CN114782358A

CN114782358A - Method and device for automatically calculating blood vessel deformation and storage medium

Info

Publication number: CN114782358A
Application number: CN202210407084.5A
Authority: CN
Inventors: 涂圣贤; 李春明; 常云霄; 李莹光
Original assignee: Shanghai Bodong Medical Technology Co ltd
Current assignee: Shanghai Bodong Medical Technology Co ltd
Priority date: 2022-04-18
Filing date: 2022-04-18
Publication date: 2022-07-22

Abstract

The invention discloses a method, a device and a storage medium for automatically calculating blood vessel deformation, which are used for acquiring blood vessel data, wherein the blood vessel data comprises image data; selecting key frame image data in different parts of the cardiac cycle from the image data according to the cardiac cycle; registering the selected key frame image data to obtain registered key frame image data; calculating relative deformation data based on the registered key frame image data; calculating absolute deformation data based on the registered key frame image data; and obtaining the deformation result of the blood vessel based on the relative deformation data and/or the absolute deformation data. The method can monitor the lumen deformation of the same position of the blood vessel at different moments in real time, can acquire the plaque stability, can be used for calculating a myocardial bridge or other special parameters, can know the overall condition of a specific coronary blood vessel, realizes the assessment of quantitative anatomical relevant parameters of the coronary heart disease, and has higher accuracy.

Description

Method and device for automatically calculating blood vessel deformation and storage medium

Technical Field

The invention relates to the technical field of medical treatment, in particular to a method and a device for automatically calculating vascular deformation and a storage medium.

Background

Generally, the greater the deformation at a particular location in a blood vessel, the more unstable the plaque and the susceptibility to adverse cardiovascular events. To date, the prior art can use intra-cavity imaging such as IVUS/OCT to assess plaque stability, but can not use coronary imaging to assess plaque stability. Coronary angiography is the most common tool for clinical assessment of coronary heart disease. If there is a way to display the deformation of the blood vessel directly using the coronary angiography imaging, it is possible to more conveniently acquire advantageous information.

Prior art 1 (application number 202110025833.3, entitled as a monitoring display method and system for automatically evaluating vascular deformation) discloses a method for identifying and detecting blood vessel contour lines in vascular deformation evaluation, but the registration mode of the contour lines in the patent may have the defects of image and central vessel key information, and influence the matching and corresponding problems between matching medical influences, for example, registration can be performed only by the trend of the lumen, so as to obtain the diameter parameters of the lumen, the obtained parameter data is single, the structural shape or change dynamics of the lumen cannot be obtained, the accuracy of the whole blood vessel evaluation is reduced, in addition, through the matching mode of the contour lines, image processing needs to be performed on the obtained image data first to obtain the contour of the blood vessel of interest, image processing steps are added, and during registration, the method can only perform registration on the selected blood vessels, and is limited in the evaluation mode of the blood vessels, so that all registration modes and effects cannot be covered.

In prior art 2 (patent application No. 202010289747.9, entitled a method, system, computing device, and storage medium for processing a blood vessel image), a method for processing a blood vessel image is disclosed, in which contour parameter information of a blood vessel segment of interest is processed to obtain a fractional flow reserve value, the method still needs to process image data, select a blood vessel of interest, and then perform computation on the entire contour of the blood vessel of interest, so as to obtain a fractional flow reserve value and an official cavity contour.

Prior art 3 (patent application No. US20170017771A1, entitled SYSTEMS AND METHODS FOR ESTIMATING tissue AND cardiovascular effects ON PLAQUE AND MONITORING PATIENT RISK) discloses a method FOR ESTIMATING a HEMODYNAMIC value in a blood vessel according to a blood vessel specific parameter AND a set model FOR a specific blood vessel to estimate a lesion of the blood vessel, wherein firstly, a calculation is being performed ON a specific blood vessel of interest, AND a plurality of blood vessels cannot be estimated AND monitored, AND secondly, PLAQUE condition of the blood vessel is estimated by a fractional flow reserve value, AND the method does not relate to comparison of blood vessel conditions at different moments, AND a result of blood vessel deformation cannot be performed.

In conventional art 4 (patent application No. JP2009106530A, entitled medical image processing apparatus, medical image processing method, and medical image diagnostic apparatus), there is disclosed medical image processing for heart diseases, in which abnormal portions of the heart are estimated based on the aforementioned heart wall information in the image information, and then based on the abnormal portion information and the images of the vessel portions, lesions of the heart vessels are acquired, and it is mainly the combination of the shape and state information of the coronary arteries obtained from C T video and the function information of the wall motion reduction region obtained from the ultrasonic image, and blood vessel lesion portions such as stenotic or occluded portions are acquired.

Therefore, a new method and a new device are needed, which do not need to acquire the contour structure of the blood vessel, can directly perform registration from the medical image, and then select a single or multiple blood vessels of interest for parameter calculation as needed, thereby adopting the technical means of image data direct registration, solving the problems of complicated image processing, missing whole image data, unidentifiable tissue structure and single selection of the blood vessels of interest in the contour registration process, and achieving the technical effect of acquiring information such as deformation parameters and deformation positions of multiple blood vessels after one-time registration.

Disclosure of Invention

In view of the above drawbacks and deficiencies, it is an object of the present invention to provide a method, an apparatus, and a storage medium for automatic calculation of vascular deformation.

In order to achieve the above purpose, the technical scheme of the invention is as follows:

a method of automated computation of vessel deformation, comprising:

acquiring blood vessel data, the blood vessel data comprising image data;

selecting key frame image data in different parts of the cardiac cycle from the image data according to the cardiac cycle;

registering the selected key frame image data to obtain registered key frame image data;

calculating relative deformation data based on the registered key frame image data;

calculating absolute deformation data based on the registered key frame image data;

and obtaining a deformation result of the blood vessel based on the relative deformation data and/or the absolute deformation data.

Selecting key frame image data in different portions of a cardiac cycle from the image data, comprising:

dividing at least one cardiac cycle into a plurality of parts according to a preset time period, and selecting multi-frame image data of each part;

by filtering, key frame image data of each section is selected from the multiple frames of image data of each section.

The selecting of the multiple frames of image data of each part comprises the following steps:

and carrying out image processing on the image data, and selecting multi-frame image data according to any one of the image definition, the blood vessel overlapping degree or the blood vessel boundary definition.

The registering the selected key frame image data includes:

performing image registration on keyframe image data of different cardiac cycle sections so that the same vessel of interest corresponds;

and calculating relative deformation data and/or absolute deformation data of the blood vessel according to the registered key frame image data.

The basis of image registration includes:

one or more of a vessel shape, a vessel size, a vessel or perivascular tissue feature of the keyframe image data.

The method further comprises the following steps:

acquiring parameters of a blood vessel of interest according to the registered key frame image data, wherein the parameters of the blood vessel of interest comprise: any one or more of the contour of the vessel, the lumen diameter, the value of the lumen diameter over time, the location of the change in the lumen diameter of the vessel, hemodynamic parameters.

The method further comprises the following steps:

and displaying the deformation result of the blood vessel through pseudo color.

And in the process of displaying the pseudo color, filling different colors according to the size of the deformation so as to reflect the size of the deformation of the blood vessel.

An automatic calculation device for vascular deformation, comprising: the device comprises an image device, a processing module and a display; the processing module comprises a selection unit, a registration unit and a calculation unit;

the image device is used for acquiring image data;

the processing module is used for processing the image data; wherein the content of the first and second substances,

the selection unit is used for selecting key frame image data in different parts of the cardiac cycle from the image data according to the cardiac cycle;

the registration unit is used for registering the selected key frame image data to obtain registered key frame image data;

the calculating unit is used for calculating relative deformation data and/or absolute deformation data according to the registered key frame image data;

and the display is used for displaying the deformation result of the blood vessel obtained based on the relative deformation data and/or the absolute deformation data.

An electronic device, comprising:

a processor; and (c) a second step of,

a memory for storing the program, wherein the program is stored in the memory,

wherein the program comprises instructions which, when executed by the processor, cause the processor to carry out the method according to the above.

A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method according to the above.

Compared with the prior art, the invention has the beneficial effects that:

the invention provides a method, a device and a storage medium for automatically calculating blood vessel deformation, which are characterized in that key frame image data of a blood vessel of interest are obtained from a medical image, then the obtained image images are accurately registered according to the image data to obtain various parameters of the blood vessel of interest at different moments, and further the lumen deformation of the same position of the blood vessel at different moments is monitored in real time, because the image data contains more information of the blood vessel of interest and tissues, accurate registration can be assisted, and the registration is more accurate and rapid, in the invention, the whole condition of a specific coronary vessel can be pre-judged and the diagnosis and prediction of the state of an illness can be carried out in time by acquiring plaque stability and simultaneously using myocardial bridge or other parameter calculation, so that the evaluation of quantitative anatomical relevant parameters of the coronary heart disease is realized, the accuracy is higher, has high clinical use value.

Drawings

FIG. 1 is a flow chart of a method for automatically calculating the deformation of a blood vessel according to the present invention;

FIG. 2 is a pseudo-color image of the method for automatically calculating vascular deformation according to the present invention;

FIG. 3 is a schematic structural diagram of an automatic calculation apparatus for vascular deformation according to the present invention;

FIG. 4 is a schematic diagram of a processing module according to the present invention;

FIG. 5 is a schematic structural diagram of an automatic calculation apparatus for vascular deformation according to the present invention;

fig. 6 is a schematic of the structure of the electronic device of the present invention.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "including" and variations thereof as used herein is intended to be open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description. It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a" or "an" in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will appreciate that references to "one or more" are intended to be exemplary and not limiting unless the context clearly indicates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

The size of the coronary vessel lumen is affected by the contraction and relaxation of the heart, in addition to the plaque itself. Under the conditions that the plaque is soft and the stress of the plaque is large, the deformation of the blood vessel lumen at the corresponding position is greatly influenced by the contraction/relaxation condition of the heart, the size of the blood vessel lumen at different moments is monitored, the plaque can be monitored in real time, and the stability of the plaque is reflected.

As shown in fig. 1, the present invention provides a method for automatically evaluating and calculating vascular deformation, comprising:

s1, obtaining blood vessel data, wherein the blood vessel data comprises image data;

in an embodiment of the present invention, the image data includes four-dimensional image data, three-dimensional image data, or two-dimensional image data; or image data containing cardiac cycle data or parameters of the vessel of interest and a lumen model. For example, the image data may be medical image data acquired by high-resolution CT, OCT, IVUS, X-ray, b-mode or other detection means, and in this embodiment, the image data needs to include an image of a blood vessel, which may be, for example, an image of a blood vessel, or a feature image of a blood vessel, where the feature image includes a geometric feature or a blood vessel contour of a reference lumen obtained by reconstructing a non-diseased state from blood vessel original geometric feature data. Wherein the parameters of the vessel of interest comprise at least: a lumen diameter of the blood vessel, a degree of change in the lumen diameter of the blood vessel over time, a location of change in the lumen diameter of the blood vessel, or a hemodynamic parameter; the hemodynamic parameter includes at least fractional flow reserve.

The pressure decreases during diastole, the vena cava blood returns to the heart, and the pressure increases during systole, pumping blood into the arteries, and each contraction and diastole of the heart constitutes a cardiac cycle (cardiac cycle). The cardiac cycle data at least comprises all data in one systolic phase and one diastolic phase, specifically including but not limited to an electrocardiogram, a shape, a length, a diameter, a bending angle, a blood flow velocity, a blood pressure and the like of a target region blood vessel, and can be acquired according to requirements. In the present invention, the image data includes: image data containing cardiac cycle data.

After obtaining the blood vessel data, the invention also comprises the following steps:

and judging whether the image contains the electrocardiogram data, if so, identifying and dividing the cardiac cycle according to the electrocardiogram data to obtain cardiac cycle data. If the electrocardiogram data is not included, the image data is processed (the processing includes automatic processing or manual selection) to obtain the cardiac cycle data.

Because the blood vessels cannot directly acquire the electrocardiographic information from the image data when contracting or expanding, for example, when one or more image images are seen, it cannot be judged that the blood vessels of interest in the image images are in an expanding or contracting state, in this embodiment, the medical images and the cardiac cycle information need to be identified, so that the time of the cardiac cycle corresponding to the image data can be identified, and based on this, the image data and the cardiac cycle data are linked through two types of modes to generate the image data;

first, it is a type of image data with cardiac cycle data:

because some image acquisition devices in the prior art can directly label the cardiac cycle data corresponding to the image when acquiring the image data, the obtained image data can carry electrocardiogram data, and the image data containing the cardiac cycle data can be obtained by directly extracting the cardiac cycle data in the image data; the image data can be directly acquired, and can be directly used without being processed, so that the operation identification is convenient and quick.

Second, for the type where the image data does not carry cardiac cycle data:

in the method, the data of the cardiac cycle is obtained through deep learning, and image data containing the data of the cardiac cycle is generated;

this is the case primarily for existing image data without electrocardiogram data, which needs to be identified and labeled. The cardiac cycle is associated with the image data and displayed simultaneously, so that the image of the target blood vessel area at the characteristic moment in any cardiac cycle can be obtained; or, after selecting the image, it is possible to obtain immediately at which moment in the cardiac cycle the vessel of interest is located.

The process specifically comprises the following steps:

acquiring image data as much as possible, acquiring diastolic data and systolic data of a target region blood vessel, labeling the diastolic data and the systolic data respectively, identifying characteristics of the diastolic data and the systolic data, training, realizing automatic identification of a cardiac cycle, and enabling image data information of the blood vessel of the target region of the blood vessel to be associated with the cardiac cycle data.

Wherein the labeling the diastolic data and the systolic data respectively comprises: labeling the image data of each frame by manually labeling the diastolic data and the systolic data.

Illustratively, there are two ways to mark the diastolic data and the systolic data separately:

the first method is manual labeling, which is experienced manual labeling, and labels the diastolic data and the systolic data manually, and performs manual labeling on each frame of image data, that is, a label is defined for each frame of image data.

And secondly, the fast labeling is carried out by utilizing the information of the electrocardiogram carried by the user, the method needs the electrocardiogram information, and then the fast labeling is carried out on each frame of image data.

And building a network model for the labeled image data, and training a neural network through deep learning, so that the neural network can have a function of quickly identifying the image data. For example, AI techniques are used to automatically detect end systole and end diastole, and the specific method is to add labeled data by deep learning, and the labeling is to label each frame of image with a label. For example, the frame is end-systolic, the frame is end-diastolic, the frame is other frames, and then the convolutional neural network is trained. If there is any more ECG data, the ECG data can be preferentially used to determine systole or diastole without the need to run the AI model. The AI technology of the invention mainly carries out deep learning through a U-Net network. U-Net network is 2015, OlafRonneberger et al propose a network structure, and U-Net network is a semantic segmentation network based on FCN, and is suitable for medical image segmentation. The U-net network structure is similar to the FCN network structure and also comprises a down-sampling stage and an up-sampling stage, the network structure only comprises a convolution layer and a pooling layer and does not comprise a full connection layer, a shallow high-resolution layer in the network is used for solving the problem of pixel positioning, and a deep layer is used for solving the problem of pixel classification, so that the segmentation of the image semantic level can be realized. The whole process is encoding and decoding (encoder-decoder), picture classification and segmentation are carried out by taking pictures as a whole, the input is an image (multi-channel or single-channel), and the output is a classified image with the same size and labels.

The U-net uses a trained neural network, using a full convolutional neural network, through which a picture of arbitrary size can be input, and the output is also a picture, so this is an end-to-end network.

Firstly, U-net constructs a Caffe frame, SGD transmission is adopted, each batch has one picture, momentum is selected to be 0.99, cross entropy loss and softmax are adopted, and the function form is as follows:

ak (x) represents the score of the feature channel (K) corresponding to each pixel (x), K represents the number of classes, pk (x) represents the classification result of the class K on the pixel x, so that the most probable result is maximized, and the probability of other classes is suppressed.

Penalty with weight:

wherein l is the true label of each pixel

w is a weight map, which distinguishes the weight of each pixel.

In order to compensate the frequency difference of different pixel points of a certain category, a GT sample is used for pre-calculating a w weight graph. Let the web learn to distinguish smaller boundaries. The end-to-end input means that the original data is directly input, and the result is finally output without manual participation in the middle.

The loss function (loss function), also called objective function (objective function), is an important equation for measuring the difference between the predicted value and the target value, and the higher the output value (loss) of the loss function is, the larger the difference is, the training of the deep neural network becomes a process for reducing the loss as much as possible. The back propagation algorithm is a back propagation motion taking error loss as a leading factor, and aims to obtain the parameters of the optimal neural network model. Specifically, the error loss is generated by transmitting the input signal in the forward direction until the output, and the parameters in the initial neural network model are updated by reversely propagating the error loss information, so that the error loss is converged. Such as a weight matrix.

The weight matrix formula is as follows:

ω c Ω → R is a weight graph to balance a certain class of frequencies;

d1: Ω → R represents the distance from a certain pixel to the background to the nearest cell boundary;

d2 Ω → R represents the distance from a certain pixel to the background to the next closest cell boundary;

setting omega 0 to 10, and sigma to 5 pixels;

the further away w0exp (-) is, almost 0, so you see far away from the tissue, the weight is essentially the same, close to Wc. The farther from the tissue, the smaller the weight, and conversely, the larger the weight of the pixel points on the boundary, so that the boundaries of tissues in adjacent images and the same tissue can be easily distinguished.

Then, the weights are initialized using a Gaussian distribution with a standard deviation of

Where N denotes the number of input nodes of a neuron, e.g., for a convolution of 3x3, the previous layer has 64 feature channels, and N-9 x 64-576.

And finally, translating, rotating, deforming and carrying out gray processing on the image, and generating smooth deformation on a coarse 3 multiplied by 3 grid by using a random displacement vector. The displacement vector is sampled from a gaussian distribution with a standard deviation of 10. Each pixel displacement is then calculated using a biquadratic interpolation. The last dropout of the coupling path also serves as data enhancement.

The method uses a sliding window to predict the class label of each pixel, provides the surrounding area (patch) of the pixel as input, and effectively utilizes data enhancement to use the available labeled data through the learning of a neural network.

The recognition mode is more intelligent and convenient, can process various different medical image information, and has the advantages of high processing speed, high accuracy and wide application range.

For the image acquisition device without the cardiac cycle data, the image data containing the cardiac cycle data, can also be directly identified in a manual mode.

The method in the embodiment needs rich medical experience of an operator, has good knowledge on biological characteristics of blood vessels, can directly identify the time in the cardiac cycle of a plurality of arbitrary image data after directly identifying the image data, and then carries out annotation identification.

S2, selecting key frame image data in different parts of the cardiac cycle from the image data according to the cardiac cycle;

the method specifically comprises the following steps: segmenting the image data in at least one cardiac cycle into a plurality of sections according to a preset time period, and then selecting key frame image data in each section:

2.1, dividing at least one cardiac cycle into a plurality of parts according to a preset time period, and selecting multi-frame image data of each part;

the method comprises the steps of dividing a cardiac cycle into a plurality of parts according to a preset time period, wherein the dividing mode can be set according to needs, is not limited to the mode in the embodiment, can be each time point corresponding to each image data which is clear in image data of one cardiac cycle and is beneficial to analysis, and can also be according to a monitoring time interval; preferably, the segmentation may be performed according to characteristics of the position of the target blood vessel region.

In the present invention, a preset time period is taken as an example for explanation, the cardiac cycle is divided into 4 parts, and each of a diastole and a systole includes two parts; illustratively, the cardiac cycle data may be divided into three portions, and the predetermined time period includes at least a diastole and a systole, the diastole being divided into two portions since the diastole is generally one time longer than the systole.

Or averagely dividing the cardiac cycle data in one cardiac cycle into a plurality of parts according to a preset time period; multiple frames of image data within each portion of the cardiac cycle are then identified based on the image data.

When multi-frame image data is selected, the multi-frame image data needs to be selected according to requirements or characteristics of the image, for example, the image data is subjected to image processing, and the processing mode can be image processing tools such as gray processing, sharpness processing, brightness processing and the like of the image, so that the image data can meet the required requirements and meet the selected standard.

The selected criteria include at least: and multiple frames of image data according to the image definition, the blood vessel overlapping degree or the blood vessel boundary definition.

When image processing is carried out, image processing can be carried out on single image data respectively according to the quality of the images, or batch unified processing can be carried out, the single image processing is suitable for the images with larger image quality difference, the whole images meet the requirements, and only the single image processing is needed; the whole processing is fast, but the requirement of due processing is difficult to be considered for the image with poor individual quality, so the two modes can be combined according to the actual situation in the actual operation.

2.2, selecting key frame image data of each part from the image data of each part through screening;

at least one set of multi-frame image data with high image quality in each part is selected as a representative as key frame image data.

And S3, registering the selected key frame image data to obtain registered key frame image data.

The method specifically comprises the following steps:

after the key frame image data of a plurality of cardiac cycles are registered, deformation image data of the blood vessel and deformation parameter data of the blood vessel are obtained, and the deformation state of the interested blood vessel is obtained.

3.1, carrying out image registration on key frame image data of different cardiac cycle parts so as to enable the same interested blood vessel to correspond;

when the key frame image data is registered, the registration can be performed in various ways, and firstly, the registration can be performed directly through the characteristics of the blood vessels, and also can be performed directly through the whole image.

The characteristic registration includes a contour registration mode, a branch structure characteristic and other registration modes, for example, the contour registration criterion is to register the blood vessel at the interested position at different moments after acquiring the contour graph of the image, and perform corresponding matching registration on the image data (contour) of a plurality of blood vessels at different moments to obtain the deformation difference of the blood vessel. The registration mode is more targeted, and can directly perform registration comparison according to the shape of the blood vessel to be obtained, so that the deformation state can be intuitively obtained.

The contour registration method specifically comprises the following steps: processing the key frame image data in different periods to obtain blood vessel contour image data; registering the key frame blood vessel contour image data in different periods to obtain the correspondence of the same interested blood vessel; the registration mode is single, only selected interested blood vessels can be registered, and the registered images are contour image data and morphological images of the blood vessels cannot be obtained.

However, the overall image matching criterion is based on feature-based image registration, gray-scale-based image registration and transform domain-based image registration, and specifically includes: one or more of the vessel shape, the vessel size, the vessel or the tissue characteristics around the vessel of the keyframe image data are correspondingly matched and registered to obtain a plurality of vessels in the image, and then specific vessel lumen parameters are obtained according to the vessels of interest to obtain the deformation difference of the vessels. The same blood vessel can be identified and registered by the images at different moments according to the blood vessel forms and tissues, the registration mode is more accurate, the obtained image information is more abundant and comprehensive, and the required blood vessel characteristics can be further extracted according to the requirements.

And 3.2, calculating relative deformation data and/or absolute deformation data of the blood vessel according to the registered key frame image data.

The method comprises the following steps:

the same interested blood vessel is corresponded, and deformation parameters of the blood vessel are calculated;

calculating the maximum vessel diameter and the minimum vessel diameter of the same vessel of interest at the same moment; and/or (c) and/or,

and judging the deformation of the target blood vessel by the diameter change of the blood vessel at the same position of the same blood vessel of interest at different moments.

In addition, the deformation parameter of the blood vessel of interest can also be reflected by coordinates and graphs, for example, a blood vessel coordinate image can be drawn, wherein the horizontal axis represents the length of the blood vessel, the vertical axis represents the diameter of the blood vessel at different positions, and the two curves represent the maximum diameter and the minimum diameter of the blood vessel at different times respectively. And, the position where the deformation is the largest is marked and displayed with a vertical line.

Specifically, the relative deformation data and the absolute deformation data include:

based on the relative deformation calculation formula of the blood vessels at different moments of the cardiac cycle:

rws (radial Wall strain), radial Wall strain, i.e. relative deformation; diammax, maximum vessel diameter; diamin, minimum vessel diameter;

calculating a formula based on the absolute deformation of blood vessels at different moments of the cardiac cycle:

absolute vascular deformation is Diammax-Diammin.

Preferably, after obtaining the deformation result of the blood vessel and determining that the target blood vessel is deformed, the method further includes:

and carrying out danger reminding by means of alarming or displaying a mark. The reminding can be realized by carrying out alarm prompting or transmitting to a specified terminal in a wireless transmission mode after intelligent identification, and the terminal can be a user mobile phone and also can be an internet cloud platform and the like. And the imaging display interface can also be used for directly carrying out annotation prompt or displaying the position of the lesion.

Preferably, after determining that the target blood vessel is deformed, the method further comprises: and identifying user information, calling image data used in a medical record according to the user information, and displaying the current blood vessel medical record image data, the current blood vessel multicycle image data, the lumen parameter and the hemodynamic parameter. The process can store all data to form the electronic medical record, help to obtain the data information of the electronic medical record in time, and save the time for seeing a doctor.

Finally, the embodiment of the invention also comprises the step of displaying the deformation result of the blood vessel through a three-dimensional or four-dimensional modeling image, a pseudo-color image and a blood vessel outline image. Illustratively, the display device displays the images in a pseudo-color, two-dimensional or three-dimensional manner, the display at least includes each image data, data coordinates, a stereo model and the like, and the display manner may be multi-screen display in one interface or single-selection display.

The three-dimensional modeling image is a three-dimensional image (volume) three-dimensional modeling structure of the blood vessel of interest, and the structure of the device is displayed through a display device; the four-dimensional modeling image is a morphological structure of four-dimensional image data (three-dimensional + time) which can be acquired in a complete heart cycle, and the image is more visual and complete to display and does not need further time marking.

As shown in fig. 2, the image is a pseudo-color image, wherein the abscissa is the distance from the initial position of the marked blood vessel, the ordinate is the lumen diameter of the blood vessel, two curves on the coordinate axis represent the maximum diameter and the minimum diameter of the lumen of the blood vessel respectively, the vertical height difference of the two curves represents the deformation values of the blood vessel in different phases, the larger the deformation value is, the darker the pseudo-color is, and the smaller the deformation value is, the lighter the pseudo-color is; color images, also known as Pseudo-Color (Pseudo-Color) images, have the Color of each pixel not directly determined by the value of each basic Color component, but rather by using the pixel as an entry address for a Color palette (palette) or Color Look-Up Table (CLUT) entry, from which the intensity value containing the actual R, G, B can be found, and if the Color in the image does not exist in the Color palette or Color Look-Up Table, the Color palette is matched with the closest Color. The colors produced by the looked-up R, G, B intensity values are not the true colors of the image itself and are therefore referred to as pseudo-colors. In the invention, the three-dimensional or two-dimensional structure of the image is virtually displayed through color filling, different depth colors of the displayed image can be given according to the numerical value of the deformation parameter data of the blood vessel, wherein the distance difference between the maximum value and the minimum value is an absolute deformation value, and the filling between the maximum value and the minimum value represents the magnitude of the absolute deformation value. In fig. 2, for example, red, orange, yellow, green, and blue indicate that the severity of vascular deformation decreases in order, for example, red indicates that vascular deformation is severe, and blue indicates that blood vessels are normal. The display mode can directly obtain a plurality of information such as the state, the structure, the parameters and the like of the blood vessel, so that the dynamic change of the blood vessel can be monitored visually. The deformation size is endowed with different colors, and the deformation size of the blood vessel is reflected.

In this embodiment, the one or more image data may be received using various medical imaging modalities. For example, according to various embodiments of the invention, a sequence of three-dimensional CT data, two-dimensional dynamic angiography data, and/or rotational angiography data may be received, although the invention is not limited thereto. The image data may be received directly from one or more image acquisition devices, such as a CT scanner or an X-ray device. The previously stored image data may also be loaded, for example, from a memory or storage device of the computer system, or some other computer-readable storage medium.

Preferably, the embodiment of the present invention may further obtain the parameter of the blood vessel of interest according to the key frame image data.

The parameters of the blood vessel include: lumen diameter of the blood vessel, degree of change of the lumen diameter of the blood vessel with time, position of change of the lumen diameter of the blood vessel, and hemodynamic parameters.

The specific acquisition of the lumen diameter of the blood vessel is: with image data, the contour image of the blood vessel is obtained, the contour image is subjected to image processing, the whole contour structure of the blood vessel can be obtained, the maximum value and the minimum value of the diameter of the lumen of the blood vessel at the same position at different moments can be further obtained, the data can visually reflect the influence of the plaque on the systolic/diastolic condition in the blood flow process, the actual blood vessel condition can be further accurately reflected, an intermediate variable with smaller error is provided for the later analysis and calculation, and the calculated value at the later stage is closer to the actual value.

When the lumen of the blood vessel is deformed, the diameter of the blood vessel changes with time or by calculating the change degree of the diameter of the blood vessel, quantitative judgment of the deformation is obtained, for example, the change of the diameter in the same cardiac cycle time can be calculated, the deformation process of the blood vessel is judged, or the deformation process of the blood vessel and the change value of the diameter of the blood vessel in a normal state are judged, the deformation degree of the blood vessel is judged, and further the severity degree of the deformation is judged. Or the position of the change of the vessel lumen diameter can acquire the position of the vessel deformation and the change process in time, and grasp the disease condition in time.

In addition, the hemodynamic parameters include at least flow velocity, pressure, and specific shear stress. By the correspondence of the above data with the image, the fluidity of the blood vessel can be reflected, and the state of the blood vessel can be indirectly obtained.

Furthermore, different medical imaging principles are different, so the contrast media used are different, and the injection time, speed, etc. are different, and angiography refers to injecting a contrast medium into a blood vessel through arterial injection or intravenous injection to visualize the blood vessel, and then observing the morphology of the blood vessel or lesion morphology using equipment such as CT, ultrasound, or nuclear magnetic resonance, digital angiography, etc. In general, the density of blood vessels and other tissues is similar, and when the blood vessels or lesions associated with the blood vessels are observed using the above-described apparatus, the display is unclear. Therefore, after the contrast agent is injected into the blood vessel, the density or the signal of the blood vessel can be greatly different from the surrounding tissues, so that the observation of the blood vessel or the lesion is clearer.

Clinically common angiography is mainly angiography under CT, referred to as CTA, or nuclear magnetic angiography, referred to as MRA, and interventional angiography performed under a digital angiography machine. The morphology of the vascular lesion can be clearly and clearly observed by these imaging.

The flow parameters of the contrast medium then include at least: flow rate, diffusion time, concentration change of the imaging medium in the vessel of interest. Therefore, depending on the type of contrast selected, a model of the diffusion of the contrast medium in the blood vessel or a model of the appearance state can be constructed so that anomalies of the blood vessel are identified.

Thus, changes in the vessel lumen can also be observed through changes in the medium, and thus a model can also be established for correlating the image data extraction time with the diffusion time, space of the contrast agent.

It should be noted that, in the embodiment of the present invention, the parameter of the blood vessel is not limited to the above parameter, and may also be other parameters related to the blood vessel, and the embodiment is an exemplary description of the above.

As shown in fig. 3 and 4, an embodiment of the present invention further provides an automatic calculation apparatus for vascular deformation, which includes an image apparatus 1, a processing module 2, and a display 3; wherein, the processing module 2 comprises a selecting unit 21, a registering unit 22 and a calculating unit 23;

the image device 1 is used for acquiring image data; as an example, a CT machine, a contrast imaging apparatus, etc.;

the processing module 2 is used for processing the image data; wherein, the first and the second end of the pipe are connected with each other,

the selecting unit 21 is configured to select, according to the cardiac cycle, key frame image data in different parts of the cardiac cycle from the image data;

a registration unit 22, configured to register the selected key frame image data to obtain registered key frame image data;

the calculating unit 23 is configured to calculate relative deformation data and/or absolute deformation data according to the registered keyframe image data;

and the display 3 is used for displaying the deformation result of the blood vessel obtained based on the relative deformation data and/or the absolute deformation data.

Wherein the image data comprises four-dimensional image data, three-dimensional image data or two-dimensional image data, or image data containing cardiac cycle data.

The system also comprises an acquisition module 4, which is specifically used for acquiring image data by extracting self-contained cardiac cycle data in the image data; or, obtaining cardiac cycle data through deep learning to generate image data; or, the cardiac cycle data is identified in a manual identification and marking mode to obtain image data.

The selecting unit 21 is specifically configured to divide at least one cardiac cycle into a plurality of portions according to a preset time period, select multi-frame image data of each portion, and select, through screening, key frame image data of each portion from the multi-frame image data of each portion;

the method comprises the steps of dividing at least one cardiac cycle into a plurality of parts, selecting multi-frame image data of each part, carrying out image processing on the image data, and selecting multi-frame image data at least comprising image definition, blood vessel outline definition or blood vessel surrounding tissue definition. The parameters of the blood vessel comprise the lumen diameter of the blood vessel, the flow parameters of the contrast medium and the blood flow mechanics parameters.

The flow parameters of the contrast medium comprise at least: flow velocity, diffusion time, concentration change of the imaging medium in the vessel of interest; the hemodynamic parameters include at least flow velocity, pressure, and specific shear stress.

The registration unit 22 is specifically configured to perform image registration on the keyframe image data in different periods so as to enable the same vessel of interest to correspond to each other;

the calculating unit 23 is configured to calculate a deformation parameter of the blood vessel according to the registered keyframe image data. The same interested blood vessel is corresponded, and deformation parameters of the blood vessel are calculated; calculating the maximum vessel diameter and the minimum vessel diameter of the same vessel of interest at the same moment; and/or judging the deformation of the target blood vessel due to the change of the diameters of the blood vessel at the same position of the same interested blood vessel at different moments.

As shown in fig. 5, the apparatus of this embodiment preferably further includes an alarm module 5 for performing a danger alert by alarming or displaying a mark.

Preferably, the storage module 6 is further included for identifying user information, retrieving image data for medical record according to the user information, and displaying current blood vessel medical record image data, current blood vessel multicycle image data, lumen parameters, and hemodynamic parameters.

An electronic device, comprising:

a processor; and (c) a second step of,

a memory for storing the program, wherein the program is stored in the memory,

wherein the program comprises instructions which, when executed by the processor, cause the processor to carry out the method of automated vessel deformation assessment computation according to any of the above embodiments.

A non-transitory computer readable storage medium storing computer instructions for causing the computer to execute the method for automatic blood vessel deformation evaluation calculation according to any one of the above embodiments.

The exemplary embodiments of the present disclosure also provide a computer program product comprising a computer program, wherein the computer program, when executed by a processor of a computer, is adapted to cause the computer to perform a method according to an embodiment of the present disclosure.

Referring to fig. 6, a block diagram of the structure of an electronic device 7, which may be a server or a client of the present disclosure, which is an example of a hardware device that can be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the electronic apparatus 7 includes an arithmetic unit 71 that can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)72 or a computer program loaded from a storage unit 78 into a Random Access Memory (RAM) 73. In the RAM 803, various programs and data necessary for the operation of the device 7 can also be stored. The arithmetic unit 71, the ROM 72, and the RAM73 are connected to each other by a bus 74. An input/output (I/O) interface 75 is also connected to bus 74.

A plurality of components in the electronic device 7 are connected to the I/O interface 75, including: an input unit 76, an output unit 77, a storage unit 78, and a communication unit 79. The input unit 76 may be any type of device capable of inputting information to the electronic device 7, and the input unit 76 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. Output unit 77 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. The storage unit 804 may include, but is not limited to, a magnetic disk and an optical disk. The communication unit 79 allows the electronic device 7 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, WiFi devices, WiMax devices, cellular communication devices, and/or the like.

The arithmetic unit 71 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the arithmetic unit 71 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The arithmetic unit 71 performs the respective methods and processes described above. For example, in some embodiments, the method of automated vascular deformation assessment calculation may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 78. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 7 via the ROM 72 and/or the communication unit 79. In some embodiments, the arithmetic unit 71 may be configured by any other suitable means (e.g. by means of firmware) to perform a method of automated vessel deformation assessment calculation.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, causes the functions/acts specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the procedures or functions described in the embodiments of the present disclosure are performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, a terminal, a user device, or other programmable apparatus. The computer program or instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer program or instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that integrates one or more available media. The usable medium may be a magnetic medium, such as a floppy disk, hard disk, magnetic tape; or an optical medium, such as a Digital Video Disc (DVD); it may also be a semiconductor medium, such as a Solid State Drive (SSD).

It will be appreciated by those skilled in the art that the foregoing specific embodiments are merely illustrative of the preferred embodiments of the invention, and that various modifications, changes, substitutions and alterations of certain parts of the invention may be made by those skilled in the art without departing from the spirit and scope of the invention.

Claims

1. A method for automatically calculating vascular deformation is characterized by comprising the following steps:

acquiring blood vessel data, the blood vessel data comprising image data;

2. The method of claim, wherein selecting keyframe image data from the image data in different portions of the cardiac cycle comprises:

by filtering, the key frame image data of each section is selected from the multi-frame image data of each section.

3. The method according to claim 2, wherein the selecting of the plurality of frames of image data of each portion comprises:

4. The method of claim 1 or 3, wherein registering the selected key frame image data comprises:

performing image registration on the keyframe image data of different cardiac cycle sections so that the same vessel of interest corresponds;

5. The method of claim 4, wherein the basis for image registration comprises:

6. The method according to claim 4 or 5, further comprising:

7. The method according to any one of claims 1 to 6, further comprising:

and displaying the deformation result of the blood vessel through pseudo color.

8. An apparatus for automatic calculation of vascular deformation, comprising: the device comprises an image device, a processing module and a display; the processing module comprises a selecting unit, a registering unit and a calculating unit;

the image device is used for collecting image data;

9. An electronic device, comprising:

a processor; and the number of the first and second groups,

a memory for storing the program, wherein the program is stored in the memory,

wherein the program comprises instructions which, when executed by the processor, cause the processor to carry out the method according to any one of claims 1 to 7.

10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method according to any one of claims 1 to 7.