CN-122025151-A - Risk assessment method, system, terminal and storage medium based on vascular ultrasound image

CN122025151ACN 122025151 ACN122025151 ACN 122025151ACN-122025151-A

Abstract

The invention relates to the technical field of intelligent ultrasonic inspection and discloses a risk assessment method, a system, a terminal and a storage medium based on a blood vessel ultrasonic image, wherein the method comprises the steps of acquiring ultrasonic echo data of a wearable ultrasonic patch, and reconstructing the ultrasonic echo data to obtain the blood vessel ultrasonic image; the method comprises the steps of obtaining clinical risk factors of a patient, analyzing a blood vessel ultrasonic image according to a vein recognition and compressibility analysis algorithm and a texture and blood flow feature extraction algorithm to obtain vein image features, inputting the vein image features and the clinical risk factors into a trained risk assessment model for assessment to obtain a vein thrombosis risk score, obtaining a time stamp and historical data, determining a risk level according to the time stamp, the historical data and the vein thrombosis risk score, and sending alarm information to medical staff. According to the invention, the risk of venous thrombosis is dynamically evaluated by constructing the risk evaluation model, so that accurate monitoring and grading early warning of the risk of venous thrombosis of a patient are realized.

Inventors

WANG XIUJUAN
YANG MINGMING
ZENG QIQIAO
LIN YINYIN
CAO QIONGYUAN

Assignees

深圳市人民医院

Dates

Publication Date: 20260512
Application Date: 20260414

Claims (10)

1. A risk assessment method based on a blood vessel ultrasound image, characterized in that the risk assessment method based on a blood vessel ultrasound image comprises: Acquiring ultrasonic echo data of a wearable ultrasonic patch, and carrying out reconstruction processing on the ultrasonic echo data according to an image reconstruction algorithm to obtain a blood vessel ultrasonic image; acquiring clinical risk factors of a patient, analyzing the blood vessel ultrasonic image according to a vein recognition and compressibility analysis algorithm and a texture and blood flow feature extraction algorithm to obtain vein image features, and inputting the vein image features and the clinical risk factors into a trained risk assessment model for assessment to obtain a vein thrombosis risk score; And acquiring the current time stamp and historical data, determining a risk level according to the time stamp, the historical data and the venous thrombosis risk score, and sending alarm information to medical staff.
2. The risk assessment method based on blood vessel ultrasonic image according to claim 1, wherein the acquiring the ultrasonic echo data of the wearable ultrasonic patch performs reconstruction processing on the ultrasonic echo data according to an image reconstruction algorithm to obtain a blood vessel ultrasonic image, and specifically comprises: acquiring ultrasonic echo data acquired by a wearable ultrasonic patch; Performing gain compensation on the ultrasonic echo data according to an image reconstruction algorithm to obtain a plurality of echo amplitude distributions; and reconstructing a plurality of echo amplitude distributions according to an interpolation reconstruction algorithm or a beam forming algorithm to obtain a blood vessel ultrasonic image.
3. The risk assessment method based on the blood vessel ultrasonic image according to claim 2, wherein reconstructing a plurality of echo amplitude distributions according to an interpolation reconstruction algorithm or a beam forming algorithm to obtain the blood vessel ultrasonic image specifically comprises: Reconstructing a plurality of echo amplitude distributions according to an interpolation reconstruction algorithm or a beam forming algorithm to obtain a two-dimensional gray-scale image; determining a one-dimensional time depth map according to the echo amplitude distribution based on a time axis; And mapping the two-dimensional gray-scale image and the one-dimensional time depth map to obtain a blood vessel ultrasonic image.
4. The risk assessment method based on a vascular ultrasound image according to claim 1, wherein the acquiring clinical risk factors of the patient analyzes the vascular ultrasound image according to a vein recognition and compressibility analysis algorithm and a texture and blood flow feature extraction algorithm to obtain vein image features, and inputs the vein image features and the clinical risk factors into a trained risk assessment model for assessment to obtain a venous thrombosis risk score, and the method specifically comprises: Acquiring clinical risk factors of a patient; identifying the vascular ultrasonic image according to a vein identification and compressibility analysis algorithm to obtain a lumen geometric parameter; performing feature extraction on the texture features and the blood flow features of the geometric parameters of the lumen according to a texture and blood flow feature extraction algorithm to obtain vein image features; Inputting the vein image characteristics and the clinical risk factors into a trained risk assessment model for assessment to obtain a vein thrombosis risk score; the risk assessment model comprises any one of a logistic regression model, a random forest model, a gradient lifting tree model and a neural network model; wherein the lumen geometry parameters include cross-sectional area, diameter, rate of change of cross-sectional area, and diameter shrinkage ratio.
5. The risk assessment method based on the blood vessel ultrasound image according to claim 4, wherein the inputting the vein image feature and the clinical risk factor into a trained risk assessment model for assessment, and obtaining a venous thrombosis risk score, specifically comprises: acquiring a historical pathological data set, and dividing the historical pathological data set to obtain a training set and a verification set; inputting the training set into an initial risk assessment model for training to obtain a trained risk assessment model; Inputting the vein image characteristics and the clinical risk factors into the trained risk assessment model for assessment to obtain a vein thrombosis risk score; the verification set is used for optimizing the structure and parameters of the risk assessment model after training.
6. The vascular ultrasound image-based risk assessment method of claim 4, wherein the blood flow characteristics include peak blood flow velocity, average blood flow velocity, blood flow direction, spectral envelope morphology, and time scale; The feature extraction is carried out on the texture feature and the blood flow feature of the geometric parameters of the lumen according to the texture and blood flow feature extraction algorithm to obtain vein image features, and the method specifically comprises the following steps: based on the gray level co-occurrence matrix, performing feature calculation on texture features of the geometric parameters of the lumen according to a texture and blood flow feature extraction algorithm to obtain a first target feature; And extracting features of the peak blood flow velocity, the average blood flow velocity, the blood flow direction, the spectrum envelope morphology and the time proportion to obtain a second target feature, and determining vein image features according to the first target feature and the second target feature.
7. The method for risk assessment based on vascular ultrasound images according to claim 1, wherein the acquiring the current time stamp and the historical data, determining a risk level according to the time stamp, the historical data and the venous thrombosis risk score, and sending alarm information to medical staff, specifically comprises: acquiring a current time stamp and historical data; Based on a trend analysis module, comparing the historical data with the time stamp, the venous thrombosis risk score and the clinical risk factor in a trend manner to obtain a time trend; If the venous thrombosis risk score exceeds a preset threshold or the time trend is an ascending trend, mapping a risk grade according to the venous thrombosis risk score, and generating alarm information according to the risk grade to remind medical staff; wherein the risk level includes low risk, medium risk, and high risk.
8. A vascular ultrasound image-based risk assessment system, the vascular ultrasound image-based risk assessment system comprising: the ultrasonic image processing module is used for acquiring ultrasonic echo data of the wearable ultrasonic patch, and carrying out reconstruction processing on the ultrasonic echo data according to an image reconstruction algorithm to obtain a blood vessel ultrasonic image; The thrombus risk assessment module is used for acquiring clinical risk factors of a patient, analyzing the blood vessel ultrasonic image according to a vein recognition and compressibility analysis algorithm and a texture and blood flow feature extraction algorithm to obtain vein image features, inputting the vein image features and the clinical risk factors into a trained risk assessment model for assessment to obtain a vein thrombus risk score; and the risk early warning module is used for acquiring the current time stamp and the historical data, determining the risk level according to the time stamp, the historical data and the venous thrombosis risk score, and sending warning information to medical staff.
9. A terminal comprising a memory, a processor and a vascular ultrasound image-based risk assessment program stored on the memory and executable on the processor, which vascular ultrasound image-based risk assessment program, when executed by the processor, implements the steps of the vascular ultrasound image-based risk assessment method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a vascular ultrasound image-based risk assessment program, which when executed by a processor, implements the steps of the vascular ultrasound image-based risk assessment method according to any one of claims 1-7.

Description

Risk assessment method, system, terminal and storage medium based on vascular ultrasound image Technical Field The invention relates to the technical field of intelligent ultrasonic inspection, in particular to a risk assessment method, a system, a terminal and a computer readable storage medium based on blood vessel ultrasonic images. Background In the current medical system, diagnosis of venous thromboembolism is primarily dependent on imaging examinations, particularly color Doppler ultrasound. In the traditional mode, ultrasonic examination is performed by an ultrasonic doctor or a doctor with corresponding qualification, and the examination result depends on manual observation of venous compressibility, lumen echo and blood flow signals to form a text report and a part of image archive. The traditional mode is suitable for single or low frequency examination, but for high risk groups needing continuous monitoring of thrombosis risk, such as large-scale orthopedic postoperative patients, cardiac surgery postoperative patients, intensive care patients and the like, continuous manual ultrasonic examination is not feasible on manpower and equipment. The existing blood vessel ultrasonic thrombus monitoring method comprises a traditional ultrasonic examination method based on manual interpretation, a remote monitoring method based on physiological signal acquisition and a machine learning auxiliary diagnosis method based on static image analysis. The methods are limited by the inability to process continuous ultrasonic data, lack of automatic risk assessment capability and insufficient centralized management of multiple devices, and are difficult to realize real-time monitoring and early warning of venous thrombosis, so that intermittent manual inspection is still relied on when continuous and multi-part thrombus risk assessment is required for high-risk people, and thrombus risk cannot be accurately early warned, and therefore, the existing vascular ultrasound image risk assessment technology is still to be improved and optimized. Disclosure of Invention The invention mainly aims to provide a risk assessment method, a system, a terminal and a computer readable storage medium based on a blood vessel ultrasonic image, and aims to solve the problems that the existing blood vessel ultrasonic thrombus monitoring method is difficult to realize real-time monitoring and early warning of venous thrombus and can not accurately early warn thrombus risk. In order to achieve the above object, the present invention provides a risk assessment method based on a blood vessel ultrasound image, the risk assessment method based on a blood vessel ultrasound image comprising the steps of: Acquiring ultrasonic echo data of a wearable ultrasonic patch, and carrying out reconstruction processing on the ultrasonic echo data according to an image reconstruction algorithm to obtain a blood vessel ultrasonic image; acquiring clinical risk factors of a patient, analyzing the blood vessel ultrasonic image according to a vein recognition and compressibility analysis algorithm and a texture and blood flow feature extraction algorithm to obtain vein image features, and inputting the vein image features and the clinical risk factors into a trained risk assessment model for assessment to obtain a vein thrombosis risk score; And acquiring the current time stamp and historical data, determining a risk level according to the time stamp, the historical data and the venous thrombosis risk score, and sending alarm information to medical staff. Optionally, in the risk assessment method based on a blood vessel ultrasound image, the acquiring ultrasound echo data of the wearable ultrasound patch performs reconstruction processing on the ultrasound echo data according to an image reconstruction algorithm to obtain the blood vessel ultrasound image, and specifically includes: acquiring ultrasonic echo data acquired by a wearable ultrasonic patch; Performing gain compensation on the ultrasonic echo data according to an image reconstruction algorithm to obtain a plurality of echo amplitude distributions; and reconstructing a plurality of echo amplitude distributions according to an interpolation reconstruction algorithm or a beam forming algorithm to obtain a blood vessel ultrasonic image. Optionally, in the risk assessment method based on a vascular ultrasound image, reconstructing a plurality of echo amplitude distributions according to an interpolation reconstruction algorithm or a beam forming algorithm to obtain a vascular ultrasound image, the method specifically includes: Reconstructing a plurality of echo amplitude distributions according to an interpolation reconstruction algorithm or a beam forming algorithm to obtain a two-dimensional gray-scale image; determining a one-dimensional time depth map according to the echo amplitude distribution based on a time axis; And mapping the two-dimensional gray-scale image and the one-dimensional time depth