CN113744246A

CN113744246A - Method and device for predicting fractional flow reserve from vascular tomography images

Info

Publication number: CN113744246A
Application number: CN202111034145.XA
Authority: CN
Inventors: 夏天祎; 曹君
Original assignee: Lepu Medical Technology Beijing Co Ltd
Current assignee: Lepu Medical Technology Beijing Co Ltd
Priority date: 2021-09-03
Filing date: 2021-09-03
Publication date: 2021-12-03
Anticipated expiration: 2041-09-03
Also published as: CN113744246B

Abstract

The embodiment of the invention relates to a method and a device for predicting fractional flow reserve according to a vascular tomography image, wherein the method comprises the following steps: acquiring a first cross-section sequence of a first tomography image; calculating the cross-sectional area and the blood movement distance of each first section to generate a first area-distance data set; performing curve conversion on the first area-distance data group sequence to generate a first curve; performing vessel stenosis segment identification on the first curve to generate a plurality of first stenosis segments; recording as first non-stenosis segments curved line segments separated by respective first stenosis segments; performing first flow reserve fraction variation prediction to generate first variation data; performing second flow reserve fraction variation prediction to generate second variation data; sorting the first variable data and the second variable data to generate a variable data sequence; and performing section flow reserve fraction prediction processing to generate a first section flow reserve fraction data sequence. The invention can reduce the detection difficulty and improve the detection safety.

Description

Method and device for predicting fractional flow reserve from vascular tomography images

Technical Field

The invention relates to the technical field of data processing, in particular to a method and a device for predicting a fractional flow reserve according to a vascular tomography image.

Background

Fractional Flow Reserve (FFR) refers to the ratio of the mean pressure in the stenotic distal coronary artery to the mean pressure in the coronary artery oral aorta at the maximum hyperemia of the coronary vessels. FFR values are conventionally obtained by Percutaneous Coronary Intervention (PCI). However, PCI detection is not only complicated in operation but also an invasive detection means, and causes a certain amount of physical damage to a detection target, which poses a certain risk.

Disclosure of Invention

The present invention aims to provide a method, an apparatus, an electronic device and a computer-readable storage medium for predicting a fractional flow reserve according to a Tomography image, which estimate a blood vessel cross-sectional area and a blood flow movement distance of a blood vessel cross-sectional sampling sequence of a three-dimensional Tomography image obtained by using a Computed Tomography Angiography (CTA) technique, generate a curve reflecting an area-distance correspondence from the estimation result, identify a blood vessel stenosis section and a non-stenosis section according to the area-distance curve, predict FFR variation of each stenosis section and each non-stenosis section, and finally predict an FFR value of each blood vessel cross-section of a blood vessel according to the predicted FFR variation. The invention can avoid personal injury caused by invasive examination, greatly reduce detection difficulty and improve detection safety.

To achieve the above object, a first aspect of the embodiments of the present invention provides a method for predicting fractional flow reserve from a vascular tomography image, the method including:

acquiring a first cross-section sequence of a first tomography image; the first tomography image is a three-dimensional tomography image; the first sequence of cross sections comprises a plurality of first cross sections; the first section is sampling information obtained by sampling a blood vessel cross section perpendicular to the blood flow direction along the blood flow direction of the first tomography image;

calculating the cross section area of each first section to generate corresponding first area data, calculating the blood movement distance to generate corresponding first distance data, and forming a corresponding first area-distance data group by the obtained first area data and the first distance data; and forming a first area-distance data set sequence by the obtained multiple groups of the first area-distance data sets;

performing curve conversion processing on the first area-distance data set sequence by taking the area as a vertical coordinate and the distance as a horizontal coordinate to generate a first curve;

performing blood vessel stenosis section identification processing on the first curve to generate a plurality of first stenosis sections; and recording as first non-stenosis segments a segment of the curve on the first curve separated by each of the first stenosis segments;

performing first fractional flow reserve variation prediction processing on each first stenosis section to generate corresponding first variation data; performing second blood flow reserve fraction variation prediction processing on each first non-stenosis section to generate corresponding second variation data;

sequencing the obtained first variable data and the second variable data according to the sequence of each first narrow section and each first non-narrow section to generate a variable data sequence;

and performing section flow reserve fraction prediction processing according to the variable quantity data sequence to generate a first section flow reserve fraction data sequence.

Preferably, the first section comprises a plurality of first section edge point coordinates; the specific steps of calculating the cross-sectional area of each first cross-section to generate corresponding first area data, calculating the blood movement distance to generate corresponding first distance data, and forming a corresponding first area-distance data set by the obtained first area data and the first distance data include:

performing closed curve fitting processing according to a plurality of first section edge point coordinates of a current first section to generate a corresponding first closed curve graph;

carrying out graph area estimation processing on the first closed curve graph to generate first area data;

carrying out graph center point estimation processing on the first closed curve graph to generate a first section center point coordinate;

calculating the blood movement distance from the first section center point coordinate to the current first section center point coordinate along the blood flowing direction to generate first distance data;

and forming the corresponding first area-distance data group by the first area data and the first distance data.

Preferably, the performing a blood vessel stenosis section identification process on the first curve to generate a plurality of first stenosis sections specifically includes:

identifying preset blood vessel stenosis section processing mode data;

if the blood vessel stenosis section processing mode data is in a first mode, identifying the peak point of the first curve to generate a plurality of first peak points; recording curves between the adjacent first peak points as first curve interval sections; calculating the absolute difference value of the distance coordinate values of the first coordinate point and the last coordinate point of the first curve interval segment to generate first interval segment distance data; carrying out average calculation on the area coordinate values of the first and last coordinate points of the first curve interval segment to generate first average area data, extracting the minimum area coordinate value of the first curve interval segment to generate first minimum area data, and calculating the ratio of the first minimum area data to the first average area data to generate a first area ratio; when the first compartment distance data is above a preset compartment distance threshold and the first area ratio is below a preset area ratio characteristic threshold, marking the first curvilinear compartment as the first narrow section;

if the blood vessel stenosis section processing mode data is in a second mode, drawing a two-dimensional blood vessel shape graph according to the first curve to generate a first blood vessel shape graph; inputting the first blood vessel shape diagram into a first intelligent model which is trained to be mature to carry out first blood vessel stenosis section segmentation processing, and obtaining a first labeled shape diagram with a plurality of blood vessel stenosis section area labels; and in the first curve, marking curve interval sections corresponding to the markers of the blood vessel narrow section areas of the first marker shape chart as the first narrow section;

if the blood vessel stenosis section processing mode data is a third mode, performing second blood vessel stenosis section segmentation processing on the first tomography image corresponding to the first curve by using a second intelligent model which is well trained to obtain a first marked tomography image with a plurality of blood vessel stenosis section area marks; and in the first curve, a curve interval section corresponding to each blood vessel stenosis region marker of the first marker tomographic image is marked as the first stenosis section.

Further, prior to using the first intelligent model, extracting a first area-distance training curve from a preset training data set; drawing a two-dimensional blood vessel shape graph according to the first area-distance training curve to generate a first training blood vessel shape graph; carrying out artificial blood vessel stenosis section area marking processing on the first training blood vessel shape diagram to generate a first training mark shape diagram with a plurality of blood vessel stenosis section area marks; inputting the first training blood vessel shape diagram into the first intelligent model to perform first blood vessel stenosis section segmentation processing, and generating a second training blood vessel shape diagram with a plurality of blood vessel stenosis section area marks; error calculation is carried out on the labeling results of the blood vessel narrow section areas of the first training labeling shape diagram and the second training blood vessel shape diagram, and the first intelligent model is reversely modulated according to the error calculation result until the error calculation result enters a preset first model error convergence range;

extracting a second area-distance training curve from a preset training data set prior to using the second intelligent model; extracting a three-dimensional tomography image corresponding to the second area-distance training curve from the training data set, and recording the three-dimensional tomography image as a first training tomography image; calculating the artificial blood flow reserve fraction of the first training tomography image according to a computational fluid dynamics method to generate a first training blood flow reserve fraction data sequence; according to the first training fractional flow reserve data sequence, carrying out artificial blood vessel stenosis section region marking processing on the first training tomographic scanning image to generate a first training marked tomographic scanning image with a plurality of blood vessel stenosis section region marks; inputting the first training tomography image into the second intelligent model to perform second blood vessel stenosis section segmentation processing, and generating a second training marking tomography image with a plurality of blood vessel stenosis section area marks; and carrying out error calculation on the labeling results of the blood vessel stenosis section areas of the first training labeling tomography image and the second training labeling tomography image, and carrying out reverse modulation on the second intelligent model according to the error calculation result until the error calculation result enters a preset second model error convergence range.

Preferably, the performing a first fractional flow reserve change amount prediction process on each of the first stenosis sections to generate corresponding first change amount data specifically includes:

analyzing the shape characteristics of the current first narrow section to generate corresponding shape characteristic data of the first narrow section; analyzing the position characteristics of the current first narrow section to generate corresponding first narrow section position characteristic data; analyzing the shape characteristics of the blood vessel where the current first narrow section is located to generate corresponding first blood vessel shape characteristic data;

inputting the first stenosis shape characteristic data, the first stenosis position characteristic data and the first vessel shape characteristic data into a mature stenosis fractional flow reserve prediction model for performing stenosis fractional flow reserve prediction processing, and generating corresponding first variance data.

Preferably, the performing a second fractional flow reserve change amount prediction process on each of the first non-stenosis sections to generate corresponding second change amount data specifically includes:

analyzing the shape feature of the current first non-narrow section to generate corresponding first non-narrow section shape feature data; analyzing the shape characteristic of the blood vessel where the current first non-stenosis section is located to generate corresponding second blood vessel shape characteristic data;

inputting the first non-stenosis section shape characteristic data and the second blood vessel shape characteristic data into a mature non-stenosis section fractional flow reserve prediction model for non-stenosis section fractional flow reserve prediction processing to generate corresponding second variable data.

Preferably, the variation data sequence includes a plurality of third variation data; the generating of the first cross-sectional fractional flow reserve data sequence by performing the cross-sectional fractional flow reserve prediction processing according to the variation data sequence specifically includes:

recording a narrow section or a non-narrow section of the first curve corresponding to the first third variation data as a first curve segment; a plurality of first sections corresponding to the first curve segments are classified into a first section set; and corresponding first section fractional flow reserve data FFR of a first section of the first section set corresponding to the first section_1FSetting a preset initial fractional flow reserve, and setting first section fractional flow reserve data FFR corresponding to the last first section of the first section set_1LIs set as (FFR)_1F+ first third variation data); recording the first cross-sections of the first set of cross-sections, except the first and last cross-sections, as first intermediate cross-sections; setting the fractional flow reserve data of the first section corresponding to any one first intermediate section as

a1 is the distance from the first intermediate cross-section to the first cross-section of the first set of cross-sections, b1 is the distance from the first intermediate cross-section to the last first cross-section of the first set of cross-sections, c1 is the distance from the first to the last first cross-section of the first set of cross-sections;

recording a narrow section or a non-narrow section of the first curve corresponding to the second third variation data as a second curve segment; a plurality of first sections corresponding to the second curve segment are classified into a second section set; and collecting the second cross-sectionFirst cross-section fractional flow reserve data FFR corresponding to a first one of the first cross-sections_2FSetting the first section fractional flow reserve data FFR corresponding to the last first section of the first section set_1LThe first section fractional flow reserve data FFR corresponding to the last first section in the second section set_2LIs set as (FFR)_2F+ second third variation data); marking the first cross-sections of the second set of cross-sections other than the first and last as second intermediate cross-sections; setting the fractional flow reserve data of the first section corresponding to any one second middle section as

a2 is the distance of the second intermediate cross-section to the first of the first cross-sections of the second set of cross-sections, b2 is the distance of the second intermediate cross-section to the last of the first cross-sections of the second set of cross-sections, c2 is the distance of the first of the second set of cross-sections to the last of the first cross-sections; and so on until the last third variable data;

sequencing all the obtained first section fractional flow reserve data according to the sequence to generate the first section fractional flow reserve data sequence.

A second aspect of an embodiment of the present invention provides an apparatus for implementing the method according to the first aspect, where the apparatus includes: the device comprises an acquisition module, a data processing module, a narrow section and non-narrow section identification module and a fractional flow reserve prediction module;

the acquisition module is used for acquiring a first section sequence of a first tomography image; the first tomography image is a three-dimensional tomography image; the first sequence of cross sections comprises a plurality of first cross sections; the first section is sampling information obtained by sampling a blood vessel cross section perpendicular to the blood flow direction along the blood flow direction of the first tomography image;

the data processing module is used for calculating the cross section area of each first cross section to generate corresponding first area data, calculating the blood movement distance to generate corresponding first distance data, and forming a corresponding first area-distance data group by the obtained first area data and the first distance data; and forming a first area-distance data set sequence by the obtained multiple groups of the first area-distance data sets; taking the area as a vertical coordinate and the distance as a horizontal coordinate, and carrying out curve conversion processing on the first area-distance data set sequence to generate a first curve;

the stenosis section and non-stenosis section identification module is used for carrying out blood vessel stenosis section identification processing on the first curve to generate a plurality of first stenosis sections; and recording as first non-stenosis segments a segment of the curve on the first curve separated by each of the first stenosis segments;

the blood flow reserve fraction prediction module is used for performing first blood flow reserve fraction variation prediction processing on each first narrow section to generate corresponding first variation data; performing second blood flow reserve fraction variation prediction processing on each first non-stenosis section to generate corresponding second variation data; sequencing the obtained first variable data and the second variable data according to the sequence of each first narrow section and each first non-narrow section to generate a variable data sequence; and performing section flow reserve fraction prediction processing according to the variable quantity data sequence to generate a first section flow reserve fraction data sequence.

A third aspect of an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a transceiver;

the processor is configured to be coupled to the memory, read and execute instructions in the memory, so as to implement the method steps of the first aspect;

the transceiver is coupled to the processor, and the processor controls the transceiver to transmit and receive messages.

A fourth aspect of embodiments of the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a computer, cause the computer to perform the method of the first aspect.

The embodiment of the invention provides a method, a device, electronic equipment and a computer readable storage medium for predicting a blood flow reserve fraction according to a blood vessel tomography image, wherein the blood vessel section area and the blood flow movement distance are estimated for a blood vessel section sampling sequence of a three-dimensional blood vessel tomography image obtained by a CTA (computed tomography angiography) technology, a curve reflecting the area-distance corresponding relation is generated according to the estimation result, a blood vessel narrow section and a non-narrow section are identified according to the area-distance curve, FFR (fringe field) variation of each narrow section and each non-narrow section is predicted, and finally, the FFR value of each blood vessel section of a blood vessel is predicted according to each predicted FFR variation. By the invention, personal injury caused by invasive inspection is avoided, the detection difficulty is greatly reduced, and the detection safety is improved.

Drawings

Fig. 1 is a schematic diagram illustrating a method for predicting fractional flow reserve according to a tomography image according to an embodiment of the present invention;

fig. 2 is a block diagram of an apparatus for predicting fractional flow reserve according to a tomography image according to a second embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Fig. 1 is a schematic diagram of a method for predicting a fractional flow reserve according to a vascular tomography image according to an embodiment of the present invention, and the method mainly includes the following steps:

step 1, acquiring a first section sequence of a first tomography image;

wherein the first tomography image is a three-dimensional tomography image; the first sequence of cross sections comprises a plurality of first cross sections; the first section is sampling information obtained by sampling the cross section of the blood vessel perpendicular to the blood flow direction along the blood flow direction of the first tomography image; the first section includes a plurality of first section edge point coordinates.

Here, the first tomographic image is a three-dimensional tomographic angiography image obtained using the CTA technique; when the cross section of the blood vessel perpendicular to the blood flow direction is sampled along the blood flow direction by the first tomography image, coordinates of each point on the blood vessel wall, namely an edge point on the cross section of the blood vessel, are taken as corresponding first section edge point coordinates, and then the first section is actually an information sequence consisting of a plurality of first section edge point coordinates; the blood flow direction is the direction of blood movement from the proximal end of the blood vessel to the distal end of the blood vessel.

Step 2, calculating the cross section area of each first section to generate corresponding first area data, calculating the blood movement distance to generate corresponding first distance data, and forming a corresponding first area-distance data group by the obtained first area data and the first distance data; and forming a first area-distance data set sequence by the obtained multiple groups of first area-distance data sets;

here, the first area data is area information of each blood vessel cross section, that is, a first cross section, the first distance data is a distance from each first cross section to a blood vessel entrance, that is, a1 st first cross section, the distance is not a straight line distance but a movement distance of blood in the blood vessel from the blood vessel entrance to the current first cross section, the first area-distance data set may represent a corresponding relationship between a blood vessel cross section and a blood movement distance on the corresponding first cross section, and the first area-distance data set sequence may represent a corresponding relationship between blood vessel cross sections and blood movement distances at different positions on the whole blood vessel;

the method specifically comprises the following steps: step 21, performing closed curve fitting processing according to a plurality of first section edge point coordinates of the current first section to generate a corresponding first closed curve graph;

here, the first closed curve pattern is an irregular pattern;

step 22, carrying out graph area estimation processing on the first closed curve graph to generate first area data;

here, the graph area estimation is performed based on an integration method of edge points and center points of the first closed curve graph to obtain first area data;

step 23, carrying out graph center point estimation processing on the first closed curve graph to generate a first section center point coordinate;

taking an average value of coordinates of all edge points on each coordinate axis as a first section center point coordinate;

step 24, calculating the blood movement distance from the first section center point coordinate to the current first section center point coordinate along the blood flowing direction to generate first distance data;

here, the first distance data corresponding to the first cross section should be 0;

when the blood movement distance from the center point coordinate of the first section to the center point coordinate of the second first section is calculated, firstly, the straight-line distance between the center point coordinate of the second first section and the center point coordinate of the first section is calculated to generate first relative distance data, and then the sum of the first distance data (the first distance data corresponding to the first section) corresponding to the previous first section and the first relative distance data is used as the first distance data corresponding to the second first section;

when the blood movement distance from the center point coordinate of the first section to the center point coordinate of the third section is calculated, firstly, the straight-line distance between the center point coordinate of the third section and the center point coordinate of the second section is calculated to generate second relative distance data, and then the sum of the first distance data (the first distance data corresponding to the second section) corresponding to the previous first section and the second relative distance data is used as the first distance data corresponding to the third section;

repeating the steps until first distance data corresponding to the last first section are obtained;

step 25, forming a corresponding first area-distance data group by the first area data and the first distance data;

here, the first area-distance data set represents a correspondence between a cross section of the blood vessel on the corresponding first section and a blood movement distance;

and 26, forming a first area-distance data set sequence by the obtained multiple sets of first area-distance data sets.

Here, the first area-distance data set sequence represents the correspondence between the blood vessel cross-section and the blood movement distance at different positions throughout the blood vessel.

And 3, carrying out curve conversion processing on the first area-distance data set sequence by taking the area as a vertical coordinate and the distance as a horizontal coordinate to generate a first curve.

Here, when curve conversion processing is performed on the first area-distance data group sequence, the first area data of each first area-distance data group in the first area-distance data group sequence is taken as a ordinate and the first distance data is taken as an abscissa, area-distance coordinate point marks are made on a two-dimensional coordinate system with the area as an ordinate and the distance as an abscissa to obtain a plurality of area-distance coordinate points, and the area-distance coordinate points are sequentially connected to obtain an initial curve;

in order to reduce the noise of the initial curve, a filter processing method aiming at non-periodic signals can be further adopted to carry out curve smoothing processing on the initial curve, so that a first curve capable of reflecting the change trend of the blood vessel cross section and the blood movement distance is obtained.

Step 4, carrying out blood vessel stenosis section identification processing on the first curve to generate a plurality of first stenosis sections; and recording curve segments on the first curve separated by first narrow segments as first non-narrow segments;

step 41, performing blood vessel stenosis section identification processing on the first curve to generate a plurality of first stenosis sections;

here, the embodiment of the present invention provides three blood vessel stenosis identification methods, which respectively correspond to three modes of preset system parameter blood vessel stenosis processing mode data: a first mode, a second mode, and a third mode;

the method specifically comprises the following steps: step 411, identifying preset blood vessel stenosis section processing mode data; if the blood vessel stenosis section processing mode data is the first mode, go to step 412; if the blood vessel stenosis section processing mode data is the second mode, go to step 413; if the stenosis section processing mode data is the third mode, go to step 414;

here, if the blood vessel stenosis section processing mode data is the first mode, which indicates that the first blood vessel stenosis section identification method is currently adopted, the processing is performed in the subsequent step 412; if the blood vessel stenosis section processing mode data is the second mode, which indicates that the second blood vessel stenosis section identification method is currently adopted, the subsequent step 413 performs processing; if the processing mode data of the blood vessel narrow section is the third mode, which indicates that the current adopted mode is the third blood vessel narrow section identification mode, the subsequent step 414 is used for processing;

step 412, identifying the peak points of the first curve to generate a plurality of first peak points; recording curves between adjacent first peak points as first curve interval sections; calculating the absolute difference value of the distance coordinate values of the first coordinate point and the last coordinate point of the first curve interval segment to generate first interval segment distance data; carrying out average calculation on the area coordinate values of the first and last coordinate points of the first curve interval segment to generate first average area data, extracting the minimum area coordinate value of the first curve interval segment to generate first minimum area data, and calculating the ratio of the first minimum area data to the first average area data to generate a first area ratio; when the first interval distance data is higher than a preset interval distance threshold and the first area ratio is lower than a preset area ratio characteristic threshold, marking the first curve interval as a first narrow section; go to step 42;

here, when the first blood vessel stenosis region identification method is used for processing, firstly, the peak points of the first curve are taken as sub-segment division conditions, the region between every two peak points is taken as a sub-segment, namely a first curve interval segment, and the head and the tail of each first curve interval segment respectively correspond to an area-distance coordinate point;

and then judging the stenosis section of the blood vessel for each first curve interval section:

firstly, calculating the coordinate values of the horizontal axes of the first coordinate point and the last coordinate point, namely the absolute difference value of the distance coordinate values to obtain first interval distance data;

for example, the head and tail coordinate points of the current first curve interval segment are respectively: coordinate point 1 (distance 1, area 1) and coordinate point 2 (distance 2, area 2), the first interval distance data is | distance 2-distance 1|, where | | is an absolute value symbol;

secondly, calculating the coordinate values of the longitudinal axes of the first coordinate point and the last coordinate point, namely the average value of the area coordinate values to obtain first average area data; extracting a minimum longitudinal axis coordinate value, namely a minimum area coordinate value from the first curve interval segment to serve as first minimum area data; calculating a first area ratio (first minimum area data/first average area data) according to the first minimum area data and the first average area data;

for example, the head and tail coordinate points of the current first curve interval segment are respectively: coordinate point 1 (distance 1, area 1) and coordinate point 2 (distance 2, area 2), where the minimum area coordinate value of the current first curve interval segment corresponds to coordinate point 3 (distance 3, area 3), and the first average area data is (area 1+ area 2)/2, the first minimum area data is area 3, and the first area ratio is first minimum area data/first average area data is area 3/((area 1+ area 2)/2) is 2 area 3/(area 1+ area 2);

finally, judging the first interval distance data and the first area ratio according to preset characteristic threshold parameters such as interval distance threshold, area ratio characteristic threshold and the like, and if the first interval distance data is not less than the interval distance threshold and the first area ratio is not more than the area ratio characteristic threshold, determining that the current first curve interval is a blood vessel narrow section and marking the blood vessel narrow section as the first narrow section;

step 413, performing two-dimensional vessel shape drawing according to the first curve to generate a first vessel shape drawing; inputting the first blood vessel shape diagram into a first intelligent model which is trained to be mature to carry out first blood vessel stenosis section segmentation processing, and obtaining a first labeled shape diagram with a plurality of blood vessel stenosis section area labels; in the first curve, the curve interval sections corresponding to the markers of the blood vessel narrow section areas of the first marker shape diagram are marked as first narrow sections; go to step 42;

further, before using the first intelligent model, extracting a first area-distance training curve from a preset training data set; drawing a two-dimensional blood vessel shape graph according to the first area-distance training curve to generate a first training blood vessel shape graph; carrying out artificial blood vessel stenosis section area marking processing on the first training blood vessel shape graph to generate a first training marking shape graph with a plurality of blood vessel stenosis section area marks; inputting the first training blood vessel shape diagram into a first intelligent model to perform first blood vessel stenosis section segmentation processing, and generating a second training blood vessel shape diagram with a plurality of blood vessel stenosis section area marks; error calculation is carried out on the labeling results of the blood vessel narrow section areas of the first training labeling shape diagram and the second training blood vessel shape diagram, and the first intelligent model is reversely modulated according to the error calculation result until the error calculation result enters a preset first model error convergence range;

when the second blood vessel stenosis section identification method is used for processing, firstly, a two-dimensional blood vessel shape diagram, namely a first blood vessel shape diagram, is constructed by referring to the corresponding relation between the blood vessel section area and the blood movement distance reflected by the first curve, and the difference between the diagram and the previous first tomography image is that the first blood vessel shape diagram has no background noise, and the image identification result is more accurate; then inputting the first blood vessel shape diagram into a trained mature two-dimensional image blood vessel stenosis semantic recognition model, namely a first intelligent model, and performing two-dimensional image blood vessel stenosis semantic segmentation processing, namely first blood vessel stenosis section segmentation processing, so as to obtain a semantic recognition image, namely a first labeled shape diagram, with a plurality of blood vessel stenosis section object labeling frames, namely blood vessel stenosis section area labels; then marking curve interval sections corresponding to the marks of the blood vessel narrow section areas in the first curve as first narrow sections;

the first intelligent model is actually a model type capable of realizing an end-to-end two-dimensional image semantic segmentation function in the artificial intelligent model, and can be selected and configured according to factors such as computing resources and computing efficiency of the model during specific implementation; before the first intelligent model is used, the model needs to be supervised and trained; during training, monitoring the output of the model, namely a second training blood vessel shape graph by using a first training mark shape graph marked in the artificial blood vessel narrow section area;

step 414, performing second vessel stenosis section segmentation processing on the first tomography image corresponding to the first curve by using a second intelligent model with mature training to obtain a first marked tomography image with a plurality of vessel stenosis section area marks; and in the first curve, marking curve interval sections corresponding to the marks of the blood vessel narrow section areas of the first marked tomography image as first narrow sections;

further, before using the second intelligent model, extracting a second area-distance training curve from a preset training data set; extracting a three-dimensional tomography image corresponding to the second area-distance training curve from the training data set, and recording the three-dimensional tomography image as a first training tomography image; calculating the artificial blood flow reserve fraction of the first training tomographic image according to a computational fluid dynamics method to generate a first training blood flow reserve fraction data sequence; according to the first training fractional flow reserve data sequence, carrying out artificial blood vessel stenosis section region marking processing on the first training tomographic image to generate a first training marked tomographic image with a plurality of blood vessel stenosis section region marks; inputting the first training tomography image into a second intelligent model to perform second blood vessel stenosis section segmentation processing, and generating a second training marked tomography image with a plurality of blood vessel stenosis section area marks; error calculation is carried out on the labeling results of the blood vessel stenosis section areas of the first training labeling tomography image and the second training labeling tomography image, and the second intelligent model is reversely modulated according to the error calculation result until the error calculation result enters a preset second model error convergence range;

when the third blood vessel stenosis section identification mode is used for processing, a three-dimensional tomography image corresponding to the first curve, namely a first tomography image is input into a trained three-dimensional image blood vessel stenosis semantic identification model based on a computational fluid dynamics method, namely a second intelligent model for performing three-dimensional image blood vessel stenosis semantic segmentation processing, namely second blood vessel stenosis section segmentation processing, and therefore a semantic identification image with a plurality of blood vessel stenosis section object marking frames, namely blood vessel stenosis section area marks, namely a first marked tomography image is obtained; then marking curve interval sections corresponding to the marks of the blood vessel narrow section areas in the first curve as first narrow sections;

the second intelligent model is actually a model type capable of realizing the end-to-end three-dimensional image semantic segmentation function in the artificial intelligent model, and can be selected and configured according to the factors of the model such as computing resources, computing efficiency and the like during specific implementation; before using the second intelligent model, the model needs to be supervised and trained; during training, manually calculating fractional flow reserve data corresponding to each point on a blood vessel in a first training tomographic image by using a related calculation tool according to a computational fluid dynamics method to obtain a corresponding first training fractional flow reserve data sequence, and performing artificial blood vessel stenosis section region labeling processing on the first training tomographic image according to the first training fractional flow reserve data sequence to obtain supervision data with a plurality of blood vessel stenosis section region labels, namely a first training labeled tomographic image; then, the first training mark tomography image is used for monitoring the model output, namely the second training mark tomography image;

the curve segments on the first curve separated by the first narrow segments are marked as first non-narrow segments, step 42.

For example, on a first curve, the interval segment of the curve between coordinate points a to B is identified as a first narrow segment, and then the segment of the curve between the 1 st coordinate point to coordinate point a on the first curve and the segment of the curve between coordinate point B to the last 1 coordinate point are both identified as a first non-narrow segment.

Step 5, performing first flow reserve fraction variation prediction processing on each first narrow section to generate corresponding first variation data; performing second blood flow reserve fraction variation prediction processing on each first non-stenosis section to generate corresponding second variation data;

the first variation data is the absolute difference between the fractional flow reserve at the outlet and the fractional flow reserve at the inlet of the blood vessel corresponding to the first stenosis section; the second variation data is the absolute difference of the fractional flow reserve at the outlet and the fractional flow reserve at the inlet of the blood vessel corresponding to the first non-stenosis section;

step 51, performing first fractional flow reserve variation prediction processing on each first stenosis section to generate corresponding first variation data;

here, when the first fractional flow reserve change amount prediction processing is performed on each first stenosis segment, the embodiment of the present invention predicts the fractional flow reserve change amount of the current first stenosis segment based on the stenosis segment shape feature, the stenosis segment position feature, and the vessel shape feature of the blood vessel in which the first stenosis segment is located;

the method specifically comprises the following steps: step 511, analyzing the shape characteristics of the current first narrow section to generate corresponding shape characteristic data of the first narrow section; analyzing the position characteristics of the current first narrow section to generate corresponding position characteristic data of the first narrow section; analyzing the shape characteristics of the blood vessel where the current first narrow section is located to generate corresponding first blood vessel shape characteristic data;

here, the first stenosis shape characteristic data is a set of shape information of each first stenosis, the first stenosis position characteristic data is a set of information of a relative position of each first stenosis on the vessel tree, and the first vessel shape characteristic data is a set of information of a relative position of each first stenosis on the vessel tree;

the three analysis processes are specifically as follows:

(1) when analyzing the shape characteristics of the current first stenosis:

step A-1, marking an entrance section, a narrowest section and an exit section of a current first narrow section on a vessel tree of a first tomography image;

step A-2, calculating blood movement distances of first cross sections at the head and the tail of the inlet section to generate a first inlet section length, calculating blood movement distances of first cross sections at the head and the tail of the narrowest section to generate a first narrowest section length, and calculating blood movement distances of first cross sections at the head and the tail of the outlet section to generate a first outlet section length;

step A-3, extracting first area data corresponding to a first initial section of the inlet section to generate first inlet area data, extracting the minimum value of the first area data of all first sections corresponding to the narrowest section to generate first narrowest area data, and extracting first area data corresponding to a last first section of the outlet section to generate first outlet area data;

step A-4, calculating an average value of area data of a first inlet and an area data of a first outlet to generate first inlet and outlet average area data, calculating a ratio of the first narrowest area data to the first inlet to generate a first narrow area ratio, and calculating a ratio of the first narrowest area data to the first inlet to generate a second narrow area ratio;

step A-5, combining the length of the first inlet section, the length of the first narrowest section, the length of the first outlet section, the area data of the first inlet, the area data of the first narrowest section and the area data of the first outlet into a first narrow section shape characteristic set, and combining the first narrow area ratio and the second narrow area ratio into a second narrow section shape characteristic set;

step A-6, combining the first and second narrow section shape feature sets into first narrow section shape feature data;

(2) when analyzing the stenosis position characteristics of the current first stenosis:

step B-1, marking blood vessel bifurcation points before and after a current first narrow section on a blood vessel tree of a first tomography image; if the blood vessel bifurcation points exist before and after the current first narrow section, taking the region between the blood vessel bifurcation points nearest before and after the current first narrow section as a first cut-off region corresponding to the current first narrow section; if only the front of the current first narrow section has a blood vessel bifurcation point, taking a region from the nearest blood vessel bifurcation point to the blood flow outlet of the blood vessel tree before the current first narrow section as a first cut-off region corresponding to the current first narrow section; if only a blood vessel bifurcation point exists behind the current first stenosis section, taking a region from a blood flow inlet of the blood vessel tree to the nearest blood vessel bifurcation point behind the current first stenosis section as a first cut-off region corresponding to the current first stenosis section; if no blood vessel bifurcation point exists before or after the current first narrow section, taking the whole area between the blood flow inlet and the blood flow outlet of the blood vessel tree as a first cut-off area corresponding to the current first narrow section; calculating the blood movement distance from the initial position of the current first narrow section to the initial position of the first cut-off region to generate first narrow section position characteristic data;

b-2, tracing back the intersection point on the blood vessel tree of the first tomography image from the initial position of the current first narrow section in the direction opposite to the blood flow moving direction; when each intersection point is traced, judging whether the current blood vessel is the main branch blood vessel at the current intersection point, and if not, taking a tracing path from the current first narrow section to the current intersection point as a first blood vessel region; tracing the intersection point on the blood vessel tree from the end position of the current first narrow section in the same direction as the blood flow moving direction; when each intersection point is traced, judging whether the current blood vessel is the main branch blood vessel at the current intersection point, and if not, taking a tracing path from the current first narrow section to the current intersection point as a first two-blood vessel area; a first blood vessel area is formed by the first blood vessel area, the current first narrow section and the first two blood vessel areas; calculating the blood movement distance from the starting position of the current first narrow section to the ending position of the first blood vessel area to generate first and second narrow section position characteristic data;

step B-3, tracing back the blood vessel tree from the initial position of the current first narrow section on the blood vessel tree of the first tomography image in the direction opposite to the blood flow moving direction until the blood flow inlet of the blood vessel tree, and taking a tracing back path from the current first narrow section to the blood flow inlet of the blood vessel tree as a second blood vessel region; performing intersection tracing from the end position of the current first narrow section on the blood vessel tree in the same direction as the blood flow moving direction, continuously performing intersection tracing downwards along the main blood vessel at the current intersection when tracing to each intersection until the blood flow outlet of the blood vessel tree, and taking a tracing path from the current first narrow section to the blood flow outlet of the blood vessel tree as a second blood vessel region; a second vessel region is composed of the second first vessel region, the current first stenosis and the second vessel region; calculating the blood movement distance from the initial position of the current first narrow section to the initial position of the second blood vessel area to generate first three-narrow section position characteristic data;

step B-4, combining the first narrow section position characteristic data, the second narrow section position characteristic data and the third narrow section position characteristic data to form first narrow section position characteristic data;

(3) when analyzing the shape characteristics of the blood vessel in which the current first stenosis is located:

step C-1, extracting first area data corresponding to the initial position of the first cutting area to generate first cutting initial area data, extracting first area data corresponding to a bifurcation point before a current first narrow section in the first cutting area to generate first cutting bifurcation area data, extracting minimum first area data in the first cutting area to generate first cutting minimum area data, and counting the number of the first narrow sections contained in the first cutting area to generate the number of the first narrow sections; forming first blood vessel shape characteristic data by first cut starting area data, first cut bifurcation area data, first cut minimum area data and first narrow section quantity;

c-2, extracting first area data corresponding to the end position of the first blood vessel region to generate first two-blood vessel shape characteristic data;

c-3, counting the number of first narrow sections from the initial position to the current first narrow section in the second blood vessel region to generate first three-blood-vessel shape characteristic data;

step C-4, combining the first blood vessel shape characteristic data, the second blood vessel shape characteristic data and the first blood vessel shape characteristic data to form first blood vessel shape characteristic data;

step 512, inputting the first stenosis section shape characteristic data, the first stenosis section position characteristic data and the first blood vessel shape characteristic data into a mature stenosis section blood flow reserve fraction variation prediction model for performing stenosis section blood flow reserve fraction variation prediction processing to generate corresponding first variation data;

here, the prediction model of fractional flow reserve variation in a narrow segment may be implemented by using a Multilayer Feed-Forward Neural Network (ML _ NN), may be implemented by using a Support Vector Regression (SVR) model, and may be implemented by using an eXtreme Gradient boost (boost) model;

step 52, performing second fractional flow reserve variation prediction processing on each first non-stenosis section to generate corresponding second variation data;

here, when the second fractional flow reserve change amount prediction processing is performed on each first non-stenosis portion, the embodiment of the present invention predicts the current fractional flow reserve change amount of the first non-stenosis portion based on the non-stenosis portion shape feature of each first non-stenosis portion and the vessel shape feature of the blood vessel in which the first non-stenosis portion is located;

the method specifically comprises the following steps: step 521, analyzing the shape characteristics of the current first non-narrow section to generate corresponding first non-narrow section shape characteristic data; analyzing the shape characteristics of the blood vessel where the current first non-narrow section is located to generate corresponding second blood vessel shape characteristic data;

here, the first non-stenosis section shape feature data is a set of shape information of each first non-stenosis section, and the second blood vessel shape feature data is a set of information of a relative position on the blood vessel tree of a blood vessel section where each first non-stenosis section is located;

the two analysis processes are specifically as follows:

(1) in analyzing the shape characteristics of the current first non-stenosis:

d-1, calculating the blood movement distance of the head and tail first sections of the current first non-stenosis section to generate a first non-stenosis section length; extracting first area data corresponding to a first initial section of a current first non-narrow section to generate second inlet area data, and extracting first area data corresponding to a last first section of the current first non-narrow section to generate second outlet area data; calculating an absolute difference between the area data at the second outlet and the area data at the second inlet to generate first non-narrow section difference area data; calculating the ratio of the first non-stenosis differential area data to the first non-stenosis length to generate a first non-stenosis ratio;

d-2, calculating the curvature radius of the current first non-narrow section to generate the curvature radius of the first non-narrow section;

step D-3, forming first non-stenosis shape characteristic data by the first non-stenosis ratio and the first non-stenosis curvature radius;

(2) when analyzing the shape characteristics of the blood vessel in which the current first non-stenosis section is located:

step E-1, marking blood vessel bifurcation points before and after a current first non-stenosis section on a blood vessel tree of a first tomography image; if the vessel bifurcation points exist before and after the current first non-stenosis section, taking the region between the vessel bifurcation points nearest before and after the current first non-stenosis section as a second truncation region corresponding to the current first non-stenosis section; if only the front part of the current first non-narrow section has a blood vessel bifurcation point, taking the region from the nearest blood vessel bifurcation point in front of the current first non-narrow section to the blood flow outlet of the blood vessel tree as a second truncation region corresponding to the current first non-narrow section; if only a blood vessel bifurcation point exists behind the current first non-stenosis section, taking a region from a blood flow inlet of the blood vessel tree to the nearest blood vessel bifurcation point behind the current first non-stenosis section as a second truncation region corresponding to the current first non-stenosis section; if no blood vessel bifurcation point exists before or after the current first non-stenosis section, taking all areas between the blood flow inlet and the blood flow outlet of the blood vessel tree as a second truncation area corresponding to the current first non-stenosis section; counting the maximum stenosis rate of all first stenosis sections contained in the second truncation area to generate second blood vessel shape characteristic data;

e-2, tracing back the intersection point on the blood vessel tree of the first tomography image from the initial position of the current first non-narrow section in the direction opposite to the blood flow movement direction; when each intersection point is traced, judging whether the current blood vessel is the main branch blood vessel at the current intersection point, and if not, taking a tracing path from the current first non-narrow section to the current intersection point as a third blood vessel area; tracing the intersection point on the blood vessel tree from the end position of the current first non-narrow section in the same direction as the blood flow moving direction; when each intersection point is traced, judging whether the current blood vessel is the main branch blood vessel at the current intersection point, and if not, taking a tracing path from the current first non-narrow section to the current intersection point as a third blood vessel area; a third vessel region consisting of a third first vessel region, a current first non-stenosis and a third second vessel region; extracting first area data corresponding to the end position of the third blood vessel region to generate second blood vessel shape characteristic data;

step E-3, tracing back the blood vessel tree from the initial position of the current first non-narrow section to the blood flow inlet of the blood vessel tree in the direction opposite to the blood flow moving direction on the blood vessel tree of the first tomography image, and taking a tracing back path from the current first non-narrow section to the blood flow inlet of the blood vessel tree as a fourth blood vessel region; performing intersection tracing from the end position of the current first non-narrow section on the blood vessel tree in the same direction as the blood flow moving direction, continuously performing intersection tracing downwards along the main blood vessel at the current intersection when tracing to each intersection until the blood flow outlet of the blood vessel tree, and taking a tracing path from the current first non-narrow section to the blood flow outlet of the blood vessel tree as a fourth blood vessel area; a fourth vessel region consisting of a fourth first vessel region, a current first non-stenosis and a fourth second vessel region; carrying out mean value calculation on all first area data of a second truncation region closest to the starting position of a fourth blood vessel region to generate first truncation average area data; counting the number of bifurcation points from the starting position of the fourth blood vessel region to the starting position of the current first non-narrow section to generate a first number of bifurcation points; forming second third blood vessel shape characteristic data by the first segmentation average area data and the first bifurcation point number;

e-4, combining the first blood vessel shape characteristic data, the second blood vessel shape characteristic data and the second blood vessel shape characteristic data to form second blood vessel shape characteristic data;

step 522, inputting the first non-stenosis section shape characteristic data and the second blood vessel shape characteristic data into a mature non-stenosis section fractional flow reserve variation prediction model for non-stenosis section fractional flow reserve variation prediction processing, and generating corresponding second variation data.

Here, the non-stenosis fractional flow reserve variation prediction model may be implemented by using an ML _ NN network, an SVR model, or an XGBoost model.

Step 6, sequencing the obtained plurality of first variable data and second variable data according to the sequence of each first narrow section and each first non-narrow section to generate a variable data sequence;

wherein the variation data sequence includes a plurality of third variation data.

The sequence of the first narrow sections and the first non-narrow sections is the sequence from the entrance of the vessel tree in the direction of blood flow movement.

Step 7, performing section flow reserve fraction prediction processing according to the variable quantity data sequence to generate a first section flow reserve fraction data sequence;

here, since the fractional flow reserve variation of each stenosis or non-stenosis section on the vessel tree from the entrance is obtained, the fractional flow reserve values of the head and tail positions of each section can be obtained sequentially from the first section; because the fractional flow reserve values of the edge points on each blood vessel section are the same, if the fractional flow reserve values of the edge points of each section of each segment are required to be calculated, the fractional flow reserve values of the corresponding sections are only required to be calculated; when calculating the fractional flow reserve value of a certain cross section, calculating according to the blood movement distance between the current cross section and the head and tail positions of the current segmentation, the blood movement distance between the head and tail positions of the current segmentation and the fractional flow reserve value between the head and tail positions of the current segmentation, wherein the fractional flow reserve value of the current cross section is (the blood movement distance between the current cross section and the tail positions of the current segmentation and the fractional flow reserve value at the head and tail positions of the current segmentation/the blood movement distance at the head and tail positions of the current segmentation) + (the blood movement distance between the current cross section and the head positions of the current segmentation and the fractional flow reserve value at the tail positions of the current segmentation and the blood movement distance at the head and tail positions of the current segmentation and the fractional flow reserve value at the head and tail positions of the current segmentation);

the method specifically comprises the following steps: step 71, marking a narrow section or a non-narrow section of the first curve corresponding to the first third variation data as a first curve segment; a plurality of first sections corresponding to the first curve segments are classified into a first section set; and corresponding first section fractional flow reserve data FFR corresponding to a first section of the first section set_1FSetting a preset initial fractional flow reserve, and setting first section fractional flow reserve data FFR corresponding to the last first section of the first section set_1LIs set as (FFR)_1F+ first third variation data); recording first cross sections except the first and last cross sections in the first set of cross sections as first intermediate cross sections; setting the fractional flow reserve data of the first section corresponding to any first intermediate section as

Where a1 is the distance from the first intermediate cross-section to the first cross-section of the first set of cross-sections, b1 is the distance from the first intermediate cross-section to the last first cross-section of the first set of cross-sections, and c1 is the distance from the first to the last first cross-section of the first set of cross-sections;

here, in the first segment, the fractional flow reserve value of the head position of the current segment is the first cross-section fractional flow reserve data FFR corresponding to the first cross-section of the first cross-section set_1FIs a preset initial fractional flow reserve; initial fractional flow reserve under normal conditionsCan be set to 1;

step 72, marking the narrow section or the non-narrow section of the first curve corresponding to the second third variation data as a second curve segment; a plurality of first cross sections corresponding to the second curve segment are classified into a second cross section set; and corresponding first section fractional flow reserve data FFR of a first section of the second section set_2FSetting the first section fractional flow reserve data FFR corresponding to the last first section of the first section set_1LAnd corresponding first section fractional flow reserve data FFR to the last first section of the second section set_2LIs set as (FFR)_2F+ second third variation data); marking first cross sections of the second set of cross sections other than the first and last as second intermediate cross sections; setting the fractional flow reserve data of the first section corresponding to any second intermediate section as

Repeating the above steps until the last third variable data;

wherein a2 is the distance of the second intermediate cross-section to the first cross-section of the second set of cross-sections, b2 is the distance of the second intermediate cross-section to the last first cross-section of the second set of cross-sections, and c2 is the distance of the first to last first cross-section of the second set of cross-sections;

here, in the segments subsequent to the first segment, the fractional flow reserve value at the head position of the current segment is the fractional flow reserve value at the tail position of the previous segment;

and 73, sequencing all the obtained first section fractional flow reserve data in sequence to generate a first section fractional flow reserve data sequence.

Here, the first cross-section fractional flow reserve data sequence is a fractional flow reserve value set for all sampling cross-sections of the first tomographic image.

It should be noted that, if the fractional flow reserve of any blood vessel position point on the first tomographic image is to be calculated, two first cross sections that are closest to each other before and after are obtained by searching from the first cross section sequence according to the coordinate of the current blood vessel position point and the blood flow movement direction: a first front adjacent cross section and a first back adjacent cross section; recording mapping points of the current blood vessel position point on the first front adjacent section and the first back adjacent section as a first front mapping point and a first back mapping point; calculating the blood flow movement distance between the first front adjacent section and the first rear adjacent section to generate a first total distance, calculating the blood flow movement distance from the current blood vessel position point to the first front mapping point to generate a first front distance, and calculating the blood flow movement distance from the current blood vessel position point to the first rear mapping point to generate a first rear distance; extracting first section blood flow reserve fraction data corresponding to a first front adjacent section and a first back adjacent section from the first section blood flow reserve fraction data sequence to generate first front section blood flow reserve fraction data and first back section blood flow reserve fraction data; the fractional flow reserve at the current vessel location point is calculated (first posterior spacing, first anterior cross-sectional fractional flow reserve data/first total spacing) + (first anterior spacing, first posterior cross-sectional fractional flow reserve data/first total spacing).

Fig. 2 is a block diagram of an apparatus for predicting fractional flow reserve according to a blood vessel tomography image according to a second embodiment of the present invention, where the apparatus may be a terminal device or a server for implementing the method according to the second embodiment of the present invention, or an apparatus connected to the terminal device or the server for implementing the method according to the second embodiment of the present invention, and the apparatus may be an apparatus or a chip system of the terminal device or the server, for example. As shown in fig. 2, the apparatus includes: the system comprises an acquisition module 201, a data processing module 202, a stenosis section and non-stenosis section identification module 203 and a fractional flow reserve prediction module 204.

The acquisition module 201 is configured to acquire a first cross-sectional sequence of first tomographic images; the first tomography image is a three-dimensional tomography image; the first sequence of cross sections comprises a plurality of first cross sections; the first section is sampling information obtained by sampling a cross section of the blood vessel perpendicular to the blood flow direction along the blood flow direction on the first tomographic image.

The data processing module 202 is configured to perform cross-sectional area calculation on each first cross-section to generate corresponding first area data, perform blood movement distance calculation to generate corresponding first distance data, and form a corresponding first area-distance data set from the obtained first area data and the first distance data; and forming a first area-distance data set sequence by the obtained multiple groups of first area-distance data sets; and carrying out curve conversion processing on the first area-distance data set sequence by taking the area as a vertical coordinate and the distance as a horizontal coordinate to generate a first curve.

The stenosis section and non-stenosis section identification module 203 is used for performing blood vessel stenosis section identification processing on the first curve to generate a plurality of first stenosis sections; and the curve segments on the first curve separated by the first narrow segments are identified as first non-narrow segments.

The fractional flow reserve prediction module 204 is configured to perform a first fractional flow reserve variation prediction process on each first stenosis segment to generate corresponding first variation data; performing second blood flow reserve fraction variation prediction processing on each first non-stenosis section to generate corresponding second variation data; sequencing the obtained plurality of first variable data and second variable data according to the sequence of each first narrow section and each first non-narrow section to generate a variable data sequence; and performing section blood flow reserve fraction prediction processing according to the variable quantity data sequence to generate a first section blood flow reserve fraction data sequence.

The device for predicting fractional flow reserve according to the tomography image of the blood vessel provided by the embodiment of the invention can execute the method steps in the embodiment of the method, and the implementation principle and the technical effect are similar, and are not repeated herein.

It should be noted that the division of the modules of the above apparatus is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity, or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, the obtaining module may be a processing element separately set up, or may be implemented by being integrated in a chip of the apparatus, or may be stored in a memory of the apparatus in the form of program code, and a processing element of the apparatus calls and executes the functions of the determining module. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, when some of the above modules are implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor that can invoke the program code. As another example, these modules may be integrated together and implemented in the form of a System-on-a-chip (SOC).

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, 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 instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, bluetooth, microwave, etc.). 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, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), etc.

Fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention. The electronic device may be the terminal device or the server, or may be a terminal device or a server connected to the terminal device or the server and implementing the method according to the embodiment of the present invention. As shown in fig. 3, the electronic device may include: a processor 301 (e.g., a CPU), a memory 302, a transceiver 303; the transceiver 303 is coupled to the processor 301, and the processor 301 controls the transceiving operation of the transceiver 303. Various instructions may be stored in memory 302 for performing various processing functions and implementing the methods and processes provided in the above-described embodiments of the present invention. Preferably, the electronic device according to an embodiment of the present invention further includes: a power supply 304, a system bus 305, and a communication port 306. The system bus 305 is used to implement communication connections between the elements. The communication port 306 is used for connection communication between the electronic device and other peripherals.

The system bus mentioned in fig. 3 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM) and may also include a Non-Volatile Memory (Non-Volatile Memory), such as at least one disk Memory.

The Processor may be a general-purpose Processor, including a central processing unit CPU, a Network Processor (NP), and the like; but also a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components.

It should be noted that the embodiment of the present invention also provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the method and the processing procedure provided in the above-mentioned embodiment.

The embodiment of the invention also provides a chip for running the instructions, and the chip is used for executing the method and the processing process provided by the embodiment.

Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims

1. A method of predicting fractional flow reserve from a vascular tomography image, the method comprising:

2. The method of predicting fractional flow reserve from a tomographic image of claim 1, wherein the first section includes a plurality of first section edge point coordinates; the specific steps of calculating the cross-sectional area of each first cross-section to generate corresponding first area data, calculating the blood movement distance to generate corresponding first distance data, and forming a corresponding first area-distance data set by the obtained first area data and the first distance data include:

3. The method according to claim 1, wherein the performing a vessel stenosis section identification process on the first curve to generate a plurality of first stenosis sections comprises:

identifying preset blood vessel stenosis section processing mode data;

4. The method for predicting fractional flow reserve according to a tomographic image of claim 3,

prior to using the first intelligent model, extracting a first area-distance training curve from a preset training data set; drawing a two-dimensional blood vessel shape graph according to the first area-distance training curve to generate a first training blood vessel shape graph; carrying out artificial blood vessel stenosis section area marking processing on the first training blood vessel shape diagram to generate a first training mark shape diagram with a plurality of blood vessel stenosis section area marks; inputting the first training blood vessel shape diagram into the first intelligent model to perform first blood vessel stenosis section segmentation processing, and generating a second training blood vessel shape diagram with a plurality of blood vessel stenosis section area marks; error calculation is carried out on the labeling results of the blood vessel narrow section areas of the first training labeling shape diagram and the second training blood vessel shape diagram, and the first intelligent model is reversely modulated according to the error calculation result until the error calculation result enters a preset first model error convergence range;

5. The method according to claim 1, wherein the performing a first fractional flow reserve change amount prediction process on each of the first stenosis sections to generate corresponding first change amount data specifically comprises:

6. The method according to claim 1, wherein the second fractional flow reserve change amount prediction processing is performed on each of the first non-stenosis sections to generate corresponding second change amount data, and specifically comprises:

7. The method of predicting fractional flow reserve according to a tomographic image of claim 1, wherein the change amount data sequence includes a plurality of third change amount data; the generating of the first cross-sectional fractional flow reserve data sequence by performing the cross-sectional fractional flow reserve prediction processing according to the variation data sequence specifically includes:

recording a narrow section or a non-narrow section of the first curve corresponding to the first third variation data as a first curve segment; a plurality of first sections corresponding to the first curve segments are classified into a first section set; and corresponding first section fractional flow reserve data FFR of a first section of the first section set corresponding to the first section_1FSetting a preset initial fractional flow reserve, and setting first section fractional flow reserve data FFR corresponding to the last first section of the first section set_1LIs set as (FFR)_1F+ first third variation data); recording the first cross-sections of the first set of cross-sections, except the first and last cross-sections, as first intermediate cross-sections; is provided withThe fractional flow reserve data of the first section corresponding to any one of the first intermediate sections is

recording a narrow section or a non-narrow section of the first curve corresponding to the second third variation data as a second curve segment; a plurality of first sections corresponding to the second curve segment are classified into a second section set; and corresponding first section fractional flow reserve data FFR of a first section in the second section set_2FSetting the first section fractional flow reserve data FFR corresponding to the last first section of the first section set_1LThe first section fractional flow reserve data FFR corresponding to the last first section in the second section set_2LIs set as (FFR)_2F+ second third variation data); marking the first cross-sections of the second set of cross-sections other than the first and last as second intermediate cross-sections; setting the fractional flow reserve data of the first section corresponding to any one second middle section as

8. An apparatus for implementing the method steps of predicting fractional flow reserve from a vessel tomography image according to any of claims 1 to 7, the apparatus comprising: the device comprises an acquisition module, a data processing module, a narrow section and non-narrow section identification module and a fractional flow reserve prediction module;

9. An electronic device, comprising: a memory, a processor, and a transceiver;

the processor is used for being coupled with the memory, reading and executing the instructions in the memory to realize the method steps of any one of claims 1 to 7;

10. A computer-readable storage medium having stored thereon computer instructions which, when executed by a computer, cause the computer to perform the method of any of claims 1-7.