A method of ultrasound examination and clinical management of a fetus with a nuchal cord and related apparatus

Abstract

The application discloses an ultrasound examination and clinical management method for a fetus with umbilical cord torsion and related equipment. The application triggers a suspected umbilical cord torsion risk identification process based on the complaint information of a pregnant woman, and determines whether to enter key ultrasound screening through preliminary assessment. Through multi-section analysis of ultrasound image data, the morphological characteristics of the umbilical cord are extracted, and whether the fetus has growth restriction is evaluated in combination with the fetal growth parameters to form an ultrasound key screening result. Based on the preliminary assessment result and the ultrasound screening result, the risk level of the fetus is determined, and a corresponding clinical intervention strategy is formulated according to the risk level. Through stratified screening, information fusion and risk grading, the standardized management of the fetus with suspected umbilical cord torsion is realized, the early identification ability of the umbilical cord torsion is improved, the timeliness of clinical intervention is improved, and effective decision support is provided for the clinic.

Description

Technical Field

[0001] This specification relates to the field of health management, and more specifically, this application relates to an ultrasound examination and clinical management method and related equipment for fetuses with umbilical cord torsion. Background Technology

[0002] Ultrasound examination is a common tool in obstetrics for assessing fetal growth and development and intrauterine status. However, current technology still has significant limitations in treating umbilical cord torsion, a rare and critical pregnancy complication. Umbilical cord torsion can lead to fetal growth restriction, intrauterine distress, and even intrauterine fetal death. However, routine prenatal ultrasound has a low detection rate for this type of lesion, making it difficult to identify related risks in a timely and accurate manner. This results in frequent cases of misdiagnosis, missed diagnosis, and delayed diagnosis in clinical practice.

[0003] In related technologies, research on umbilical cord abnormalities mostly focuses on morphological descriptions or individual imaging indicators, lacking a systematic ultrasound examination method and a unified key observation strategy for suspected umbilical cord torsion. Simultaneously, at the clinical management level, standardized assessment and intervention pathways have not yet been established. When pregnant women exhibit key signals such as decreased fetal movement but the imaging findings are atypical, further examination and intervention are easily delayed. Furthermore, existing protocols struggle to integrate static ultrasound indicators with the dynamic physiological state of the fetus, lacking continuous risk assessment and clear intervention decision-making criteria.

[0004] Therefore, there is an urgent need for a method that can overcome the limitations of routine ultrasound examinations, integrate pregnant women's complaints with multidimensional assessment information, and provide a clear and actionable clinical management pathway to improve the efficiency of identifying suspected umbilical cord torsion and the standardization of clinical management, thereby reducing the risk of adverse pregnancy outcomes. Summary of the Invention

[0005] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0006] Firstly, this application proposes a method for ultrasound examination and clinical management of fetuses with umbilical cord torsion, including: Obtain the pregnant woman's chief complaint information. When the above-mentioned pregnant woman's chief complaint of decreased or absent fetal movement is detected, the suspected umbilical cord torsion risk identification process is triggered. A preliminary assessment is performed on the fetus corresponding to the pregnant woman to form a preliminary assessment result of the fetus's condition. The preliminary assessment includes the acquisition and analysis of fetal heart rate monitoring results and / or biophysical score results. When the above preliminary condition assessment results show abnormalities, or when the above preliminary condition assessment results are insufficient to rule out umbilical cord-related high-risk conditions, ultrasound imaging data of the fetal umbilical cord spiral are obtained. Based on the aforementioned ultrasound imaging data, the presence of signs of umbilical cord torsion is determined, and the presence of fetal growth restriction in the fetus is assessed to obtain the results of the ultrasound screening. Based on the above preliminary status assessment results and the above key ultrasound screening results, the risk level of the above fetuses was determined; Based on the aforementioned risk levels, appropriate clinical intervention strategies are employed to complete the tiered management of the aforementioned fetuses suspected of having umbilical cord torsion.

[0007] In one feasible implementation, the process of obtaining the pregnant woman's chief complaint information, and triggering a suspected umbilical cord torsion risk identification process when the pregnant woman's chief complaint of decreased or absent fetal movement is detected, includes: Collect information on fetal movement complaints from pregnant women within a preset time range; The above-mentioned complaints about fetal movement are identified by complaint type to determine whether the complaints are related to decreased or absent fetal movement. When the above-mentioned complaints about fetal movement are determined to be due to decreased or absent fetal movement, a suspected umbilical cord torsion risk trigger result is generated. The aforementioned suspected umbilical cord torsion risk triggering results will be used as the triggering condition for performing the preliminary assessment operation.

[0008] In one feasible implementation, the aforementioned preliminary assessment of the fetus corresponding to the pregnant woman to form a preliminary fetal condition assessment result includes: Obtain the fetal heart rate monitoring data and / or biophysical score data of the above-mentioned fetuses; The above-mentioned fetal heart rate monitoring data and / or the above-mentioned biophysical score data were standardized and analyzed. The preliminary assessment results of the fetus's condition were generated based on the processed data.

[0009] In one feasible implementation, the above-mentioned preliminary fetal condition assessment result generated based on the processed data includes: Temporal and stability features were extracted from the standardized fetal heart rate monitoring data and / or biophysical score data to obtain temporal and stability features. A multidimensional evaluation feature vector is constructed based on the aforementioned temporal and stability characteristics. The above multidimensional evaluation feature vectors are input into the preset state evaluation model to calculate the comprehensive evaluation parameters; Based on the correspondence between the above comprehensive assessment parameters and the preset state intervals, the preliminary state assessment results of the above fetuses are determined.

[0010] In one feasible implementation, the aforementioned multidimensional evaluation feature vector is input into a preset state evaluation model to calculate comprehensive evaluation parameters, including: The features in the above multidimensional evaluation feature vector are grouped according to their data source and time attribute to form a feature set that includes at least a short-term fluctuation feature group and a continuous trend feature group. Perform intragroup consistency analysis on features within different feature groups to obtain stability description parameters for each feature group. Based on the stability description parameters of each feature group, the multidimensional evaluation feature vectors are restructured to generate a state representation vector that reflects the pattern of fetal state changes. The aforementioned state representation vector is input into the aforementioned state evaluation model to calculate the aforementioned comprehensive evaluation parameters.

[0011] In one feasible implementation, the determination of whether the umbilical cord shows signs of torsion based on the ultrasound imaging data, and the assessment of whether the fetus exhibits fetal growth restriction, are used to obtain key ultrasound screening results, including: If the above preliminary condition assessment results show abnormalities or umbilical cord-related risks cannot be ruled out, obtain ultrasound imaging data of the fetal umbilical cord spiral. Multi-sectional analysis was performed on the above ultrasound image data to extract the morphological features of the umbilical cord; Based on the above morphological characteristics, determine whether the umbilical cord shows signs of torsion; Based on fetal growth parameters, determine whether the above fetuses exhibit fetal growth restriction. The above-mentioned key ultrasound screening results are generated based on the presence of signs of torsion and the presence of fetal growth restriction.

[0012] In one feasible implementation, the above-mentioned multi-sectional analysis of the ultrasound image data to extract the morphological features of the umbilical cord includes: Continuously distributed multi-section ultrasound image data were acquired along different scanning directions in the aforementioned fetal umbilical cord spiral region. Based on the positional relationship of the umbilical cord in the ultrasound images of each of the above sections, the spatial correspondence of the umbilical cord is reconstructed to form a three-dimensional morphological representation of the umbilical cord; In the above three-dimensional morphological representation, the spatial orientation variation characteristics of the umbilical cord axis are extracted, and the axis direction deflection parameters between adjacent cross-sections are calculated; Based on the cumulative spatial variation of the aforementioned axial deflection parameters, it is determined whether the umbilical cord exhibits torsional morphological characteristics.

[0013] Secondly, the present invention also proposes an ultrasound examination and clinical management system for fetuses with umbilical cord torsion, comprising: The triggering unit is used to obtain the pregnant woman's chief complaint information. When the above-mentioned pregnant woman's chief complaint of decreased or absent fetal movement is detected, the suspected umbilical cord torsion risk identification process is triggered. The preliminary assessment unit is used to perform preliminary assessment operations on the fetus corresponding to the pregnant woman in order to form the preliminary status assessment results of the fetus. The preliminary assessment operations include the acquisition and analysis of fetal heart rate monitoring results and / or biophysical score results. The acquisition unit is used to acquire ultrasound image data of the fetal umbilical cord spiral when the above preliminary status assessment results show abnormalities or the above preliminary status assessment results are insufficient to rule out umbilical cord-related high-risk conditions. The in-depth assessment unit is used to determine whether there are signs of torsion in the umbilical cord based on the ultrasound imaging data, and to assess whether the fetus has a state of fetal growth restriction, so as to obtain the results of the ultrasound key screening. The determination unit is used to determine the risk level of the fetus based on the above preliminary status assessment results and the above key ultrasound screening results. The invocation unit is used to invoke the corresponding clinical intervention strategy based on the aforementioned risk level in order to complete the graded management of the aforementioned fetuses suspected of umbilical cord torsion.

[0014] Thirdly, the present invention also proposes an electronic device comprising: a memory and a processor, characterized in that the processor is used to execute a computer program stored in the memory to implement the steps of the ultrasound examination and clinical management method for fetuses with umbilical cord torsion as described in any of the first aspects.

[0015] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the ultrasound examination and clinical management method for fetuses with umbilical cord torsion as described in any of the first aspects.

[0016] In summary, this method breaks through the traditional passive diagnostic model that relies primarily on imaging abnormalities as the trigger, taking the pregnant woman's complaint of decreased or absent fetal movement as the starting point for the risk identification process. When a pregnant woman presents with key subjective symptoms, the suspected umbilical cord torsion risk identification process is initiated, allowing potentially high-risk cases to be included in the key assessment scope at an early stage before atypical imaging manifestations. This effectively compensates for the insufficient sensitivity of conventional ultrasound in diagnosing umbilical cord torsion and significantly reduces the risk of missing the intervention window due to waiting for imaging abnormalities. This method uses a tiered assessment mechanism of preliminary assessment and focused screening to conduct a progressively in-depth objective analysis of the fetal status. After the risk identification process is initiated, the overall physiological status of the fetus is initially assessed through fetal heart rate monitoring and / or biophysical scoring, forming a preliminary status assessment result, which serves as an important criterion for whether to proceed with targeted ultrasound examinations. This tiered design avoids the waste of resources caused by blindly performing high-intensity ultrasound examinations on all pregnant women and ensures that when potential risks exist, more refined imaging assessments can be initiated in a timely manner, improving the efficiency and rationality of the clinical examination pathway. By conducting targeted image acquisition and analysis of the umbilical cord, the determination of umbilical cord torsion signs becomes more targeted and repeatable, improving the effectiveness of ultrasound examination in identifying umbilical cord torsion. This method simultaneously assesses the presence of umbilical cord torsion signs and fetal growth restriction during the key ultrasound screening phase, jointly considering local morphological abnormalities and overall growth performance. By integrating these two types of information into a unified key ultrasound screening result, it can more comprehensively reflect the actual impact of umbilical cord abnormalities on fetal development, avoiding one-sided judgments based solely on a single imaging feature or growth indicator, thereby improving the stability and clinical reliability of risk assessment results. This method integrates multi-source information such as the pregnant woman's chief complaint, preliminary condition assessment results, and key ultrasound screening results, and determines the corresponding risk level of the fetus based on this. Through a structured risk grading approach, previously scattered and isolated clinical information is transformed into risk level outputs that can directly guide decision-making. Risk assessment no longer relies on individual physician experience but is based on a unified assessment logic, significantly improving the consistency and feasibility of risk assessment. This method invokes matching clinical intervention strategies according to different risk levels, achieving graded management of fetuses suspected of umbilical cord torsion. By clarifying the management intensity and intervention methods under different risk levels, clinicians can obtain clear action guidelines when facing suspected cases. This is conducive to taking timely and active intervention measures in high-risk situations, and to avoiding unnecessary over-treatment in low-risk situations, thereby improving the overall efficiency of clinical management while ensuring the safety of the fetus.In summary, the method proposed in this application systematically solves the problems of low diagnostic sensitivity, inconsistent management paths, delayed clinical response, and insufficient basis for intervention decisions in related technologies by moving the risk identification node forward, constructing a hierarchical assessment path, clarifying key ultrasound observation areas, integrating multidimensional assessment information, and providing clear risk classification and intervention guidelines. It plays a significant role in improving the efficiency of suspected umbilical cord torsion identification and standardizing clinical management.

[0017] Other advantages, objectives and features of this application will be apparent in part from the description which follows, and in part from what those skilled in the art will understand through study and practice of this application. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic flowchart of an ultrasound examination and clinical management method for a fetus with umbilical cord torsion, provided as an embodiment of this application; Figure 2 A schematic diagram of the structure of an ultrasound examination and clinical management system for fetuses with umbilical cord torsion, provided in an embodiment of this application; Figure 3 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0019] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The technical solutions of the embodiments of this application will now be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0020] Please see Figure 1This is a flowchart illustrating an ultrasound examination and clinical management method for fetuses with umbilical cord torsion, provided in an embodiment of this application. Specifically, it may include: S110. Obtain the pregnant woman's chief complaint information. When the above-mentioned pregnant woman's chief complaint of decreased or absent fetal movement is detected, the suspected umbilical cord torsion risk identification process is triggered. S120. Perform a preliminary assessment on the fetus corresponding to the pregnant woman to form a preliminary assessment result of the fetus's condition, wherein the preliminary assessment includes the acquisition and analysis of fetal heart rate monitoring results and / or biophysical score results. S130. When the above preliminary status assessment results show abnormalities, or when the above preliminary status assessment results are insufficient to rule out umbilical cord-related high-risk conditions, obtain ultrasound imaging data of the fetal umbilical cord spiral. S140. Based on the above ultrasound imaging data, determine whether there are signs of torsion in the umbilical cord, and assess whether the fetus has a state of fetal growth restriction, so as to obtain the results of ultrasound key screening. S150. Based on the above preliminary status assessment results and the above key ultrasound screening results, determine the risk level of the above fetuses; S160. Based on the above risk level, invoke the corresponding clinical intervention strategy to complete the graded management of the above suspected umbilical cord torsion fetuses.

[0021] For example, the pregnant woman's subjective feelings are used as the starting point for risk identification. When the system obtains the pregnant woman's chief complaint and detects that the pregnant woman has reduced or absent fetal movement, it does not make a diagnosis directly. Instead, it uses the chief complaint as a high-risk trigger signal to initiate the risk identification process for suspected umbilical cord torsion, thereby avoiding delays in intervention due to reliance solely on imaging results.

[0022] After the risk identification process is initiated, a preliminary assessment is performed on the fetus corresponding to the pregnant woman. This preliminary assessment objectively characterizes the fetus's current overall physiological state by acquiring and analyzing fetal heart rate monitoring results and / or biophysical score results, thereby forming a preliminary fetal condition assessment result. This assessment result is used to reflect whether there are any obvious abnormalities in the fetus, or whether there are still potential high-risk conditions that cannot be ruled out by routine assessment.

[0023] When the preliminary assessment results show abnormalities, or when no clear abnormalities are found but the risk of umbilical cord-related high-risk conditions is not ruled out, this embodiment further guides the patient into a targeted imaging examination phase, namely, acquiring ultrasound image data of the fetal umbilical cord spiral. By limiting the focus of ultrasound examination to the umbilical cord spiral region, the specificity of image acquisition is improved, avoiding inefficient and low-specificity generalized observation throughout the process.

[0024] After obtaining the ultrasound image data, the presence of signs of umbilical cord torsion is determined based on this data. Simultaneously, fetal growth parameters are used to assess whether the fetus exhibits signs of growth restriction, thus forming a focused ultrasound screening result. This result comprehensively reflects the correlation between local umbilical cord morphological abnormalities and fetal developmental status.

[0025] Subsequently, this embodiment combines the preliminary condition assessment results with the ultrasound key screening results for joint analysis, and determines the corresponding risk level of the fetus based on this. This multi-source information fusion approach transforms a single complaint, single monitoring result, or single imaging result into a structured risk grading result, improving the stability and reliability of risk assessment.

[0026] Finally, based on the determined risk level, appropriate clinical intervention strategies are implemented to manage fetuses suspected of having umbilical cord torsion in a tiered manner. Different risk levels correspond to different management intensities and intervention methods, thereby ensuring timely intervention while avoiding unnecessary overtreatment and achieving standardized and refined clinical management of fetuses suspected of having umbilical cord torsion.

[0027] In summary, this method breaks through the traditional passive diagnostic model that relies primarily on imaging abnormalities as the trigger, taking the pregnant woman's complaint of decreased or absent fetal movement as the starting point for the risk identification process. When a pregnant woman presents with key subjective symptoms, the suspected umbilical cord torsion risk identification process is initiated, allowing potentially high-risk cases to be included in the key assessment scope at an early stage before atypical imaging manifestations. This effectively compensates for the insufficient sensitivity of conventional ultrasound in diagnosing umbilical cord torsion and significantly reduces the risk of missing the intervention window due to waiting for imaging abnormalities. This method uses a tiered assessment mechanism of preliminary assessment and focused screening to conduct a progressively in-depth objective analysis of the fetal status. After the risk identification process is initiated, the overall physiological status of the fetus is initially assessed through fetal heart rate monitoring and / or biophysical scoring, forming a preliminary status assessment result, which serves as an important criterion for whether to proceed with targeted ultrasound examinations. This tiered design avoids the waste of resources caused by blindly performing high-intensity ultrasound examinations on all pregnant women and ensures that when potential risks exist, more refined imaging assessments can be initiated in a timely manner, improving the efficiency and rationality of the clinical examination pathway. This method clearly defines key observation areas during ultrasound examinations. By selectively acquiring and analyzing images of the umbilical cord, it makes the assessment of umbilical cord torsion signs more targeted and repeatable, improving the effectiveness of ultrasound examinations in identifying umbilical cord torsion. During the key ultrasound screening phase, this method simultaneously assesses the presence of umbilical cord torsion signs and whether the fetus exhibits growth restriction, considering both local morphological abnormalities and overall growth performance. By integrating these two types of information into a unified key ultrasound screening result, it can more comprehensively reflect the actual impact of umbilical cord abnormalities on fetal development, avoiding one-sided judgments based solely on a single imaging feature or growth indicator, thereby improving the stability and clinical reliability of risk assessment results. This method integrates multi-source information from the pregnant woman's complaints, preliminary condition assessment results, and key ultrasound screening results, and determines the corresponding risk level for the fetus based on this information. Through a structured risk grading approach, previously scattered and isolated clinical information is transformed into a risk level output that can directly guide decision-making. This makes risk assessment no longer dependent on individual physician experience, but based on a unified assessment logic, significantly improving the consistency and feasibility of risk assessment. This method employs differentiated clinical intervention strategies based on varying risk levels to achieve tiered management of fetuses suspected of having umbilical cord torsion. By clearly defining the management intensity and intervention methods at different risk levels, clinicians receive clear guidance when facing suspected cases. This facilitates timely and proactive intervention in high-risk situations while avoiding unnecessary overtreatment in low-risk cases, thereby improving overall clinical management efficiency while ensuring fetal safety.In summary, the method proposed in this application systematically solves the problems of low diagnostic sensitivity, inconsistent management paths, delayed clinical response, and insufficient basis for intervention decisions in related technologies by moving the risk identification node forward, constructing a hierarchical assessment path, clarifying key ultrasound observation areas, integrating multidimensional assessment information, and providing clear risk classification and intervention guidelines. It plays a significant role in improving the efficiency of suspected umbilical cord torsion identification and standardizing clinical management.

[0028] In one feasible implementation, the process of obtaining the pregnant woman's chief complaint information, and triggering a suspected umbilical cord torsion risk identification process when the pregnant woman's chief complaint of decreased or absent fetal movement is detected, includes: Collect information on fetal movement complaints from pregnant women within a preset time range; The above-mentioned complaints about fetal movement are identified by complaint type to determine whether the complaints are related to decreased or absent fetal movement. When the above-mentioned complaints about fetal movement are determined to be due to decreased or absent fetal movement, a suspected umbilical cord torsion risk trigger result is generated. The aforementioned suspected umbilical cord torsion risk triggering results will be used as the triggering condition for performing the preliminary assessment operation.

[0029] For example, firstly, pregnant women's subjective complaints about fetal movement are collected within a preset time frame. This subjective complaint information can originate from outpatient consultations, emergency room records, or changes in fetal movement reported proactively by the pregnant woman during follow-up visits. By limiting the time frame, premature or outdated subjective complaint information is avoided from being included in risk assessments, thereby improving the timeliness and reliability of the subjective complaint information.

[0030] After obtaining the aforementioned fetal movement complaints, the complaints are processed for complaint type identification. This identification process does not simply record the pregnant woman's description, but rather performs structured analysis on the complaints, classifying them into different complaint types such as normal fetal movement, decreased fetal movement, or absent fetal movement. This achieves standardized expression of the pregnant woman's complaints and reduces judgment bias caused by different expressions.

[0031] When the identification results indicate that the pregnant woman's complaint is of decreased or absent fetal movement, this embodiment does not directly draw a diagnostic conclusion based on this. Instead, it generates a suspected umbilical cord torsion risk trigger result. This trigger result serves as a risk warning signal, indicating that the fetus may have umbilical cord-related risks that require further evaluation, thereby initiating subsequent evaluation operations at the process level.

[0032] Finally, the suspected umbilical cord torsion risk trigger result is used as the trigger condition for performing the initial assessment operation. That is to say, only after the risk trigger result is generated will the system or clinical process proceed to the subsequent preliminary assessment steps such as fetal heart rate monitoring and biophysical scoring. This realizes a risk assessment process driven by the pregnant woman's complaint and proceeding step by step, avoiding blindly initiating complex examinations without clear risk signals, while ensuring that key risk signals are not ignored.

[0033] In one feasible implementation, the aforementioned preliminary assessment of the fetus corresponding to the pregnant woman to form a preliminary fetal condition assessment result includes: Obtain the fetal heart rate monitoring data and / or biophysical score data of the above-mentioned fetuses; The above-mentioned fetal heart rate monitoring data and / or the above-mentioned biophysical score data were standardized and analyzed. The preliminary assessment results of the fetus's condition were generated based on the processed data.

[0034] For example, fetal heart rate monitoring data and / or biophysical score data are first acquired. The fetal heart rate monitoring data may include a fetal heart rate curve and its recorded changes over time, and the biophysical score data may include score items generated by ultrasound or monitoring. By acquiring at least one data source, the preliminary assessment can cover both acute fetal conditions (e.g., immediate changes reflected by fetal heart rate monitoring) and comprehensive fetal conditions (e.g., the overall condition reflected by biophysical scores), thereby improving the adaptability of the preliminary assessment to different risk manifestations.

[0035] After data acquisition, the fetal heart rate monitoring data and / or the biophysical score data are standardized and analyzed. The standardization process transforms data from different sources and formats into comparable structured data, such as aligning monitoring data by time and standardizing its format, and standardizing score data by removing missing items, ensuring that subsequent analysis is unaffected by differences in acquisition equipment, recording methods, or representation. Based on this, analysis is performed, extracting evaluation parameters that can be used for state characterization from the standardized data, thus transforming the evaluation process from descriptive records into computable input.

[0036] A preliminary fetal status assessment is generated based on the processed data. This preliminary assessment is not simply a list of monitoring data or scores, but rather a summary output of the processed data, forming a structured result that can be directly used for process branch decisions. For example, it may generate status outputs such as "preliminary assessment abnormality" or "preliminary assessment no clear abnormality but risk still needs to be ruled out," triggering subsequent steps. By solidifying the preliminary assessment results in a structured form, different operators can obtain a consistent basis for judgment under the same data input. Furthermore, it allows for joint analysis with subsequent ultrasound screening results, thus supporting a continuous process for determining risk levels and invoking clinical intervention strategies.

[0037] In one feasible implementation, the above-mentioned preliminary fetal condition assessment result generated based on the processed data includes: Temporal and stability features were extracted from the standardized fetal heart rate monitoring data and / or biophysical score data to obtain temporal and stability features. A multidimensional evaluation feature vector is constructed based on the aforementioned temporal and stability characteristics. The above multidimensional evaluation feature vectors are input into the preset state evaluation model to calculate the comprehensive evaluation parameters; Based on the correspondence between the above comprehensive assessment parameters and the preset state intervals, the preliminary state assessment results of the above fetuses are determined.

[0038] For example, firstly, temporal feature extraction and stability feature extraction are performed on the standardized fetal heart rate monitoring data and / or biophysical score data to obtain temporal and stability features. Temporal features are used to characterize the evolution of fetal status over time, such as reflecting fluctuations, trends, or staged abnormalities in fetal heart rate monitoring signals over time. Stability features are used to characterize the persistence and consistency of fetal status within the observation window, such as distinguishing between "short-term occasional fluctuations" and "persistent abnormal states." By extracting temporal and stability features in parallel, this embodiment can simultaneously cover the two key dimensions of "whether abnormal manifestations exist" and "whether the abnormality is persistent," thereby improving the ability of preliminary assessment to identify different risk patterns and reducing the probability of misjudgment caused by transient noise or occasional fluctuations.

[0039] After obtaining the time-series features and the stability features, a multidimensional assessment feature vector is constructed based on both. This multidimensional assessment feature vector is a unified data representation form that combines multiple features according to a preset dimensional order, allowing features from different sources and of different types to be input into subsequent calculations with the same structure. In other words, this embodiment transforms heterogeneous data such as "monitoring curves" and "scoring results" into a vectorized expression that the model can process, thereby providing a consistent data interface for subsequent quantitative assessments and facilitating comparison and reuse across different cases, different devices, or different time points.

[0040] Subsequently, the multidimensional assessment feature vector is input into a preset state assessment model to calculate the comprehensive assessment parameters. The state assessment model is used to achieve joint modeling and fusion calculation of multidimensional features, and its output comprehensive assessment parameters can serve as a quantitative representation of the overall fetal state level. By introducing this state assessment model, this embodiment avoids the limitations of relying on a single indicator or empirical threshold for judgment. Instead, it fuses the contributions of multiple features through a unified computational framework, enabling the comprehensive assessment parameters to reflect the integrity and consistency of the fetal state, thereby improving the stability and interpretability of the preliminary assessment results.

[0041] Finally, based on the correspondence between comprehensive assessment parameters and preset state intervals, the preliminary state assessment result for the fetus is determined. The preset state intervals are used to map continuous comprehensive assessment parameters to discrete state outputs, such as normal, suspicious, or abnormal state types, thereby transforming the model output into a structured judgment result that can be directly used for process control. This embodiment, through a comprehensive assessment parameter and state interval mapping mechanism, transforms continuous calculation results into preliminary state assessment results that can be directly referenced in subsequent processes. This allows the results to serve as input conditions for entering key ultrasound screening, determining risk levels, and invoking clinical intervention strategies, thus achieving the integration and closure of the preliminary assessment results throughout the entire management process.

[0042] In one feasible implementation, the aforementioned multidimensional evaluation feature vector is input into a preset state evaluation model to calculate comprehensive evaluation parameters, including: The features in the above multidimensional evaluation feature vector are grouped according to their data source and time attribute to form a feature set that includes at least a short-term fluctuation feature group and a continuous trend feature group. Perform intragroup consistency analysis on features within different feature groups to obtain stability description parameters for each feature group. Based on the stability description parameters of each feature group, the multidimensional evaluation feature vectors are restructured to generate a state representation vector that reflects the pattern of fetal state changes. The aforementioned state representation vector is input into the aforementioned state evaluation model to calculate the aforementioned comprehensive evaluation parameters.

[0043] For example, this embodiment further refines the implementation process of "inputting multi-dimensional evaluation feature vectors into a preset state evaluation model and calculating comprehensive evaluation parameters". This makes the calculation of comprehensive evaluation parameters no longer a simple fusion of all features, but rather the features are first organized in a structured manner and characterized in a consistent way, and then the representation vectors reflecting the state change pattern are input into the model for calculation. This improves the ability of comprehensive evaluation parameters to distinguish between "continuous anomalies" and "short-term fluctuations", and enhances the stability and repeatability of the evaluation output.

[0044] Specifically, the features in the multidimensional evaluation feature vector are first grouped according to their data source and time attribute, forming a feature set that includes at least a short-term fluctuation feature group and a continuous trend feature group. The data source attribute distinguishes whether the features originate from fetal heart rate monitoring data or biophysical score data, thus avoiding bias caused by direct mixing of differences in statistical scale, sampling frequency, or expression format between different data sources. The time attribute distinguishes whether the features tend to reflect instantaneous changes within a short time window or trend changes over a longer time scale. Through this grouping, this embodiment completes "homogeneous feature classification" before entering model calculation, providing clear calculation objects for subsequent consistency analysis and laying the foundation for extracting state change patterns.

[0045] After feature grouping, intra-group consistency analysis is performed on features within different feature groups to obtain stability description parameters for each feature group. The core of intra-group consistency analysis is to determine whether features within the same group show a consistent direction of change or similar magnitude of change within the same time period, thereby quantifying the stability of the feature group. The resulting stability description parameters are used to characterize whether the fetal state changes reflected by the feature group are persistent and consistent. For example, if a short-term fluctuation feature group shows high volatility and poor consistency, it is more likely to correspond to occasional fluctuations or noise influences. If a persistent trend feature group shows high consistency and persistent changes, it is more likely to correspond to true state trend changes. By introducing stability description parameters, this embodiment expands "feature values ​​themselves" to "stability representation of feature groups," so that subsequent model inputs not only include state performance but also the reliability and persistence of state performance.

[0046] Based on the stability description parameters of each feature group, the multidimensional assessment feature vector is structurally reorganized to generate a state representation vector reflecting the pattern of fetal state changes. This structural reorganization is not a simple splicing of features, but rather, while retaining the original information of each feature group, it integrates the stability description parameters of each feature group into the vector expression. This allows the new state representation vector to simultaneously reflect the combination of "short-term fluctuations" and "persistent trends," as well as their respective stability levels. This step elevates the original multidimensional feature vector to a "pattern-level representation," enabling subsequent models to more directly identify whether the fetal state is biased towards transient perturbations or persistent abnormalities, thereby improving the sensitivity of the comprehensive assessment parameters to state change patterns.

[0047] The state representation vector is input into the state assessment model to calculate the comprehensive assessment parameters. Since the state representation vector encodes the stability and trend information of different feature groups, the state assessment model can perform a more robust fusion assessment of the overall fetal state based on this vector when calculating the comprehensive assessment parameters, thereby outputting comprehensive assessment parameters that reflect the fetal state level and its change patterns. These comprehensive assessment parameters can then be used as input for a preset state interval mapping to further determine the preliminary state assessment results and provide a consistent quantitative basis for subsequent risk stratification and clinical intervention strategy initiation.

[0048] In one feasible implementation, the determination of whether the umbilical cord shows signs of torsion based on the ultrasound imaging data, and the assessment of whether the fetus exhibits fetal growth restriction, are used to obtain key ultrasound screening results, including: If the above preliminary condition assessment results show abnormalities or umbilical cord-related risks cannot be ruled out, obtain ultrasound imaging data of the fetal umbilical cord spiral. Multi-sectional analysis was performed on the above ultrasound image data to extract the morphological features of the umbilical cord; Based on the above morphological characteristics, determine whether the umbilical cord shows signs of torsion; Based on fetal growth parameters, determine whether the above fetuses exhibit fetal growth restriction. The above-mentioned key ultrasound screening results are generated based on the presence of signs of torsion and the presence of fetal growth restriction.

[0049] For example, this embodiment first uses the preliminary condition assessment result as the entry condition for focused ultrasound screening. Only when the preliminary condition assessment result shows abnormalities, or when the preliminary condition assessment result does not show clear abnormalities but still cannot rule out umbilical cord-related risks, is further ultrasound imaging data of the fetal umbilical cord spiral acquired. By establishing image acquisition based on the "preliminary assessment trigger" condition, it is possible to avoid blindly conducting high-intensity screening without risk indications, while ensuring rapid entry into the targeted imaging verification stage when potential risks exist, thereby achieving a tiered advancement at the process level.

[0050] After obtaining the ultrasound image data, this embodiment performs multi-sectional analysis on the image data to extract the morphological features of the umbilical cord. Multi-sectional analysis refers to acquiring continuous or multiple sets of sectional images around the spiral region of the fetal umbilical cord from different scanning directions or different imaging planes, locating the key structural positions of the umbilical cord in each section, and then extracting feature information that can characterize the morphological structure of the region. Multi-sectional analysis can reduce the risk of misjudgment caused by angle, occlusion, or imaging artifacts in a single section, allowing subsequent judgment of torsion signs to be based on more comprehensive and cross-verifiable imaging evidence.

[0051] After extracting the morphological features of the umbilical cord, this embodiment determines whether there are signs of umbilical cord torsion based on these features. This determination process takes the morphological features as input and outputs a result indicating either the presence of torsion signs or the absence of clear torsion signs, transforming the identification of torsion signs from a subjective description into a structured result that can be used for process control. Because this embodiment focuses the observation area on the umbilical cord region at the insertion site on the fetal abdominal wall, the determination logic is more targeted, thereby improving the efficiency of identifying suspected umbilical cord torsion risks.

[0052] Simultaneously, fetal growth parameters are combined in parallel or sequentially to determine whether fetal growth restriction exists. These fetal growth parameters can be derived from growth estimation information obtained through routine ultrasound measurements. They are compared with reference ranges for the corresponding gestational age or evaluated according to preset rules to output a judgment result indicating whether fetal growth restriction exists. The purpose of incorporating fetal growth restriction assessment into the same screening process is that even if no clear signs of torsion are found on umbilical cord imaging, fetal growth restriction can still serve as an important indicator of umbilical cord-related chronic risks, thus providing auxiliary evidence for subsequent risk level determination.

[0053] Finally, this embodiment generates a focused ultrasound screening result based on the determination of whether there are signs of torsion and whether there is fetal growth restriction. This focused ultrasound screening result contains information from both dimensions in a structured manner, enabling subsequent steps to determine the risk level and apply clinical intervention strategies based on the combined information.

[0054] In one feasible implementation, the above-mentioned multi-sectional analysis of the ultrasound image data to extract the morphological features of the umbilical cord includes: Continuously distributed multi-section ultrasound image data were acquired along different scanning directions in the aforementioned fetal umbilical cord spiral region. Based on the positional relationship of the umbilical cord in the ultrasound images of each of the above sections, the spatial correspondence of the umbilical cord is reconstructed to form a three-dimensional morphological representation of the umbilical cord; In the above three-dimensional morphological representation, the spatial orientation variation characteristics of the umbilical cord axis are extracted, and the axis direction deflection parameters between adjacent cross-sections are calculated; Based on the cumulative spatial variation of the aforementioned axial deflection parameters, it is determined whether the umbilical cord exhibits torsional morphological characteristics.

[0055] For example, this embodiment refines the process of performing multi-section analysis on ultrasound image data and extracting umbilical cord morphological features into an executable spatial reconstruction and quantitative characterization process. This makes the determination of whether the umbilical cord has torsion morphological features no longer rely on subjective observation of a single section, but is based on a structured determination based on the spatial correspondence between multi-section images and the changing pattern of the axis direction, thereby improving the stability and repeatability of torsion sign recognition.

[0056] Specifically, firstly, continuous multi-slice ultrasound image data is acquired along different scanning directions in the spiral region of the fetal umbilical cord. Continuous distribution means acquiring adjacent slice images within the same target area according to a preset scanning path or interval, ensuring traceable spatial continuity between adjacent slices. Different scanning directions refer to acquisition on at least two different scanning directions or different imaging planes to reduce problems such as occlusion, artifacts, or unclear display of local structures caused by a single imaging angle. Through the above acquisition method, the multi-slice images obtained in this embodiment possess both local continuity and multi-angle cross-verification capability, thus providing basic data for subsequent spatial reconstruction.

[0057] After acquiring multi-sectional images, the spatial correspondence of the umbilical cord is reconstructed based on the positional relationships of the umbilical cord in each section of ultrasound images to form a three-dimensional morphological representation of the umbilical cord. Positional relationships can be understood as the relative positional trajectory of the umbilical cord in different sections and its relative geometrical relationship with surrounding anatomical reference structures. By matching and associating corresponding points or regions of the same umbilical cord structure in adjacent sections, spatial correspondences between sections are established. Using this spatial correspondence, the umbilical cord structural information originally scattered across multiple two-dimensional sections can be unified into a single spatial framework, thus forming a three-dimensional morphological representation that reflects the spatial morphology of the umbilical cord. Through the establishment of this three-dimensional morphological representation, this embodiment elevates two-dimensional observation to spatial structural expression, laying the foundation for the quantitative extraction of torsional morphological features.

[0058] After obtaining the three-dimensional morphological representation, this embodiment extracts the spatial orientation variation features of the umbilical cord axis from this representation and calculates the axis direction deflection parameters between adjacent cross-sections. The axis can be understood as the main direction centerline of the umbilical cord in the spatial morphological representation, used to characterize the overall orientation of the umbilical cord. The spatial orientation variation features are used to depict the directional change law of the axis at different spatial positions. By calculating the amplitude of directional change or deflection angle between corresponding axis segments of adjacent cross-sections, the axis direction deflection parameters are obtained, transforming the torsion phenomenon, which originally relied on visual judgment, into a calculable and comparable parameterized representation. The introduction of this deflection parameter can effectively distinguish between local slight bending and torsional structures with continuous rotational characteristics, thereby improving the objectivity of subsequent judgments.

[0059] Finally, based on the cumulative spatial changes in the axial deflection parameters, the presence of torsion morphology in the umbilical cord is determined. Cumulative change emphasizes that torsion is a continuous spatial change in direction; a single section or a single deflection is insufficient to determine torsion. Instead, a comprehensive judgment should be made based on the cumulative spatial sequence of deflection parameters across multiple adjacent sections. When the deflection parameters exhibit a continuous unidirectional or cumulative change pattern across multiple adjacent sections, this can be used as a basis for determining the presence of torsion morphology in the umbilical cord. If the deflection parameters exhibit random fluctuations or no continuous cumulative trend, the confidence level of the torsion determination can be reduced. This embodiment achieves structured extraction and determination of umbilical cord torsion morphology features, enabling it to stably support subsequent torsion sign assessment and the generation of ultrasound-focused screening results.

[0060] Secondly, this invention also proposes an ultrasound examination and clinical management system for fetuses with umbilical cord torsion, such as... Figure 2 As shown, it includes: Triggering unit 21 is used to obtain the pregnant woman's chief complaint information. When the above-mentioned pregnant woman's chief complaint of reduced or absent fetal movement is detected, the suspected umbilical cord torsion risk identification process is triggered. The preliminary assessment unit 22 is used to perform a preliminary assessment operation on the fetus corresponding to the pregnant woman to form a preliminary assessment result of the fetus's condition. The preliminary assessment operation includes the acquisition and analysis of fetal heart rate monitoring results and / or biophysical score results. The acquisition unit 23 is used to acquire ultrasound image data of the fetal umbilical cord spiral when the above preliminary status assessment results show abnormalities or the above preliminary status assessment results are insufficient to rule out umbilical cord-related high-risk conditions. The depth assessment unit 24 is used to determine whether there is a torsion sign in the umbilical cord based on the ultrasound imaging data, and at the same time to assess whether the fetus has a fetal growth restriction status, so as to obtain the ultrasound key screening results. The determination unit 25 is used to determine the risk level of the fetus based on the above preliminary status assessment results and the above key ultrasound screening results. Calling unit 26 is used to call the clinical intervention strategy that matches the risk level mentioned above in order to complete the graded management of the above-mentioned suspected umbilical cord torsion fetuses.

[0061] In one feasible implementation, an ultrasound examination and clinical management system for fetuses with umbilical cord torsion can also perform any step of the method proposed in the first aspect.

[0062] Thirdly, the present invention also proposes an electronic device 300, such as... Figure 3 As shown, it includes a memory 310, a processor 320, and a computer program 311 stored on the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements the steps of the ultrasound examination and clinical management method for fetuses with umbilical cord torsion as described in any of the first aspects.

[0063] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the computer program is executed by a processor, it implements the steps of the ultrasound examination and clinical management method for fetuses with umbilical cord torsion as described in any one of the first aspects.

[0064] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0065] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0067] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0068] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0069] This application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device performs the voice-based identity recognition process in the corresponding embodiment. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0070] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0071] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0072] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0073] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0074] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0075] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for ultrasound examination and clinical management of fetuses with umbilical cord torsion, characterized in that, include: Obtain the pregnant woman's chief complaint information. When the pregnant woman's chief complaint of decreased or absent fetal movement is detected, the suspected umbilical cord torsion risk identification process is triggered. A preliminary assessment is performed on the fetus corresponding to the pregnant woman to form a preliminary assessment result of the fetus's condition, wherein the preliminary assessment includes the acquisition and analysis of fetal heart rate monitoring results and / or biophysical score results; When the preliminary condition assessment results show abnormalities, or when the preliminary condition assessment results are insufficient to rule out umbilical cord-related high-risk conditions, ultrasound imaging data of the fetal umbilical cord spiral are obtained. Based on the ultrasound imaging data, the presence of signs of umbilical cord torsion is determined, and the presence of fetal growth restriction is assessed to obtain the results of key ultrasound screening. Based on the preliminary condition assessment results and the ultrasound screening results, the risk level of the fetus is determined; Based on the risk level, a matching clinical intervention strategy is invoked to complete the triage management of the suspected umbilical cord torsion fetus.

2. The method for ultrasound examination and clinical management of fetuses with umbilical cord torsion according to claim 1, characterized in that, The process of obtaining the pregnant woman's chief complaint information, and triggering a suspected umbilical cord torsion risk identification process when the pregnant woman's chief complaint of decreased or absent fetal movement is detected, includes: Collect information on fetal movement complaints from pregnant women within a preset time range; The reported fetal movement information is analyzed to identify the type of complaint in order to determine whether the reported fetal movement is due to decreased or absent fetal movement. When the reported fetal movement complaint is determined to be a decrease or disappearance of fetal movement, a suspected umbilical cord torsion risk trigger result is generated. The suspected umbilical cord torsion risk trigger result will be used as the trigger condition for performing the preliminary assessment operation.

3. The method for ultrasound examination and clinical management of fetuses with umbilical cord torsion according to claim 1, characterized in that, The preliminary assessment of the fetus corresponding to the pregnant woman, to form a preliminary assessment result of the fetus's condition, includes: Obtain fetal heart rate monitoring data and / or biophysical score data of the fetus; The fetal heart rate monitoring data and / or the biophysical score data are standardized and analyzed. A preliminary assessment of the fetus's condition is generated based on the processed data.

4. The method for ultrasound examination and clinical management of fetuses with umbilical cord torsion according to claim 3, characterized in that, The preliminary assessment of the fetus's condition based on the processed data includes: Temporal and stability features were extracted from the standardized fetal heart rate monitoring data and / or biophysical score data to obtain temporal and stability features. A multidimensional evaluation feature vector is constructed based on the temporal features and the stability features; The multidimensional evaluation feature vector is input into a preset state evaluation model to calculate the comprehensive evaluation parameters; Based on the correspondence between the comprehensive evaluation parameters and the preset state intervals, the preliminary state evaluation result of the fetus is determined.

5. The method for ultrasound examination and clinical management of fetuses with umbilical cord torsion according to claim 4, characterized in that, The multidimensional evaluation feature vector is input into a preset state evaluation model to calculate comprehensive evaluation parameters, including: The features in the multidimensional evaluation feature vector are grouped according to their data source and time attribute to form a feature set that includes at least a short-term fluctuation feature group and a continuous trend feature group. Perform intragroup consistency analysis on features within different feature groups to obtain stability description parameters for each feature group. Based on the stability description parameters of each feature group, the multidimensional evaluation feature vector is restructured to generate a state representation vector that reflects the pattern of fetal state changes. The state representation vector is input into the state evaluation model to calculate the comprehensive evaluation parameters.

6. The method for ultrasound examination and clinical management of fetuses with umbilical cord torsion according to claim 1, characterized in that, The process involves determining whether the umbilical cord shows signs of torsion based on the ultrasound imaging data, and simultaneously assessing whether the fetus exhibits signs of fetal growth restriction, to obtain key ultrasound screening results, including: If the preliminary condition assessment results show abnormalities or umbilical cord-related risks cannot be ruled out, ultrasound imaging data of the fetal umbilical cord spiral shall be obtained. Multi-sectional analysis was performed on the ultrasound image data to extract the morphological features of the umbilical cord; Based on the morphological characteristics, determine whether the umbilical cord shows signs of torsion; Determine whether the fetus exhibits fetal growth restriction by combining fetal growth parameters; The ultrasound screening results are generated based on the presence of signs of torsion and the presence of fetal growth restriction.

7. The method for ultrasound examination and clinical management of fetuses with umbilical cord torsion according to claim 6, characterized in that, The step of performing multi-sectional analysis on the ultrasound image data to extract the morphological features of the umbilical cord includes: Continuously distributed multi-section ultrasound image data were acquired along different scanning directions in the spiral region of the fetal umbilical cord. Based on the positional relationship of the umbilical cord in each of the said cross-sectional ultrasound images, the spatial correspondence of the umbilical cord is reconstructed to form a three-dimensional morphological representation of the umbilical cord; In the three-dimensional morphological representation, the spatial orientation variation characteristics of the umbilical cord axis are extracted, and the axis direction deflection parameters between adjacent cross-sections are calculated; Based on the cumulative spatial variation of the axial deflection parameters, it is determined whether the umbilical cord exhibits torsional morphological characteristics.

8. An ultrasound examination and clinical management system for fetuses with umbilical cord torsion, characterized in that, include: The triggering unit is used to obtain the pregnant woman's chief complaint information. When the pregnant woman's chief complaint of decreased or absent fetal movement is detected, the suspected umbilical cord torsion risk identification process is triggered. A preliminary assessment unit is used to perform preliminary assessment operations on the fetus corresponding to the pregnant woman to form a preliminary assessment result of the fetus's condition, wherein the preliminary assessment operation includes the acquisition and analysis of fetal heart rate monitoring results and / or biophysical score results; The acquisition unit is used to acquire ultrasound image data of the umbilical cord spiral when the preliminary status assessment result shows an abnormality or the preliminary status assessment result is insufficient to rule out a high-risk condition related to the umbilical cord. The depth assessment unit is used to determine whether there are signs of torsion in the umbilical cord based on the ultrasound imaging data, and at the same time to assess whether the fetus has a fetal growth restriction, so as to obtain the ultrasound key screening results. The determining unit is used to determine the risk level of the fetus based on the preliminary status assessment results and the ultrasound key screening results; The invocation unit is used to invoke a matching clinical intervention strategy based on the risk level in order to complete the graded management of the suspected umbilical cord torsion fetus.

9. An electronic device, comprising: The memory and processor are characterized in that the processor is used to execute a computer program stored in the memory to implement the steps of the ultrasound examination and clinical management method for fetuses with umbilical cord torsion as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the ultrasound examination and clinical management method for fetuses with umbilical cord torsion as described in any one of claims 1-7.

Images