CN113838028A - Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium - Google Patents
Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium Download PDFInfo
- Publication number
- CN113838028A CN113838028A CN202111119626.0A CN202111119626A CN113838028A CN 113838028 A CN113838028 A CN 113838028A CN 202111119626 A CN202111119626 A CN 202111119626A CN 113838028 A CN113838028 A CN 113838028A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- carotid artery
- sample
- neural network
- image
- 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.)
- Granted
Links
- 210000001715 carotid artery Anatomy 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 34
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 176
- 238000001514 detection method Methods 0.000 claims abstract description 73
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 70
- 238000010586 diagram Methods 0.000 claims abstract description 40
- 238000005070 sampling Methods 0.000 claims abstract description 31
- 230000006870 function Effects 0.000 claims description 45
- 238000002604 ultrasonography Methods 0.000 claims description 34
- 239000013598 vector Substances 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 8
- 239000000523 sample Substances 0.000 description 91
- 230000004913 activation Effects 0.000 description 16
- 230000017531 blood circulation Effects 0.000 description 10
- 238000010606 normalization Methods 0.000 description 6
- 238000011176 pooling Methods 0.000 description 6
- 208000026106 cerebrovascular disease Diseases 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000001168 carotid artery common Anatomy 0.000 description 1
- 210000000269 carotid artery external Anatomy 0.000 description 1
- 210000004004 carotid artery internal Anatomy 0.000 description 1
- 208000006170 carotid stenosis Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003205 diastolic effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 208000037804 stenosis Diseases 0.000 description 1
- 230000036262 stenosis Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000019553 vascular disease Diseases 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0891—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of blood vessels
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/48—Diagnostic techniques
- A61B8/488—Diagnostic techniques involving Doppler signals
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5207—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of raw data to produce diagnostic data, e.g. for generating an image
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- 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
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Theoretical Computer Science (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Public Health (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pathology (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Vascular Medicine (AREA)
- Quality & Reliability (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention provides a carotid artery ultrasonic automatic Doppler method, which comprises the following steps: acquiring a carotid artery ultrasonic image; inputting the carotid artery ultrasonic image into a convolutional neural network detection model to extract characteristics to obtain an output characteristic diagram; extracting a preset number of image blocks from the output characteristic diagram; recording the position information of each image block on the output characteristic diagram; the convolutional neural network detection model obtains a blood vessel angle in the carotid artery ultrasonic image based on the preset number of image blocks; the convolutional neural network detection model obtains the position of a blood vessel in the carotid artery ultrasonic image based on the preset number of image blocks; calculating the width of the blood vessel based on the obtained position of the blood vessel; and automatically generating a sampling gate on the carotid artery ultrasonic image based on the obtained blood vessel angle, blood vessel position and blood vessel width. The invention can simplify the operation of a doctor during carotid artery ultrasonic Doppler examination and improve the working efficiency of the doctor.
Description
Technical Field
The invention belongs to the technical field of ultrasonic equipment, and particularly relates to an automatic carotid artery ultrasonic Doppler method.
Background
The incidence of cerebrovascular diseases is rising year by year, and the non-invasive detection method is adopted to discover the existence of extracranial arterial vascular diseases at an early stage and treat the diseases in time, so that the method is an effective means for preventing and reducing the incidence of cerebrovascular diseases and has important clinical significance. The above extracranial artery vessels mainly refer to carotid vessels. Carotid vessels detected by carotid ultrasound comprise common carotid artery, internal carotid artery and external carotid artery, and are one of effective means for diagnosing and evaluating carotid lesions. The carotid artery ultrasonic examination has the characteristics of simple and convenient operation, strong repeatability, economy, practicability, easy acceptance by patients and the like; therefore, it is often used for screening normal people and examining the disease condition of high risk group with cerebrovascular disease, including before, during and after operation and follow-up.
Carotid artery ultrasound examination includes comprehensive analysis of two-dimensional structures, doppler spectra, and the like. The two-dimensional structure analysis can observe the inner diameter of the blood vessel and is used for judging whether the lumen is expanded, narrowed, twisted, normally traveled, the thickness of the intima and whether plaque exists. Doppler spectrum analysis acquires a blood flow spectrum to observe blood flow velocity, and judges whether the blood flow velocity is increased or decreased. Blood flow velocity often corresponds to a two-dimensional structure, such as an increase in blood flow velocity often due to a narrowing of the carotid lumen. Doppler spectroscopy is also used to obtain peak systolic blood flow velocity, end diastolic blood flow velocity and internal carotid to common carotid flow velocity ratios.
At present, when a doctor uses ultrasonic equipment to carry out carotid artery ultrasonic Doppler examination, firstly, the position of a probe is adjusted to ensure that a carotid artery ultrasonic image is clearest; then adjusting the Doppler angle (namely the angle of the sampling gate), wherein the range is generally between plus or minus 30 degrees; the width of the parallelogram sampling gate is adjusted, and the width of the sampling gate is generally 1/3 of the width of the blood vessel; finally, a frame of carotid image and a frame of representative Doppler spectrum are recorded, and the peak systolic flow rate is measured. The physician performs the above steps to ensure accurate measurement of peak systolic flow. If the doctor does not perform the above steps, blood flow sampling is incorrect, peak flow rate is increased or decreased artificially, and errors occur when the systolic peak flow rate ratio is calculated to evaluate the luminal stenosis. In this case, if there is clinically significant carotid stenosis, it may lead to erroneous judgment.
However, when doctors work, the number of patients to be detected is large, and the workload is large; if the procedure of carotid ultrasound examination can be simplified by an automated algorithm, the working efficiency of the doctor can be directly improved.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an automatic carotid artery ultrasonic Doppler method so as to simplify the operation of a doctor during carotid artery ultrasonic Doppler examination and improve the working efficiency of the doctor; the application also provides ultrasonic equipment and a storage medium corresponding to the method. In order to achieve the technical purpose, the embodiment of the invention adopts the technical scheme that:
in a first aspect, an embodiment of the present invention provides a carotid artery ultrasound automatic doppler method, where the method includes:
acquiring a carotid artery ultrasonic image;
inputting the carotid artery ultrasonic image into a convolutional neural network detection model to extract characteristics to obtain an output characteristic diagram;
extracting a preset number of image blocks from the output characteristic diagram; recording the position information of each image block on the output characteristic diagram;
the convolutional neural network detection model obtains a blood vessel angle in the carotid artery ultrasonic image based on the preset number of image blocks;
the convolutional neural network detection model obtains the position of a blood vessel in the carotid artery ultrasonic image based on the preset number of image blocks;
calculating the width of the blood vessel based on the obtained position of the blood vessel;
and automatically generating a sampling gate on the carotid artery ultrasonic image based on the obtained blood vessel angle, blood vessel position and blood vessel width.
Further, the inputting the carotid artery ultrasound image into a convolutional neural network detection model to extract features to obtain an output feature map specifically includes:
and inputting the carotid artery ultrasonic image into a convolutional neural network detection model, extracting characteristics of the convolutional neural network detection model through a plurality of groups of layer groups comprising a convolutional layer, a pooling layer, a batch normalization layer and an activation function layer, and obtaining an output characteristic diagram at the activation function layer of the last layer group.
Further, the extracting a preset number of image blocks on the output feature map specifically includes:
performing sliding window operation on the output feature map, and extracting an image block based on the pixel position; the extracting the image block based on the pixel position includes: and traversing each pixel on the output feature map by taking the pixel position as a center to extract an image block or extracting image blocks from every other pixel on the output feature map.
Further, the extracting the image block includes extracting a plurality of image blocks with different sizes and different preset aspect ratios.
Further, the obtaining, by the convolutional neural network detection model, a blood vessel angle in the carotid artery ultrasound image based on the preset number of image blocks specifically includes:
outputting a first prediction output vector containing a plurality of blood vessel angle prediction probabilities for each image block through the convolutional neural network detection model;
determining image blocks with highest blood vessel angle prediction probability in all first prediction output vectors;
and taking the blood vessel angle corresponding to the category with the highest blood vessel angle prediction probability in the first prediction output vector of the image block with the highest blood vessel angle prediction probability as the blood vessel angle in the carotid artery ultrasonic image.
Further, the obtaining, by the convolutional neural network detection model, a blood vessel position in the carotid artery ultrasound image based on the preset number of image blocks specifically includes:
outputting a second prediction output vector containing a predicted blood vessel position for each image block through the convolutional neural network detection model;
and restoring the position of the image block with the highest blood vessel angle prediction probability on the output characteristic map to the carotid artery ultrasonic image, and obtaining the position of the blood vessel in the carotid artery ultrasonic image by combining the predicted position of the blood vessel in the image block.
Further, the calculating of the blood vessel width based on the obtained blood vessel position specifically includes:
generating a straight line perpendicular to the length direction of the blood vessel by passing through the middle point of the width direction of the blood vessel based on the position of the blood vessel;
calculating the gradient value of each pixel point on the straight line from the midpoint of the blood vessel to one direction of the straight line;
when the gradient value of the accumulated preset number of pixel points is larger than a preset threshold value, determining a first pixel point in the preset number of pixel points as a side edge point of the blood vessel when the gradient value is met for the first time; acquiring the distance from the center point of the blood vessel to the edge point of one side;
and calculating the width of the blood vessel according to the distance from the midpoint of the blood vessel to the edge point of one side.
Further, the automatically generating a sampling gate on the carotid artery ultrasound image based on the obtained blood vessel angle, blood vessel position and blood vessel width comprises:
setting the center of the sampling gate at the center point of the position of the blood vessel in the carotid artery ultrasonic image; the angle of the sampling gate is the obtained angle of the blood vessel; the width of the sampling gate is less than or equal to the width of the obtained blood vessel.
Further, the convolutional neural network detection model is obtained by training in the following way:
acquiring a sample carotid artery ultrasonic image, wherein the sample carotid artery ultrasonic image is marked with blood vessel angle information and a blood vessel position mark;
inputting the sample carotid artery ultrasonic image into a convolutional neural network detection model to extract characteristics to obtain a sample output characteristic diagram;
extracting a preset number of sample image blocks on the sample output characteristic diagram; recording the position information of each sample image block on the sample output characteristic diagram;
dividing the sample image blocks into positive sample image blocks and negative sample image blocks according to a preset rule; the blood vessel angle of the positive sample image block is the blood vessel angle marked by the sample carotid artery ultrasound image corresponding to the positive sample image block;
and training the convolutional neural network detection model according to the positive sample image blocks and the negative sample image blocks.
Further, the extracting a predetermined number of sample image blocks on the sample output feature map includes:
performing sliding window operation on the sample output characteristic diagram, and extracting a sample image block based on the pixel position; the extracting a sample image block based on pixel location comprises: and traversing each pixel on the sample output characteristic diagram to extract a sample image block or extracting the sample image blocks at intervals of a plurality of pixels on the sample output characteristic diagram by taking the pixel position as a center.
Further, the dividing the sample image block into a positive sample image block and a negative sample image block according to a predetermined rule includes:
calculating the intersection and comparison of each sample image block and the corresponding blood vessel of the blood vessel position mark in the sample carotid artery ultrasonic image, wherein the intersection and comparison is the ratio of the intersection to the union;
and taking the sample image blocks with the intersection ratio larger than a set threshold value as positive sample image blocks, and otherwise, taking the sample image blocks as negative sample image blocks.
Further, the training the convolutional neural network detection model according to the positive sample image blocks and the negative sample image blocks comprises:
inputting the positive sample image blocks and the negative sample image blocks into the convolutional neural network detection model;
outputting, by the convolutional neural network detection model, a first prediction output vector containing a plurality of vessel angle prediction probabilities for each of the sample image blocks; calculating a first loss function for vessel angle prediction;
outputting a second prediction output vector containing a predicted blood vessel position for each image block through the convolutional neural network detection model; calculating a second loss function for vessel location prediction;
and reversely transmitting the function value of the first loss function and the function value of the second loss function back to the convolutional neural network detection model for updating and iteration to obtain the trained convolutional neural network detection model.
As a pre-selection, the first loss function is shown in equation (1),
Loss(prob1,prob2)=max(0,-β(prob1-prob2)+margin) (1)
wherein, prob1,prob2Predicting probabilities of the two sample image blocks on a blood vessel angle class; when the convolutional neural network detection model is required to output that the prediction probability prob1 in the blood vessel angle class of the first sample image block is greater than the prediction probability prob2 in the blood vessel angle class of the second sample image block, the value of beta is 1, otherwise the value of beta is-1; margin is a hyper-parameter and takes a value of 0.4-0.6;
the second loss function is shown in equation (2),
where out represents the output second prediction output vector and truth represents the true vessel position.
Preferably, each input of the first loss function is a pair of a positive sample image block and a negative sample image block.
Preferably, the convolutional neural network detection model adopts a pyramid structure and comprises three groups of layer groups including a convolutional layer, a pooling layer, a batch normalization layer and an activation function layer;
in the convolutional neural network detection model with the pyramid structure, the low-layer features output by the first activation function layer are up-sampled and then added with the middle-layer features output by the second activation function layer to obtain a feature fused with the low-layer and middle-layer, and the feature fused with the low-layer and middle-layer is up-sampled and then added with the high-layer features output by the third activation function layer to obtain a feature fused with the low-layer, middle-layer and high-layer.
In a second aspect, an embodiment of the present invention provides an ultrasound apparatus, including:
a memory storing a computer program;
a processor for executing the computer program, the computer program when executed performing the steps of the method as described above.
In a third aspect, an embodiment of the present invention provides a storage medium, in which a computer program is stored, the computer program being configured to perform the steps of the method as described above when executed.
The technical scheme provided by the embodiment of the invention has the following beneficial effects: the full automation of the generation process of the sampling gate is realized, and the sampling gate is automatically generated on the carotid artery ultrasonic image only by providing the carotid artery ultrasonic image when the sampling gate is used, so that the working efficiency of a doctor is obviously improved, and the time for the doctor to carry out the carotid artery ultrasonic Doppler examination is greatly saved.
Drawings
FIG. 1 is a schematic diagram of an ultrasound image of the carotid artery in an embodiment of the invention.
FIG. 2 is a schematic diagram of a generated sample gate in an embodiment of the invention.
FIG. 3 is a flow chart of a method in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In a first aspect, an embodiment of the present invention provides a method for obtaining blood vessel information and automatically generating a sample gate, including:
acquiring a carotid artery ultrasonic image;
inputting the carotid artery ultrasonic image into a convolutional neural network detection model to extract characteristics to obtain an output characteristic diagram;
extracting a preset number of image blocks from the output characteristic diagram; recording the position information of each image block on the output characteristic diagram;
the convolutional neural network detection model obtains a blood vessel angle in the carotid artery ultrasonic image based on the preset number of image blocks;
the convolutional neural network detection model obtains the position of a blood vessel in the carotid artery ultrasonic image based on the preset number of image blocks;
calculating the width of the blood vessel based on the obtained position of the blood vessel;
and automatically generating a sampling gate on the carotid artery ultrasonic image based on the obtained blood vessel angle, blood vessel position and blood vessel width.
The method can predict the blood vessel angle and the blood vessel position of the input carotid artery ultrasonic image through a convolution neural network detection model, and then can conveniently calculate the blood vessel width based on the blood vessel position; finally, automatically generating a sampling gate; the automatic processing process can simplify the operation of a doctor during the carotid artery ultrasonic Doppler examination, and obviously improve the working efficiency of the doctor; by adopting an artificial intelligence method, the time for the doctor to carry out carotid artery ultrasonic Doppler examination is greatly saved;
specifically, the inputting the carotid artery ultrasound image into a convolutional neural network detection model to extract features to obtain an output feature map includes: inputting the carotid artery ultrasonic image into a convolutional neural network detection model, extracting characteristics of the convolutional neural network detection model through a plurality of groups of layer groups comprising a convolutional layer, a pooling layer, a batch normalization layer and an activation function layer, and obtaining an output characteristic diagram at the activation function layer of the last layer group; the characteristic extraction comprises the steps of extracting blood vessel edge characteristics, texture characteristics and global structure characteristics; therefore, more comprehensive characteristics can be extracted from the carotid artery ultrasonic image;
specifically, the extracting a preset number of image blocks on the output feature map includes: performing sliding window operation on the output feature map, and extracting an image block based on the pixel position; the extracting the image block based on the pixel position includes: traversing each pixel on the output characteristic diagram to extract an image block or extracting image blocks on the output characteristic diagram at intervals by taking the pixel position as a center; the extraction process of the image blocks can ensure that a section of the blood vessel exists in at least one image block; specifically, a plurality of image blocks with different sizes and different preset length-width ratios can be extracted;
specifically, the obtaining, by the convolutional neural network detection model, a blood vessel angle in the carotid artery ultrasound image based on the preset number of image blocks includes: outputting a first prediction output vector containing a plurality of blood vessel angle prediction probabilities for each image block through the convolutional neural network detection model; determining image blocks with highest blood vessel angle prediction probability in all first prediction output vectors; taking the blood vessel angle corresponding to the category with the highest blood vessel angle prediction probability in the first prediction output vector of the image block with the highest blood vessel angle prediction probability as the blood vessel angle in the carotid artery ultrasonic image;
specifically, the obtaining, by the convolutional neural network detection model, a blood vessel position in the carotid artery ultrasound image based on the preset number of image blocks includes: outputting a second prediction output vector containing a predicted blood vessel position for each image block through the convolutional neural network detection model; restoring the position of the image block with the highest blood vessel angle prediction probability on the output characteristic diagram to the carotid artery ultrasonic image, and obtaining the position of the blood vessel in the carotid artery ultrasonic image by combining the predicted position of the blood vessel in the image block;
the processing process of the convolutional neural network detection model can obtain a more accurate processing result;
specifically, the position of the blood vessel in the obtained carotid artery ultrasound image can be represented by a blood vessel prediction rectangular box;
specifically, the calculating of the width of the blood vessel based on the obtained position of the blood vessel includes: generating a straight line perpendicular to the length direction of the blood vessel by passing through the middle point of the width direction of the blood vessel based on the position of the blood vessel; calculating the gradient value of each pixel point on the straight line from the midpoint of the blood vessel to one direction of the straight line by using a Sobel operator; when the gradient value of the accumulated preset number of pixel points is larger than a preset threshold value, determining a first pixel point in the preset number of pixel points as a side edge point of the blood vessel when the gradient value is met for the first time; acquiring the distance from the center point of the blood vessel to the edge point of one side; calculating the width of the blood vessel according to the distance from the midpoint of the blood vessel to the edge point of one side, wherein the width of the blood vessel is twice of the distance from the midpoint of the blood vessel to the edge point of one side;
wherein, the gradient of the vertical direction of the blood vessel is calculated by the Sobel operator, and the Sobel operator is as follows:
the gradient value at one pixel (x, y) is calculated by the formula:
the gradient is 1 x f (x-1, y-1) +2 x f (x, y-1) +1 x f (x +1, y-1) +0 x f (x-1, y) +0 x f (x, y) +0 f (x +1, y) + (-1) f (x-1, y +1) + (-2) f (x, y +1) + (-1) f (x +1, y +1) f () represents the pixel value of the image-taking pixel;
in another embodiment, the calculating a vessel width based on the obtained vessel position comprises: generating a straight line perpendicular to the length direction of the blood vessel by passing through the middle point of the width direction of the blood vessel based on the position of the blood vessel; traversing and calculating the Euclidean distance of pixel values of two adjacent pixel points on the straight line from the midpoint of the blood vessel to the bottom; when the Euclidean distance between the pixel values of the two adjacent pixel points is larger than a set threshold value, taking the next pixel point of the two adjacent pixel points as a candidate backwall point of the blood vessel; when the pixel value of any preset number of pixel points in the continuously set number of pixel points does not exist between the midpoint of the blood vessel and the candidate back wall point is larger than a fixed value, determining the candidate back wall point as an edge point of the blood vessel; acquiring the distance from the center point of the blood vessel to the edge point; determining the width of the blood vessel according to the distance from the midpoint of the blood vessel to the edge point;
specifically, the automatically generating a sampling gate on the carotid artery ultrasonic image based on the obtained blood vessel angle, blood vessel position and blood vessel width comprises: the center of the sampling gate is arranged at the central point of the position of the blood vessel in the carotid artery ultrasonic image, so that the sampling gate is positioned in the middle area of the position of the blood vessel, and the blood flow sampling is more accurate; the angle of the sampling gate is the obtained angle of the blood vessel; the width of the sampling gate is smaller than or equal to the obtained blood vessel width, for example, the width of the sampling gate is 1/3-1/2 of the obtained blood vessel width, so that blood flow can be sampled in an optimal area;
in one embodiment, a carotid ultrasound image is first acquired, preferably a carotid ultrasound long axis image, as shown in FIG. 1; dark black carotid vessels (approximately in a transverse orientation) were visible in the upper middle region of the image; inputting the carotid artery ultrasonic image into a convolutional neural network detection model, extracting characteristics of the convolutional neural network detection model through a plurality of groups of layer groups comprising a convolutional layer, a pooling layer, a batch normalization layer and an activation function layer, and obtaining an output characteristic diagram at the activation function layer of the last layer group; performing sliding window operation on the output feature map, and extracting an image block based on the pixel position; the extracting the image block based on the pixel position includes: traversing each pixel on the output characteristic diagram to extract an image block or extracting image blocks on the output characteristic diagram at intervals by taking the pixel position as a center; outputting, by the convolutional neural network detection model for each of the image blocks, a first prediction output vector comprising a plurality of vessel angle prediction probabilities, e.g., [0.02,0.8,0.1, ·..,0,0.01], the first prediction output vector including 14 classes, negative sample image blocks as the 0 th class, -30 °, -25 °, -20 °, -15 °, -10 °, -5 °,0 °, 5 °, 10 °, 15 °, 20 °, 25 °, 30 °, 13 vessel angles as the remaining 13 classes; in the first prediction output vector, the prediction probability of a negative sample image block is 0.02, the prediction probability of a-30-degree blood vessel angle is 0.8, the prediction probability of a-25-degree blood vessel angle is 0.1.... 25-degree blood vessel angle is 0, the prediction probability of a 30-degree blood vessel angle is 0.01, and the sum of all prediction probabilities is 1; assuming that the maximum prediction probability in other first prediction output vectors is less than 0.8, the image block of which the first prediction output vector is [0.02,0.8, 0.1.... 0,0.01] can be determined; then, the-30-degree blood vessel angle corresponding to the category with the blood vessel angle prediction probability of 0.8 in the first prediction output vector of the image block is used as the blood vessel angle in the obtained carotid artery ultrasonic image; outputting a second prediction output vector containing a predicted blood vessel position for each image block through the convolutional neural network detection model; restoring the position of the image block with the highest blood vessel angle prediction probability on the output characteristic diagram to the carotid artery ultrasonic image, and obtaining the position of the blood vessel in the carotid artery ultrasonic image by combining the predicted position of the blood vessel in the image block; the vessel position in the obtained carotid artery ultrasound image can be represented by a vessel prediction rectangular box (such as the larger rectangular box in FIG. 2); the larger one of the rectangular boxes in fig. 2 represents a blood vessel prediction rectangular box, and the smaller one of the rectangular boxes represents a sampling gate; the second prediction output vector adopts a 4-dimensional vector to represent the predicted blood vessel position in the image block; the blood vessel prediction rectangular frame is not necessarily required to be displayed, can also be hidden, and only needs four position values to be represented; then, the width of the blood vessel is calculated according to the obtained position of the blood vessel, and the calculation method is as described above; finally, automatically generating a sampling gate on the carotid artery ultrasonic image based on the obtained blood vessel angle, the blood vessel position and the blood vessel width; particularly, the center of a sampling door is arranged at the central point of the position of a blood vessel in the carotid artery ultrasonic image; the angle of the sampling gate is the obtained angle of the blood vessel; 1/2, the width of the sampling gate is the width of the obtained blood vessel;
how to train to obtain the convolutional neural network detection model will be described below; the convolutional neural network detection model is obtained by training in the following way:
firstly, obtaining a sample carotid artery ultrasonic image, and collecting the sample carotid artery ultrasonic images which are as comprehensive as possible, such as sample carotid artery ultrasonic images with different image depths and different collection objects; the sample carotid artery ultrasonic image is marked with blood vessel angle information and a blood vessel position mark; specifically, the collected sample carotid artery ultrasonic image can be marked by an image marking person, and blood vessel angle information is marked on the sample carotid artery ultrasonic image, for example, the sample carotid artery ultrasonic image is totally classified into 13, namely-30 degrees, -25 degrees, -20 degrees, -15 degrees, -10 degrees, -5 degrees, -0 degrees, 5 degrees, 10 degrees, 15 degrees, 20 degrees, 25 degrees and 30 degrees; marking a blood vessel position mark on the sample carotid artery ultrasonic image, namely marking a section of complete carotid artery blood vessel in the sample carotid artery ultrasonic image by using a blood vessel marking rectangular frame;
inputting the sample carotid artery ultrasonic image into a convolutional neural network detection model to extract characteristics to obtain a sample output characteristic diagram; specifically, features of the sample carotid ultrasound image can be extracted through a plurality of groups of layer groups including a convolution layer, a pooling layer, a batch normalization layer and an activation function layer, and an output feature map is obtained on the activation function layer of the last layer group;
then, performing sliding window operation on the sample output characteristic diagram, and extracting a sample image block based on the pixel position; the extracting a sample image block based on pixel location comprises: traversing each pixel on the sample output characteristic diagram to extract a sample image block or extracting sample image blocks on the sample output characteristic diagram at intervals by taking the pixel position as a center; recording the position information of each sample image block on the sample output characteristic diagram;
dividing the sample image blocks into positive sample image blocks and negative sample image blocks according to a preset rule, wherein the method comprises the following steps: calculating the intersection and comparison of each sample image block and the corresponding blood vessel of the blood vessel position mark in the sample carotid artery ultrasonic image, wherein the intersection and comparison is the ratio of the intersection to the union; taking the sample image blocks with the intersection ratio larger than a set threshold value of 0.8 as positive sample image blocks, and taking the sample image blocks as negative sample image blocks if the intersection ratio is not larger than the set threshold value;
training the convolutional neural network detection model according to the positive sample image blocks and the negative sample image blocks, comprising: inputting the positive sample image blocks and the negative sample image blocks into the convolutional neural network detection model; outputting, by the convolutional neural network detection model, a first prediction output vector containing a plurality of vessel angle prediction probabilities for each of the sample image blocks; calculating a first loss function for vessel angle prediction; outputting a second prediction output vector containing a predicted blood vessel position for each image block through the convolutional neural network detection model; calculating a second loss function for vessel location prediction;
the first loss function is shown in equation (1),
Loss(prob1,prob2)=max(0,-β(prob1-prob2)+margin) (1)
wherein, prob1,prob2Predicting probabilities of the two sample image blocks on a blood vessel angle class; when the convolutional neural network detection model is required to output that the prediction probability prob1 in the blood vessel angle class of the first sample image block is greater than the prediction probability prob2 in the blood vessel angle class of the second sample image block, the value of beta is 1, otherwise the value of beta is-1; margin is a hyper-parameter, and the value is 0.5; when two prediction probabilities prob1,prob2When the expected sample difference is met, the first loss function is 0, otherwise, the first loss function is greater than 0;
preferably, each input of the first loss function is a pair of positive sample image blocks and a negative sample image block; to obtain better training effect;
the second loss function is shown in equation (2),
wherein out represents the outputted second prediction output vector, and truth represents the true blood vessel position (i.e. the position information of the marked blood vessel marking rectangular frame in the sample carotid artery ultrasound image);
reversely transmitting the function value of the first loss function and the function value of the second loss function back to the convolutional neural network detection model for updating and iteration to obtain a trained convolutional neural network detection model;
according to the method, two different loss functions are adopted in a convolutional neural network detection model, so that the prediction precision can be improved; wherein the first loss function is an ordered loss function that is not affected by class imbalance;
preferably, the convolutional neural network detection model adopts a pyramid structure and comprises three groups of layer groups including a convolutional layer, a pooling layer, a batch normalization layer and an activation function layer; so as to combine the detail information of the middle and lower layers and the abstract information of the high layer in the convolutional neural network detection model to obtain better detection capability; in the convolutional neural network detection model with the pyramid structure, the low-layer features output by a first activation function layer are up-sampled and then added with the middle-layer features output by a second activation function layer to obtain a feature fusing the low-layer and middle-layer, and the feature fusing the low-layer and middle-layer is up-sampled and then added with the high-layer features output by a third activation function layer to obtain a feature fusing the low-layer, middle-layer and high-layer;
in a second aspect, embodiments of the present invention also provide an ultrasound apparatus, including: a processor and a memory; the processor and the memory are communicated with each other, and the memory is stored with a computer program; the processor is configured to run the computer program, which when run performs the steps of the method as described above; the Processor may be a CPU, or other general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other Programmable logic device; the memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, a hard disk, or a solid state disk; the memory may also comprise a combination of memories of the kind described above.
In a third aspect, embodiments of the present invention also propose a storage medium having a computer program stored therein, the computer program being configured to perform the steps of the method as described hereinbefore when executed. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to examples, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A carotid artery ultrasound automatic Doppler method, characterized in that the method comprises:
acquiring a carotid artery ultrasonic image;
inputting the carotid artery ultrasonic image into a convolutional neural network detection model to extract characteristics to obtain an output characteristic diagram;
extracting a preset number of image blocks from the output characteristic diagram; recording the position information of each image block on the output characteristic diagram;
the convolutional neural network detection model obtains a blood vessel angle in the carotid artery ultrasonic image based on the preset number of image blocks;
the convolutional neural network detection model obtains the position of a blood vessel in the carotid artery ultrasonic image based on the preset number of image blocks;
calculating the width of the blood vessel based on the obtained position of the blood vessel;
and automatically generating a sampling gate on the carotid artery ultrasonic image based on the obtained blood vessel angle, blood vessel position and blood vessel width.
2. The carotid artery ultrasound automatic doppler method according to claim 1, wherein said extracting a predetermined number of image blocks on said output feature map specifically comprises:
performing sliding window operation on the output feature map, and extracting an image block based on the pixel position; the extracting the image block based on the pixel position includes: and traversing each pixel on the output feature map by taking the pixel position as a center to extract an image block or extracting image blocks from every other pixel on the output feature map.
3. The carotid artery ultrasound automatic doppler method according to any of claims 1 to 2, wherein the convolutional neural network detection model obtains a vessel angle in a carotid artery ultrasound image based on the preset number of image blocks, specifically comprising:
outputting a first prediction output vector containing a plurality of blood vessel angle prediction probabilities for each image block through the convolutional neural network detection model;
determining image blocks with highest blood vessel angle prediction probability in all first prediction output vectors;
and taking the blood vessel angle corresponding to the category with the highest blood vessel angle prediction probability in the first prediction output vector of the image block with the highest blood vessel angle prediction probability as the blood vessel angle in the carotid artery ultrasonic image.
4. The carotid artery ultrasound automatic doppler method according to claim 3, wherein the convolutional neural network detection model obtains the position of the blood vessel in the carotid artery ultrasound image based on the preset number of image blocks, specifically comprising:
outputting a second prediction output vector containing a predicted blood vessel position for each image block through the convolutional neural network detection model;
and restoring the position of the image block with the highest blood vessel angle prediction probability on the output characteristic map to the carotid artery ultrasonic image, and obtaining the position of the blood vessel in the carotid artery ultrasonic image by combining the predicted position of the blood vessel in the image block.
5. The carotid artery ultrasound automatic doppler method of claim 1, wherein said automatically generating a sample gate on the carotid artery ultrasound image based on the obtained vessel angle, vessel position and vessel width comprises:
setting the center of the sampling gate at the center point of the position of the blood vessel in the carotid artery ultrasonic image; the angle of the sampling gate is the obtained angle of the blood vessel; the width of the sampling gate is less than or equal to the width of the obtained blood vessel.
6. The carotid artery ultrasound automatic Doppler method according to any of claims 1 to 2, characterized in that the convolutional neural network detection model is trained by:
acquiring a sample carotid artery ultrasonic image, wherein the sample carotid artery ultrasonic image is marked with blood vessel angle information and a blood vessel position mark;
inputting the sample carotid artery ultrasonic image into a convolutional neural network detection model to extract characteristics to obtain a sample output characteristic diagram;
extracting a preset number of sample image blocks on the sample output characteristic diagram; recording the position information of each sample image block on the sample output characteristic diagram;
dividing the sample image blocks into positive sample image blocks and negative sample image blocks according to a preset rule; the blood vessel angle of the positive sample image block is the blood vessel angle marked by the sample carotid artery ultrasound image corresponding to the positive sample image block;
and training the convolutional neural network detection model according to the positive sample image blocks and the negative sample image blocks.
7. The carotid artery ultrasound automatic Doppler method of claim 6,
the extracting a preset number of sample image blocks on the sample output feature map includes:
performing sliding window operation on the sample output characteristic diagram, and extracting a sample image block based on the pixel position; the extracting a sample image block based on pixel location comprises: traversing each pixel on the sample output characteristic diagram to extract a sample image block or extracting sample image blocks on the sample output characteristic diagram at intervals by taking the pixel position as a center;
the dividing the sample image blocks into positive sample image blocks and negative sample image blocks according to a predetermined rule includes:
calculating the intersection and comparison of each sample image block and the corresponding blood vessel of the blood vessel position mark in the sample carotid artery ultrasonic image, wherein the intersection and comparison is the ratio of the intersection to the union;
and taking the sample image blocks with the intersection ratio larger than a set threshold value as positive sample image blocks, and otherwise, taking the sample image blocks as negative sample image blocks.
8. The carotid artery ultrasound automatic doppler method of claim 6, wherein said training of said convolutional neural network detection model from said positive sample patch and said negative sample patch comprises:
inputting the positive sample image blocks and the negative sample image blocks into the convolutional neural network detection model;
outputting, by the convolutional neural network detection model, a first prediction output vector containing a plurality of vessel angle prediction probabilities for each of the sample image blocks; calculating a first loss function for vessel angle prediction;
outputting a second prediction output vector containing a predicted blood vessel position for each image block through the convolutional neural network detection model; calculating a second loss function for vessel location prediction;
and reversely transmitting the function value of the first loss function and the function value of the second loss function back to the convolutional neural network detection model for updating and iteration to obtain the trained convolutional neural network detection model.
9. An ultrasound device, comprising:
a memory storing a computer program;
a processor for running the computer program, the computer program when running performing the steps of the method of any one of claims 1 to 8.
10. A storage medium characterized in that,
the storage medium has stored therein a computer program configured to perform the steps of the method of any one of claims 1 to 8 when executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111119626.0A CN113838028B (en) | 2021-09-24 | 2021-09-24 | Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111119626.0A CN113838028B (en) | 2021-09-24 | 2021-09-24 | Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113838028A true CN113838028A (en) | 2021-12-24 |
CN113838028B CN113838028B (en) | 2024-08-06 |
Family
ID=78969740
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111119626.0A Active CN113838028B (en) | 2021-09-24 | 2021-09-24 | Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113838028B (en) |
Citations (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5237646A (en) * | 1992-10-13 | 1993-08-17 | Hewlett-Packard Company | Pixel image enhancement employing a reduced template memory store |
US6390984B1 (en) * | 2000-09-14 | 2002-05-21 | Ge Medical Systems Global Technology Company, Llc | Method and apparatus for locking sample volume onto moving vessel in pulsed doppler ultrasound imaging |
WO2002097714A1 (en) * | 2001-04-09 | 2002-12-05 | Lifespan Biosciences, Inc. | Computer method for image pattern recognition in organic material |
US20160098589A1 (en) * | 2014-08-29 | 2016-04-07 | Definiens Ag | Applying Pixelwise Descriptors to a Target Image that are Generated by Segmenting Objects in Other Images |
CN106408017A (en) * | 2016-09-13 | 2017-02-15 | 天津大学 | Ultrasonic carotid artery intima media thickness measurement device and method based on deep learning |
CN108280397A (en) * | 2017-12-25 | 2018-07-13 | 西安电子科技大学 | Human body image hair detection method based on depth convolutional neural networks |
CN108764186A (en) * | 2018-06-01 | 2018-11-06 | 合肥工业大学 | Personage based on rotation deep learning blocks profile testing method |
CN108921825A (en) * | 2018-06-12 | 2018-11-30 | 北京羽医甘蓝信息技术有限公司 | The method and device of the facial skin points shape defect of detection based on deep learning |
CN109674493A (en) * | 2018-11-28 | 2019-04-26 | 深圳蓝韵医学影像有限公司 | Method, system and the equipment of medical supersonic automatic tracing carotid artery vascular |
CN110136157A (en) * | 2019-04-09 | 2019-08-16 | 华中科技大学 | A kind of three-dimensional carotid ultrasound image vascular wall dividing method based on deep learning |
CN110136056A (en) * | 2018-02-08 | 2019-08-16 | 华为技术有限公司 | The method and apparatus of image super-resolution rebuilding |
CN110189299A (en) * | 2019-04-22 | 2019-08-30 | 华中科技大学 | A kind of cerebrovascular events automatic identifying method and system based on MoileNet |
CN110766643A (en) * | 2019-10-28 | 2020-02-07 | 电子科技大学 | Microaneurysm detection method facing fundus images |
CN111144163A (en) * | 2018-11-02 | 2020-05-12 | 无锡祥生医疗科技股份有限公司 | Vein and artery identification system based on neural network |
CN111134727A (en) * | 2018-11-02 | 2020-05-12 | 无锡祥生医疗科技股份有限公司 | Puncture guiding system for vein and artery identification based on neural network |
CN111476159A (en) * | 2020-04-07 | 2020-07-31 | 哈尔滨工业大学 | Method and device for training and detecting detection model based on double-angle regression |
US20200258223A1 (en) * | 2018-05-14 | 2020-08-13 | Tempus Labs, Inc. | Determining biomarkers from histopathology slide images |
WO2020215557A1 (en) * | 2019-04-24 | 2020-10-29 | 平安科技(深圳)有限公司 | Medical image interpretation method and apparatus, computer device and storage medium |
CN111954805A (en) * | 2018-02-06 | 2020-11-17 | 密歇根大学董事会 | System and method for analysis and remote interpretation of optical histological images |
CN112017185A (en) * | 2020-10-30 | 2020-12-01 | 平安科技(深圳)有限公司 | Focus segmentation method, device and storage medium |
CN112037163A (en) * | 2019-05-17 | 2020-12-04 | 深圳市理邦精密仪器股份有限公司 | Blood flow automatic measurement method and device based on ultrasonic image |
CN112704515A (en) * | 2019-10-25 | 2021-04-27 | 深圳迈瑞生物医疗电子股份有限公司 | Doppler parameter adjusting method and related equipment |
CN113066061A (en) * | 2021-03-24 | 2021-07-02 | 同心医联科技(北京)有限公司 | Aneurysm detection method, system, terminal and medium based on MRA |
CN113749690A (en) * | 2021-09-24 | 2021-12-07 | 无锡祥生医疗科技股份有限公司 | Blood flow measuring method and device for blood vessel and storage medium |
CN114202504A (en) * | 2021-09-24 | 2022-03-18 | 无锡祥生医疗科技股份有限公司 | Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium |
-
2021
- 2021-09-24 CN CN202111119626.0A patent/CN113838028B/en active Active
Patent Citations (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5237646A (en) * | 1992-10-13 | 1993-08-17 | Hewlett-Packard Company | Pixel image enhancement employing a reduced template memory store |
US6390984B1 (en) * | 2000-09-14 | 2002-05-21 | Ge Medical Systems Global Technology Company, Llc | Method and apparatus for locking sample volume onto moving vessel in pulsed doppler ultrasound imaging |
WO2002097714A1 (en) * | 2001-04-09 | 2002-12-05 | Lifespan Biosciences, Inc. | Computer method for image pattern recognition in organic material |
US20160098589A1 (en) * | 2014-08-29 | 2016-04-07 | Definiens Ag | Applying Pixelwise Descriptors to a Target Image that are Generated by Segmenting Objects in Other Images |
CN106408017A (en) * | 2016-09-13 | 2017-02-15 | 天津大学 | Ultrasonic carotid artery intima media thickness measurement device and method based on deep learning |
CN108280397A (en) * | 2017-12-25 | 2018-07-13 | 西安电子科技大学 | Human body image hair detection method based on depth convolutional neural networks |
CN111954805A (en) * | 2018-02-06 | 2020-11-17 | 密歇根大学董事会 | System and method for analysis and remote interpretation of optical histological images |
CN110136056A (en) * | 2018-02-08 | 2019-08-16 | 华为技术有限公司 | The method and apparatus of image super-resolution rebuilding |
US20200258223A1 (en) * | 2018-05-14 | 2020-08-13 | Tempus Labs, Inc. | Determining biomarkers from histopathology slide images |
CN108764186A (en) * | 2018-06-01 | 2018-11-06 | 合肥工业大学 | Personage based on rotation deep learning blocks profile testing method |
CN108921825A (en) * | 2018-06-12 | 2018-11-30 | 北京羽医甘蓝信息技术有限公司 | The method and device of the facial skin points shape defect of detection based on deep learning |
CN111144163A (en) * | 2018-11-02 | 2020-05-12 | 无锡祥生医疗科技股份有限公司 | Vein and artery identification system based on neural network |
CN111134727A (en) * | 2018-11-02 | 2020-05-12 | 无锡祥生医疗科技股份有限公司 | Puncture guiding system for vein and artery identification based on neural network |
CN109674493A (en) * | 2018-11-28 | 2019-04-26 | 深圳蓝韵医学影像有限公司 | Method, system and the equipment of medical supersonic automatic tracing carotid artery vascular |
CN110136157A (en) * | 2019-04-09 | 2019-08-16 | 华中科技大学 | A kind of three-dimensional carotid ultrasound image vascular wall dividing method based on deep learning |
CN110189299A (en) * | 2019-04-22 | 2019-08-30 | 华中科技大学 | A kind of cerebrovascular events automatic identifying method and system based on MoileNet |
WO2020215557A1 (en) * | 2019-04-24 | 2020-10-29 | 平安科技(深圳)有限公司 | Medical image interpretation method and apparatus, computer device and storage medium |
CN112037163A (en) * | 2019-05-17 | 2020-12-04 | 深圳市理邦精密仪器股份有限公司 | Blood flow automatic measurement method and device based on ultrasonic image |
CN112704515A (en) * | 2019-10-25 | 2021-04-27 | 深圳迈瑞生物医疗电子股份有限公司 | Doppler parameter adjusting method and related equipment |
CN110766643A (en) * | 2019-10-28 | 2020-02-07 | 电子科技大学 | Microaneurysm detection method facing fundus images |
CN111476159A (en) * | 2020-04-07 | 2020-07-31 | 哈尔滨工业大学 | Method and device for training and detecting detection model based on double-angle regression |
CN112017185A (en) * | 2020-10-30 | 2020-12-01 | 平安科技(深圳)有限公司 | Focus segmentation method, device and storage medium |
CN113066061A (en) * | 2021-03-24 | 2021-07-02 | 同心医联科技(北京)有限公司 | Aneurysm detection method, system, terminal and medium based on MRA |
CN113749690A (en) * | 2021-09-24 | 2021-12-07 | 无锡祥生医疗科技股份有限公司 | Blood flow measuring method and device for blood vessel and storage medium |
CN114202504A (en) * | 2021-09-24 | 2022-03-18 | 无锡祥生医疗科技股份有限公司 | Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium |
Non-Patent Citations (3)
Title |
---|
乔文凡;慎利;戴延帅;曹云刚;: "联合膨胀卷积残差网络和金字塔池化表达的高分影像建筑物自动识别", 地理与地理信息科学, no. 05, 27 August 2018 (2018-08-27) * |
刘琼;戴柯;周然;黄文健;丁明跃;: "超声图像中颈动脉血管自动识别算法研究", 生命科学仪器, no. 06, 25 December 2019 (2019-12-25) * |
黄滨阳: ""基于量子优化和深度学习的图像重建算法研究"", 《中国硕士学位论文全文数据库》, 15 February 2021 (2021-02-15) * |
Also Published As
Publication number | Publication date |
---|---|
CN113838028B (en) | 2024-08-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102491988B1 (en) | Methods and systems for using quantitative imaging | |
US10453191B2 (en) | Automated intravascular plaque classification | |
CN108898595B (en) | Construction method and application of positioning model of focus region in chest image | |
CN112529894B (en) | Thyroid nodule diagnosis method based on deep learning network | |
CN110197713B (en) | Medical image processing method, device, equipment and medium | |
JP2021531885A (en) | Ultrasound system with artificial neural network for guided liver imaging | |
CN111476757A (en) | Coronary artery patch data detection method, system, storage medium and terminal | |
CN111539930A (en) | Dynamic ultrasonic breast nodule real-time segmentation and identification method based on deep learning | |
CN112381164B (en) | Ultrasound image classification method and device based on multi-branch attention mechanism | |
WO2014109708A1 (en) | A method and system for assessing fibrosis in a tissue | |
CN111768366A (en) | Ultrasonic imaging system, BI-RADS classification method and model training method | |
CN112508884B (en) | Comprehensive detection device and method for cancerous region | |
CN111340128A (en) | Lung cancer metastatic lymph node pathological image recognition system and method | |
Khan et al. | Benchmark methodological approach for the application of artificial intelligence to lung ultrasound data from covid-19 patients: From frame to prognostic-level | |
CN114202504A (en) | Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium | |
CN113570594A (en) | Method and device for monitoring target tissue in ultrasonic image and storage medium | |
Xing et al. | Automatic detection of A‐line in lung ultrasound images using deep learning and image processing | |
CN113313714B (en) | Coronary OCT (optical coherence tomography) image lesion plaque segmentation method based on improved U-Net network | |
US20220061920A1 (en) | Systems and methods for measuring the apposition and coverage status of coronary stents | |
CN117197594B (en) | Deep neural network-based heart shunt classification system | |
CN113902738A (en) | Heart MRI segmentation method and system | |
CN115760851B (en) | Ultrasonic image data processing equipment, system and computer readable storage medium based on machine learning | |
CN113838028B (en) | Carotid artery ultrasonic automatic Doppler method, ultrasonic equipment and storage medium | |
CN111265234A (en) | Method and system for judging properties of lung mediastinal lymph nodes | |
CN116168029A (en) | Method, device and medium for evaluating rib fracture |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |