CN114463267A - Fractional flow reserve prediction method and device based on optical coherence tomography and computer storage medium - Google Patents
Fractional flow reserve prediction method and device based on optical coherence tomography and computer storage medium Download PDFInfo
- Publication number
- CN114463267A CN114463267A CN202111641922.7A CN202111641922A CN114463267A CN 114463267 A CN114463267 A CN 114463267A CN 202111641922 A CN202111641922 A CN 202111641922A CN 114463267 A CN114463267 A CN 114463267A
- Authority
- CN
- China
- Prior art keywords
- module
- lumen
- image
- blood vessel
- bifurcation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012014 optical coherence tomography Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000003860 storage Methods 0.000 title claims abstract description 7
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 82
- 239000012530 fluid Substances 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 44
- 239000000523 sample Substances 0.000 claims description 44
- 230000003287 optical effect Effects 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 27
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 13
- 230000017531 blood circulation Effects 0.000 claims description 11
- 230000001965 increasing effect Effects 0.000 claims description 10
- 239000013307 optical fiber Substances 0.000 claims description 8
- 244000208734 Pisonia aculeata Species 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 6
- 208000031481 Pathologic Constriction Diseases 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 5
- 210000004369 blood Anatomy 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 230000035487 diastolic blood pressure Effects 0.000 claims description 5
- 230000036262 stenosis Effects 0.000 claims description 5
- 208000037804 stenosis Diseases 0.000 claims description 5
- 230000035488 systolic blood pressure Effects 0.000 claims description 5
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000011010 flushing procedure Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 15
- 238000003384 imaging method Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 9
- 210000004351 coronary vessel Anatomy 0.000 description 8
- 238000003745 diagnosis Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000003902 lesion Effects 0.000 description 4
- 201000000057 Coronary Stenosis Diseases 0.000 description 3
- 206010011089 Coronary artery stenosis Diseases 0.000 description 3
- 206010020565 Hyperaemia Diseases 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 238000002608 intravascular ultrasound Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000002560 therapeutic procedure Methods 0.000 description 3
- OIRDTQYFTABQOQ-KQYNXXCUSA-N adenosine Chemical compound C1=NC=2C(N)=NC=NC=2N1[C@@H]1O[C@H](CO)[C@@H](O)[C@H]1O OIRDTQYFTABQOQ-KQYNXXCUSA-N 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 238000003973 irrigation Methods 0.000 description 2
- 230000002262 irrigation Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- ZKHQWZAMYRWXGA-KQYNXXCUSA-J ATP(4-) Chemical compound C1=NC=2C(N)=NC=NC=2N1[C@@H]1O[C@H](COP([O-])(=O)OP([O-])(=O)OP([O-])([O-])=O)[C@@H](O)[C@H]1O ZKHQWZAMYRWXGA-KQYNXXCUSA-J 0.000 description 1
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- ZKHQWZAMYRWXGA-UHFFFAOYSA-N Adenosine triphosphate Natural products C1=NC=2C(N)=NC=NC=2N1C1OC(COP(O)(=O)OP(O)(=O)OP(O)(O)=O)C(O)C1O ZKHQWZAMYRWXGA-UHFFFAOYSA-N 0.000 description 1
- 208000037260 Atherosclerotic Plaque Diseases 0.000 description 1
- 239000002126 C01EB10 - Adenosine Substances 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 229960005305 adenosine Drugs 0.000 description 1
- 229940068274 adenosine injection Drugs 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000002586 coronary angiography Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 208000031225 myocardial ischemia Diseases 0.000 description 1
- 210000004165 myocardium Anatomy 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 229940124549 vasodilator Drugs 0.000 description 1
- 239000003071 vasodilator agent Substances 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
- A61B5/0261—Measuring blood flow using optical means, e.g. infrared light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10101—Optical tomography; Optical coherence tomography [OCT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Hematology (AREA)
- Cardiology (AREA)
- Physiology (AREA)
- Pathology (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Geometry (AREA)
- Endoscopes (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method, a device and a computer storage medium for predicting fractional flow reserve based on optical coherence tomography, wherein a multitask learning model is established, and a lumen and a bifurcation in an OCT image are identified simultaneously by adopting an end-to-end network structure; meanwhile, in consideration of certain structural characteristics and spatial position relations of the tube cavity and the bifurcation, a multi-task learning model based on spatial structure constraint is constructed, accurate identification of the tube cavity and the bifurcation is achieved, meanwhile, the problems of structural information loss, class imbalance and the like in a traditional network model are solved, and the generalization capability of the model is improved; in order to realize automatic selection of a reference frame and solve the problem of similarity of OCT healthy blood vessels and non-healthy blood vessels in vision, an OCT healthy blood vessel classification network based on triple loss is provided; and then, a fluid dynamics program is utilized, the area of the contour of the lumen, the bifurcation and a reference frame are combined, the FFR prediction technology based on multiple parameters is proposed and constructed, and the FFR is accurately measured and calculated.
Description
Technical Field
The invention belongs to the technical field of medical treatment, and particularly relates to a method and a device for predicting fractional flow reserve of optical coherence tomography imaging.
The background art comprises the following steps:
optical Coherence Tomography (OCT), an imaging technique for intracavity imaging, uses the basic principle of weak coherent Optical interferometers to record the reflected light of biological tissues at different depths and then computer reconstructs the reflected light signal to form a biological tissue structure image which can be easily identified. Fast imaging, high resolution, accurate plaque identification and accurate stent implantation effect evaluation gradually make OCT an important imaging technology in coronary heart disease diagnosis and PCI interventional therapy. Compared with Intravascular Ultrasound (IVUS), the OCT image has the resolution of 10-20 μm (the resolution of the IVUS is about 100 μm), so that the anatomical stenosis degree can be accurately distinguished, and the type and the shape of plaque in the blood vessel wall can be seen clearly, thereby evaluating lesion more accurately.
Fractional Flow Reserve (FFR) refers to the ratio of the maximum blood Flow provided by the coronary artery to the area of the myocardium supplied when a lesion occurs to the maximum blood Flow provided by the area theoretically without a lesion. Long-term scientific research and clinical tests show that the FFR can be used as a 'gold standard' for functional evaluation of coronary artery stenosis, and the FFR can accurately judge the relation between coronary artery stenosis lesion and myocardial ischemia, correctly guide coronary artery interventional therapy, and evaluate the result and prognosis of the coronary artery interventional therapy. It is generally accepted that intervention is required when the FFR value of a diseased vessel is less than 0.75, but FFR measurement has the disadvantage that adenosine injection is required to achieve maximal hyperemia in the patient's blood vessels, which is not possible for patients with loss of renal function or patients who do not respond well to injected drugs, and the health of the patient is not guaranteed. Moreover, the reaction time required for inserting the pressure guide wire is long, so that the patient is painful; meanwhile, the detection cost in the pressure guide wire body is generally higher, and the medical cost is higher. Therefore, the current FFR detection prevalence is low.
In order to solve the problem that the method for detecting the fractional flow reserve needs to be matched with vasodilator medicines such as adenosine triphosphate to induce the maximum hyperemia reaction, the patient who is not suitable for related medicines cannot be detected, the health of the patient cannot be guaranteed, invasive operation is achieved, and due to the fact that the pressure guide wire is inserted in the measurement mode, not only is the operation of a doctor troublesome, but also the time is long, the patient is painful, the cost of the pressure guide wire in each time needs about 1 ten thousand RMB, and the cost is high. With the development of technology, many researchers developed some imaging means to assist in FFR calculation, and the intra-cavity image-based method proposed by the hangzhou pulse flow company is representative of the FFR calculation.
CN111134651, publication date: 2020-05-12, a method, apparatus, system and computer storage medium for calculating fractional flow reserve based on intra-luminal images are described, wherein the method for obtaining fractional flow reserve comprises step S1 of obtaining image data related to coronary vessels and constructing a corresponding three-dimensional vessel model by processing the image data; wherein the image data relating to coronary vessels comprises: intra-cavity image data and coronary angiography image data; step S2, calculating a blood flow equation according to the three-dimensional blood vessel model and the fluid dynamics method to obtain the blood dynamics parameter distribution of the coronary artery in the region expressed by the three-dimensional blood vessel model; and step S3, calculating the fractional flow reserve according to the hemodynamic parameters acquired in step S2, and accurately calculating and acquiring the patient coronary artery FFR.
However, in the real practice process, the fractional flow reserve is calculated by using the prior art, and although the luminal area is effectively identified, the selection of the reference frame (normal/healthy lumen) usually needs to be performed manually, which not only takes more time, but also needs a doctor to have more abundant clinical experience, and is easy to introduce subjective errors, thereby reducing the prediction accuracy of FFR.
Disclosure of Invention
The technical problem to be solved by the invention is that a multi-task learning model is established, and an end-to-end network structure is adopted to identify the tube cavity and the bifurcation in the OCT image at the same time; meanwhile, considering that the tube cavity and the bifurcation have certain structural characteristics and spatial position relation, a multi-task learning model based on spatial structure constraint is constructed, the precise identification of the tube cavity and the bifurcation is realized, the problems of structural information loss, category imbalance and the like in the traditional network model are solved, and the generalization capability of the model is improved; in order to realize automatic selection of a reference frame and solve the problem of similarity of OCT healthy blood vessels and non-healthy blood vessels in vision, an OCT healthy blood vessel classification network based on triple loss is provided; and then, a fluid dynamics program is utilized, the lumen contour area, the bifurcation and the reference frame are combined, the FFR prediction technology based on multiple parameters is proposed and constructed, and the FFR is accurately measured and calculated.
In order to realize the technical task, the invention adopts the following technical scheme to realize:
the device for predicting the fractional flow reserve based on the optical coherence tomography image comprises a probe interface module, a display module, a detection module, a signal processing module and a data calculation module, wherein the detection module, the probe interface module, the signal processing module, the data calculation module and the display module are sequentially connected;
the probe interface module is used for transmitting and receiving optical signals and is linked with the detection module for retraction;
the detection module comprises a catheter 1, an elastic component 2, an optical fiber 3, a probe 4, a guide wire 5, a transparent outer sleeve 6 and a flushing fluid outlet 7, is used for transmitting optical signals emitted by the probe interface module and transmitting the optical signals returned from tissues back to the probe interface module, the signals are transmitted to the signal processing module through the probe interface module, and are mainly used for transmitting the optical signals emitted by the probe interface module and transmitting the optical signals returned from the tissues back to the probe interface module, and the signals are transmitted to the signal processing module through the probe interface module.
The signal processing module is used for converting the optical signal input by the probe interface module into image information; and carrying out data calibration and image enhancement on the image information;
the data acquisition unit superposes and interferes the optical signal reflected from the tissue and the optical signal reflected by the reference reflector at the same time, the generated interference signal is detected by the photoelectric detector, and the interfered optical signal is converted into an electric signal by the detector, so that the data acquisition is realized. Because the electrical signal output by the detector is weak, a signal amplifier is required to amplify the electrical signal, and the amplified electrical signal is sent to a data processing unit;
the data processing unit is used for carrying out signal conversion on the electric signal input by the data acquisition unit to obtain image information and carrying out data calibration and image enhancement on the image information;
the data calculation module is used for constructing a combined lumen and bifurcation identification frame based on the OCT image and a multitask learning mechanism, processing signals input by the detection module to obtain the edge, the shape and the structural space information of the lumen of the blood vessel, acquiring the boundary of the lumen of the blood vessel, and calculating the area of the lumen of the blood vessel to obtain the bifurcation position;
the method comprises the steps of processing images input by a data processing unit, constructing a healthy blood vessel identification model based on triples, identifying healthy blood vessels in a pull-back OCT image by increasing the difference between classes and the similarity in the classes, and selecting a reference frame by combining the lumen area and the bifurcation position;
further utilizing a fluid dynamics model, combining the lumen area of the blood vessel and the area of a reference frame, calculating the blood flow volume and the flow resistance in the blood vessel, and combining the actually measured systolic pressure and diastolic pressure data to obtain the FFR value in the blood vessel, thereby realizing the full-automatic calculation of the FFR;
and the display module is used for displaying the processing result obtained by the data calculation module on a display.
The invention also discloses a fractional flow reserve prediction method based on the optical coherence tomography image, which comprises the following steps:
step 3, constructing a recognition multitask learning model of the pipe cavity and the bifurcation;
step 4, establishing a priori constraint condition of the contours of the lumen and the bifurcation;
step 5, combining the prior constraint conditions of the contours in the step 4, executing a multi-task learning model learning task for identifying the lumen and the bifurcation to obtain the spatial information of the edge, the shape and the structure of the lumen of the blood vessel, and calculating the area of the lumen of the blood vessel to obtain the position of the bifurcation;
step 6, constructing a healthy blood vessel identification model based on the triples, identifying healthy blood vessels in the pull-back OCT image by increasing the difference between the classes and the similarity in the classes, and selecting a reference frame by combining the lumen area and the bifurcation position;
and 7, constructing a full-automatic FFR prediction model by utilizing a fluid dynamics program and combining the lumen area of the blood vessel and the area of the reference frame, and calculating to obtain the FFR value in the blood vessel.
The present invention may also be embodied as a storage medium comprising any one of a number of computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the fractional flow reserve prediction method based on optical coherence tomography imaging in general of the present invention.
Compared with the prior art, the invention has the following positive beneficial effects
(1) The optical coherence tomography has the remarkable characteristic of high resolution, compared with the traditional angiography imaging technology, the optical coherence tomography has the resolution of several microns, the resolution effect is close to the level of a tissue pathological section, no damage is caused to the tissue, the necessary intravascular characteristic data is collected for FFR prediction by utilizing OCT-FFR, the predicted FFR value is more accurate, and the clinical diagnosis and treatment reference significance is higher.
(2) By utilizing the reference frame automatic identification technology, the full-automatic OCT-FFR technology is realized, the diagnosis time is reduced, the images of the FFR calculated by the subjective difference of doctors are reduced, and the primary doctors can also carry out effective auxiliary diagnosis.
(3) The OCT and FFR are combined, a more accurate coronary artery image with the specificity of a patient can be obtained in the OCT image, a virtual FFR prediction result is more reliable and accurate, the imaging evaluation can be performed on the stenosis degree of a myocardial vessel, the influence of stenosis on far-end blood flow can be analyzed, and the functional evaluation can be performed on coronary artery stenosis. Compared with the conventional FFR, the OCT-FFR is more accurate and detailed, not only can the FFR value prediction of a diseased blood vessel be realized, but also the coronary atherosclerotic plaque can be accurately evaluated through intravascular three-dimensional imaging, and more comprehensive diseased blood vessel information is provided for doctors, so that more theoretical references are provided for formulating and selecting personalized treatment schemes.
(4) The prediction of the fractional flow reserve based on the intravascular optical coherence tomography image belongs to a non-invasive technology, and compared with the traditional pressure guide wire measurement of FFR, the blood vessel of a patient is in the maximum hyperemia state without introducing adenosine, so that the pain of the patient is relieved, the diagnosis time is obviously reduced, and the medical efficiency is effectively improved.
Drawings
Fig. 1 is a schematic structural diagram of a fractional flow reserve predicting apparatus based on optical coherence tomography images according to the present invention.
Fig. 2 is a schematic structural diagram of a data processing unit in a signal processing module of the fractional flow reserve predicting device based on optical coherence tomography images according to the present invention.
Fig. 3 is another schematic structural diagram of a data processing unit in a signal processing module of the fractional flow reserve predicting device based on optical coherence tomography images according to the present invention.
Fig. 4 is a schematic structural diagram of a data calculation module of the fractional flow reserve prediction apparatus based on optical coherence tomography images according to the present invention.
Fig. 5 is a flowchart of a fractional flow reserve prediction method based on optical coherence tomography images according to the present invention.
FIG. 6 is a schematic diagram of a recognition multitask learning model network structure of lumens, bifurcations and stents according to the present invention.
FIG. 7 is a schematic diagram of triple loss principle in the healthy blood vessel identification model of the present invention
Fig. 8 is an initial operation interface diagram of the fractional flow reserve predicting apparatus based on optical coherence tomography image according to the present invention.
Fig. 9 shows that the fractional flow reserve prediction method based on optical coherence tomography completes image calibration and image enhancement to obtain an OCT image.
Fig. 10 is a schematic diagram of the fractional flow reserve prediction method based on optical coherence tomography images according to the present invention, wherein the lumen and bifurcation identification effect is shown.
Fig. 11 is a schematic diagram illustrating the effect of bifurcation position in the fractional flow reserve predicting method based on optical coherence tomography.
Fig. 12 is a schematic diagram illustrating an effect of automatic selection of a reference frame in the fractional flow reserve prediction method based on optical coherence tomography.
Fig. 13 is a schematic diagram illustrating the effect of FFR prediction results in the fractional flow reserve prediction method based on optical coherence tomography images.
The symbols in fig. 1 represent the following meanings: 1. a conduit; 2. an elastic member; 3. an optical fiber; 4. a probe; 5. a guide wire; 6. a transparent outer jacket; 7. a rinse liquid outlet; 8. the wall of the blood vessel.
The present invention will be described in more detail with reference to the accompanying drawings and embodiments.
Detailed Description
Referring to fig. 1, the apparatus for predicting fractional flow reserve based on optical coherence tomography images of the present invention comprises a probe interface module, a display module, a detection module, a signal processing module and a data calculation module, wherein the detection module, the probe interface module, the signal processing module, the data calculation module and the display module are sequentially connected;
the probe interface module is used for transmitting and receiving optical signals and is linked with the detection module for retraction;
the detection module comprises a catheter 1, an elastic component 2, an optical fiber 3, a probe 4, a guide wire 5, a transparent outer sleeve 6 and a washing liquid outlet 7, is used for transmitting optical signals emitted by the probe interface module and transmitting the optical signals returned from tissues back to the probe interface module, and the signals are sent to the signal processing module through the probe interface module.
The signal processing module is used for converting the optical signal input by the probe interface module into image information; and carrying out data calibration and image enhancement on the image information;
the data calculation module is used for constructing a combined lumen and bifurcation identification frame based on the OCT image and a multitask learning mechanism, processing signals input by the detection module to obtain the edge, the shape and the structural space information of the lumen of the blood vessel, acquiring the boundary of the lumen of the blood vessel, and calculating the area of the lumen of the blood vessel to obtain the bifurcation position;
processing signals input by a signal processing module to construct a healthy blood vessel identification model based on triples, identifying healthy blood vessels in a pull-back OCT image by increasing the difference between classes and the similarity in the classes, and selecting a reference frame by combining the lumen area and the bifurcation position;
further utilizing a fluid dynamics model, combining the lumen area of the blood vessel and the area of a reference frame, calculating the blood flow and the pressure loss in the blood vessel, and combining the actually measured systolic pressure and diastolic pressure data to obtain the FFR value in the blood vessel, thereby realizing the full-automatic calculation of the FFR;
and the display module is used for displaying the processing result obtained by the data calculation module on a display.
Referring to fig. 2 to fig. 3, the signal processing module at least includes a data acquisition unit and a data processing unit connected in sequence. And the data acquisition unit acquires the data of the signals acquired by the detection module through the detection interface module.
The data acquisition unit superposes and interferes the optical signal reflected from the tissue and the optical signal reflected by the reference reflector at the same time, the generated interference signal is detected by the photoelectric detector, and the interfered optical signal is converted into an electric signal by the detector, so that the data acquisition is realized. Because the electrical signal output by the detector is weak, a signal amplifier is required to amplify the electrical signal, and the amplified electrical signal is sent to a data processing unit;
the data processing unit at least comprises a signal conversion module, an image calibration module and an image enhancement module, wherein the signal conversion module is used for converting the electric signal output by the data acquisition unit into image information; the image calibration module is used for respectively carrying out data calibration on the image obtained by the signal conversion module or the image cutting module; and the image enhancement module is used for enhancing the image of the image which is calibrated and reconstructed by the image calibration module.
The data calculation module unit at least comprises a tube cavity and a bifurcation module which are connected in sequence; the device comprises a lumen area calculation module, a reference frame automatic identification module and an FFR full-automatic prediction module; the lumen and bifurcation identification module is used for extracting contour information aiming at the lumen and bifurcation information of the blood vessel; the lumen area calculation module is used for acquiring the lumen boundary of the blood vessel according to the edge, the shape and the structural space information of the lumen of the blood vessel and calculating the lumen area of the blood vessel; the reference frame automatic calculation module is used for constructing a healthy lumen identification model by utilizing a triple loss function, increasing the correlation in the classes and the difference between the classes, and then automatically selecting the position of a reference frame by combining the bifurcation position; the FFR full-automatic prediction module calculates blood flow volume and flow resistance in the blood vessel by utilizing a fluid dynamics model and combining the lumen area of the blood vessel and the area of a reference frame, and obtains an FFR value in the blood vessel by combining with actually measured systolic pressure and diastolic pressure data.
Referring to fig. 3, the apparatus for predicting fractional flow reserve based on optical coherence tomography image of the present invention is shown, wherein the data processing unit of the signal processing module has another structural diagram, and the data preprocessing unit further includes an image cropping module for segmenting the image information obtained by the signal conversion module and extracting the specific region of the image.
And a cleaning module is also arranged between the probe interface module and the detection module.
With further reference to fig. 1, the apparatus for predicting fractional flow reserve based on optical coherence tomography images of the present invention further includes a catheter 1, an elastic member 2, and an optical fiber 3, wherein the catheter 1 includes an internal portion and an external portion, a cleaning module is disposed on the external portion of the catheter 1, and the detection module is connected to the probe interface module through the external portion of the catheter 1; a probe 4, an optical fiber 3 and an elastic member 2 are arranged in the body of the catheter 1, the probe 4 is communicated with the probe interface module through the optical fiber 3, and the elastic member 2 is arranged on the optical fiber 3. The elastic component 2 can be any component capable of generating elastic deformation, such as a spring tube, and the like, so that the probe 4 can axially reciprocate along the catheter under the deformation constraint condition of the elastic component 2 to acquire the relevant data information of the blood vessel lumen and the outer elastic membrane.
One end of the interior of the detection module catheter 1, which is far away from the exterior of the catheter 1, is provided with a flushing liquid outlet 7. Irrigation liquid is injected from the cleaning module into the catheter 1 and is discharged from the irrigation liquid outlet 7.
A transparent outer sleeve 6 is sleeved on the inner side and the outer side of the body of the catheter 1, and the depth of the transparent outer sleeve 6 in the body of the catheter 1 does not exceed the axial position of the probe 4 in the body of the catheter 1.
The transparent outer sleeve 6 is arranged outside the inside of the body of the catheter 1 and mainly aims at assisting the fixation of the catheter 1 in the position inside the body.
Referring to fig. 5, the fractional flow reserve predicting method based on optical coherence tomography of the present invention includes the following steps:
step 3, constructing a multi-task learning model for identifying the tube cavity and the bifurcation;
step 4, establishing a priori constraint condition of the contours of the lumen and the bifurcation;
step 5, combining the prior constraint conditions of the contours in the step 4, executing a multi-task learning model learning task for identifying the lumen and the bifurcation to obtain the spatial information of the edge, the shape and the structure of the lumen of the blood vessel, and calculating the area of the lumen of the blood vessel to obtain the position of the bifurcation;
step 6, constructing a healthy blood vessel identification model based on the triples, identifying healthy blood vessels in the pull-back OCT image by increasing the difference between the classes and the similarity in the classes, and selecting a reference frame by combining the lumen area and the bifurcation position;
and 7, constructing a full-automatic FFR prediction model by utilizing a fluid dynamics program and combining the lumen area of the blood vessel and the area of the reference frame, and calculating to obtain the FFR value in the blood vessel.
Referring to fig. 6, the structure of the lumen and bifurcation identification multitask learning model network is shown schematically. Considering that lumens and bifurcations have the own structure and contour characteristics, in order to utilize structure information without increasing the labeling cost, the technology extracts the contour of a mask, thereby constructing two parallel convolutional neural networks, wherein the sizes of convolution kernels adopted comprise convolution of 5x5 and convolution of 3x3, the sizes of lumens and bifurcations are considered to have different sizes in different images, so jump connection is adopted, a shallow down-sampling layer and a deep up-sampling layer are connected, thereby realizing feature fusion on different semantic levels, a nonlinear activation function adopts Relu, a pooling layer adopts the maximum value, the input size of an image is 704x704, the mean value and variance adopted by data preprocessing are the mean value [0.406,0.456,0.485] and the variance [0.225,0.224,0.229] of an agennet, a pre-training network is not adopted, the size of each batch (Imbatch) during training is 32, the maximum value of the data round (epoch) was 100, the initial learning rate was 0.01, and an Adam optimizer was used. The invention uses the multi-task learning model to construct the mask prediction and contour drawing multi-task learning model, and the learning model can realize plug and play. The module consists of two parallel convolution filters and can simultaneously learn two related tasks. The module processes class imbalance, reduces outliers, alleviates structural information loss, and can well process multi-instance object segmentation. The learning model helps the network to learn a plurality of related tasks in parallel, so that the network has better generalization capability. Wherein both mask prediction and contour extraction are classification tasks.
Further, the prior constraint conditions of the contours and the forked contours in the step 4 are to add a contour loss function to the network loss function, so that the model learns more structural information, and the specific formula is as follows:
Ltotal loss＝λ1(LLumen mask+LBifurcated mask)+λ2(LLumen profile+LBifurcated profile)
Wherein L represents a loss function, using negative likelihood logarithms, i.e.
Where x represents the position of a pixel in the representation,
representing the prediction probability, λ, of the network model relative to the true label l1、λ2Weight parameters in the multitask learning representing mask and contour, respectively.
In order to realize automatic selection of the reference frame, the special scheme adopts a ResNet101 network to classify the OCT images, and the OCT images are divided into healthy blood vessels and unhealthy blood vessels. Considering that there are big intra-class difference and small inter-class difference between healthy blood vessels and unhealthy blood vessels, the patent proposes a healthy blood vessel identification model of a triplet, see fig. 7, by using a triplet loss function, the distance between healthy blood vessels can be made smaller, and the distance between healthy blood vessels and unhealthy blood vessels can be increased, so that the classification accuracy is improved, specifically, the triplet loss function is:
L＝max(d(fhealth 1-fHealth 2)-d(fHealth 1-fNon-health 1)+margin,0)
Wherein the function d (-) represents the Euclidean distance, fHealth 1、fHealth 2Depth feature representing healthy vessel extraction, fNon-health 1Representing the extracted features of non-healthy vessels, margin is a bias term. The reference frame location can then be selected to be within 10mm of healthy vessel each, proximally and distally from the minimum luminal area and not at the maximum luminal area of the bifurcation location.
Further, by combining a Bernoulli equation, a momentum equation, a Navier-Stokes equation, a lumen area and a reference frame area in fluid dynamics, the multi-parameter FFR model adopted by the method is as follows:
ΔP＝FV+FV2
wherein, PProximal endRepresenting the near-end pressure of OCT data,. DELTA.P is the intravascular pressure loss and. mu.is the viscosity of the blood, typically 4.0X 10-3Pa.S, L represents the length of the vessel lumen, AAutomaticIndicating an automatically selected reference frame, AsThe area of the lumen at the stenosis, V denotes the blood flow velocity, k denotes the coefficient of influence of the inlet and outlet on the pressure drop, and is usually taken to be 1, ρ denotes the blood density, and ρ is 1050kg/m3。
The following is an actual test case related to the invention, and the key technical effects of the whole scheme are read through an operation interface.
First, after data acquisition, a data processing interface is performed (fig. 8), and the system performs image calibration and image enhancement to obtain an IVUS image (fig. 9).
The fractional flow reserve predicting method based on optical coherence tomography images of the invention is shown in a schematic diagram 10 of lumen and bifurcation identification effects.
Referring to fig. 11, a schematic diagram of the method for identifying the bifurcation position is shown.
FIG. 12 is a diagram illustrating the effect of the automatic reference frame selection result according to the present invention.
FIG. 13 is a graphical representation of the OCT-FFR results of the present invention.
The present invention may also be applied to a storage medium embodied as any one of computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the fractional flow reserve prediction method based on optical coherence tomography as a whole of the present invention.
Claims (14)
1. The utility model provides a fractional flow reserve prediction unit based on optical coherence tomography image, includes probe interface module, display module, its characterized in that: the device comprises a probe module, a probe interface module, a signal processing module, a data calculation module and a display module, wherein the probe module, the probe interface module, the signal processing module, the data calculation module and the display module are sequentially connected;
the probe interface module is used for transmitting and receiving optical signals and is linked with the detection module for retraction;
the detection module comprises a catheter 1, an elastic component 2, an optical fiber 3, a probe 4, a guide wire 5, a transparent outer sleeve 6 and a flushing fluid outlet 7, is used for transmitting optical signals emitted by the probe interface module and transmitting the optical signals returned from the tissues back to the probe interface module, and the signals are sent to the signal processing module through the probe interface module;
the signal processing module is used for converting the optical signal transmitted or received by the detection module into image information; data calibration and image enhancement are carried out on the image information;
the data calculation module is used for constructing a combined lumen and bifurcation identification frame based on the OCT image and a multitask learning mechanism, processing signals input by the detection module to obtain the edge, the shape and the structural space information of the lumen of the blood vessel, acquiring the boundary of the lumen of the blood vessel, and calculating the area of the lumen of the blood vessel to obtain the bifurcation position;
the method comprises the steps of identifying healthy blood vessels in a pull-back OCT image by constructing a healthy blood vessel identification model based on triples, increasing the difference between classes and the similarity in the classes, and selecting a reference frame by combining the area of a lumen and the branching position;
further utilizing a fluid dynamics model, combining the lumen area of the blood vessel and the area of a reference frame, calculating the blood flow volume and the flow resistance in the blood vessel, and combining the actually measured systolic pressure and diastolic pressure data to obtain the FFR value in the blood vessel, thereby realizing the full-automatic calculation of the FFR;
and the display module is used for displaying the processing result obtained by the data calculation module on a display.
2. The fractional flow reserve predicting device according to claim 1, wherein: the signal processing module at least comprises a data acquisition unit and a data processing unit which are sequentially connected, and the data acquisition unit acquires data of the signal acquired by the detection module through the detection interface module;
the data processing unit at least comprises a signal conversion module, an image calibration module and an image enhancement module, wherein the signal conversion module is used for converting the electric signal signals received by the data acquisition unit into image information; the image calibration module is used for respectively carrying out data calibration on the image obtained by the signal conversion module or the image cutting module; the image enhancement module is used for carrying out image enhancement on the image which is calibrated and reconstructed by the image calibration module;
the data calculation module unit at least comprises a tube cavity, a bifurcation module, a tube cavity area calculation module, a reference frame automatic identification module and an FFR full-automatic prediction module which are connected in sequence; the lumen and bifurcation identification module is used for extracting contour information aiming at the lumen and bifurcation information of the blood vessel; the lumen area calculation module is used for acquiring the lumen boundary of the blood vessel according to the edge, the shape and the structural space information of the lumen of the blood vessel and calculating the lumen area of the blood vessel; the reference frame automatic calculation module is used for constructing a healthy lumen identification model by utilizing a triple loss function, increasing the correlation in the classes and the difference between the classes, and then automatically selecting the position of a reference frame by combining the bifurcation position; the FFR full-automatic prediction module calculates blood flow volume and flow resistance in the blood vessel by utilizing a fluid dynamics model and combining the lumen area of the blood vessel and the area of a reference frame, and obtains an FFR value in the blood vessel by combining with actually measured systolic pressure and diastolic pressure data.
3. The fractional flow reserve predicting device according to claim 2, wherein: the data processing unit also comprises an image cutting module which is used for dividing the image information obtained by the signal conversion module and extracting the specific area of the image.
4. The fractional flow reserve predicting device according to claim 1 or 2, wherein: and a cleaning module is also arranged between the probe interface module and the detection module.
5. The fractional flow reserve predicting device according to claim 4, wherein: the detection module further comprises a conduit (1), an elastic component (2) and a cable (3), the conduit (1) comprises an internal part and an external part, a cleaning module is arranged on the external part of the conduit (1), and the detection module is connected with the probe interface module through the external part of the conduit (1); an ultrasonic probe (4), a cable (3) and an elastic component (2) are arranged in the body of the catheter (1), the ultrasonic probe (4) is communicated with the probe interface module through the cable (3), and the elastic component (2) is arranged on the cable (3).
6. The fractional flow reserve predicting device according to claim 5, wherein: one end of the interior of the detection module catheter (1), which is far away from the exterior of the catheter (1), is provided with a flushing liquid outlet (7).
7. The fractional flow reserve predicting device according to claim 5 or 6, wherein: the outer side of the inner part of the body of the catheter (1) is also sleeved with a transparent outer sleeve (6), and the depth of the transparent outer sleeve (6) in the inner part of the body of the catheter (1) is not more than the axial position of the ultrasonic probe (4) in the inner part of the body of the catheter (1).
8. A fractional flow reserve prediction method based on optical coherence tomography images is characterized by comprising the following steps: the method comprises the following steps:
step 1: the optical signal of the near infrared light returning from the tissue is superposed and interfered with the optical signal reflected by the reference reflector, the generated interference signal is detected by the photoelectric detector, the interfered optical signal is converted into an electric signal by the detector, and the amplified electric signal is sent to the signal processing module through the probe interface module to finish signal data acquisition;
step 2, carrying out signal conversion, image calibration and image enhancement on the acquired signal data to finish image data acquisition;
step 3, constructing a multi-task learning model for identifying the tube cavity and the bifurcation;
step 4, establishing a priori constraint condition of the contours of the lumen and the bifurcation;
step 5, combining the prior constraint conditions of the contours in the step 4, executing a multi-task learning model learning task for identifying the lumen and the bifurcation to obtain the spatial information of the edge, the shape and the structure of the lumen of the blood vessel, and calculating the area of the lumen of the blood vessel to obtain the position of the bifurcation;
step 6, constructing a healthy blood vessel identification model based on the triples, identifying healthy blood vessels in the pull-back OCT image by increasing the difference between the classes and the similarity in the classes, and selecting a reference frame by combining the lumen area and the bifurcation position;
and 7, constructing a full-automatic FFR prediction model by utilizing a fluid dynamics program and combining the lumen area of the blood vessel and the area of the reference frame, and calculating to obtain the FFR value in the blood vessel.
9. The fractional flow reserve prediction method based on optical coherence tomography image as claimed in claim 8, wherein: and the step 2 also comprises the step of cutting the acquired signal data into images.
10. The fractional flow reserve prediction method based on optical coherence tomography image as claimed in claim 8, wherein: and 3, constructing two parallel convolutional neural networks of a lumen and bifurcation recognition multitask learning model network structure, wherein the sizes of adopted convolutional kernels comprise convolutional layers of 5x5 and convolutional layers of 3x 3.
11. The fractional flow reserve prediction method based on optical coherence tomography image as claimed in claim 8, wherein: the prior constraint conditions of the contours and the forked contours in the step 4 are that a contour loss function is added into a network loss function, so that the model learns more structural information, and the specific formula is as follows:
Ltotal loss＝λ1(LLumen mask+LBifurcated mask)+λ2(LLumen profile+LBifurcated profile)
Wherein L represents a loss function, using negative likelihood logarithms, i.e.
Where x represents the position of a pixel in the representation,
representing the prediction probability, λ, of the network model relative to the true label l1、λ2Weight parameters in the multitask learning representing mask and contour, respectively.
12. The fractional flow reserve prediction method based on optical coherence tomography image as claimed in claim 8, wherein: step 6, constructing a healthy blood vessel identification model based on the triplet, wherein the healthy blood vessel identification model of the triplet is as follows:
L＝max(d(fhealth 1-fHealth 2)-d(fHealth 1-fNon-health 1)+margin,0)
Wherein the function d (-) represents the Euclidean distance, fHealth 1、fHealth 2Depth feature representing healthy vessel extraction, fNon-health 1Representing the extracted features of non-healthy vessels, margin is a bias term.
13. The fractional flow reserve prediction method based on optical coherence tomography image as claimed in claim 8, wherein: the FFR calculation model is as follows:
ΔP＝FV+FV2
wherein, PProximal endRepresenting the near-end pressure of OCT data,. DELTA.P is the intravascular pressure loss and. mu.is the viscosity of the blood, typically 4.0X 10-3Pa.S, L represents the length of the vessel lumen, AAutomaticIndicating an automatically selected reference frame, AsThe area of the lumen at the stenosis, V denotes the blood flow velocity, k denotes the coefficient of influence of the inlet and outlet on the pressure drop, and is usually taken to be 1, ρ denotes the blood density, and ρ is 1050kg/m3。
14. A storage medium storing computer-readable instructions which, when executed by one or more processors, cause the one or more processors to perform the fractional flow reserve prediction method based on optical coherence tomography images of claims 8-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111641922.7A CN114463267A (en) | 2021-12-29 | 2021-12-29 | Fractional flow reserve prediction method and device based on optical coherence tomography and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111641922.7A CN114463267A (en) | 2021-12-29 | 2021-12-29 | Fractional flow reserve prediction method and device based on optical coherence tomography and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114463267A true CN114463267A (en) | 2022-05-10 |
Family
ID=81408134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111641922.7A Pending CN114463267A (en) | 2021-12-29 | 2021-12-29 | Fractional flow reserve prediction method and device based on optical coherence tomography and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114463267A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140379269A1 (en) * | 2011-08-03 | 2014-12-25 | Lightlab Imaging, Inc. | Systems, methods and apparatus for determining a fractional flow reserve |
| CN107730540A (en) * | 2017-10-09 | 2018-02-23 | 全景恒升（北京）科学技术有限公司 | The computational methods of coronary artery parameter based on high-precision Matching Model |
| US10249048B1 (en) * | 2017-11-15 | 2019-04-02 | Beijing Curacloud Technology Co., Ltd. | Method and system for predicting blood flow features based on medical images |
| CN111134651A (en) * | 2019-12-09 | 2020-05-12 | 杭州脉流科技有限公司 | Method, device and system for calculating fractional flow reserve based on intracavity images and computer storage medium |
| CN112535466A (en) * | 2020-12-16 | 2021-03-23 | 成都全景恒升科技有限公司 | Blood flow reserve fraction calculation method based on blood vessel image |
-
2021
- 2021-12-29 CN CN202111641922.7A patent/CN114463267A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140379269A1 (en) * | 2011-08-03 | 2014-12-25 | Lightlab Imaging, Inc. | Systems, methods and apparatus for determining a fractional flow reserve |
| CN107730540A (en) * | 2017-10-09 | 2018-02-23 | 全景恒升（北京）科学技术有限公司 | The computational methods of coronary artery parameter based on high-precision Matching Model |
| US10249048B1 (en) * | 2017-11-15 | 2019-04-02 | Beijing Curacloud Technology Co., Ltd. | Method and system for predicting blood flow features based on medical images |
| CN111134651A (en) * | 2019-12-09 | 2020-05-12 | 杭州脉流科技有限公司 | Method, device and system for calculating fractional flow reserve based on intracavity images and computer storage medium |
| CN112535466A (en) * | 2020-12-16 | 2021-03-23 | 成都全景恒升科技有限公司 | Blood flow reserve fraction calculation method based on blood vessel image |
Non-Patent Citations (1)
| Title |
|---|
| KYUNG EUN LEE 等: "A vessel length-based method to compute coronary fractional flow reserve from optical coherence tomography images", 《BIOMEDICAL ENGINEERING ONLINE》, 26 June 2017 (2017-06-26) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11741613B2 (en) | Systems and methods for classification of arterial image regions and features thereof | |
| JP6792768B2 (en) | Calculation method and system of blood flow reserve ratio | |
| CN107730540B (en) | Coronary parameter calculation method based on high-precision matching model | |
| US9852504B2 (en) | Automatic stent detection | |
| US20220346885A1 (en) | Artificial intelligence coregistration and marker detection, including machine learning and using results thereof | |
| CN111134651B (en) | Method, device and system for calculating fractional flow reserve based on intracavity images and computer storage medium | |
| CN113557576A (en) | Method and system for configuring and using neural networks in characterizing physiological systems | |
| CN108665449B (en) | Deep learning model and device for predicting blood flow characteristics on blood flow vector path | |
| CN108717874B (en) | Method and device for obtaining blood vessel pressure value based on specific physiological parameters | |
| CN116030968A (en) | Blood flow reserve score prediction method and device based on intravascular ultrasound image | |
| CN212365043U (en) | Data processing system based on blood vessel image | |
| CN113876304B (en) | Method and device for determining FFR (fringe field switching) based on OCT (optical coherence tomography) image and contrast image | |
| US20220335612A1 (en) | Automated analysis of image data to determine fractional flow reserve | |
| CN114463267A (en) | Fractional flow reserve prediction method and device based on optical coherence tomography and computer storage medium | |
| CN114515144A (en) | System for detecting flow rate and pressure of thoracic aortic dissection false cavity and in-vivo measurement method | |
| Xiao | Key Technologies of New Type of Intravascular Ultrasound Image Processing | |
| CN115272447B (en) | Multi-modal image-based fractional flow reserve calculation method, device and equipment | |
| CN221535325U (en) | Diagnostic catheter | |
| CN117036302B (en) | Method and system for determining calcification degree of aortic valve | |
| WO2024071121A1 (en) | Computer program, information processing method, and information processing device | |
| CN116664938A (en) | Coronary plaque type determining method and device, electronic equipment and storage medium | |
| CN116452732A (en) | Method, device and equipment for generating three-dimensional model of urethra and cavity organ | |
| IL269223B2 (en) | Automated analysis of image data to determine fractional flow reserve | |
| CN115299916A (en) | Cerebral blood flow detection method based on CNN-GRU network model | |
| CN118415665A (en) | Blood vessel detection device and method based on fiber bragg grating |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |