Cerebral artery embolism position detection method and device, electronic equipment and storage medium

Abstract

The invention discloses a cerebral artery embolism position detection method and device, electronic equipment and a storage medium. The method comprises the following steps: firstly, acquiring mark positions of multiple groups of cerebral artery images for embolism; preprocessing the obtained feature data, and extracting image omics feature data from the preprocessed cerebral artery embolism image through a feature extraction algorithm; and then importance screening is carried out on the extracted features by using a random forest algorithm, classification prediction is carried out on the extracted features by using various machine learning models, and finally, a model with optimal performance is selected to predict the embolism position. According to the method, the position of the cerebral artery embolism is predicted by utilizing the texture features of the radiomics, and the position of the cerebral artery embolism can be better predicted. According to the method, importance screening is carried out on the extracted feature data by utilizing the random forest model, and the screening method is beneficial to removing features which have little influence on model prediction, so that the model is simplified, and the training efficiency and generalization ability of the model are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a detection method, device, electronic equipment and storage medium for detecting the position of cerebral artery embolism. Background Art

[0002] Cerebral artery embolism is a common cause of serious diseases such as stroke. Early diagnosis and timely intervention are crucial to the treatment effect of patients. At present, analysis methods based on medical images have gradually been applied to clinical diagnosis, but how to effectively extract meaningful features from images and accurately locate the embolism position is still an important research direction. However, the existing embolism detection methods based on medical images mainly rely on manual analysis, which is inefficient and highly subjective, and difficult to adapt to large-scale clinical applications. With the development of machine learning and image processing technology, automated embolism detection systems have gradually become a research hotspot.

[0003] This technology can assist doctors to quickly and accurately detect the location of cerebral artery embolism, thereby improving diagnostic efficiency and accuracy. Timely detection of cerebral artery embolism is crucial for developing effective treatment plans. Early identification of the location of embolism can help doctors choose appropriate intervention measures and improve patient prognosis. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a method, device, electronic device and storage medium for detecting the location of cerebral artery embolism. The technical solution of the present invention can efficiently and accurately detect the location of cerebral artery embolism.

[0005] According to one aspect of the present invention, a method for detecting the location of cerebral artery embolism is provided, which comprises the following steps:

[0006] Obtain multiple sets of cerebral artery images to mark the location of embolism:

[0007] The acquired cerebral artery embolism images are preprocessed, including data binarization, morphological corrosion and dilation operations; the marked position of embolism in the cerebral artery image, namely the embolism area, is extracted, and Gaussian smoothing is performed on the embolism area to eliminate noise and preserve the main feature data.

[0008] The obtained feature data is preprocessed, the cerebral artery embolism image contains multiple structural features, and the preprocessing steps include binarization processing, morphological processing and Gaussian smoothing processing.

[0009] The feature data of radiomics are extracted from the preprocessed cerebral artery embolism images by a feature extraction algorithm, wherein the features include but are not limited to: texture features, shape features and density features.

[0010] The random forest algorithm is used to screen the importance of the extracted features, and the features whose importance is greater than the preset threshold are selected as the input of the classification model.

[0011] A variety of machine learning models were used to classify and predict the extracted features, including support vector machine (SVM), decision tree (DT), K nearest neighbor (KNN), logistic regression (LR), naive Bayes (NB), multilayer perceptron (MLP), random forest (RF), AdaBoost and gradient boosted decision tree (GBDT); the classification performance of all machine learning models was evaluated, and the performance evaluation indicators included: accuracy, precision, recall, F1 score, AUC value, sensitivity and specificity; finally, the model with the best performance was selected to predict the embolism location.

[0012] Furthermore, the random forest algorithm is used to screen the extracted features according to their importance. The specific operations are as follows:

[0013] The extracted feature data and target labels are input into the random forest model for training. The random forest learns the relationship between the input features and the target variable by building multiple decision trees. The nodes of each tree in the random forest are split based on a certain feature. Whenever a feature is used for splitting, the model calculates the contribution of the split to reducing the uncertainty of the prediction. As the tree is built, the contributions of all used features are accumulated, and the total importance score of each feature is finally obtained. The feature importance algorithm provides an importance score for each feature, ranging from 0 to 1. The higher the score, the greater the impact of the feature on the model.

[0014] According to a second aspect of the present invention, there is provided a device for detecting the position of cerebral artery embolism, comprising:

[0015] The acquisition module is used to acquire image data of cerebral arteries from medical imaging data, especially image information of arterial embolism positions.

[0016] The processing module is used to perform preprocessing operations on the cerebral artery embolism image obtained by the acquisition module, specifically including:

[0017] Binarization processing: Threshold the gray value in the image to make it easier to distinguish the embolism area from the background in the image.

[0018] Morphological operation: first perform the erosion operation and then the dilation operation to remove the noise in the image and enhance the edge of the embolism area.

[0019] Gaussian smoothing: Gaussian blurring is performed on the image to reduce high-frequency noise in the image, smooth the image edges, and make the embolism area more prominent.

[0020] The extraction module is used to extract features from the image preprocessed by the processing module, specifically including:

[0021] Texture feature extraction: Extract texture features in the image based on the gray-level co-occurrence matrix (GLCM) of the image, such as gray-level region size matrix features, gray-level run length matrix features, gray-level length dependence matrix features, gray-level co-occurrence matrix features, and first-order statistical features.

[0022] Shape feature extraction: Using geometric methods, the relevant shape features are extracted by analyzing the embolism shape in the image.

[0023] Density feature extraction: Density features are calculated by analyzing the pixel intensity distribution in the image (calculating the intensity values ​​of all pixels in the embolism area). The embolism properties are further described based on the density features of the embolism area in the image, which include but are not limited to average density and peak density.

[0024] The classification module uses a machine learning model to perform classification prediction based on the various image features extracted by the extraction module. This module includes:

[0025] Multiple machine learning models: including but not limited to support vector machine (SVM), decision tree (DT), K-nearest neighbor algorithm (KNN), logistic regression (LR), naive Bayes (NB), multi-layer perceptron (MLP), random forest (RF), AdaBoost and gradient boosted decision tree (GBDT).

[0026] Classification analysis: By comparing the classification performance of multiple models (such as accuracy, precision, recall rate, F1 value, AUC and other indicators), the model with the best performance is selected to predict the embolism location.

[0027] The output module outputs the final cerebral artery embolism location detection results according to the prediction results of the classification module. The specific operation is: the prediction results of the model are saved in a new column "embolism location prediction" in the table, and the predicted category label is reversely encoded into the original label and saved.

[0028] According to a third aspect of the present invention, there is provided an electronic device, comprising:

[0029] A processor; a memory for storing processor-executable instructions; wherein the processor is configured to call the memory to store instructions to execute any one of the methods described in the first aspect.

[0030] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores computer program instructions, and the computer program instructions are executed by a processor to implement any one of the methods described in the first aspect.

[0031] In an embodiment of the present invention, the predicted position of embolism in multiple groups of cerebral artery images can be obtained, and multiple groups of cerebral artery embolism image feature data can be extracted respectively, and the morphological features, morphological features and texture features representing the arterial morphology are extracted therefrom, and multiple machine learning models are used to detect the position of cerebral artery embolism for classification.

[0032] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention.

[0033] The beneficial effects of the present invention are as follows:

[0034] The present invention uses the texture features of radiomics to predict the location of cerebral artery embolism (M1 embolism or M2 embolism). Radiomics texture features can convert quantitative information in images into numerical features that are easy to analyze. These features can be used in machine learning or deep learning models to better predict the location of cerebral artery embolism.

[0035] The present invention utilizes a random forest model to perform importance screening on the extracted feature data. This screening method helps to remove features that have little impact on model prediction, thereby simplifying the model and improving the training efficiency and generalization ability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present invention and, together with the specification, are used to explain the technical solutions of the present invention.

[0037] Figure 1 This is a flow chart of a method for detecting the position of cerebral artery embolism according to an embodiment of the present invention;

[0038] Figure 2 This is a flow chart of step S10 in a method for detecting the position of cerebral artery embolism according to an embodiment of the present invention;

[0039] Figure 3 This is a flow chart of step S20 in a method for detecting the position of cerebral artery embolism according to an embodiment of the present invention;

[0040] Figure 4 This is a flow chart of step S30 in a method for detecting the position of cerebral artery embolism according to an embodiment of the present invention;

[0041] Figure 5 A structural block diagram showing a device for detecting the position of cerebral artery embolism according to an embodiment of the present invention;

[0042] Figure 6 is a block diagram of an electronic device 100 according to an embodiment of the present invention;

[0043] Figure 7 FIG. 2 is a block diagram of another electronic device 200 according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] Various exemplary embodiments, features and aspects of the present invention will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0045] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0046] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0047] In addition, in order to better illustrate the present invention, numerous specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present invention can be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present invention.

[0048] It can be understood that the above-mentioned various method embodiments mentioned in the present invention can be combined with each other to form a combined embodiment without violating the principle logic. Due to space limitations, the present invention will not go into details.

[0049] The embodiment of the present invention provides a method for detecting cerebral artery embolism, the execution subject of the method may be an image processing device, for example, the method for dynamic detection of lesion location may be executed by a terminal device or a server or other processing device, wherein the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the method for detecting cerebral artery embolism may be implemented by a processor calling a computer-readable instruction stored in a memory.

[0050] Figure 1 FIG. 4 is a flow chart showing a method for detecting cerebral artery embolism according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0051] S10: obtaining the marked positions of embolism in multiple sets of cerebral artery images;

[0052] In some possible implementations, the cerebral artery embolism image can be obtained by taking a three-dimensional brain image by taking a CT (computed tomography) or MRI (magnetic resonance imaging). The specific method may include: setting the number of scanning layers, layer thickness and inter-layer distance of the imaging device; collecting brain images according to the number of scanning layers, layer thickness and inter-layer distance. Among them, the brain image obtained in the embodiment of the present invention is composed of multiple layers of images, which can be regarded as a three-dimensional image structure, and the image of the entire brain structure is formed by multiple layers of images. The reconstructed three-dimensional image is visualized through software such as 3D Slicer and ITK-Snap, which helps doctors observe vascular lesions more intuitively.

[0053] In some possible implementations, brain images may be requested from other electronic devices or servers to obtain multiple groups of brain images.

[0054] When a brain image is obtained, the predicted position of the embolic lesion in the image can be detected. The type of lesion can be cerebral artery embolism, ischemia, tumor or other brain disease, but is not specifically limited. By processing the brain image, the predicted position of the lesion in each layer of the image can be detected. In an embodiment of the present invention, lesion detection can be achieved by a convolutional neural network (CNN), or it can also be achieved using a traditional algorithm. For example, the convolutional neural network may include at least one of a region candidate network, a residual network, and a mask-based target recognition network, and the traditional algorithm may include a region growing method, a K-means clustering algorithm, a classifier, and the like. The above method is only an exemplary description, and those skilled in the art may implement it in other ways.

[0055] In an embodiment of the present invention, the predicted position of the lesion can be represented in matrix or vector form, with a first marker representing the area where the lesion is located in the brain image, where the first marker can be 1, and the area outside the first marker can be represented by a second marker, for example, the second marker can be 0.

[0056] S20: extracting the imaging features of the multiple groups of cerebral artery embolism areas respectively;

[0057] In some possible implementations, feature extraction of cerebral artery embolism images may include:

[0058] The PyRadiomics tool is used to extract radiomic features, including but not limited to texture features, shape features, and density features. Texture features can be used to reflect the grayscale distribution pattern and texture details in the cerebral artery embolism area, shape features can describe the geometric morphology of embolic lesions, and density features help determine the type and state of tissue.

[0059] S30: Classifying the location of cerebral arterial embolism using machine learning models

[0060] In some possible implementations, the features extracted from the cerebral artery embolism location will be used as input to a machine learning model. The machine learning model used may include, but is not limited to, support vector machine (SVM), random forest (RF), gradient boosted decision tree (GBDT), multi-layer perceptron (MLP), and convolutional neural network (CNN).

[0061] In some possible implementations, the model can be trained to classify the location of cerebral artery embolism based on input image features. The output of the model can be different embolism location categories, such as M1, M2, etc. The classification process can also be combined with cross-validation and other techniques to tune the model to improve classification accuracy and robustness.

[0062] The steps of the embodiments of the present invention are described in detail below with reference to the accompanying drawings. Figure 2 The flowchart of step S10 in a method for detecting cerebral artery embolism position in an embodiment of the present invention is shown in FIG. 1 , wherein the step of obtaining the marked positions of embolism in multiple groups of cerebral artery images, i.e., embolism areas, includes:

[0063] S11: Acquire multiple sets of cerebral artery imaging data.

[0064] Multiple sets of image data of cerebral arteries can be obtained through medical imaging equipment (such as CT or MRI). Each set of images can correspond to different scanning angles so as to fully cover the structure of cerebral arteries.

[0065] S12: Preprocess the cerebral artery image to obtain the embolism area.

[0066] In this step, the acquired cerebral artery image data is binarized to obtain the embolic area. First, all unique labels (pixel values) in the image are obtained. Assume that the label value 0 represents the background, 1 represents the blood vessel, and 2 represents the embolism. If the label has 3 values, indicating the presence of background (0) and blood vessel (1), a new mask is created through the conditional indexing method, replacing 1 (blood vessel) with 0 (background). If the label value is 2 (embolism), the value is directly retained and the background value is set to 0. The marked position of the embolism, i.e., the embolic area, is thus obtained.

[0067] As described in the above embodiment, in the embodiment of the present invention, obtaining multiple sets of cerebral artery image data is the basis of the entire embolism position detection process. The cerebral artery image data can be obtained through medical imaging equipment such as CT and MRI, and the obtained image data can cover different structures and angles of the cerebral artery to provide comprehensive vascular information.

[0068] Figure 3 A flowchart of step S20 in a method for detecting the location of cerebral artery embolism according to an embodiment of the present invention is shown. The steps of extracting multiple groups of imaging features of the locations of cerebral embolism include the following operations:

[0069] S21: Preprocessing the acquired embolization area.

[0070] First, the cerebral artery embolism area is corroded to remove small noise points;

[0071] Then, the cerebral artery embolism area is expanded to restore the size of the target area;

[0072] The connected region labeling method is used to extract the largest connected region in the image and use it as the region of interest (ROI);

[0073] Based on the pixel spacing of the region of interest, the volume and average density of the region of interest are calculated.

[0074] Through these preprocessing steps, the noise and artifacts in the image can be effectively removed, and the resolution of the embolism area and the accuracy of detection can be improved.

[0075] S22: Shape feature extraction.

[0076] The shape characteristics of the embolic area after pretreatment are extracted using geometric methods (geometric methods are mainly used to analyze and quantify the spatial structure of the target area. Geometric methods can help extract important features such as the volume, surface area, and shape of an object for subsequent analysis for diagnosis, classification, or other research.) The morphological characteristics reflect the geometric shape of the embolism and provide important information for evaluating its properties.

[0077] S23: Density feature extraction.

[0078] The density feature is calculated by analyzing the pixel intensity distribution in the image (calculating the intensity values ​​of all pixels in the embolic region). The embolic properties are further described based on the density feature of the embolic region after preprocessing in the image, and the density feature includes but is not limited to the average density and the peak density.

[0079] S24: Texture feature extraction.

[0080] Radiomics methods are used to extract (an analysis method based on image data, which aims to extract a large number of quantitative features from medical images to help detect, grade and predict prognosis of diseases. The core of radiomics is to convert quantitative information in images into numerical features that are easy to analyze. These features can be used in machine learning or deep learning models to support medical diagnosis, personalized treatment and clinical research.) Texture features of the embolism area after preprocessing, such as gray-level co-occurrence matrix (GLCM) features. These texture features help analyze the tissue structure and heterogeneity inside the embolism, further supporting clinical diagnosis.

[0081] Figure 4 A flow chart of step S30 in a method for detecting cerebral artery embolism position according to an embodiment of the present invention is shown, wherein the classification of cerebral artery embolism position using the machine learning model comprises:

[0082] S31: Data preparation.

[0083] The extracted morphological features are used as input data, and these features are organized into a format suitable for use by machine learning models. Ensure the integrity of the data set, handle missing values ​​(use a simple filler to handle missing values. The strategy is 'mean', that is, fill missing values ​​with the mean of the column), and divide the data into training sets, validation sets, and test sets for subsequent model training and evaluation.

[0084] S32: Feature selection.

[0085] The extracted features are screened for importance using the random forest algorithm, and the extracted feature data and target labels are input into the random forest model for training. The random forest learns the relationship between the input features and the target variable by building multiple decision trees. The nodes of each tree in the random forest are split based on a certain feature. Whenever a feature is used for splitting, the model calculates the contribution of the split to reducing the uncertainty of the prediction. As the tree is built, the contributions of all used features are accumulated to obtain the total importance score of each feature. The feature importance algorithm provides an importance score for each feature, ranging from 0 to 1. The higher the score, the greater the impact of the feature on the model. Features with importance greater than the preset threshold are screened out as input to the classification model.

[0086] The filtered features are the most effective input for classification tasks.

[0087] S33: Model selection.

[0088] Select an appropriate machine learning model based on task requirements and data characteristics.

[0089] Optional models include support vector machine (SVM), decision tree (DT), K nearest neighbor (KNN), logistic regression (LR), naive Bayes (NB), multi-layer perceptron (MLP), random forest (RF), AdaBoost and gradient boosted decision tree (GBDT) and deep learning models (such as convolutional neural networks, etc.), ensuring that the selected model can make full use of the input features for accurate classification.

[0090] S34: Model training and validation.

[0091] The selected machine learning model is trained using the training set, and the model parameters are adjusted by minimizing the loss function so that it can learn the mapping relationship between the input features and the location of cerebral artery embolism.

[0092] Evaluate model performance on the validation set, calculate classification accuracy, recall, F1-score and other indicators to ensure that the model performs well on unseen data. At the same time, use a cross-validation strategy to ensure the robustness and generalization ability of the model.

[0093] S35: Analysis of classification results.

[0094] Conduct in-depth analysis of the classification results of the model on the test set to identify correct and incorrect instances of classification. Based on the results, evaluate the classification effect of the model, and evaluate and analyze the model performance by comparing the predicted results with the true labels. Evaluation indicators include accuracy, precision, recall, and F1-Score to ensure that the final classification results can provide effective support for clinical diagnosis.

[0095] Those skilled in the art will appreciate that, in the above method of specific implementation, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of the steps should be determined by their functions and possible internal logic.

[0096] In addition, the present invention also provides a cerebral artery embolism position detection device, an electronic device, a computer-readable storage medium, and a program, all of which can be used to implement any cerebral artery embolism position detection method provided by the present invention. The corresponding technical solutions and descriptions are referred to the corresponding records in the method part and will not be repeated here.

[0097] Figure 5 FIG. 4 is a block diagram of a device for detecting cerebral artery embolism position according to an embodiment of the present invention. Figure 5 As shown, the cerebral artery embolism position detection device comprises:

[0098] The acquisition module is used to acquire image data of cerebral arteries from medical imaging data, especially image information of arterial embolism positions.

[0099] The processing module is used to perform preprocessing operations on the cerebral artery embolism image obtained by the acquisition module, specifically including:

[0100] Binarization processing: Threshold the gray value in the image to make it easier to distinguish the embolism area from the background in the image.

[0101] Morphological operation: first perform the erosion operation and then the dilation operation to remove the noise in the image and enhance the edge of the embolism area.

[0102] Gaussian smoothing: Gaussian blurring is performed on the image to reduce high-frequency noise in the image, smooth the image edges, and make the embolism area more prominent.

[0103] The extraction module is used to extract features from the image preprocessed by the processing module, specifically including:

[0104] Texture feature extraction: Extract texture features in the image based on the gray-level co-occurrence matrix (GLCM) of the image, such as gray-level region size matrix features, gray-level run length matrix features, gray-level length dependence matrix features, gray-level co-occurrence matrix features, and first-order statistical features.

[0105] Shape feature extraction: Using geometric methods, the relevant shape features are extracted by analyzing the embolism shape in the image.

[0106] Density feature extraction: Density features are calculated by analyzing the pixel intensity distribution in the image (calculating the intensity values ​​of all pixels in the embolism area). The embolism properties are further described based on the density features of the embolism area in the image. The density features may include, but are not limited to, average density and peak density.

[0107] The classification module uses a machine learning model to perform classification prediction based on the various image features extracted by the extraction module. This module includes:

[0108] Multiple machine learning models: including but not limited to support vector machine (SVM), decision tree (DT), K-nearest neighbor algorithm (KNN), logistic regression (LR), naive Bayes (NB), multi-layer perceptron (MLP), random forest (RF), AdaBoost and gradient boosted decision tree (GBDT).

[0109] Classification analysis: By comparing the classification performance of multiple models (such as accuracy, precision, recall rate, F1 value, AUC and other indicators), the model with the best performance is selected to predict the embolism location.

[0110] The output module outputs the final cerebral artery embolism location detection results according to the prediction results of the classification module. The specific operation is: the prediction results of the model are saved in a new column "embolism location prediction" in the table, and the predicted category label is reversely encoded into the original label and saved.

[0111] In some embodiments, the functions or modules included in the apparatus provided in the embodiments of the present invention can be used to execute the method described in the above method embodiment. The specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0112] The embodiment of the present invention further provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium may be a non-volatile computer-readable storage medium.

[0113] An embodiment of the present invention further provides an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured as the above method.

[0114] The electronic device may be provided as a terminal, a server, or a device in other forms.

[0115] Figure 6 A block diagram of an electronic device 100 according to an embodiment of the present invention is shown. For example, the electronic device 100 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0116] Reference Figure 6 The electronic device 100 may include one or more of the following components: a processing component 101, a memory 102, a power component 103, a multimedia component 104, an audio component 105, an input / output (I / O) interface 106, a sensor component 107, and a communication component 108.

[0117] The processing component 101 generally controls the overall operation of the electronic device 100, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 101 may include one or more processors 110 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 101 may include one or more modules to facilitate the interaction between the processing component 101 and other components. For example, the processing component 101 may include a multimedia module to facilitate the interaction between the multimedia component 104 and the processing component 101.

[0118] The memory 102 is configured to store various types of data to support operations on the electronic device 100. Examples of such data include instructions for any application or method operating on the electronic device 100, contact data, phone book data, messages, pictures, videos, etc. The memory 102 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0119] The power supply assembly 103 provides power to various components of the electronic device 100. The power supply assembly 103 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 100.

[0120] The multimedia component 104 includes a screen that provides an output interface between the electronic device 100 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 104 includes a front camera and / or a rear camera. When the electronic device 100 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0121] The audio component 105 is configured to output and / or input audio signals. For example, the audio component 105 includes a microphone (MIC), and when the electronic device 100 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 102 or sent via the communication component 108. In some embodiments, the audio component 105 also includes a speaker for outputting audio signals.

[0122] I / O interface 106 provides an interface between processing component 101 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0123] The sensor assembly 107 includes one or more sensors for providing various aspects of status assessment for the electronic device 100. For example, the sensor assembly 107 can detect the open / closed state of the electronic device 100, the relative positioning of components, such as the display and keypad of the electronic device 100, and the sensor assembly 107 can also detect the position change of the electronic device 100 or a component of the electronic device 100, the presence or absence of user contact with the electronic device 100, the orientation or acceleration / deceleration of the electronic device 100, and the temperature change of the electronic device 100. The sensor assembly 107 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 107 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 107 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0124] The communication component 108 is configured to facilitate wired or wireless communication between the electronic device 100 and other devices. The electronic device 100 can access a wireless network based on a communication standard, such as WiFi, 4G or 5G, or a combination thereof. In an exemplary embodiment, the communication component 108 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 108 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0125] In an exemplary embodiment, the electronic device 100 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0126] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 102 including computer program instructions, which can be executed by a processor 110 of an electronic device 100 to perform the above method.

[0127] Figure 7 2 is a block diagram of another electronic device 200 according to an embodiment of the present invention. For example, the electronic device 200 may be provided as a server. Figure 6, the electronic device 200 includes a processing component 201, which further includes one or more processors, and a memory resource represented by a memory 203, for storing instructions that can be executed by the processing component 201, such as an application. The application stored in the memory 203 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 201 is configured to execute the instructions to perform the above method.

[0128] The electronic device 200 may further include a power supply component 202 configured to perform power management of the electronic device 200, a wired or wireless network interface 204 configured to connect the electronic device 200 to a network, and an input / output (I / O) interface 205. The electronic device 200 may operate based on an operating system stored in the memory 203, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0129] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 203 including computer program instructions, which can be executed by the processing component 201 of the electronic device 200 to perform the above method.

[0130] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0131] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0132] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0133] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0134] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0135] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0136] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0137] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0138] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for detecting the location of cerebral artery embolism, characterized in that: It includes the following steps: Obtain multiple sets of cerebral artery images to mark the location of embolism: Preprocess the acquired cerebral artery embolism images, including data binarization, morphological corrosion and dilation operations; extract the location of cerebral artery embolism, perform Gaussian smoothing on the cerebral artery embolism location area, eliminate noise, and save the main feature data; Preprocessing the obtained feature data, wherein the cerebral artery embolism image contains multiple structural features, and the preprocessing steps include binarization processing, morphological processing and Gaussian smoothing processing; Extracting imaging feature data from the preprocessed cerebral artery embolism images by a feature extraction algorithm, wherein the features include but are not limited to: texture features, shape features and density features; Use the random forest algorithm to screen the extracted features by importance, and select features whose importance is greater than the preset threshold as the input of the classification model; Use multiple machine learning models to classify and predict the extracted features; The classification performance of all machine learning models was evaluated, and finally the model with the best performance was selected to predict the embolism location.

2. A method for detecting the location of cerebral artery embolism according to claim 1, characterized in that: The machine learning models include support vector machine, decision tree, K nearest neighbor, logistic regression, naive Bayes, multi-layer perceptron, random forest, AdaBoost and gradient boosting decision tree; performance evaluation indicators include: accuracy, precision, recall, F1 score, AUC value, sensitivity and specificity.

3. The method for detecting the location of cerebral artery embolism according to claim 1, characterized in that: The specific operations of using the random forest algorithm to screen the importance of the extracted features are as follows: The extracted feature data and target labels are input into the random forest model for training. The random forest learns the relationship between the input features and the target variable by building multiple decision trees. The nodes of each tree in the random forest will be split based on a certain feature. Whenever a feature is used for splitting, the model will calculate the contribution of the split to reducing the prediction uncertainty. As the tree is built, the contributions of all used features will be accumulated, and finally the total importance score of each feature will be obtained. The feature importance algorithm provides an importance score for each feature, ranging from 0 to 1, with higher scores indicating a greater impact of the feature on the model.

4. The method for detecting the location of cerebral artery embolism according to claim 1, characterized in that: When making classification predictions, select an appropriate machine learning model based on task requirements and data characteristics for classification predictions.

5. The method for detecting the location of cerebral artery embolism according to claim 1, characterized in that: Obtain multiple sets of cerebral artery images to mark the location of the embolism, i.e. the embolism area, including: S11: Acquire multiple sets of cerebral artery imaging data; Multiple sets of image data of cerebral arteries are obtained through medical imaging equipment; each set of images corresponds to a different scanning angle so as to fully cover the structure of cerebral arteries; S12: Preprocess the cerebral artery images to obtain the embolism area; The acquired cerebral artery image data is binarized to obtain the embolism area. First, all unique labels in the image are obtained; the label value 0 is defined to represent the background, 1 is defined to represent the blood vessel, and 2 is defined to represent the embolism. If the label has 3 values, indicating the presence of background and blood vessels, a new mask is created through the conditional indexing method to replace 1 with 0. If the label value is 2, the value is directly retained and the background value is set to 0.

6. A method for detecting the location of cerebral artery embolism according to claim 1 or 5, characterized in that: Extracting feature data of radiomics includes the following operations: S21: pre-processing the acquired embolization area; First, the cerebral artery embolism area is corroded to remove small noise points; Then, the cerebral artery embolism area is expanded to restore the size of the target area; Use the connected region labeling method to extract the largest connected region in the image and use it as the region of interest; Based on the pixel spacing of the region of interest, the volume and average density of the region of interest are calculated; S22: shape feature extraction; The shape features of the pre-processed embolic area are extracted using geometric methods; Morphological features reflect the geometry of the embolus and provide important information for evaluating its nature; S23: density feature extraction; Calculate density features by analyzing pixel intensity distribution in the image; further describe embolic properties according to density features of the embolic area after preprocessing in the image, wherein the density features include but are not limited to average density and peak density; S24: texture feature extraction; Radiomics methods were used to extract the texture features of the embolized area after pretreatment.

7. A device for detecting the location of cerebral artery embolism, characterized in that: include: An acquisition module, used for acquiring image data of cerebral arteries from medical imaging data, especially image information of arterial embolism positions; The processing module is used to perform preprocessing operations on the cerebral artery embolism image obtained by the acquisition module, specifically including: Binarization: Thresholding the gray value in the image to make it easier to distinguish the embolic area from the background; Morphological operation: first perform corrosion operation and then dilation operation to remove noise in the image and enhance the edge of the embolism area; Gaussian smoothing: Gaussian blurring is performed on the image to reduce high-frequency noise in the image, smooth the image edge, and make the embolism area more prominent; The extraction module is used to extract features from the image preprocessed by the processing module, specifically including: Texture feature extraction: Extract texture features in images based on the gray-level co-occurrence matrix of the image, such as gray-level region size matrix features, gray-level run length matrix features, gray-level length dependence matrix features, gray-level co-occurrence matrix features, and first-order statistical features; Shape feature extraction: using geometric methods to analyze the embolism shape in the image and extract relevant shape features; Density feature extraction: calculate density features by analyzing the pixel intensity distribution in the image; further describe the embolic properties based on the density features of the embolic area in the image, the density features include but are not limited to average density and peak density; The classification module uses a machine learning model to perform classification prediction based on the various image features extracted by the extraction module. This module includes: Multiple machine learning models: including but not limited to support vector machines, decision trees, K-nearest neighbor algorithms, logistic regression, naive Bayes, multi-layer perceptrons, random forests, AdaBoost, and gradient boosted decision trees; Classification analysis: By comparing the classification performance of multiple models, the model with the best performance is selected to predict the embolism location; The output module outputs the final cerebral artery embolism location detection result according to the prediction result of the classification module.

8. An electronic device, characterized in that: include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to call the memory-stored instructions to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The storage medium stores computer program instructions, and the computer program instructions are executed by a processor to implement the method according to any one of claims 1 to 6.

Images