Lung segment function evaluation method based on drainage basin characteristics

Abstract

The invention relates to the technical field of medical image processing, in particular to a lung segment function evaluation method based on drainage basin characteristics, which comprises the following steps: acquiring medical image data of a lung; based on the medical image data, constructing a digital model of a lung blood vessel network and an airway network; calculating network features of the pulmonary vessel network and the airway network based on the digital model; generating a blood supply function score and a ventilation function score according to the network features; calculating a comprehensive function score based on the blood supply function score and the ventilation function score; according to the method, the characteristics of the pulmonary vascular network and the airway network are comprehensively analyzed, advanced network analysis and machine learning technologies are combined, multi-dimensional evaluation of the pulmonary segment function is achieved, digital models of the pulmonary vascular network and the airway network are constructed, and the pulmonary segment function evaluation accuracy is improved. And then comprehensively describing the characteristics of the lung structure by calculating a series of network characteristics, such as centrality, efficiency and density.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and more specifically, to a method for evaluating lung segment function based on watershed features. Background Art

[0002] With the continuous development of medical imaging technology, the evaluation methods of lung function are also constantly improving. Traditional lung function evaluation mainly relies on lung function tests, such as vital capacity, forced expiratory volume in one second and other indicators. However, these methods can often only provide information on overall lung function and cannot accurately evaluate the function of specific lung segments.

[0003] In recent years, lung segment function assessment methods based on medical imaging have gradually become a research hotspot. These methods usually use imaging methods such as CT or MRI, combined with image processing technology, to analyze the lung structure. For example, some studies have evaluated pulmonary ventilation function by analyzing the lung parenchyma density in CT images, or evaluated pulmonary blood perfusion by contrast CT. These methods have improved the accuracy of lung segment function assessment to a certain extent, but there are still some limitations.

[0004] First, existing methods often only focus on one aspect of the lungs, such as only considering lung parenchymal density or only analyzing vascular structure, which makes it difficult to fully reflect the functional status of the lung segments. Second, these methods usually use simple threshold segmentation or morphological analysis, which fails to fully utilize the rich information contained in medical images. Furthermore, most existing methods only perform static analysis, which makes it difficult to reflect the dynamic changes in lung function.

[0005] In addition, existing lung segment function assessment methods are also insufficient in predicting prognosis. Most methods only provide current functional status assessment and cannot effectively predict the patient's future prognosis. This limitation makes clinicians lack reliable reference when formulating long-term treatment plans.

[0006] In the face of these problems, new methods that can comprehensively and accurately evaluate lung segment function and predict prognosis are urgently needed. The ideal method should be able to comprehensively consider multiple characteristics of the lungs, make full use of medical image information, and combine advanced data analysis technology to achieve dynamic evaluation and prediction of lung segment function. Summary of the invention

[0007] The present invention is proposed to solve the above technical problems. The present invention provides a lung segment function evaluation method based on watershed characteristics, aiming to achieve a comprehensive and accurate evaluation of lung segment function and provide a reliable prognosis prediction.

[0008] In order to solve the above technical problems, the present invention adopts the following technical solutions: The lung segment function assessment method based on watershed characteristics includes: The acquisition steps include: Acquire medical imaging data of the lungs; Processing steps include: constructing a digital model of the pulmonary vascular network and the airway network based on the medical imaging data; Based on the digital model, calculating network characteristics of the pulmonary vascular network and airway network; generating a blood supply function score and a ventilation function score according to the network characteristics; Calculating a comprehensive function score based on the blood supply function score and the ventilation function score; Output steps include: The comprehensive functional score is output as a lung segment function assessment result.

[0009] Preferably, the digital model of the pulmonary vascular network and the airway network is constructed including: Segmenting the medical image data to extract pulmonary blood vessels and airway structures; Based on the extracted pulmonary vascular and airway structures, a three-dimensional network model is constructed; A topological analysis is performed on the three-dimensional network model to determine network nodes and connection relationships.

[0010] Preferably, the calculating of the network features of the pulmonary vascular network and the airway network comprises calculating one or more of the following features: Network centrality; Network efficiency; Network density; Network connectivity; Network robustness.

[0011] Preferably, the computing network centrality specifically includes: Counting the number of nodes and edges of the pulmonary vascular network and the airway network; Calculate the degree of each node and perform normalization; Based on the normalized node degree, the PageRank algorithm is used to calculate the weight of the network node.

[0012] Preferably, the generation of the blood supply function score specifically includes: Calculating the blood supply weight of each lung segment based on the network characteristics of the pulmonary vascular network; normalizing the blood supply weight; The blood supply function score of each lung segment was calculated based on the normalized blood supply weight.

[0013] Preferably, generating a ventilation function score specifically includes: Calculating the ventilation weight of each lung segment based on the network characteristics of the airway network and lung parenchyma density information; normalizing the ventilation weight; The ventilation function score of each lung segment was calculated based on the normalized ventilation weight.

[0014] Preferably, the method further comprises a prognosis prediction step: Establishing a machine learning model based on the comprehensive functional score; The machine learning model is used to generate a patient prognosis probability assessment result.

[0015] Preferably, the establishing of the machine learning model specifically includes: Collect historical patient data, including comprehensive functional scores and actual prognosis; training a machine learning model using the patient history data; The machine learning model is validated and optimized.

[0016] Preferably, the data preprocessing step is also included: Performing denoising processing on the medical image data; Performing standardization processing on the medical imaging data; The principal component analysis method is used to reduce the dimension of the processed medical image data.

[0017] Preferably, the output step further comprises: Generate a visual lung segment function assessment report, including the blood supply function score, ventilation function score and comprehensive function score of each lung segment; The lung segment function assessment report is sent to a medical terminal device for doctors to make clinical decision references.

[0018] The method of the present invention has the following significant technical effects: The method of the present invention achieves a multi-dimensional assessment of lung segment function by comprehensively analyzing the characteristics of the pulmonary vascular network and airway network, combined with advanced network analysis and machine learning techniques. This method not only overcomes the limitation of the existing technology that only focuses on a single feature, but also makes full use of the rich information in medical images to improve the accuracy and comprehensiveness of the assessment.

[0019] Specifically, the method of the present invention first constructs a digital model of the pulmonary blood vessels and airways, and then comprehensively characterizes the characteristics of the pulmonary structure by calculating a series of network features, such as centrality, efficiency, density, etc. This network analysis-based method can reveal complex structural information that is difficult to capture with traditional methods, providing a new perspective for functional evaluation.

[0020] More importantly, the method of the present invention integrates the blood supply function score and the ventilation function score to generate a comprehensive function score, thereby achieving a comprehensive assessment of the lung segment function. This comprehensive score not only reflects the blood supply and ventilation status of the lung segment, but also takes into account the mutual influence of these two aspects, thereby providing a more accurate and reliable function assessment result.

[0021] In addition, the method of the present invention also introduces machine learning technology to establish a prognosis prediction model based on the comprehensive functional score. This innovation enables the method to not only evaluate the current functional status of the lung segment, but also predict the future prognosis, providing more comprehensive support for clinical decision-making.

[0022] In general, the method of the present invention achieves a comprehensive and accurate assessment of lung segment function and prognosis prediction through innovative technologies such as multidimensional analysis, network feature extraction, comprehensive scoring and machine learning prediction. This method not only overcomes the limitations of existing technologies, but also provides a new tool for the diagnosis, treatment and prognosis assessment of respiratory diseases. It can help doctors better understand the patient's lung function status and develop more personalized and accurate treatment plans, thereby improving treatment effects and patient prognosis.

[0023] The method of the present invention also has good scalability and adaptability. By adjusting the selection and weight of network features and optimizing the machine learning model, the method can adapt to different types of lung diseases and different clinical needs. This flexibility makes the method likely to play an important role in the diagnosis and treatment of various respiratory diseases and contribute to the development of precision medicine. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 The figure is an overall flow chart of the method of the present invention.

[0025] Figure 2 A flow chart for constructing a digital model of the present invention.

[0026] Figure 3 The flowchart of the network characteristic calculation of the present invention.

[0027] Figure 4 A flow chart for scoring blood supply function of the present invention.

[0028] Figure 5 Flow chart for scoring ventilatory function of the present invention.

[0029] Figure 6 Flow chart for scoring the comprehensive functionality of the present invention. DETAILED DESCRIPTION

[0030] like Figure 1-6As shown, the present invention provides a method for evaluating lung segment function based on watershed features. The method makes full use of medical imaging technology and network analysis theory to achieve a comprehensive evaluation of lung segment function. The present invention will be described in detail below in conjunction with specific implementation methods.

[0031] First, the method of the present invention includes an acquisition step, a processing step and an output step. In the acquisition step, the method acquires medical image data of the lungs. Preferably, these medical image data can be CT (Computed Tomography) scan images or MRI (Magnetic Resonance Imaging) images. These high-resolution medical images provide a basis for subsequent analysis.

[0032] In the processing step, the method of the present invention first constructs a digital model of the pulmonary vascular network and airway network based on the acquired medical image data. Specifically, this step can be achieved by image segmentation technology. For example, a threshold segmentation method or a region growing method can be used to extract the vascular and airway structures. Then, these structures are converted into a three-dimensional network model through a three-dimensional reconstruction technology.

[0033] Next, the method calculates the network characteristics of the pulmonary vascular network and airway network based on the constructed digital model. These network characteristics include but are not limited to network centrality, network efficiency, network density, network connectivity and network robustness. For example, network centrality can be calculated by the PageRank algorithm, network efficiency can be measured by the average shortest path length, and network density can be evaluated by the tightness of the connection between nodes.

[0034] After obtaining these network features, the method generates a blood supply function score and a ventilation function score based on these features. The blood supply function score mainly reflects the performance of the pulmonary vascular network, while the ventilation function score reflects the performance of the airway network. Preferably, the calculation of these two scores can be weighted summation, where the weights can be optimized by a machine learning algorithm.

[0035] Finally, the method calculates a comprehensive functional score based on the blood supply function score and the ventilation function score. This comprehensive score comprehensively reflects the overall functional status of the lung segment. For example, the following formula can be used to calculate the comprehensive score: , in, For comprehensive function rating, Score blood supply function. Score the ventilation function. and is the weight coefficient, and + = 1.

[0036] In the output step, the method outputs the calculated comprehensive function score as the lung segment function assessment result. This result can provide an important diagnostic reference for doctors.

[0037] Furthermore, when constructing the digital model of the pulmonary vascular network and the airway network, the method of the present invention also includes segmenting the medical image data to extract the pulmonary vascular and airway structures. This step can use a variety of image segmentation algorithms, such as a segmentation method based on region growing method, level set method or deep learning. For example, the accuracy of using the U-Net network to segment the blood vessels and airways can reach more than 95%.

[0038] After extracting the pulmonary blood vessels and airway structures, the method constructs a three-dimensional network model based on these structures. This step can use a skeletonization algorithm, such as a distance transform method or a thinning algorithm. Preferably, the Lee algorithm can be used for skeletonization, which can well preserve the topological structure of the network.

[0039] Finally, this method performs topological analysis on the constructed three-dimensional network model to determine the network nodes and connection relationships. This step can use algorithms in graph theory, such as depth-first search (DFS) or breadth-first search (BFS). In this way, a complete network topology structure can be obtained, laying the foundation for subsequent network feature calculations.

[0040] When calculating the network characteristics of the pulmonary vascular network and the airway network, the method of the present invention includes calculating one or more of network centrality, network efficiency, network density, network connectivity and network robustness. These characteristics reflect the performance of the network from different perspectives.

[0041] For example, network centrality reflects the importance of a node in the network. It can be measured using indicators such as degree centrality, betweenness centrality, or eigenvector centrality. The degree centrality calculation formula is: , in, For Node The degree centrality of For Node The degree, is the total number of nodes in the network.

[0042] Network efficiency reflects the ability of a network to transmit information. It can be measured by the average shortest path length, calculated as: , Where E is the network efficiency, n is the number of nodes, is the shortest path length between nodes i and j.

[0043] Network density reflects the tightness of network connections and can be calculated by the ratio of the actual number of edges to the maximum possible number of edges: , Among them, D is the network density, m is the actual number of edges, and n is the number of nodes.

[0044] The calculation of these network features provides an important basis for subsequent functional scoring. By comprehensively considering these features, the functional status of the lung segments can be comprehensively evaluated, providing strong support for clinical diagnosis and treatment decisions. In a preferred embodiment of the present invention, the step of calculating the centrality of the network is further refined. First, the method counts the number of nodes and edges of the pulmonary vascular network and airway network. This step lays the foundation for subsequent analysis and can intuitively reflect the scale and complexity of the network.

[0045] Next, this method calculates the degree of each node and performs normalization. The degree of a node reflects the number of direct connections between the node and other nodes and is a basic indicator for measuring the importance of a node. Normalization can eliminate the impact of network size on the degree value, allowing networks of different sizes to be compared. The normalization formula is as follows: , in, is the normalized degree value of node v, is the original degree value of node v, and are the minimum and maximum degree values ​​in the network respectively.

[0046] Finally, this method uses the PageRank algorithm to calculate the weights of network nodes based on the normalized node degrees. The PageRank algorithm was originally used for web page ranking, but it can also be effectively applied to other types of network analysis. In the present invention, the use of the PageRank algorithm can more comprehensively consider the importance of nodes, not only considering the direct connection of the node, but also considering the influence of indirect connection. The calculation formula of PageRank is as follows: , Among them, PR(v) is the PageRank value of node v, d is the damping factor (usually 0.85), N(v) is the set of nodes pointing to node v, and L(u) is the out-degree of node u.

[0047] The method of the present invention calculates network centrality in this way, which can more accurately reflect the importance of each node in the pulmonary vascular and airway network, and provide an important basis for subsequent functional evaluation.

[0048] In the process of generating the blood supply function score, the method of the present invention first calculates the blood supply weight of each lung segment based on the network characteristics of the pulmonary vascular network. The network characteristics here may include the centrality, efficiency, density and other indicators mentioned above. The calculation of the blood supply weight can be done by weighted summation, for example: , in, is the blood supply weight of the ith lung segment, , and are the centrality, efficiency and density indexes of the lung segment, , and is the corresponding weight coefficient.

[0049] Next, the method normalizes the calculated blood supply weights. The purpose of normalization is to unify the blood supply weights of different lung segments to the same scale for easy comparison and subsequent processing. The normalization formula can use the minimum-maximum normalization method mentioned above.

[0050] Finally, this method calculates the blood supply function score of each lung segment based on the normalized blood supply weight. The score can be calculated directly using the normalized weights, or some nonlinear transformations can be performed to better reflect the characteristics of the blood supply function. For example, the sigmoid function can be used for transformation: , in, is the blood supply function score of the ith lung segment, is the normalized blood supply weight, It is an adjustment parameter used to control the steepness of the function.

[0051] In the process of generating ventilation function score, the method of the present invention adopts similar steps, but adds consideration of lung parenchymal density information. First, the method calculates the ventilation weight of each lung segment based on the network characteristics of the airway network and lung parenchymal density information. The introduction of lung parenchymal density information can better reflect the ventilation status of the alveoli and improve the accuracy of the score.

[0052] The ventilation weight can be calculated using the following formula: , in, is the ventilation weight of the ith lung segment, is the airway network feature of the lung segment (which may be the weighted sum of multiple features), is the lung parenchymal density of the lung segment, and is the weight coefficient. Note that , because the lower the lung parenchyma density, the better the ventilation function is usually.

[0053] Next, the method also normalizes the ventilation weights and then calculates the ventilation function score of each lung segment. The calculation method can be similar to the blood supply function score, and can also be appropriately adjusted according to the characteristics of the ventilation function.

[0054] In this way, the method of the present invention can comprehensively consider the factors of blood supply and ventilation, and provide a reliable basis for the comprehensive evaluation of lung segment function. This evaluation method not only takes into account the characteristics of the anatomical structure, but also combines the performance of physiological functions, and can provide more comprehensive and accurate reference information for clinical diagnosis and treatment decisions. In another embodiment of the present invention, a prognosis prediction step is also included. The introduction of this step enables the method to not only evaluate the current lung segment function status, but also predict the patient's future prognosis, providing more comprehensive support for clinical decision-making.

[0055] Specifically, the method first establishes a machine learning model based on the comprehensive functional score calculated previously. The purpose of this model is to establish a correlation between the comprehensive functional score and the patient's prognosis. Preferably, a variety of machine learning algorithms can be used, such as support vector machine (SVM), random forest (Random Forest) or deep neural network (DNN). When selecting a specific algorithm, it is necessary to consider the characteristics of the data and the requirements of the prediction task.

[0056] For example, if a support vector machine is used, the following decision function can be used: , Where x is the input feature vector (mainly the comprehensive function score in this case), is the label of the training sample, is the Lagrange multiplier, is the kernel function, and b is the bias term. The kernel function can choose the Gaussian kernel: , in, is the parameter of the Gaussian kernel and needs to be tuned by methods such as cross-validation.

[0057] After building a machine learning model, this method uses the model to generate a patient prognosis probability assessment result. This result can be a binary classification (such as the probability of a good prognosis and a poor prognosis) or a multi-classification (such as the probability distribution of short-term, medium-term, and long-term prognosis). For example, using the Softmax function can get a multi-classification probability output: , in, is the original output of the model for the jth class, and K is the total number of classes.

[0058] In order to improve the accuracy of prognosis prediction, the method of the present invention takes a series of measures when establishing a machine learning model. First, the method collects patient historical data, including comprehensive functional scores and actual prognosis. These historical data provide a basis for model training. During the data collection process, attention should be paid to the quality and representativeness of the data, and different types and degrees of lung diseases should be covered as much as possible.

[0059] Next, the method uses the collected patient history data to train the machine learning model. During the training process, techniques such as cross-validation can be used to evaluate the performance of the model and adjust the model parameters. For example, k-fold cross-validation can be used to divide the data set into k parts, and k-1 parts are used as training sets each time, and the remaining 1 part is used as a validation set, and the cycle is repeated k times. This method can effectively avoid overfitting and improve the generalization ability of the model.

[0060] Finally, this method verifies and optimizes the trained machine learning model. Verification can use an independent test set to evaluate the performance of the model on new data. If the model performs poorly, you can consider adjusting the model structure, adding features, or using ensemble learning to optimize it. For example, you can use the Adaboost algorithm to build multiple weak classifiers and then combine them into a strong classifier: , in, is the tth weak classifier, is the weight of the classifier.

[0061] In another embodiment of the present invention, a data preprocessing step is also included. The purpose of this step is to improve the accuracy and efficiency of subsequent analysis. First, the method performs denoising on medical image data. Medical images, especially CT and MRI images, often contain a certain degree of noise, which may affect subsequent analysis. De-noising can be performed using a variety of methods, such as Gaussian filtering, median filtering or wavelet transform. For example, the formula using Gaussian filtering is as follows: , Where (x, y) is the pixel coordinate, is the standard deviation of the Gaussian function.

[0062] Next, this method performs standardization on the denoised medical image data. The purpose of standardization is to unify image data obtained from different sources and different devices to the same scale for subsequent processing. Commonly used standardization methods include Z-score standardization and Min-Max standardization. For example, the formula for Z-score standardization is as follows: , Among them, x is the original data, is the mean, is the standard deviation.

[0063] Finally, this method uses the principal component analysis (PCA) method to reduce the dimension of the processed medical image data. PCA can effectively reduce the dimension of the data while retaining most of the information, thereby improving the efficiency of subsequent processing. The core of PCA is to solve the eigenvalues ​​and eigenvectors of the covariance matrix: , Where C is the covariance matrix, is the eigenvector, is the corresponding eigenvalue.

[0064] In the output step of the present invention, in addition to outputting the comprehensive function score as the lung segment function assessment result, it also includes generating a visualized lung segment function assessment report. This report includes the blood supply function score, ventilation function score and comprehensive function score of each lung segment. The visualization method can be a color-coded 3D lung model, in which different colors represent different function scores. For example, red, yellow and green can be used to represent lung segments with poor, medium and good functions, respectively.

[0065] In addition, this method also sends the generated lung segment function assessment report to the medical terminal device for doctors to make clinical decision reference. This step can be achieved through the hospital's internal network or a secure cloud service. In this way, doctors can view the patient's lung segment function assessment results anytime and anywhere, which facilitates diagnosis and treatment decisions.

[0066] In general, the lung segment function assessment method based on watershed characteristics provided by the present invention achieves a comprehensive assessment of lung segment function and prognosis prediction by comprehensively considering the characteristics of the pulmonary vascular network and airway network and combining advanced data processing and machine learning technologies. This method not only improves the accuracy of lung segment function assessment, but also provides more comprehensive and reliable reference information for clinical decision-making, and is expected to play an important role in the diagnosis and treatment of respiratory diseases.

[0067] The above description is only a preferred specific implementation manner of the present invention; however, the protection scope of the present invention is not limited thereto; any person familiar with the art who, within the scope disclosed by the present invention, makes equivalent replacements or changes based on the scheme and improved concepts of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A lung segment function assessment method based on watershed characteristics, characterized in that: include: The acquisition steps include: Acquire medical imaging data of the lungs; Processing steps include: constructing a digital model of the pulmonary vascular network and the airway network based on the medical imaging data; Based on the digital model, calculating network characteristics of the pulmonary vascular network and airway network; generating a blood supply function score and a ventilation function score according to the network characteristics; Calculating a comprehensive function score based on the blood supply function score and the ventilation function score; Output steps include: The comprehensive functional score is output as a lung segment function assessment result.

2. The method according to claim 1, characterized in that The digital model of the pulmonary vascular network and the airway network is constructed as follows: Segmenting the medical image data to extract pulmonary blood vessels and airway structures; Based on the extracted pulmonary vascular and airway structures, a three-dimensional network model is constructed; A topological analysis is performed on the three-dimensional network model to determine network nodes and connection relationships.

3. The method according to claim 1, characterized in that The calculating of the network features of the pulmonary vascular network and the airway network includes calculating one or more of the following features: Network centrality; Network efficiency; Network density; Network connectivity; Network robustness.

4. The method according to claim 3, characterized in that The computing network centrality specifically includes: Counting the number of nodes and edges of the pulmonary vascular network and the airway network; Calculate the degree of each node and perform normalization; Based on the normalized node degree, the PageRank algorithm is used to calculate the weight of the network node.

5. The method according to claim 1, characterized in that: The generated blood supply function score specifically includes: Calculating the blood supply weight of each lung segment based on the network characteristics of the pulmonary vascular network; normalizing the blood supply weight; The blood supply function score of each lung segment was calculated based on the normalized blood supply weight.

6. The method according to claim 1, characterized in that Generating a ventilation function score specifically includes: Calculating the ventilation weight of each lung segment based on the network characteristics of the airway network and lung parenchyma density information; normalizing the ventilation weight; The ventilation function score of each lung segment was calculated based on the normalized ventilation weight.

7. The method according to claim 1, characterized in that It also includes the prognosis prediction step: Establishing a machine learning model based on the comprehensive functional score; The machine learning model is used to generate a patient prognosis probability assessment result.

8. The method according to claim 7, characterized in that The establishment of the machine learning model specifically includes: Collect historical patient data, including comprehensive functional scores and actual prognosis; training a machine learning model using the patient history data; The machine learning model is validated and optimized.

9. The method according to claim 1, characterized in that: It also includes data preprocessing steps: Performing denoising processing on the medical image data; Performing standardization processing on the medical imaging data; The principal component analysis method is used to reduce the dimension of the processed medical image data.

10. The method according to claim 1, characterized in that The output step further comprises: Generate a visual lung segment function assessment report, including the blood supply function score, ventilation function score and comprehensive function score of each lung segment; The lung segment function assessment report is sent to a medical terminal device for doctors to make clinical decision references.

Images