CN117618108A - Methods for predicting the effect of implantation of an in vivo device and related products - Google Patents
Methods for predicting the effect of implantation of an in vivo device and related products Download PDFInfo
- Publication number
- CN117618108A CN117618108A CN202311722952.XA CN202311722952A CN117618108A CN 117618108 A CN117618108 A CN 117618108A CN 202311722952 A CN202311722952 A CN 202311722952A CN 117618108 A CN117618108 A CN 117618108A
- Authority
- CN
- China
- Prior art keywords
- implantation
- historical
- blood flow
- vivo device
- vivo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001727 in vivo Methods 0.000 title claims abstract description 196
- 238000002513 implantation Methods 0.000 title claims abstract description 172
- 230000000694 effects Effects 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000017531 blood circulation Effects 0.000 claims abstract description 119
- 238000004088 simulation Methods 0.000 claims abstract description 45
- 238000004364 calculation method Methods 0.000 claims abstract description 37
- 230000006872 improvement Effects 0.000 claims abstract description 37
- 230000002601 intratumoral effect Effects 0.000 claims description 17
- 230000002490 cerebral effect Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 210000004204 blood vessel Anatomy 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 239000012530 fluid Substances 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 3
- 210000004369 blood Anatomy 0.000 claims description 3
- 239000002184 metal Substances 0.000 claims description 3
- 230000000004 hemodynamic effect Effects 0.000 abstract description 5
- 238000005094 computer simulation Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 18
- 239000007943 implant Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 206010028980 Neoplasm Diseases 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000007917 intracranial administration Methods 0.000 description 4
- 239000000470 constituent Substances 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000009472 formulation Methods 0.000 description 3
- 238000002595 magnetic resonance imaging Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000002583 angiography Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 206010002329 Aneurysm Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007428 craniotomy Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000012567 medical material Substances 0.000 description 1
- 238000002324 minimally invasive surgery Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000002610 neuroimaging Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Abstract
The present disclosure discloses a method for predicting the effect of implantation of an in vivo device and related products. The method comprises the following steps: acquiring medical images, in-vivo device information and blood flow parameters of a patient; inputting the medical image, the in-vivo device information and the blood flow parameters of the patient into an implantation effect prediction model corresponding to the in-vivo device information; and receiving a prediction result regarding the implantation morphology and the blood flow improvement parameter of the in-vivo device from an output of an implantation effect prediction model, wherein the implantation effect prediction model is model-trained in advance using sample data obtained by the simulation calculation. According to the scheme of the embodiment of the disclosure, the simulation calculation of the finite element model of the implantation of the in-vivo device and the hemodynamic model after the implantation of the in-vivo device can be completed by using the implantation effect prediction model, so that the prediction results of the implantation form and the blood flow improvement parameters of the in-vivo device can be automatically output. By simplifying a large number of simulation modeling flows, the making efficiency of the implantation scheme of the in-vivo device is improved.
Description
Technical Field
The present disclosure relates generally to the field of medical image analysis technology. More particularly, the present disclosure relates to a method, system, electronic device, and storage medium for predicting an in vivo device implantation effect.
Background
With the continuous development of minimally invasive techniques, the continuous progress of neuro-interventional therapy techniques, the continuous innovation of neuroimaging, medical materials and microcatheter techniques, the treatment means of intracranial diseases are gradually changed from craniotomy to intravascular interventional therapy. The endovascular intervention is used as an emerging minimally invasive surgery, has high requirements on the accuracy of a preoperative scheme, and has influence on the surgical effect on different tumor body forms and vascular forms and different physical states of patients, so that the endovascular intervention has very high dependence on the experience of doctors.
In order to accurately formulate a preoperative scheme and ensure an operative effect, the prior art provides a finite element simulation method. The method simulates the in vivo device implantation process in a computer by simplifying the complex biomechanical process into discrete finite elements to predict the morphology and effect of the consumable during implantation, such as the position, shape, size, etc. of the consumable. The prediction result obtained by the method can help doctors to make more accurate decisions and plans before the operation.
However, there are a large number of modeling flows in the execution process of the finite element simulation method, which are complicated and have low calculation efficiency, so the implantation condition of the in-vivo device in the actual operation cannot be predicted rapidly by using the simulation method, and the customization efficiency of the preoperative scheme needs to be improved.
In view of the foregoing, it is desirable to provide an in-vivo device implantation effect prediction scheme, so as to simplify the flow of simulation modeling, and further improve the efficiency of in-vivo device implantation scheme formulation.
Disclosure of Invention
To address at least one or more of the technical problems mentioned above, the present disclosure proposes, among other aspects, in vivo device implantation effect prediction schemes.
In a first aspect, the present disclosure provides a method for predicting an in vivo device implantation effect comprising: acquiring medical images, in-vivo device information and blood flow parameters of a patient; inputting the medical image, the in-vivo device information and the blood flow parameters of the patient into an implantation effect prediction model corresponding to the in-vivo device information; and receiving a prediction result regarding the implantation morphology and the blood flow improvement parameter of the in-vivo device from an output of an implantation effect prediction model, wherein the implantation effect prediction model is model-trained in advance using sample data obtained by the simulation calculation.
In some embodiments, wherein the sample data comprises: historical medical images, historical in-vivo device information, historical patient blood flow parameters, and historical device implantation morphology and historical blood flow improvement parameters corresponding thereto; prior to acquiring the medical image, the in-vivo device information, and the patient blood flow parameters, the method further comprises: collecting historical medical images, historical in-vivo device information and historical patient blood flow parameters; performing simulation calculation according to the historical medical image, the historical in-vivo device information and the historical patient blood flow parameters to obtain a corresponding historical device implantation form and historical blood flow improvement parameters; and constructing sample data based on the historical medical image, the historical in-vivo device information, the historical patient blood flow parameters, the corresponding historical device implantation morphology and the historical blood flow improvement parameters so as to train an implantation effect prediction model corresponding to the historical in-vivo device information.
In some embodiments, wherein performing the simulation calculation based on the historical medical image, the historical in-vivo device information, and the historical patient blood flow parameters to obtain the historical device implantation profile and the historical blood flow improvement parameters corresponding thereto comprises: constructing a cerebral blood vessel three-dimensional model according to the historical medical images; obtaining an in-vivo device three-dimensional model according to the historical in-vivo device information; implanting the three-dimensional model of the in-vivo device into the three-dimensional model of the cerebral blood vessel by a finite element method to obtain a history device implantation form; and calculating the historical blood flow improvement parameters by a computational fluid dynamics method based on the historical device implantation morphology, the cerebrovascular three-dimensional model and the historical patient blood flow parameters.
In some embodiments, wherein the in-vivo device information comprises an in-vivo device model, an in-vivo device design drawing, or an in-vivo device three-dimensional model, wherein the obtaining in-vivo device information comprises: acquiring in-vivo device information and implantation positions of in-vivo devices indicated by selected instructions fed back to a man-machine interaction unit by an operator; or, the model of the in-vivo device and the selected implantation position which are input to the man-machine interaction unit by the operator are obtained.
In some embodiments, an in-vivo device comprises: a spring coil, a blood flow guiding device or an intratumoral turbulence device; in response to the in-vivo device being a coil, the device implantation modality includes an implantation modality image, a loading rate, and wall shear stress; in response to the in-vivo device being a blood flow guiding device or an intratumoral turbulence device, the device implantation modality includes an implantation modality image, metal coverage, and wall shear stress.
In some embodiments, wherein the patient blood flow parameters comprise: blood flow velocity, blood density and viscosity prior to implantation; the blood flow improvement parameters include: blood flow velocity after implantation.
In some embodiments, wherein receiving predictions regarding in vivo device implantation morphology and blood flow improvement parameters from an output of the implantation effect prediction model comprises: an implantation morphology image, a blood flow chart, and a blood flow pressure chart of the in-vivo device are displayed on a display apparatus.
In a second aspect, the present disclosure provides a system for predicting an in vivo device implantation effect comprising: a data acquisition unit for receiving medical images, in-vivo device information, and patient blood flow parameters; a prediction model unit, which is provided with an implantation effect prediction model and is used for receiving the medical image, the in-vivo device information and the blood flow parameters of the patient acquired by the data acquisition unit, and processing the medical image, the in-vivo device information and the blood flow parameters of the patient by using the implantation effect prediction model corresponding to the in-vivo device information so as to output the prediction results of the implantation form and the blood flow improvement parameters of the device; the simulation calculation unit is used for calculating the implantation form of the historical device and the historical blood flow improvement parameter corresponding to the historical medical image, the historical in-vivo device information and the historical blood flow parameter simulation according to the historical medical image, the historical in-vivo device information and the historical blood flow parameter simulation so as to form sample data of a training implantation effect prediction model; and a human-computer interaction unit including a display device for receiving a prediction result regarding the implantation morphology and the blood flow improvement parameter of the in-vivo device from an output of the implantation effect prediction model, and an input device for receiving an operation instruction.
In a third aspect, the present disclosure provides an electronic device comprising: a processor; and a memory storing executable program instructions that, when executed by the processor, cause the apparatus to implement a method according to any one of the first aspects.
In a fourth aspect, the present disclosure provides a computer-readable storage medium having stored thereon computer-readable instructions which, when executed by one or more processors, implement the method of any one of the first aspects.
By the method for predicting an implant effect of an in vivo device provided above, embodiments of the present disclosure train an implant effect prediction model by simulating calculated sample data, such that the implant effect prediction model can simulate the process of the simulated calculation. The implantation effect prediction model completes the simulation calculation of the finite element model implanted by the in-vivo device and the hemodynamic model implanted by the in-vivo device according to the medical image, the in-vivo device information and the blood flow parameters of the patient, and further obtains the prediction result of the implantation form and the blood flow improvement parameters of the in-vivo device. The simulation calculation is completed by using the implantation effect prediction model, so that a large number of simulation modeling flows can be simplified, and the making efficiency of an implantation scheme of the in-vivo device is improved.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:
fig. 1 illustrates an exemplary flowchart of a method for predicting an in vivo device implantation effect in accordance with some embodiments of the present disclosure;
fig. 2 illustrates an exemplary flowchart of a method for predicting an in vivo device implantation effect in accordance with further embodiments of the present disclosure;
FIG. 3 illustrates an exemplary flowchart of a training method of an implant effect prediction model in accordance with some embodiments of the present disclosure;
FIG. 4 illustrates an exemplary flow chart of a simulated computing method for constructing sample data in accordance with some embodiments of the present disclosure;
fig. 5 illustrates an exemplary block diagram of a system for predicting an in vivo device implantation effect in accordance with some embodiments of the present disclosure;
fig. 6 shows an exemplary block diagram of the electronic device of an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the disclosure. Based on the embodiments in this disclosure, all other embodiments that may be made by those skilled in the art without the inventive effort are within the scope of the present disclosure.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the present disclosure is for the purpose of describing particular embodiments only, and is not intended to be limiting of the disclosure. As used in the specification and claims of this disclosure, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should be further understood that the term "and/or" as used in the present disclosure and claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
Specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
Exemplary application scenarios
The preoperative scheme making method based on finite element simulation is to simplify the complex biomechanical process into discrete finite elements and simulate the implantation process of the in-vivo device in a computer so as to predict the form and effect of consumable materials in the implantation process. It requires at least the construction of three-dimensional models of the in-vivo device, three-dimensional models of the human blood vessel, finite element models of the implantation procedure, and hemodynamic models during execution, and therefore this approach can create a significant amount of modeling overhead.
The modeling flow is not only tedious, but also generates a great deal of calculation work, and has higher requirements on the modeling level of doctors. The time limit of the preoperative scheme formulation and the limitation of the doctor modeling level are limited, and in practical application, the preoperative scheme formulation method based on finite element simulation cannot quickly and accurately predict the implantation condition of the in-vivo device, which prevents the application of simulation technology and artificial intelligence technology in interventional operation.
Exemplary application scenario
In view of this, the embodiments of the present disclosure provide an in-vivo device implantation effect prediction scheme, which obtains sample data of a model through simulation calculation, and further trains an implantation effect prediction model capable of simulating a simulation calculation process, and utilizes the model to automatically and rapidly complete prediction of an implantation effect of an in-vivo device, thereby improving the efficiency of the preoperative scheme and reducing the requirement on the modeling level of a doctor.
Fig. 1 illustrates an exemplary flowchart of a method 100 for predicting an in vivo device implantation effect in accordance with some embodiments of the present disclosure. As shown in fig. 1, in step S101, a medical image, in-vivo device information, and a patient blood flow parameter are acquired. In this embodiment, the medical images include, but are not limited to, computed tomography (CT, computed Tomography), magnetic resonance imaging (MRI, magnetic Resonance Imaging) or digital subtraction angiography (DSA, digital Subtraction Angiography) images, and the medical images of the patient can be fed back with information about the morphology of the patient's cerebral vessels and the shape of the intracranial tumor, and a three-dimensional model of the patient's cerebral vessels and the intracranial tumor can be constructed using the information.
The in-vivo device information refers to information capable of indicating parameters such as the shape of the in-vivo device, and may include, but is not limited to, the model number of the in-vivo device, the design drawing or three-dimensional model of the in-vivo device, and the like. Further, the in-vivo device information may also include a release location of the in-vivo device. Still further, the in-vivo device in this embodiment includes at least the following three types: spring coils, blood flow guiding devices and intratumoral turbulence devices.
The patient blood flow parameters are used for feeding back the blood flow condition of the patient, and the complex biomechanical process of the human body can be better simulated by combining the patient blood flow parameters so as to more accurately predict the implantation condition of the in-vivo device in the real operation. Further, the patient blood flow parameters include: blood flow velocity, blood density and viscosity prior to implantation.
In step S102, the medical image, the in-vivo device information, and the patient blood flow parameter are input to the implantation effect prediction model corresponding to the in-vivo device information. In this embodiment, the implantation effect prediction model performs model training in advance using sample data obtained by the simulation calculation. Because of the large difference in the morphology of different in-vivo devices, different implantation effect prediction models may be set for different types of in-vivo devices in order to improve the prediction performance of the implantation effect prediction model.
For example, an implantation effect prediction model may be trained for the spring coil, an implantation effect prediction model may be trained for the blood flow guiding device, an implantation effect prediction model may be trained for the intratumoral turbulence device, and when step S102 is performed, which of the three in-vivo devices is determined according to the in-vivo device information acquired in step S101, thereby invoking the corresponding implantation effect prediction model.
In step S103, a prediction result regarding the implantation morphology and the blood flow improvement parameter of the in-vivo device is received from the output of the implantation effect prediction model. In the present embodiment, the blood flow improvement parameters include: blood flow velocity after implantation. Further, the relevant prediction data of the in vivo device implantation morphology varies for different types of in vivo devices. Taking a spring ring, a blood flow guiding device and an intratumoral turbulence device as examples, when the internal device is the spring ring, the implantation form of the device comprises implantation form images, filling rate and wall shear stress; when the in-vivo device is a blood flow guiding device or an intratumoral turbulence device, the device implantation modality includes an implantation modality image, metal coverage, and wall shear stress.
According to the prediction result of the implantation form of the in-vivo device output by the implantation effect prediction model, a doctor can evaluate the implantation effect of the in-vivo device. According to the prediction result of the blood flow improvement parameter output by the implantation effect prediction model, a doctor can evaluate the treatment effect after implantation of the in-vivo device.
In order to increase the intuitiveness of the prediction results, the prediction results may be visualized by means of a display device. For example, step S103 may display an implantation morphology image, a blood flow chart, and a blood flow pressure chart of the in-vivo device on the display apparatus.
In the method shown in this embodiment, the sample data used in training the implantation effect prediction model is derived from simulation calculation, so that the sample data of the model has higher accuracy and reliability. After machine learning is performed based on the sample data, the implantation effect prediction model can realize simulation of simulation calculation, and an accurate, reliable and efficient means is provided for predicting implantation form and implantation effect of the in-vivo device.
From the description of the process performed in step S102 in the foregoing embodiment, it may be known that, before step S102, the type of the in-vivo device may also be determined according to the in-vivo device information, so as to invoke the implantation effect prediction model for the type of in-vivo device.
Further, the in-vivo device information may include an in-vivo device model, an in-vivo device design drawing, or an in-vivo device three-dimensional model, and an operator may input in-vivo device information to the system through actions such as inputting, selecting, or importing.
Based on the foregoing, further embodiments of the present disclosure provide yet another method for predicting an in vivo device implantation effect, and fig. 2 shows an exemplary flowchart of a method 200 for predicting an in vivo device implantation effect according to further embodiments of the present disclosure.
As shown in fig. 2, in step S201, a medical image, in-vivo device information, and a patient blood flow parameter are acquired. In this embodiment, there are various ways of acquiring in-vivo device information. For example, in some embodiments, in-vivo device information and implantation locations of in-vivo devices indicated by selected instructions fed back by an operator to a human-machine interaction unit may be obtained. Still further exemplary, in other embodiments, the model of the in-vivo device and the selected implantation location entered or imported by the operator into the human-machine interaction unit are obtained. For example, the human-computer interaction unit may be a touch display device or a display device connected to an input device, where the operator selects the implantation site and/or the in-vivo device in the displayed cerebrovascular model directly or through the input device.
In step S202, the type of the in-vivo device is determined from the in-vivo device information. In some embodiments, three-dimensional models of various models of in-vivo devices are pre-stored in the system, and when model information of the in-vivo device is acquired, the system can identify the type of in-vivo device to which the model belongs and retrieve the three-dimensional model thereof. Alternatively, in other embodiments, the display device may display the stored in-vivo device for the operator to select a desired in-vivo device on the display device.
In step S203, an implantation effect prediction model for the type of in-vivo device is invoked. In this embodiment, the implantation effect prediction model of the different types of in-vivo devices is stored in the system in advance, and is called according to the information determined in step S202.
In step S204, the medical image, in-vivo device information, and patient blood flow parameters are input to the retrieved implantation effect prediction model. It should be noted that, the step S204 in the present embodiment is identical to the content of the step S102 in the previous embodiment, and will not be described herein.
In step S205, a prediction result regarding the implantation morphology and the blood flow improvement parameter of the in-vivo device is received from the output of the implantation effect prediction model. It should be noted that, the step S205 in the present embodiment is identical to the content of the step S103 in the previous embodiment, and will not be described herein.
A method of predicting the implantation effect of an in vivo device by an implantation effect prediction model is described above in connection with the embodiments of fig. 1 and 2, which require training of the model using sample data prior to use of the implantation effect prediction model.
Turning now to the training method of the implant effect prediction model, fig. 3 illustrates an exemplary flowchart of a training method 300 of the implant effect prediction model according to some embodiments of the present disclosure, as shown in fig. 3, in step S301, historical medical images, historical in-vivo device information, and historical patient blood flow parameters are acquired. Because the implantation effect prediction model simulates the simulation calculation process, the input data of the implantation effect prediction model during training is consistent with the input data of the simulation calculation, namely, the sample data of the implantation effect prediction model comprises historical medical images, historical in-vivo device information and historical patient blood flow parameters. The source of the historical medical image is the same as that of the medical image, and similarly, the content of the historical in-vivo device information can refer to the content of the in-vivo device information, and the content of the historical patient blood flow parameter can refer to the patient blood flow parameter.
In step S302, a simulation calculation is performed according to the historical medical image, the historical in-vivo device information and the historical patient blood flow parameters to obtain a historical device implantation configuration and a historical blood flow improvement parameter corresponding to the historical medical image and the historical in-vivo device information. In this embodiment, the simulation calculations include, but are not limited to, finite element simulation analysis and hemodynamic analysis. By executing step S302, the historical medical image, the historical in-vivo device information, and the historical patient blood flow parameters may be obtained, which are determined by simulation calculation.
It should be noted that, the implantation form and the historical blood flow improvement parameter of the historical device obtained by the simulation calculation may be understood as an implantation effect prediction result with a high degree of fitting with the actual situation, so that the historical medical image, the historical in-vivo device information and the historical patient blood flow parameter obtained in the step S301, and the implantation form and the historical blood flow improvement parameter of the historical device obtained in the step S302 may be used to form sample data with high reliability.
In step S303, sample data is constructed based on the historical medical image, the historical in-vivo device information, the historical patient blood flow parameters, and the corresponding historical device implantation modality and historical blood flow improvement parameters. The sample data is used for training an implantation effect prediction model corresponding to the historical in-vivo device information. For example, in the model training process, a neural network model based on physical information may be used, and machine learning may be performed using the sample data described above, so as to obtain a trained implantation effect prediction model.
In some embodiments, different types of in-vivo devices have corresponding implant effect prediction models, so sample data may also be classified according to historical in-vivo device information, thereby forming sample data for the different types of in-vivo devices for training the corresponding types of implant effect prediction models.
As can be seen from the foregoing embodiment described in connection with fig. 3, the sample data is obtained through simulation calculation, and a simulation calculation method in the process of constructing the sample data is described below. Fig. 4 illustrates an exemplary flow chart of a simulated computing method 400 for constructing sample data according to some embodiments of the present disclosure, it being understood that the simulated computing method for constructing sample data is a specific implementation in step S302 described previously, and thus the features described previously in connection with fig. 3 may be similarly applied thereto.
As shown in fig. 4, in step S401, a three-dimensional model of a cerebral blood vessel is constructed from the historical medical image. In the step, the historical medical image can be subjected to processing such as segmentation, reduction, three-dimensional reconstruction and format conversion, so that interference of a background image is eliminated, and a more accurate three-dimensional cerebrovascular model is constructed. The three-dimensional model of a cerebral blood vessel includes a three-dimensional physical model of a cerebral blood vessel and a three-dimensional physical model of an intracranial tumor body.
In step S402, an in-vivo device three-dimensional model is obtained from the historical in-vivo device information. In some embodiments, step S402 may construct a three-dimensional model of the in-vivo device based on the geometric features and load conditions of the in-vivo device. In other embodiments, the three-dimensional model of the in-vivo device may be pre-built and stored in the system for direct recall at the time of use.
In this embodiment, the execution timing between the step S401 and the step S402 is not strictly required. Step S402 may be performed before step S401, or may be performed in parallel with step S401.
In step S403, the in-vivo device three-dimensional model is implanted into the cerebrovascular three-dimensional model by the finite element method to obtain a historic device implantation shape. The finite element method, which may also be referred to as finite element analysis (FEA, finite Element Analysis), uses a mathematical approximation method to simulate real geometry and load conditions, and by simple and interactive elements, a finite number of unknowns can be used to approximate an infinite number of real systems. The method can realize the accurate simulation of the implantation process and the release process of the in-vivo device in the cerebral vessels by a finite element method, and obtain the three-dimensional shape of the in-vivo device after implantation.
Further, the in-vivo device may also have an introduction device, and the simulation of the in-vivo device implantation process is accomplished by adding and releasing constraints of the introduction device and/or the cerebral blood vessel on the in-vivo device during the implantation of the in-vivo device three-dimensional model into the cerebral blood vessel three-dimensional model by the finite element method.
Taking an intratumoral turbulence device as an example, in clinical surgery, a doctor needs to push the intratumoral turbulence device outwards from a micro-catheter by pushing a guide wire so as to convey the intratumoral turbulence device to an aneurysm, and specifically, the tail end of the intratumoral turbulence device can be gradually released by mutually matching two operations of pushing the guide wire and retracting the micro-catheter. Simulation of this procedure can achieve implantation of the intratumoral spoiler model into the microcatheter by applying constraints and loads to the proximal and distal markers of the intratumoral spoiler. And as the constraint applied by the micro-catheter model to the intratumoral turbulence device model is eliminated, the intratumoral turbulence device model is gradually unfolded, and finally, the history device implantation form is formed.
In step S404, a historical blood flow improvement parameter is calculated by a computational fluid dynamics method based on the historical device implantation morphology, the cerebrovascular three-dimensional model, and the historical patient blood flow parameter. After the in vivo device is implanted into the cerebrovascular model, computational fluid dynamics (CFD, computational Fluid Dynamics) calculations may be performed on the implanted model to simulate and analyze the phenomena and characteristics of blood flow.
The CFD calculation can be briefly divided into five parts, namely a modeling part, a grid division part, a boundary condition setting part, a numerical solution part and a post-processing part, wherein the modeling part is used for establishing an actual blood flow model into a blood flow dynamic model, the grid division part is used for dividing the blood flow dynamic model into discrete small grids so as to be used for calculating blood flow parameters, the boundary condition setting part is used for giving boundary conditions such as an inlet and outlet of a cerebral blood vessel, the inlet and outlet speed and pressure of the cerebral blood vessel, and the like, the content of the part can be obtained based on a historical device implantation form and a cerebral blood vessel three-dimensional model, the numerical solution part is used for solving a Navier-Stokes equation by using a numerical method based on the boundary conditions so as to obtain various parameters of a flow field, and the post-processing part can be used for analyzing and displaying a numerical calculation result, such as drawing a flow diagram, a pressure distribution diagram, and the like.
Embodiments of the present disclosure also provide a system for predicting an in vivo device implantation effect, fig. 5 illustrates an exemplary block diagram of a system 500 for predicting an in vivo device implantation effect, according to some embodiments of the present disclosure. As shown in fig. 5, the system includes: the system comprises a data acquisition unit 501, a prediction model unit 502, a simulation calculation unit 503 and a human-computer interaction unit 504.
In this embodiment, the data acquisition unit 501 is configured to receive medical images, in-vivo device information, and patient blood flow parameters. The type of medical image, the content of the in-vivo device information, and the content of the blood flow parameters of the patient are described in detail in the foregoing embodiments, and are not described herein.
In this embodiment, the prediction model unit 502 is equipped with an implantation effect prediction model for receiving the medical image, the in-vivo device information, and the patient blood flow parameter acquired by the data acquisition unit 501, and processing the medical image, the in-vivo device information, and the patient blood flow parameter by using the implantation effect prediction model corresponding to the in-vivo device information to output a prediction result of the device implantation form and the blood flow improvement parameter. The training method of the implantation effect prediction model is described in detail in the foregoing embodiment in connection with fig. 3, and will not be described herein.
The implantation effect prediction model is a neural network based on big data and physical information, and the prediction model unit learns simulation results such as morphology, hemodynamics and the like after the implantation of the in-vivo device to form an intelligent model capable of simulating simulation calculation.
In this embodiment, the simulation calculation unit 503 is configured to calculate, according to the historical medical image, the historical in-vivo device information, and the historical patient blood flow parameter, the historical device implantation configuration and the historical blood flow improvement parameter corresponding thereto in a simulation manner, so as to form sample data for training the implantation effect prediction model. The construction process of the sample data is described in detail in the foregoing embodiment in connection with fig. 4, and will not be described herein.
In this embodiment, the man-machine interaction unit 504 may include a display device for receiving the prediction result regarding the implantation morphology and the blood flow improvement parameter of the in-vivo apparatus from the output of the implantation effect prediction model and capable of visually presenting the same, and an input device for receiving the operation instruction. The operating instructions may be, for example, selected instructions or input instructions for indicating in-vivo device information and implantation location of the in-vivo device.
For example, the operator can autonomously select different types and release positions of the spring coil, the blood flow guiding device or the intratumoral turbulence device according to the condition of the patient, and the trained implantation effect prediction model can be used for performing prediction simulation on the release form and the blood flow dynamics of various types of the in-vivo device selected by the operator. Through the man-machine interaction unit, an operator can predict and evaluate the implantation process and the result of the in-vivo device before and during the operation, thereby better grasping the operation skill and improving the success rate of the operation.
In order to implement the method steps of the disclosure described above in connection with the accompanying drawings at the software and hardware level, the embodiment of the disclosure further provides an electronic device as shown in fig. 6. In particular, fig. 6 shows an exemplary block diagram of an electronic device 600 of an embodiment of the disclosure.
As shown in fig. 6, an electronic device 600 of the present disclosure may include a processor 610 and a memory 620. Specifically, the memory 620 has stored thereon executable program instructions. The program instructions, when executed by the processor 610, cause the electronic device to perform the method steps as described hereinbefore in connection with fig. 1-4.
It will be appreciated that, to clearly illustrate aspects of the present disclosure and avoid obscuring the prior art, the electronic device 600 of fig. 6 only shows constituent elements relevant to embodiments of the present disclosure, while omitting those constituent elements that may be necessary to practice embodiments of the present disclosure but fall within the prior art scope. Accordingly, based on the present disclosure, one of ordinary skill in the art will clearly appreciate that the electronic device 600 of the present disclosure may also include common constituent elements that are different from those illustrated in fig. 6.
In an exemplary implementation scenario, the processor 610 described above may control the overall operation of the electronic device 600. For example, the processor 610 may control the operation of the electronic device 600 by executing programs stored in the memory 620. In terms of implementation, the processor 610 of the present disclosure may be implemented as a Central Processing Unit (CPU), an application processor (Application Processor, AP), an artificial intelligence processor chip (Intelligent Processing Unit, IPU), or the like provided in the electronic device 600. Further, the processor 610 of the present disclosure may also be implemented in any suitable manner. For example, the processor 610 may take the form of, for example, a microprocessor or processor, and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), a programmable logic controller, and an embedded microcontroller, among others.
In terms of storage, the memory 620 may be used to store hardware for various data, instructions that are processed in the electronic device 600. For example, the memory 620 may store processed data and data to be processed in the electronic device 600. The memory 620 may store data sets that have been processed or are to be processed by the processor 610. Further, the memory 620 may store applications, drivers, etc. to be driven by the electronic device 600. For example: memory 620 may store various programs for model construction, information identification, and the like to be executed by processor 610. The memory 620 may be a DRAM, but the present disclosure is not limited thereto. By type, the memory 620 may include at least one of volatile memory or non-volatile memory. The nonvolatile memory may include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), flash memory, phase change RAM (PRAM), magnetic RAM (MRAM), resistive RAM (RRAM), ferroelectric RAM (FRAM), and the like. Volatile memory can include Dynamic RAM (DRAM), static RAM (SRAM), synchronous DRAM (SDRAM), PRAM, MRAM, RRAM, ferroelectric RAM (FeRAM), and the like. In an embodiment, the memory 620 may include at least one of a Hard Disk Drive (HDD), a Solid State Drive (SSD), a high density flash memory (CF), a Secure Digital (SD) card, a Micro-secure digital (Micro-SD) card, a Mini-secure digital (Mini-SD) card, an extreme digital (xD) card, a cache (caches), or a memory stick.
In summary, specific functions implemented by the memory 620 and the processor 610 of the electronic device 600 provided in the embodiments of the present disclosure may be explained in comparison with the foregoing embodiments in the present disclosure, and may achieve the technical effects of the foregoing embodiments, which will not be repeated herein.
Additionally or alternatively, the disclosure may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon computer program instructions (or computer programs, or computer instruction code) which, when executed by a processor of an electronic device (or electronic device, server, etc.), cause the processor to perform part or all of the steps of the above-described methods according to the disclosure.
While various embodiments of the present disclosure have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, changes, and substitutions will occur to those skilled in the art without departing from the spirit and scope of the present disclosure. It should be understood that various alternatives to the embodiments of the disclosure described herein may be employed in practicing the disclosure. The appended claims are intended to define the scope of the disclosure and are therefore to cover all equivalents or alternatives falling within the scope of these claims.
Claims (10)
1. A method for predicting the effect of implantation of an in vivo device, comprising:
acquiring medical images, in-vivo device information and blood flow parameters of a patient;
inputting the medical image, the in-vivo device information, and the patient blood flow parameter to an implantation effect prediction model corresponding to the in-vivo device information; and
and receiving a prediction result regarding the implantation morphology and the blood flow improvement parameter of the in-vivo device from an output of the implantation effect prediction model, wherein the implantation effect prediction model is model-trained in advance using sample data obtained by simulation calculation.
2. The method of claim 1, wherein the sample data comprises: historical medical images, historical in-vivo device information, historical patient blood flow parameters, and historical device implantation morphology and historical blood flow improvement parameters corresponding thereto; prior to the acquiring the medical image, the in-vivo device information, and the patient blood flow parameters, the method further comprises:
collecting the historical medical images, the historical in-vivo device information and the historical patient blood flow parameters; and
performing simulation calculation according to the historical medical image, the historical in-vivo device information and the historical patient blood flow parameters to obtain a corresponding historical device implantation form and historical blood flow improvement parameters; and
sample data is constructed based on the historical medical image, the historical in-vivo device information, the historical patient blood flow parameters, the corresponding historical device implantation morphology and the historical blood flow improvement parameters, so as to train an implantation effect prediction model corresponding to the historical in-vivo device information.
3. The method of claim 2, wherein performing a simulation calculation based on the historical medical image, the historical in-vivo device information, and the historical patient blood flow parameters to obtain a historical device implantation profile and a historical blood flow improvement parameter corresponding thereto comprises:
constructing a cerebral blood vessel three-dimensional model according to the historical medical image;
obtaining an in-vivo device three-dimensional model according to the historical in-vivo device information;
implanting the in-vivo device three-dimensional model into the cerebrovascular three-dimensional model by a finite element method to obtain a historical device implantation shape; and
the historical blood flow improvement parameters are calculated by a computational fluid dynamics method based on the historical device implantation morphology, the cerebrovascular three-dimensional model, and the historical patient blood flow parameters.
4. The method of any of claims 1-3, wherein the in-vivo device information comprises an in-vivo device model, an in-vivo device plan, or an in-vivo device three-dimensional model, wherein obtaining in-vivo device information comprises:
acquiring in-vivo device information and implantation positions of in-vivo devices indicated by selected instructions fed back to a man-machine interaction unit by an operator;
or,
and acquiring the model of the in-vivo device and the selected implantation position which are input by an operator to the man-machine interaction unit.
5. A method according to any one of claims 1-3, wherein the in vivo device comprises: a spring coil, a blood flow guiding device or an intratumoral turbulence device;
in response to the in-vivo device being a spring coil, the device implantation modality includes an implantation modality image, a loading rate, and wall shear stress;
in response to the in-vivo device being a blood flow guiding device or an intratumoral turbulence device, the device implantation modality includes an implantation modality image, a metal coverage rate, and wall shear stress.
6. A method according to any one of claims 1-3, wherein the patient blood flow parameters comprise: blood flow velocity, blood density and viscosity prior to implantation; the blood flow improvement parameters include: blood flow velocity after implantation.
7. The method of any of claims 1-3, wherein receiving predictions regarding the in vivo device implantation morphology and blood flow improvement parameters from the output of the implantation effect prediction model comprises:
an implantation morphology image, a blood flow chart, and a blood flow pressure chart of the in-vivo device are displayed on a display apparatus.
8. A system for predicting the effect of implantation of an in vivo device, comprising:
a data acquisition unit for receiving medical images, in-vivo device information, and patient blood flow parameters;
a prediction model unit, which is provided with an implantation effect prediction model, and is used for receiving the medical image, the in-vivo device information and the blood flow parameters of the patient acquired by the data acquisition unit, and processing the medical image, the in-vivo device information and the blood flow parameters of the patient by using the implantation effect prediction model corresponding to the in-vivo device information so as to output a prediction result of the implantation form and the blood flow improvement parameters of the device;
a simulation calculation unit for calculating a historical device implantation form and a historical blood flow improvement parameter corresponding to the historical medical image, the historical in-vivo device information and the historical patient blood flow parameter according to the historical medical image, the historical in-vivo device information and the historical patient blood flow parameter simulation so as to form sample data for training the implantation effect prediction model; and
a human-computer interaction unit comprising a display device for receiving a prediction result regarding the in-vivo device implantation morphology and blood flow improvement parameter from an output of the implantation effect prediction model, and an input device for receiving an operation instruction.
9. An electronic device, comprising:
a processor; and
a memory storing executable program instructions that, when executed by the processor, cause the apparatus to implement the method of any one of claims 1-7.
10. A computer readable storage medium having stored thereon computer readable instructions which, when executed by one or more processors, implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311722952.XA CN117618108A (en) | 2023-12-14 | 2023-12-14 | Methods for predicting the effect of implantation of an in vivo device and related products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311722952.XA CN117618108A (en) | 2023-12-14 | 2023-12-14 | Methods for predicting the effect of implantation of an in vivo device and related products |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117618108A true CN117618108A (en) | 2024-03-01 |
Family
ID=90026871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311722952.XA Pending CN117618108A (en) | 2023-12-14 | 2023-12-14 | Methods for predicting the effect of implantation of an in vivo device and related products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117618108A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198202A (en) * | 2012-12-19 | 2013-07-10 | 首都医科大学 | Image simulation method for intracranial aneurysm interventional therapy stent implantation |
| KR20170128699A (en) * | 2016-05-13 | 2017-11-23 | 이에이트 주식회사 | In-vivo information visualization method, apparatus performing the same and blood stream fluid analysis simulation program |
| CN111067532A (en) * | 2019-12-16 | 2020-04-28 | 天津市威曼生物材料有限公司 | Method and device for acquiring parameters of internal fixation system of fracture |
| CN114357842A (en) * | 2022-01-10 | 2022-04-15 | 吕孟哲 | Method and system for implanting novel blood flow interference device in simulated intracranial aneurysm cavity |
-
2023
- 2023-12-14 CN CN202311722952.XA patent/CN117618108A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103198202A (en) * | 2012-12-19 | 2013-07-10 | 首都医科大学 | Image simulation method for intracranial aneurysm interventional therapy stent implantation |
| KR20170128699A (en) * | 2016-05-13 | 2017-11-23 | 이에이트 주식회사 | In-vivo information visualization method, apparatus performing the same and blood stream fluid analysis simulation program |
| CN111067532A (en) * | 2019-12-16 | 2020-04-28 | 天津市威曼生物材料有限公司 | Method and device for acquiring parameters of internal fixation system of fracture |
| CN114357842A (en) * | 2022-01-10 | 2022-04-15 | 吕孟哲 | Method and system for implanting novel blood flow interference device in simulated intracranial aneurysm cavity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7077319B2 (en) | Machine learning of anatomical model parameters | |
| JP7267743B2 (en) | Systems and methods for routing conduit lines, such as catheters, within a vessel | |
| US10595790B2 (en) | Method and system for personalized non-invasive hemodynamic assessment of renal artery stenosis from medical images | |
| CN107851464B (en) | Method and system for disease progression modeling and therapy optimization for individual patients | |
| EP3282380B1 (en) | Method and system for determining treatments by modifying patient-specific geometrical models | |
| RU2017101161A (en) | SYSTEM AND METHOD FOR AUTOMATIC PLANNING OF TREATMENT | |
| US20100130878A1 (en) | Systems, apparatus and processes for automated blood flow assessment of vasculature | |
| CN106529117A (en) | Physiology-driven decision support for therapy planning | |
| CN110664524B (en) | Devices, systems, and media for guiding stent implantation in a vessel | |
| US10758125B2 (en) | Enhanced personalized evaluation of coronary artery disease using an integration of multiple medical imaging techniques | |
| EP2949268B1 (en) | System and method for mapping patient data from one physiological state to another physiological state | |
| US11341672B2 (en) | Method and device for detecting an anatomical feature of a section of a blood vessel | |
| JP6651402B2 (en) | Medical image processing apparatus, medical image diagnostic apparatus, and program | |
| EP3428925B1 (en) | Method and system for clinical decision support with local and remote analytics | |
| US20190019286A1 (en) | Method and System for Clinical Decision Support with Local and Remote Analytics | |
| CN113180824B (en) | Shaping needle form simulation method and device for microcatheter shaping, computer equipment and storage medium | |
| CN103823956A (en) | Method and device for determination of contrast medium operation parameter and imaging equipment | |
| US11139082B2 (en) | Method for classifying a risk for thrombus formation in an organ, system for classifying a risk for thrombus formation in an organ, a computer program product and a computer readable medium | |
| KR20230118054A (en) | Method and system for predicting biomarker expression in medical image | |
| CN117618108A (en) | Methods for predicting the effect of implantation of an in vivo device and related products | |
| US8594765B2 (en) | Method for providing an aid for use in the therapeutic treatment of a somatic subject | |
| US20220000566A1 (en) | Method and system for creating a navigation plan for a catheter with a robot | |
| CN113143305A (en) | Providing a set of blood flow parameters for vascular malformations | |
| US11694330B2 (en) | Medical image processing apparatus, system, and method | |
| WO2023102229A1 (en) | Aneurysm modeling and risk prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |