CN116849702A - Evaluation method and system for kidney health condition based on three-dimensional echocardiography - Google Patents
Evaluation method and system for kidney health condition based on three-dimensional echocardiography Download PDFInfo
- Publication number
- CN116849702A CN116849702A CN202310648775.9A CN202310648775A CN116849702A CN 116849702 A CN116849702 A CN 116849702A CN 202310648775 A CN202310648775 A CN 202310648775A CN 116849702 A CN116849702 A CN 116849702A
- Authority
- CN
- China
- Prior art keywords
- renal
- resistance index
- renal artery
- model
- blood flow
- 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
- 210000003734 kidney Anatomy 0.000 title claims abstract description 50
- 230000036541 health Effects 0.000 title claims abstract description 33
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 238000002592 echocardiography Methods 0.000 title description 13
- 210000002796 renal vein Anatomy 0.000 claims abstract description 69
- 210000002254 renal artery Anatomy 0.000 claims abstract description 67
- 238000000034 method Methods 0.000 claims abstract description 27
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 26
- 238000003062 neural network model Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000003862 health status Effects 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000000747 cardiac effect Effects 0.000 claims abstract description 8
- 230000017531 blood circulation Effects 0.000 claims description 42
- 230000003205 diastolic effect Effects 0.000 claims description 8
- 238000013210 evaluation model Methods 0.000 claims description 4
- 230000000306 recurrent effect Effects 0.000 claims description 4
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 22
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000002068 genetic effect Effects 0.000 description 5
- 230000015654 memory Effects 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000002792 vascular Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 206010020772 Hypertension Diseases 0.000 description 1
- 206010030113 Oedema Diseases 0.000 description 1
- 208000031481 Pathologic Constriction Diseases 0.000 description 1
- 206010067171 Regurgitation Diseases 0.000 description 1
- 208000007536 Thrombosis Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 208000007502 anemia Diseases 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 229940088597 hormone Drugs 0.000 description 1
- 239000005556 hormone Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000036262 stenosis Effects 0.000 description 1
- 208000037804 stenosis Diseases 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013175 transesophageal echocardiography Methods 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- 208000037911 visceral disease Diseases 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/02—Measuring pulse or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/06—Measuring blood flow
-
- 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
- A61B8/483—Diagnostic techniques involving the acquisition of a 3D volume of data
-
- 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
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
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)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- General Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Surgery (AREA)
- Computing Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Hematology (AREA)
- Cardiology (AREA)
- Multimedia (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a system for acquiring a renal artery resistance index and a renal vein resistance index, a using method thereof and an evaluation system for evaluating the health condition of a kidney by using the system, wherein the using method comprises the following steps: acquiring a preprocessed three-dimensional echocardiogram of the kidney region through a preprocessing module; inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model through an input module, wherein the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model; outputting, by a model processing module, a renal artery resistance index and a renal vein resistance index based on the first kidney health status assessment model. The invention utilizes the advantages of the cyclic neural network and the depth residual neural network, so that the judgment result according to the three-dimensional echocardiogram is more accurate, and the recognition speed is faster.
Description
Technical Field
The invention belongs to the technical field of automatic control, and particularly relates to a system for acquiring a renal artery resistance index and a renal vein resistance index and a use method thereof.
Background
Kidneys are one of the vital organs in the body and are responsible for removing waste and excess water from the blood and producing hormones and other vital chemicals. When kidney function is impaired, a range of symptoms may result, including hypertension, anemia, edema, and the like.
Echocardiography is a preferred noninvasive technique for examining anatomical structures and functional states of internal organs and large blood vessels by using the special physical characteristics of ultrasonic shortwaves. Ultrasonic diagnosis of visceral diseases was first applied in 1954. There are three types of clinical applications: m-mode, two-dimensional, and doppler echocardiography. Studies are being undertaken that have been initiated primarily for clinical use with real-time three-dimensional echocardiography, various loading echocardiography (including motion and drug induction), transesophageal echocardiography, acoustic imaging, tissue doppler, and the like.
How to apply the three-dimensional echocardiography to the identification of the health condition of the kidney and how to more accurately identify the health degree by using the existing neural network model are the problems to be studied at present.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the present invention proposes a system for obtaining a renal artery resistance index and a renal vein resistance index, comprising:
a preprocessing module for acquiring a preprocessed three-dimensional echocardiogram of the kidney region;
the input module is used for inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model, and the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model;
a model processing module for outputting a renal artery resistance index and a renal vein resistance index based on the first renal health status assessment model.
The invention also provides a method for using the system for obtaining the renal artery resistance index and the renal vein resistance index, which comprises the following steps:
step S101, acquiring a preprocessed three-dimensional echocardiogram of a kidney region through a preprocessing module;
step S103, inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model through an input module, wherein the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model;
step S105, the model processing module outputs a renal artery resistance index and a renal vein resistance index based on the first kidney health status evaluation model.
Wherein, the step S101 includes:
collecting ultrasonic cardiogram data of a kidney region, and storing the data into a digital image;
generating a three-dimensional echocardiogram based on the echocardiogram data on a time sequence;
respectively denoising, smoothing and enhancing the acquired digital images according to the time sequence;
and obtaining the pretreated three-dimensional echocardiogram.
The first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model, and specifically comprises the following steps:
taking the time sequence of each two-dimensional image of the preprocessed three-dimensional echocardiogram as a time step, taking the two-dimensional image of each time step as the input of a cyclic neural network model, and outputting a first output result, wherein the two-dimensional image is the preprocessed image of each time sequence;
taking the preprocessed two-dimensional image of each time step as the input of a depth residual error network model, and outputting a second output result;
inputting the first processing result and the second processing result into a full connection layer;
outputting, by the fully connected layer, a third output of the first kidney health assessment model, the third output including a renal artery resistance index and a renal vein resistance index.
Wherein, the step S105 includes:
step S1051, identifying a renal artery and a renal vein;
step S1053, obtaining blood flow velocity of the renal artery and the renal vein;
step S1055, calculating resistance indexes R1 and R2 of the renal artery and the renal vein, respectively.
Wherein the renal artery resistance index r1= (maximum systolic blood flow velocity of the renal artery-minimum diastolic blood flow velocity of the renal artery)/maximum systolic blood flow velocity of the renal artery;
r2= (maximum blood flow velocity of renal vein-minimum blood flow velocity of renal vein)/maximum blood flow velocity of renal vein.
Wherein, the step S1051 includes:
based on the preprocessed three-dimensional echocardiogram, renal arteries and renal veins are identified using a multi-planar reconstruction technique.
Wherein, the step S1053 includes:
the maximum systolic blood flow velocity of the renal artery, the minimum diastolic blood flow velocity of the renal artery, the minimum blood flow velocity of the renal vein, and the maximum blood flow velocity of the renal vein are obtained based on the Doppler technique.
The invention also provides an evaluation system for evaluating the kidney health condition by using the system for acquiring the renal artery resistance index and the renal vein resistance index, and the evaluation system further comprises an output module for outputting an evaluation result based on the renal artery resistance index and the renal vein resistance index.
Wherein the output module evaluates the kidney health condition based on the following formula:
v=α×lnr1+β×lnr2, wherein the smaller V is the greater the likelihood that the kidney health is problematic.
The method further comprises the steps of: and if V is larger than a preset threshold value, sending out prompt information.
Compared with the prior art, the invention has the following advantages: the advantages of the cyclic neural network and the depth residual neural network are utilized, so that the judgment result according to the three-dimensional echocardiogram is more accurate, and the recognition speed is faster.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart illustrating a method of use of a system for deriving a renal artery resistance index and a renal vein resistance index in accordance with an embodiment of the present invention;
FIG. 2 is a diagram illustrating a system for obtaining a renal artery resistance index and a renal vein resistance index in accordance with an embodiment of the present invention;
fig. 3 is an evaluation system showing evaluation of renal health status using a system for acquiring a renal artery resistance index and a renal vein resistance index in accordance with an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two.
It should be understood that although the terms first, second, third, etc. may be used to describe … … in embodiments of the present invention, these … … should not be limited to these terms. These terms are only used to distinguish … …. For example, the first … … may also be referred to as the second … …, and similarly the second … … may also be referred to as the first … …, without departing from the scope of embodiments of the present invention.
It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a commodity or device comprising such element.
Alternative embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Embodiment 1,
As shown in fig. 1, the invention discloses a method for using a system for acquiring a renal artery resistance index and a renal vein resistance index, which comprises the following steps:
step S101, acquiring a preprocessed three-dimensional echocardiogram of a kidney region through a preprocessing module;
step S103, inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model through an input module, wherein the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model;
step S105, the model processing module outputs a renal artery resistance index and a renal vein resistance index based on the first kidney health status evaluation model.
Embodiment II,
The invention provides a use method of a system for acquiring a renal artery resistance index and a renal vein resistance index, which comprises the following steps:
step S101, acquiring a preprocessed three-dimensional echocardiogram of a kidney region through a preprocessing module;
step S103, inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model through an input module, wherein the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model;
step S105, the model processing module outputs a renal artery resistance index and a renal vein resistance index based on the first kidney health status evaluation model.
Wherein, the step S101 includes:
collecting ultrasonic cardiogram data of a kidney region, and storing the data into a digital image;
generating a three-dimensional echocardiogram based on the echocardiogram data on a time sequence;
respectively denoising, smoothing and enhancing the acquired digital images according to the time sequence;
and obtaining the pretreated three-dimensional echocardiogram.
The first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model, and specifically comprises the following steps:
taking the time sequence of each two-dimensional image of the preprocessed three-dimensional echocardiogram as a time step, taking the two-dimensional image of each time step as the input of a cyclic neural network model, and outputting a first output result, wherein the two-dimensional image is the preprocessed image of each time sequence;
taking the preprocessed two-dimensional image of each time step as the input of a depth residual error network model, and outputting a second output result;
inputting the first processing result and the second processing result into a full connection layer;
outputting, by the fully connected layer, a third output of the first kidney health assessment model, the third output including a renal artery resistance index and a renal vein resistance index.
The recurrent neural network is suitable for processing the sequence data, and can be used for splitting the image into the sequence data according to a certain mode for processing. For example, an image may be divided into several small regions, and then local features are extracted within each small region using a recurrent neural network, thereby obtaining global features of the entire image.
The deep residual neural network is a model capable of solving the problem of gradient disappearance or explosion in the deep neural network training process. By introducing residual blocks, the network can still learn useful features efficiently when deep.
Therefore, the cyclic neural network and the depth residual neural network can be combined, the cyclic neural network is used for extracting local features, and then the depth residual neural network is used for performing deeper feature learning. Specifically, a cyclic neural network-depth residual neural network model with residual connection can be designed, wherein the cyclic neural network is used for extracting local features, and the depth residual neural network is responsible for further extracting and transmitting the features, so that the feature representation of the whole image is finally obtained.
In one implementation, a recurrent neural network model needs to be built first: each time series of two-dimensional images in the three-dimensional echocardiographic image is regarded as a time step, and the data of each time step is used as the input of the cyclic neural network. Here, a cyclic neural network model with LSTM layer (long and short term memory) can be built, which has excellent historical information memory capability, and can better capture the characteristic of the change of renal vascular parameters with time.
Constructing a depth residual neural network model: to better capture static spatial features, a depth residual neural network may be used. The depth residual neural network consists of multiple convolutional layers, including cross-layer connections to prevent gradient vanishing problems. In this model, the input is a two-dimensional image of each time step and the output is a predicted value of the renal vascular parameter.
Integrating a cyclic neural network and a depth residual neural network model: the outputs of the two models are integrated together and post-processed using the fully connected layers to generate final renal vascular parameter assessment results.
Model training and evaluation: the model is trained using the training data and evaluated using the test data. Various evaluation metrics may be employed, such as Mean Square Error (MSE), mean Absolute Error (MAE), etc.
The following is a complex cyclic neural network-depth residual neural network model formula:
h t =F t (h t-1 ,x t )=H(h t-1 +G(x t ,h t-1 ) Wherein h t Representing the hidden state, x, at time step t t Representing the input at time step t, G represents the depth residual neural network sub-network for learning x t And h t-1 Difference between them, and add it to h t-1 Generating residual blocks, wherein H represents a cyclic neural network sub-network for learning the last time step hidden state H t-1 And the sum of the residual blocks calculated at the current time step. This mouldThe model uses the residual connection of the depth residual neural network and the cyclic structure of the cyclic neural network, and can better process the long-term dependency relationship in the sequence data.
In one embodiment, the preprocessed three-dimensional echocardiography can be optimized to find the optimal two-dimensional image of the three-dimensional echocardiography. The genetic algorithm can be adopted for optimization:
(1) Determining a fitness function: the fitness function is used to evaluate the performance of each individual, and for the echocardiographic data slicing problem, the fitness function may select an index of slice quality, slice number, etc. as an evaluation criterion.
(2) Initializing a population: an initial set of solutions is randomly generated, for example, a number of points are randomly selected on the echocardiographic data as slice locations.
(3) Selection operation: individuals with high fitness are selected from the population to retain excellent genetic information. The operations may be performed using a common selection operator such as roulette selection.
(4) Crossover operation: and (3) carrying out cross operation on the selected individuals to fuse the gene information of the individuals, so as to generate new individuals. For example, single point crossing, multi-point crossing, or the like can be employed.
(5) Mutation operation: to increase the diversity of the population, the genetic information of certain individuals is randomly altered. For example, the coordinates of a certain slice position may be randomly changed.
(6) Calculating a fitness value, and comparing with a termination condition: for the newly generated individual, its fitness value is calculated and compared with the existing optimal solution. If the termination condition is met (e.g., the maximum number of iterations is reached or the fitness reaches a set target value), then the optimal slicing result is output.
(6) Repeating the above steps until the termination condition is reached.
In summary, by genetic algorithm, we can find the best slice position and number of slices in the echocardiographic data, thus obtaining more accurate diagnosis results.
The genetic algorithm can be used as the front end part of the model to screen the input time series image data so as to shorten the processing time and obtain the judging result more quickly.
Wherein, the step S105 includes:
step S1051, identifying a renal artery and a renal vein;
step S1053, obtaining blood flow velocity of the renal artery and the renal vein;
step S1055, calculating resistance indexes R1 and R2 of the renal artery and the renal vein, respectively.
Wherein the renal artery resistance index r1= (maximum systolic blood flow velocity of the renal artery-minimum diastolic blood flow velocity of the renal artery)/maximum systolic blood flow velocity of the renal artery;
r2= (maximum blood flow velocity of renal vein-minimum blood flow velocity of renal vein)/maximum blood flow velocity of renal vein.
Wherein, the step S1051 includes:
based on the preprocessed three-dimensional echocardiogram, renal arteries and renal veins are identified using a multi-planar reconstruction technique.
In one embodiment, for blood flow velocity of the renal veins, the spatial distribution of velocity vectors, including velocity magnitude and direction, at each point in time is provided by the three-dimensional echocardiography. Such information can be obtained by calculating the volume flow from each velocity vector, i.e. the volume of blood passing a certain cross section per unit time, to obtain the blood flow of the renal veins.
In one embodiment, the blood flow velocity in the renal veins should be constant, smooth, and the direction should be centripetal flow under normal conditions. If an occlusion or reversal of blood flow direction occurs in the renal vein, there may be a problem of thrombus or valve regurgitation.
Therefore, parameters such as the diameter, the morphology, the blood flow velocity and the like of the renal artery and vein can be observed through the three-dimensional echocardiography, and the blood flow condition of the renal artery and vein can be estimated according to the data.
When the blood flow condition of the renal artery is evaluated, the change of the blood flow velocity of the renal artery in the systolic period and the diastolic period can be observed through the three-dimensional echocardiogram, so that parameters such as the resistance index of the renal blood vessel and the like are obtained, and whether the renal artery has abnormal conditions such as stenosis or blockage or the like is judged.
In one embodiment, the pressure gradient may also be calculated for evaluation. For pressure gradients, the three-dimensional echocardiography provides a blood velocity profile within the renal veins, which can be calculated according to the Bernoulli principle. The bernoulli principle considers that under steady state conditions, the total energy along a streamline remains unchanged. Thus, inside the renal veins, the total energy of the fluid consists of its static, kinetic and gravitational potential energy, while the static and velocity of points within the renal veins can be measured by three-dimensional echocardiography. By the Bernoulli equation, the pressure gradient within the renal vein can be calculated.
Wherein, the step S1053 includes:
the maximum systolic blood flow velocity of the renal artery, the minimum diastolic blood flow velocity of the renal artery, the minimum blood flow velocity of the renal vein, and the maximum blood flow velocity of the renal vein are obtained based on the Doppler technique.
In one embodiment, by Doppler techniques, sound waves are transmitted to the selected ROI after the scan region is determined and the reflection of the signal is monitored. As blood flows, the reflected signal changes. From these changes, the bleeding flow velocity can be calculated.
In one embodiment, the diameter of the vessel in each time step may be calculated by segmenting and tracking the vessel in the image. Diameter is an important physiological parameter that can reflect the systolic and diastolic states of the cardiovascular system and can also be used to calculate the flow of blood vessels.
In one embodiment, the wall thickness of the vessel in each time step may be calculated by segmenting and measuring the vessel boundaries.
Example III
As shown in fig. 2, the present invention proposes a system for acquiring a renal artery resistance index and a renal vein resistance index, which includes:
a preprocessing module for acquiring a preprocessed three-dimensional echocardiogram of the kidney region;
the input module is used for inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model, and the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model;
a model processing module for outputting a renal artery resistance index and a renal vein resistance index based on the first renal health status assessment model.
Example IV
As shown in fig. 3, the present invention further provides an evaluation system for evaluating the health condition of the kidney by using the system for acquiring the renal artery resistance index and the renal vein resistance index, which further includes an output module for outputting the evaluation result based on the renal artery resistance index and the renal vein resistance index, in addition to the preprocessing module, the input module, and the model processing module described in the third embodiment.
Wherein the output module evaluates the kidney health status based on the following formula:
v=α×lnr1+β×lnr2, wherein the smaller V is the greater the likelihood that the kidney health status is problematic; and if V is larger than a preset threshold value, sending out prompt information.
Example five
The disclosed embodiments provide a non-transitory computer storage medium storing computer executable instructions that perform the method steps described in the embodiments above.
It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local Area Network (AN) or a Wide Area Network (WAN), or can be connected to AN external computer (for example, through the Internet using AN Internet service provider).
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
The foregoing description of the preferred embodiments of the present invention has been presented for purposes of clarity and understanding, and is not intended to limit the invention to the particular embodiments disclosed, but is intended to cover all modifications, alternatives, and improvements within the spirit and scope of the invention as outlined by the appended claims.
Claims (11)
1. A system for obtaining a renal artery resistance index and a renal vein resistance index, comprising:
a preprocessing module for acquiring a preprocessed three-dimensional echocardiogram of the kidney region;
the input module is used for inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model, and the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model;
a model processing module for outputting a renal artery resistance index and a renal vein resistance index based on the first renal health status assessment model.
2. A method of using the system for deriving renal artery resistance index and renal vein resistance index as claimed in claim 1 comprising the steps of:
step S101, acquiring a preprocessed three-dimensional echocardiogram of a kidney region through a preprocessing module;
step S103, inputting the preprocessed three-dimensional ultrasonic cardiac map into a first kidney health condition assessment model through an input module, wherein the first kidney health condition assessment model is formed by combining a cyclic neural network model and a depth residual error network model;
step S105, the model processing module outputs a renal artery resistance index and a renal vein resistance index based on the first kidney health status evaluation model.
3. The method of using the system for obtaining a renal artery resistance index and a renal vein resistance index as defined in claim 2, wherein said step S101 comprises:
collecting ultrasonic cardiogram data of a kidney region, and storing the data into a digital image;
generating a three-dimensional echocardiogram based on the echocardiogram data on a time sequence;
respectively denoising, smoothing and enhancing the acquired digital images according to the time sequence;
and obtaining the pretreated three-dimensional echocardiogram.
4. The method of using the system for obtaining a renal artery resistance index and a renal vein resistance index as defined in claim 2, wherein said first renal health assessment model is composed of a recurrent neural network model and a depth residual network model, and specifically comprises:
taking the time sequence of each two-dimensional image of the preprocessed three-dimensional echocardiogram as a time step, taking the two-dimensional image of each time step as the input of a cyclic neural network model, and outputting a first output result, wherein the two-dimensional image is the preprocessed image of each time sequence;
taking the preprocessed two-dimensional image of each time step as the input of a depth residual error network model, and outputting a second output result;
inputting the first processing result and the second processing result into a full connection layer;
outputting, by the fully connected layer, a third output of the first kidney health assessment model, the third output including a renal artery resistance index and a renal vein resistance index.
5. The method of using the system for obtaining a renal artery resistance index and a renal vein resistance index as defined in claim 2, wherein said step S105 comprises:
step S1051, identifying a renal artery and a renal vein;
step S1053, obtaining blood flow velocity of the renal artery and the renal vein;
step S1055, calculating resistance indexes R1 and R2 of the renal artery and the renal vein, respectively.
6. A method of using the system for obtaining a renal artery resistance index and a renal vein resistance index as defined in claim 3, wherein said renal artery resistance index r1= (maximum systolic blood flow velocity of the renal artery-minimum diastolic blood flow velocity of the renal artery)/maximum systolic blood flow velocity of the renal artery;
r2= (maximum blood flow velocity of renal vein-minimum blood flow velocity of renal vein)/maximum blood flow velocity of renal vein.
7. The method of using the system for obtaining a renal artery resistance index and a renal vein resistance index of claim 5, wherein said step S1051 comprises:
based on the preprocessed three-dimensional echocardiogram, renal arteries and renal veins are identified using a multi-planar reconstruction technique.
8. The method of using the system for obtaining a renal artery resistance index and a renal vein resistance index of claim 5, wherein said step S1053 comprises:
the maximum systolic blood flow velocity of the renal artery, the minimum diastolic blood flow velocity of the renal artery, the minimum blood flow velocity of the renal vein, and the maximum blood flow velocity of the renal vein are obtained based on the Doppler technique.
9. An evaluation system for evaluating renal health condition using the system for acquiring renal artery resistance index and renal vein resistance index of claim 1, wherein: an output module is also included for outputting the evaluation result based on the renal artery resistance index and the renal vein resistance index.
10. The assessment system of claim 9, wherein the output module assesses the kidney health status based on the following formula:
v=α=lnr1+β+lnr2, where the smaller V the greater the likelihood that the kidney health will be problematic.
11. The evaluation system of claim 10, further comprising: and if V is larger than a preset threshold value, sending out prompt information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310648775.9A CN116849702A (en) | 2023-06-01 | 2023-06-01 | Evaluation method and system for kidney health condition based on three-dimensional echocardiography |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310648775.9A CN116849702A (en) | 2023-06-01 | 2023-06-01 | Evaluation method and system for kidney health condition based on three-dimensional echocardiography |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116849702A true CN116849702A (en) | 2023-10-10 |
Family
ID=88225751
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310648775.9A Pending CN116849702A (en) | 2023-06-01 | 2023-06-01 | Evaluation method and system for kidney health condition based on three-dimensional echocardiography |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116849702A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101347343A (en) * | 2007-07-17 | 2009-01-21 | 株式会社东芝 | Apparatus of acquiring ultrasonic images |
CN108542427A (en) * | 2018-04-08 | 2018-09-18 | 深圳市贝斯曼精密仪器有限公司 | A kind of wearable ultrasonic doppler blood flow detector and detection method |
RU2723749C1 (en) * | 2019-11-20 | 2020-06-17 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Амурская государственная медицинская академия" Министерства здравоохранения Российской Федерации | Diagnostic technique for early signs of renal hemodynamics deficiency in patients with chronic obstructive pulmonary disease complicated by chronic pulmonary heart disease |
CN111402207A (en) * | 2020-03-02 | 2020-07-10 | 中山大学附属第一医院 | Ultrasonic angiography video data analysis method based on composite neural network |
US20200320774A1 (en) * | 2019-02-20 | 2020-10-08 | Canon Medical Systems Corporation | Medical image processing apparatus and medical image processing method |
CN113724187A (en) * | 2021-03-16 | 2021-11-30 | 腾讯科技(深圳)有限公司 | Medical image processing method, medical image processing device, electronic equipment and storage medium |
CN116058864A (en) * | 2021-10-29 | 2023-05-05 | 深圳迈瑞生物医疗电子股份有限公司 | Classification display method of ultrasonic data and ultrasonic imaging system |
CN116115208A (en) * | 2022-11-18 | 2023-05-16 | 北京工业大学 | Method for predicting resting coronary microcirculation resistance based on physical driving |
-
2023
- 2023-06-01 CN CN202310648775.9A patent/CN116849702A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101347343A (en) * | 2007-07-17 | 2009-01-21 | 株式会社东芝 | Apparatus of acquiring ultrasonic images |
CN108542427A (en) * | 2018-04-08 | 2018-09-18 | 深圳市贝斯曼精密仪器有限公司 | A kind of wearable ultrasonic doppler blood flow detector and detection method |
US20200320774A1 (en) * | 2019-02-20 | 2020-10-08 | Canon Medical Systems Corporation | Medical image processing apparatus and medical image processing method |
RU2723749C1 (en) * | 2019-11-20 | 2020-06-17 | Федеральное государственное бюджетное образовательное учреждение высшего образования "Амурская государственная медицинская академия" Министерства здравоохранения Российской Федерации | Diagnostic technique for early signs of renal hemodynamics deficiency in patients with chronic obstructive pulmonary disease complicated by chronic pulmonary heart disease |
CN111402207A (en) * | 2020-03-02 | 2020-07-10 | 中山大学附属第一医院 | Ultrasonic angiography video data analysis method based on composite neural network |
CN113724187A (en) * | 2021-03-16 | 2021-11-30 | 腾讯科技(深圳)有限公司 | Medical image processing method, medical image processing device, electronic equipment and storage medium |
CN116058864A (en) * | 2021-10-29 | 2023-05-05 | 深圳迈瑞生物医疗电子股份有限公司 | Classification display method of ultrasonic data and ultrasonic imaging system |
CN116115208A (en) * | 2022-11-18 | 2023-05-16 | 北京工业大学 | Method for predicting resting coronary microcirculation resistance based on physical driving |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11207045B2 (en) | Systems and methods for estimating healthy lumen diameter and stenosis quantification in coronary arteries | |
CN110638438B (en) | Method and system for machine learning based assessment of fractional flow reserve | |
CN111476757B (en) | Coronary plaque data detection method, system, storage medium and terminal | |
CN103747742B (en) | Use the vascular characterization of ultra sonic imaging | |
CN110197713B (en) | Medical image processing method, device, equipment and medium | |
KR20190060606A (en) | Apparatus and method for diagnosis of medical image | |
Benes et al. | Automatically designed machine vision system for the localization of CCA transverse section in ultrasound images | |
KB et al. | Convolutional neural network for segmentation and measurement of intima media thickness | |
JP2016515418A (en) | Method for executing evaluation of vascular network using medical image and its utilization using computer | |
CN112150454B (en) | Aortic dissection assessment method, device, equipment and storage medium | |
KR102304339B1 (en) | Method and computing device for providing analysis information on intravascular ultrasound images of blood vessels using artificial neural networks | |
US20200074625A1 (en) | Functional measurements in echocardiography | |
US20210401407A1 (en) | Identifying an intervntional device in medical images | |
CN106659465A (en) | Ultrasound imaging system and method | |
Ashikuzzaman et al. | Low rank and sparse decomposition of ultrasound color flow images for suppressing clutter in real-time | |
Ansari et al. | Advancements in Deep Learning for B-Mode Ultrasound Segmentation: A Comprehensive Review | |
JP2023521817A (en) | System and method for non-invasive pressure measurement | |
CN116849702A (en) | Evaluation method and system for kidney health condition based on three-dimensional echocardiography | |
Feng et al. | Detecting causality using deep gaussian processes | |
Ayu et al. | U-Net Tuning Hyperparameter for Segmentation in Amniotic Fluid Ultrasonography Image | |
KR20220075126A (en) | Method for medical image segmentation and analysis using artificial intelligence | |
Lee et al. | Joint dermatological lesion classification and confidence modeling with uncertainty estimation | |
Zhang et al. | Efficient Microbubble Trajectory Tracking in Ultrasound Localization Microscopy Using a Gated Recurrent Unit-Based Multitasking Temporal Neural Network | |
CN117594244A (en) | Blood flow parameter evaluation method, device, computer equipment, medium and product | |
Prajapati et al. | Optimal Deep Learning Based Atherosclerotic Plaque Classification on Intravascular Ultrasound Images. |
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 |