values ​​described above.

[0102] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the embodiments of the microcirculation resistance value acquisition methods described above.

[0103] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the embodiments of the microcirculation resistance value acquisition methods described above.

[0104] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0105] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for obtaining microcirculation resistance values, characterized in that, The method includes: Acquire first medical imaging data and portal vein circulation models for one or more training subjects; Iterate the microcirculatory resistance value in the portal vein circulation model until the similarity between the portal vein circulation model and the portal vein of the training object meets the preset condition, and obtain the first microcirculatory resistance value of the training object. Based on the first microcirculation resistance value and the corresponding first medical image data, a mapping relationship between the microcirculation resistance value and the medical image data is trained. Based on the mapping relationship and the second medical imaging data of the target object, the second microcirculation resistance value of the target object is obtained.

2. The method according to claim 1, characterized in that, Iterating the microcirculatory resistance values ​​in the portal vein circulation model includes: The portal vein circulation model is coupled and connected to the resistor unit and the capacitor unit; Iterate over the resistance value of the resistor unit and / or the capacitance value of the capacitor unit.

3. The method according to claim 2, characterized in that, In the portal vein circulation model, each branch of the target portal vein is connected to different resistor units and capacitor units. The portal vein circulation model is coupled with the resistor units and capacitor units to form a closed loop.

4. The method according to claim 1, characterized in that, Iterating the microcirculatory resistance values ​​in the portal vein circulation model includes: Obtain the portal vein blood flow characteristic values ​​of the training object; With the portal vein blood flow characteristic value used as the solution condition for the portal vein circulation model, the microcirculation resistance value in the portal vein circulation model is iterated.

5. The method according to claim 4, characterized in that, Obtaining the venous blood flow feature values ​​of the training object includes: Acquire the mapping relationship between medical imaging data and / or preset physiological indicators and venous blood flow characteristics; Based on the mapping relationship, obtain the venous blood flow feature values ​​corresponding to the preset physiological indicators of the first medical image data and / or the training object.

6. A surgical planning method, characterized in that, The method includes: Obtain a portal vein circulation model of the target object, wherein the microcirculation resistance value of the portal vein circulation model of the target object is calculated by the method according to any one of claims 1 to 5; Based on the portal vein circulation model, simulations of various surgical procedures were performed to obtain the venous blood pressure and venous blood shunt flow rate of the portal vein circulation model after the surgery. Among them, there are one or more distinguishing features between different surgical procedures: the puncture site, puncture path, and stent type of the portal vein circulation model. Based on the venous blood pressure and the venous blood shunt flow rate, the target surgical method is selected from the multiple surgical methods.

7. The method according to claim 6, characterized in that, Based on the venous blood pressure and the venous blood shunt flow rate, a target surgical procedure is selected from the multiple surgical options, including: When the venous blood pressure and the venous blood shunt flow rate meet the set thresholds, the current surgical procedure is taken as the target surgical procedure.

8. A device for obtaining microcirculation resistance values, characterized in that, The device includes: The acquisition module is used to acquire the first medical image data and portal vein circulation model of one or more training subjects; An iterative module is used to iterate the microcirculation resistance value in the portal vein circulation model until the similarity between the portal vein circulation model and the portal vein of the training object meets a preset condition, thereby obtaining the first microcirculation resistance value of the training object. The training module is used to train a mapping relationship between the microcirculation resistance value and the corresponding medical image data based on the first microcirculation resistance value and the first medical image data. The calculation module is used to obtain the second microcirculation resistance value of the target object based on the mapping relationship and the second medical imaging data of the target object.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, 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 to 5.

Images