An abnormal connection structure identification method and device of an ultrasonic contrast dynamic image

Abstract

The application discloses an abnormal connected structure identification method and device of an ultrasonic contrast dynamic image. The method comprises the following steps: acquiring an ultrasonic contrast dynamic image sequence; extracting a developing feature of each frame of ultrasonic contrast image; determining a developing time difference of adjacent regions in the ultrasonic contrast image based on the developing feature; when the developing time difference is less than a preset threshold, determining that the corresponding adjacent region is a candidate abnormal connected region; comparing and verifying the candidate abnormal connected regions of continuous multiple frames of ultrasonic contrast images, and determining a stable abnormal connected structure from the candidate abnormal connected regions. The application can improve the stability and precision of the identification result.

Description

Technical Field

[0001] This invention relates to the field of medical image processing technology, and in particular to a method and apparatus for identifying abnormal connectivity structures in dynamic ultrasound contrast images. Background Technology

[0002] Medical ultrasound imaging technology, due to its advantages such as no ionizing radiation, high real-time performance, and ease of operation, has been widely used in the imaging examination and evaluation of various tissue structures. With the continuous development of ultrasound imaging technology, its application scope has gradually expanded, from traditional morphological structure display to comprehensive evaluation of tissue functional status and dynamic changes.

[0003] Contrast-enhanced ultrasound (CEUS) improves imaging resolution, sensitivity, and specificity by introducing a contrast agent with specific acoustic properties, building upon conventional ultrasound imaging. During CEUS imaging, the contrast agent flows, generating time-series echo changes. The resulting dynamic CEUS images reflect the entry, propagation, distribution, and decay of the contrast agent within the target area. These dynamic images are typically presented as a continuous frame sequence, providing a crucial data foundation for analyzing connectivity within or between tissues.

[0004] Currently, contrast-enhanced ultrasound (CEUS) is used not only for assessing blood perfusion but also for observing the flow of contrast agents within normal anatomical cavities such as the uterine cavity and fallopian tubes. However, in some clinical scenarios, abnormal connecting channels in CEUS images are difficult to identify using traditional methods, especially when these abnormal channels present as elongated echo channels, have irregular shapes, or have short imaging times, where existing techniques have significant limitations.

[0005] First, most existing technologies rely on the operator's experience, which leads to significant differences in interpretation results between different operators. This is especially true when the image quality is poor or the abnormal structure is small, making it difficult to guarantee the stability and consistency of the interpretation.

[0006] Secondly, traditional image processing methods are based on spatial feature analysis of single-frame images, neglecting the temporal information contained in dynamic ultrasound contrast images. When the image contains noise or motion artifacts, the recognition of abnormal connected structures is unstable, easily leading to misjudgments.

[0007] Although artificial intelligence has made some progress in image processing, existing AI models mainly focus on the static features of single-frame images, lacking full utilization of temporal variations, imaging order, and spatial propagation features. This results in insufficient stability and accuracy in model recognition when processing abnormal connected structures in dynamic ultrasound contrast images.

[0008] Therefore, in view of the shortcomings of these existing technologies, how to make full use of the temporal and spatial propagation characteristics reflected by the dynamic echo changes of the contrast agent in the dynamic image sequence of ultrasound contrast imaging, and achieve reliable identification and extraction of abnormal connected structures through computer-automated processing, has become one of the key technical problems that urgently need to be solved in the field of medical image data processing. Summary of the Invention

[0009] This invention provides a method and apparatus for identifying abnormal connected structures in dynamic ultrasound contrast images, which addresses the technical problem that existing methods for identifying abnormal connected structures still suffer from insufficient stability and accuracy.

[0010] According to one aspect of the present invention, a method for identifying abnormal connected structures in dynamic ultrasound contrast images is provided, comprising: Acquire dynamic image sequences of ultrasound contrast imaging; Extract the imaging features of each frame of ultrasound contrast imaging image; the imaging features are used to determine the change of imaging intensity of each region in the ultrasound contrast imaging image over time; The development time difference between adjacent regions in the ultrasound contrast image is determined based on the development characteristics. When the development time difference is less than a preset threshold, the corresponding adjacent region is determined as a candidate abnormal connected region; The candidate abnormal connected regions of multiple consecutive ultrasound contrast images are compared and verified to determine stable abnormal connected structures from the candidate abnormal connected regions. Optionally, after acquiring the ultrasound contrast imaging sequence, the method further includes: The ultrasound contrast images in the ultrasound contrast dynamic image sequence are preprocessed, and the preprocessing includes at least noise reduction, brightness and contrast adjustment, inter-frame stabilization and registration processing.

[0011] Optionally, the extraction of imaging features from each frame of ultrasound contrast imaging includes: Each frame of the ultrasound contrast image is divided into several regions; Determine the change in imaging intensity of the same region over time in the ultrasound contrast-enhanced dynamic image sequence; The development intensity is compared with a preset intensity threshold to determine the development start time for each region.

[0012] Optionally, determining the imaging time difference between adjacent regions in the ultrasound contrast image based on the imaging features includes: Select any two adjacent regions and calculate the difference in the development start time of the adjacent regions; When the development time difference is less than a preset threshold, determining the corresponding adjacent region as a candidate abnormal connected region includes: When the development time difference is less than a preset threshold, two adjacent regions are selected as candidate abnormal connected regions, thereby determining all candidate abnormal connected regions in the ultrasound contrast image.

[0013] Optionally, the step of comparing and verifying the candidate abnormal connected regions of consecutive multi-frame ultrasound contrast images, and determining stable abnormal connected structures from the candidate abnormal connected regions, includes: The temporal consistency of the candidate abnormal connected regions in a series of ultrasound contrast images is verified to obtain the initial screening of candidate abnormal connected regions. The initial screening candidate abnormal connected regions are subjected to spatial continuity verification, and the initial screening candidate abnormal connected regions that pass the spatial continuity verification are determined as stable abnormal connected structures.

[0014] Optionally, the step of performing temporal consistency verification on the candidate abnormal connected regions of consecutive multi-frame ultrasound contrast images to obtain preliminary candidate abnormal connected regions includes: The candidate abnormal connected regions in a series of consecutive ultrasound contrast images are compared and verified. Adjacent regions in the series of consecutive ultrasound contrast images are all considered as candidate abnormal connected regions and are determined as initial screening candidate abnormal connected regions. The step of performing spatial continuity verification on the initially screened candidate abnormal connected regions, and determining the initially screened candidate abnormal connected regions that pass the spatial continuity verification as stable abnormal connected structures, includes: The morphological features of the initial screening candidate abnormal connected regions are judged, and the initial screening candidate abnormal connected regions that meet the morphological features of abnormal connected regions are determined as stable abnormal connected structures.

[0015] Optionally, after comparing and verifying the candidate abnormal connected regions in consecutive multi-frame ultrasound contrast images to determine stable abnormal connected structures from the candidate abnormal connected regions, the method further includes: Calculate the spatial location, start and end points, and length of the abnormal connectivity structure in the ultrasound contrast image; The orientation angle of the abnormal connectivity structure is determined based on the start and end points of the abnormal connectivity structure in the ultrasound contrast image. Extract the development start time and duration of the abnormal connectivity structure; The spatial location, length, orientation angle, development start time, and duration of the abnormal connected structure are output as parameters.

[0016] According to another aspect of the present invention, an anomalous connectivity structure identification device for dynamic ultrasound contrast imaging is provided, comprising: The sequence acquisition unit is used to acquire dynamic image sequences of ultrasound contrast imaging. The feature extraction unit is used to extract the imaging features of each frame of ultrasound contrast imaging image; the imaging features are used to determine the change of imaging intensity of each region in the ultrasound contrast imaging image over time. A time difference calculation unit is used to determine the imaging time difference between adjacent regions in the ultrasound contrast image based on the imaging characteristics. The first screening unit is used to determine the corresponding adjacent region as a candidate abnormal connected region when the development time difference is less than a preset threshold. The second screening unit is used to compare and verify the candidate abnormal connected regions in a series of ultrasound contrast images, and to determine stable abnormal connected structures from the candidate abnormal connected regions.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the abnormal connectivity structure identification method for ultrasound contrast dynamic images according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the abnormal connectivity structure identification method for dynamic ultrasound contrast images according to any embodiment of the present invention.

[0019] The technical solution of this invention extracts the change in imaging intensity of each region in each frame of ultrasound contrast imaging over time, and determines the imaging time difference between adjacent regions in the ultrasound contrast imaging image; when the imaging time difference is less than a preset threshold, the corresponding adjacent region is identified as a candidate abnormal connected region; the candidate abnormal connected regions of multiple consecutive frames of ultrasound contrast imaging images are compared and verified, and stable abnormal connected structures are determined from the candidate abnormal connected regions. This invention utilizes the temporal dynamic features and spatial propagation features in dynamic ultrasound contrast imaging images to select candidate abnormal connected regions, and achieves reliable and stable identification of abnormal connected structures by comparing and verifying the candidate abnormal connected regions in multiple consecutive frames of images.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a method for identifying abnormal connected structures in dynamic ultrasound contrast images according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a method for identifying abnormal connected structures in dynamic ultrasound contrast images according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the sequential inflow process of the developer and the abnormal interconnection structure in one embodiment of the present invention; Figure 4 This is a schematic diagram of the parameterized identification results of abnormal connectivity structures identified in one embodiment of the present invention; Figure 5 This is a schematic diagram of an abnormal connectivity structure identification device for dynamic ultrasound imaging according to Embodiment 3 of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device for recognizing abnormal connectivity structures in dynamic ultrasound contrast images according to Embodiment 4 of the present invention. Detailed Implementation

[0023] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0025] Example 1 Figure 1 This is a flowchart illustrating a method for identifying connected structures in dynamic ultrasound contrast images, as provided in Embodiment 1 of the present invention. Figure 1 As shown, the method includes: S101. Obtain the dynamic image sequence of ultrasound contrast imaging.

[0026] This embodiment uses an ultrasound imaging device to acquire a dynamic sequence of contrast-enhanced ultrasound images of a target area. For example, the abdominal cavity can be used as the target area, and images can be acquired using a two-dimensional ultrasound probe in contrast-enhanced mode. The acquired dynamic sequence of contrast-enhanced ultrasound images contains a series of ultrasound images arranged in chronological order, which reflects the entry, propagation, and decay of the contrast agent.

[0027] S102. Extract the imaging features of each frame of ultrasound contrast imaging image; the imaging features are used to determine the change of imaging intensity of each region in the ultrasound contrast imaging image over time.

[0028] Each frame of the ultrasound contrast imaging image reflects the state of the contrast agent at a specific moment during its entry, propagation, and dissipation. Therefore, the imaging characteristics extracted from a single frame of ultrasound contrast imaging image can reflect the imaging status at a given moment in the image. In this embodiment, the imaging characteristics can specifically use the echo intensity of any region in the image to reflect the imaging intensity within that region. By acquiring the echo intensity of each region in each frame of the ultrasound contrast imaging dynamic image sequence, the change in imaging intensity of each region over time can be determined. It should be noted that a region can be composed of one or more pixels, such as 1 pixel, 4 pixels, or 9 pixels. The echo intensity of each region can be calculated by averaging the echo intensity of each pixel within that region, or it can be obtained by weighted calculation of the echo intensity of each pixel; this embodiment does not impose any specific limitations.

[0029] Furthermore, this embodiment can also set a development start threshold and a development end threshold, that is, compare the echo intensity of each region in the ultrasound contrast imaging dynamic image sequence with the development start threshold and the development end threshold to determine the development start time and development end time of any region. It can also plot a curve showing the change of development intensity of any region over time.

[0030] S103. Determine the development time difference between adjacent regions in the ultrasound contrast image based on the development characteristics.

[0031] S104. When the development time difference is less than a preset threshold, the corresponding adjacent region is determined as a candidate abnormal connected region.

[0032] For any frame of ultrasound contrast-enhanced image, the development time difference between any two adjacent regions in the image can be calculated using development characteristics to determine whether an adjacent region is a candidate abnormal connected region. For example, the development start time of any two adjacent regions can be subtracted to obtain the development time difference. This development time difference is then compared with a preset threshold. When the development time difference is less than the preset threshold, the corresponding adjacent region is identified as a candidate abnormal connected region. Furthermore, the above method can be used to identify all candidate abnormal connected regions in a frame of ultrasound contrast-enhanced image.

[0033] It should be noted that the preset threshold can be empirical data or set according to the needs of the experiment.

[0034] S105. The candidate abnormal connected regions of multiple consecutive ultrasound contrast images are compared and verified to determine a stable abnormal connected structure from the candidate abnormal connected regions. Due to potential noise, motion artifacts, or uneven contrast agent distribution, the stability of the identification results may be poor. Specifically, the candidate abnormal connected regions calculated from a single frame image in this embodiment may contain identification errors. Therefore, this embodiment uses candidate abnormal connected regions identified from multiple consecutive frames of ultrasound contrast imaging images for comparison and verification, in order to further filter out stable abnormal connected structures from the candidate abnormal connected regions. It should be noted that the multiple frames of ultrasound contrast imaging images used in this embodiment are ultrasound contrast imaging images during the contrast agent propagation process, meaning that the contrast agent has completely covered the target area, and no contrast agent fading has occurred in any area.

[0035] The comparative verification methods can include temporal domain verification methods and spatial domain verification methods. For example, the temporal domain verification method can determine whether a candidate abnormal connected region is a stable abnormal connected structure by judging whether the same candidate abnormal connected region in multiple consecutive frames of ultrasound contrast images remains consistent. In one embodiment, when the same candidate abnormal connected region in multiple consecutive frames of ultrasound contrast images remains consistent (for example, calculating the similarity of candidate abnormal connected regions at the same position in multiple frames of images, and determining that the candidate abnormal connected region is a stable abnormal connected structure when the similarity is greater than a preset similarity threshold), the spatial domain verification method can determine whether the spatial connectivity and morphological structure of the candidate abnormal connected region meet preset requirements. If they do, it is determined to be a stable abnormal connected structure. The above comparative verification methods are only illustrative examples, and other comparative verification methods can also be used in practice.

[0036] The technical solution of this invention extracts the change in imaging intensity of each region in each frame of ultrasound contrast imaging over time, and determines the imaging time difference between adjacent regions in the ultrasound contrast imaging image; when the imaging time difference is less than a preset threshold, the corresponding adjacent region is identified as a candidate abnormal connected region; the candidate abnormal connected regions of multiple consecutive frames of ultrasound contrast imaging images are compared and verified, and stable abnormal connected structures are determined from the candidate abnormal connected regions. This invention utilizes the temporal dynamic features and spatial propagation features in dynamic ultrasound contrast imaging images to select candidate abnormal connected regions, and achieves reliable and stable identification of abnormal connected structures by comparing and verifying the candidate abnormal connected regions in multiple consecutive frames of images.

[0037] Example 2 Figure 2 This is a flowchart illustrating a method for identifying connected structures in dynamic ultrasound contrast images, as provided in Embodiment 2 of the present invention. Figure 2 As shown, the method includes: S201. Obtain dynamic image sequences of ultrasound contrast imaging.

[0038] This embodiment uses an ultrasound imaging device to acquire a dynamic sequence of contrast-enhanced ultrasound images of a target area. For example, the abdominal cavity can be used as the target area, and images can be acquired using a two-dimensional ultrasound probe in contrast-enhanced mode. The acquired dynamic sequence of contrast-enhanced ultrasound images contains a series of ultrasound images arranged in chronological order, which reflects the entry, propagation, and decay of the contrast agent.

[0039] For example, select a set of 30 consecutive frames of contrast-enhanced ultrasound images, with each frame acquired at a 1-second interval and an image resolution of 1280x1024 pixels. The acquired images are used for subsequent processing and analysis.

[0040] S202. Preprocess the ultrasound contrast images in the ultrasound contrast dynamic image sequence. The preprocessing includes at least noise reduction, brightness and contrast adjustment, inter-frame stabilization and registration processing.

[0041] To reduce the impact of noise, motion artifacts, or uneven distribution of contrast agent on the recognition results, this embodiment can preprocess the ultrasound contrast images in the dynamic image sequence to ensure the stability and accuracy of the recognition results.

[0042] Preprocessing includes at least denoising, brightness and contrast adjustment, and inter-frame stabilization and registration. Denoising can be achieved by using median filtering (e.g., setting a window size of 3x3) to suppress noise in each frame, reducing the impact of speckle noise.

[0043] Brightness and contrast adjustment: The image can be grayscale normalized, and an adaptive contrast enhancement algorithm can be used to improve the contrast of the contrast agent area in the image. Specifically, the original image can be divided into several sub-blocks of equal size; a histogram can be calculated for each sub-block; a cropping threshold can be set to truncate the part of the histogram that exceeds the threshold, and the truncated pixels can be evenly distributed to each gray level, thereby limiting the excessive amplification of noise; histogram equalization can be performed on each sub-block; bilinear interpolation can be used to eliminate the boundary effect between sub-blocks, making the entire image transition smoothly.

[0044] Inter-frame stabilization and registration processing: Registration processing can be performed on continuous images, and image registration algorithms can reduce the impact of slight probe movements on image position. Specifically, algorithms can compensate for positional shifts caused by unintentional probe shaking and patient physiological movements, thereby integrating dynamic image sequences into a unified and stable spatiotemporal coordinate system and ensuring the temporal consistency of the image sequence.

[0045] S203. Divide each frame of the ultrasound contrast image into several regions; determine the change in imaging intensity of the same region over time in the ultrasound contrast dynamic image sequence; compare the imaging intensity with a preset intensity threshold to determine the imaging start time of each region.

[0046] First, each frame of ultrasound contrast imaging can be divided into several regions. A region can be composed of one or more pixels, such as 1 pixel, 4 pixels, or 9 pixels. For example, in this embodiment, one pixel can be divided into one region. Then, the echo intensity of any region in the image can be used to reflect the imaging intensity within that region. By acquiring the echo intensity of each region in each frame of the ultrasound contrast imaging dynamic image sequence, the change in imaging intensity of each region over time can be determined. The echo intensity of each region can be calculated by averaging the echo intensity of each pixel within that region; alternatively, it can be obtained by weighted calculation of the echo intensity of each pixel. This embodiment does not impose any specific limitations.

[0047] For each pixel or region, the development start time can be determined by comparing the echo intensity of the pixel or region with a preset threshold. For example, the echo intensity threshold can be set to the mean echo intensity of the background region plus three standard deviations. If the echo intensity of a pixel first exceeds this threshold in the time series, that time point is the development start time for that pixel. Alternatively, the development end time can be determined by comparing the echo intensity of a pixel or region with a preset threshold. For example, if, after the development start time, the echo intensity of a pixel first falls below the preset threshold in the time series, that time point is the development end time for that pixel. The period between the development start time and the development end time is the development duration, during which the change in echo intensity over time is recorded.

[0048] S204. Select any two adjacent regions and calculate the difference in the development start time of the adjacent regions; when the development time difference is less than a preset threshold, the two adjacent regions are selected as candidate abnormal connected regions, thereby determining all candidate abnormal connected regions in the ultrasound contrast imaging image.

[0049] The spatial relationship between adjacent regions can be determined by pixel neighborhood relationship or region boundary distance. For example, when there is an 8-neighborhood connection between pixels in two regions, or when the minimum Euclidean distance between the boundary pixels of two regions is less than a preset spatial threshold, the two regions are determined to be spatially adjacent.

[0050] For any frame of contrast-enhanced ultrasound image, the development start time can be extracted for each region. The difference in development time between any two adjacent regions in the image is calculated using the development characteristics to determine whether an adjacent region is a candidate abnormal connected region. For example, by traversing adjacent region pairs and calculating the difference in development start time, a preset threshold is introduced. When the development time difference is less than the preset threshold, the adjacent regions are determined to belong to the same abnormal connected structure. Thus, the corresponding adjacent regions are identified as candidate abnormal connected regions. Furthermore, all candidate abnormal connected regions in a frame of contrast-enhanced ultrasound image can be identified using the above method. It should be noted that the preset threshold can be a dynamic threshold automatically calculated based on the specific organ type or contrast agent dosage.

[0051] It should be noted that after the developing solution enters the target area, it first enters the normal cavities, and then seeps into the abnormal connecting structures between the cavities. For example... Figure 3 As shown, at times T1 and T2, the developer first enters cavities A and B, and then at time T3, it flows from cavities A and B into the abnormally connected structure. Therefore, by calculating the difference in the development start time of adjacent regions, it can be determined whether the developer can flow from one region into its adjacent region. When the difference is less than a preset threshold, the adjacent regions can be determined to be connected regions. In one embodiment, cavities A and B can be compared to the rectum and vagina. Generally, there is no connecting channel between the rectum and vagina, but when there is a channel between the rectum and vagina, it indicates that there is an abnormally connected structure between the rectum and vagina.

[0052] S205. Perform temporal consistency verification on the candidate abnormal connected regions of consecutive multi-frame ultrasound contrast images; to obtain the initial screening of candidate abnormal connected regions.

[0053] In one embodiment, the candidate abnormal connected regions in a series of consecutive ultrasound contrast images can be calculated and compared for verification. Adjacent regions in the series of consecutive ultrasound contrast images are all considered as candidate abnormal connected regions and are thus identified as initial screening candidate abnormal connected regions.

[0054] To eliminate the effects of noise, motion artifacts, or uneven distribution of contrast agents in images, this embodiment can perform temporal domain comparison verification of candidate regions in multiple consecutive frames of images.

[0055] Specifically, a time window of length K is selected during the imaging process, and the following comparative verification is performed on candidate abnormal connected regions of multiple consecutive frames of ultrasound contrast images within the window: For each pixel location or each connected region block in the image space, check whether it is marked as a candidate abnormal connected region in every frame of K consecutive images.

[0056] If a region is identified as a candidate abnormal connected region in K consecutive frames, then the region is determined as a preliminary candidate abnormal connected region; otherwise, it is discarded as transient noise or artifact.

[0057] As an optional implementation, the temporal consistency verification is not limited to requiring all K consecutive frames to meet the requirement. A proportional threshold can also be set according to clinical needs. For example, it can be required that at least M frames out of K consecutive frames are candidate regions, i.e., they are identified as initial screening candidate abnormal connected regions. In this embodiment, to achieve high specificity, it is preferable to use multiple consecutive frames where all frames are candidate abnormal connected regions.

[0058] S206. Perform spatial continuity verification on the preliminary candidate abnormal connectivity regions, and determine the preliminary candidate abnormal connectivity regions that pass the spatial continuity verification as stable abnormal connectivity structures.

[0059] It should be noted that in clinical diagnosis, abnormal connectivity structures often have significant geometric morphological features. For example, in fetal abdominal ultrasound, the abnormal connectivity structure of an abdominal aorta-umbilical vein fistula usually appears as one or more tortuous and dilated vessels connecting the aorta and the umbilical vein. Therefore, morphological features can be used to analyze whether the initial screening candidate abnormal connectivity regions are stable abnormal connectivity structures.

[0060] Specifically, in contrast-enhanced ultrasound images, abnormal connectivity structures typically appear as tortuous, dilated lumens or abnormal vascular networks, for example... Figure 3 The diagram shows an abnormal connection structure between cavity A and cavity B.

[0061] In one embodiment, the morphological features of the initial screening candidate abnormal connected regions can be judged, and the initial screening candidate abnormal connected regions that meet the morphological features of abnormal connected regions can be determined as stable abnormal connected structures.

[0062] Although the initial screening candidate abnormal connected regions have shown stability in the time domain, they may still contain some non-pathological tubular structures (such as normal blood vessel crossings) or artificial artifacts. Therefore, this embodiment further judges the morphological characteristics of the initial screening candidate abnormal connected regions, retaining only the regions that meet the typical morphological characteristics of abnormal connected regions, and finally determining them as stable abnormal connected structures.

[0063] Morphological feature judgment includes at least one or more of the following indicators and their comparison with thresholds: Tortuosity: Extract the skeleton line of the initial candidate region and calculate the ratio of the actual length of the skeleton line to the straight-line distance between its beginning and end. When this ratio is greater than a preset torsion threshold, it indicates that the structure has abnormal tortuosity, which conforms to an abnormal connectivity pattern.

[0064] Diameter Variability: Calculates the equivalent diameter at different locations along the central axis of the candidate region and calculates the coefficient of variation (standard deviation / mean) of the diameter. When the coefficient of variation exceeds a preset threshold, it indicates irregular expansion or narrowing of the lumen, which is one of the characteristics of abnormal connectivity.

[0065] Abnormal Branching: Calculates the degree of branch nodes (i.e., the number of connected branches) in the candidate region's topology. For vascular abnormal connectivity, nodes with more than 3 branches or short loop structures are considered abnormal.

[0066] Aspect Ratio and Area: Calculate the aspect ratio of the smallest bounding rectangle of the candidate region. Abnormal connectivity structures are usually linear or worm-like, and their aspect ratio should be greater than a preset threshold. Simultaneously, filter out isolated noise points with excessively small areas.

[0067] In a preferred embodiment, the above-mentioned multiple morphological features are used in combination, and the scores of each feature are weighted and summed to obtain a morphological anomaly score. If the score is greater than a preset morphological threshold, the candidate abnormal connectivity region is determined to meet the abnormal connectivity morphological features, and it is finally identified as a stable abnormal connectivity structure.

[0068] In one embodiment, for rectovaginal fistula, the abnormal connectivity structure corresponds to the abnormal communication pathway (fistula) between the rectum and vagina. Therefore, the candidate region should present a continuous channel-like connectivity pattern and be able to connect the imaging area in the rectum and the imaging area in the vagina. At the same time, its position remains basically unchanged in multiple consecutive frames (i.e., high overlap or small change in the center position), which can be used to confirm that it is a spatially continuous and stable abnormal connectivity structure.

[0069] S207. Calculate the spatial position, start and end points, and length of the abnormal connectivity structure in the ultrasound contrast image; determine the orientation angle of the abnormal connectivity structure based on the start and end points of the abnormal connectivity structure in the ultrasound contrast image; extract the imaging start time and duration of the abnormal connectivity structure.

[0070] The spatial location of the abnormal connected structure can be determined by calculating its minimum bounding rectangle; the four boundaries of this rectangle (top, bottom, left, and right) define the spatial extent of the abnormal connected structure in the image. The length of the abnormal connected structure in the image can be determined by calculating the straight-line distance (Euclidean distance) between its starting and ending points. If it is a curved fistula, the distances of each segment along its actual path are calculated and summed. The orientation angle of the abnormal connected structure can be determined by calculating the angle between its starting and ending points. The angle can be calculated using the coordinate difference between the starting and ending points. The development start time can be selected as the earliest development start time among all regions of the abnormal connected structure. The development duration can be obtained by subtracting the development start time from the latest development end time among all regions of the abnormal connected structure.

[0071] S208. The spatial position, length, orientation angle, development start time and duration of the abnormal connected structure are output as parameters.

[0072] For a given stable anomalous connectivity structure, its spatial location range, start and end points, and length in the image can be calculated. Its trajectory parameters can be obtained by calculating the angle between the start and end points. The development start time and duration of the anomalous connectivity structure can be extracted and output as parameters. Specifically, such as... Figure 4 The abnormal connectivity structure is shown, where L represents the length parameter of the abnormal connectivity structure, θ represents the structure orientation parameter, T0 represents the development start time parameter, and ΔT represents the development duration parameter.

[0073] The technical solution of this invention extracts the temporal dynamic features of contrast agent development through temporal analysis of ultrasound contrast imaging sequences, enabling more accurate identification of abnormal connected structures, especially those with short development times and complex morphologies. Furthermore, by comprehensively considering temporal dynamic features and spatial connectivity, and utilizing multi-frame consistency verification and spatial connectivity analysis, the integrity and continuity of the morphology are ensured, maintaining high recognition stability even under complex imaging conditions. Finally, by parametrically describing the recognition results and outputting structured data, it facilitates quantitative analysis, data storage, and integration with other medical systems. This parametric output method makes the recognition results of this invention more scalable, meeting the needs of different medical application scenarios.

[0074] Example 3 Figure 5 This is a schematic diagram of an abnormal connectivity structure identification device for dynamic ultrasound contrast imaging provided in Embodiment 3 of the present invention. Figure 5 As shown, the device includes: Sequence acquisition unit 501 is used to acquire dynamic image sequences of ultrasound contrast imaging. The feature extraction unit 502 is used to extract the imaging features of each frame of ultrasound contrast imaging image; the imaging features are used to determine the change of imaging intensity of each region in the ultrasound contrast imaging image over time. The time difference calculation unit 503 is used to determine the imaging time difference between adjacent regions in the ultrasound contrast image based on the imaging characteristics. The first screening unit 504 is used to determine the corresponding adjacent region as a candidate abnormal connected region when the development time difference is less than a preset threshold. The second screening unit 505 is used to compare and verify the candidate abnormal connected regions of multiple consecutive ultrasound contrast images, and to determine stable abnormal connected structures from the candidate abnormal connected regions.

[0075] The message data processing resource scheduling device provided in the embodiments of the present invention can execute the message data processing resource scheduling device method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0076] Example 4 Figure 6A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0077] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0078] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0079] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a method for identifying abnormal connectivity structures in dynamic ultrasound contrast images.

[0080] In some embodiments, a method for identifying abnormal connectivity in dynamic ultrasound contrast images can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for identifying abnormal connectivity in dynamic ultrasound contrast images described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform a method for identifying abnormal connectivity in dynamic ultrasound contrast images by any other suitable means (e.g., by means of firmware).

[0081] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0082] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0083] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0084] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0085] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0086] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0087] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0088] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying abnormal connected structures in dynamic ultrasound contrast images, characterized in that, include: Acquire dynamic image sequences of ultrasound contrast imaging; Extract the imaging features of each frame of ultrasound contrast imaging image; The imaging features are used to determine how the imaging intensity of each region in an ultrasound contrast image changes over time. The development time difference between adjacent regions in the ultrasound contrast image is determined based on the development characteristics. When the development time difference is less than a preset threshold, the corresponding adjacent region is determined as a candidate abnormal connected region; The candidate abnormal connected regions of multiple consecutive ultrasound contrast images are compared and verified to determine stable abnormal connected structures from the candidate abnormal connected regions.

2. The method for identifying abnormal connected structures in dynamic ultrasound contrast images according to claim 1, characterized in that, After acquiring the dynamic ultrasound contrast imaging sequence, the method further includes: The ultrasound contrast images in the ultrasound contrast dynamic image sequence are preprocessed, and the preprocessing includes at least noise reduction, brightness and contrast adjustment, inter-frame stabilization and registration processing.

3. The method for identifying abnormal connected structures in dynamic ultrasound contrast images according to claim 1, characterized in that, The extraction of imaging features from each frame of ultrasound contrast imaging includes: Each frame of the ultrasound contrast image is divided into several regions; Determine the change in imaging intensity of the same region over time in the ultrasound contrast-enhanced dynamic image sequence; The development intensity is compared with a preset intensity threshold to determine the development start time for each region.

4. The method for identifying abnormal connected structures in dynamic ultrasound contrast images according to claim 3, characterized in that, Determining the imaging time difference between adjacent regions in the ultrasound contrast image based on the imaging characteristics includes: Select any two adjacent regions and calculate the difference in the development start time of the adjacent regions; When the development time difference is less than a preset threshold, determining the corresponding adjacent region as a candidate abnormal connected region includes: When the development time difference is less than a preset threshold, two adjacent regions are selected as candidate abnormal connected regions, thereby determining all candidate abnormal connected regions in the ultrasound contrast image.

5. The method for identifying abnormal connected structures in dynamic ultrasound contrast images according to claim 1, characterized in that, The step of comparing and verifying the candidate abnormal connected regions in consecutive multi-frame ultrasound contrast images, and determining stable abnormal connected structures from the candidate abnormal connected regions, includes: The temporal consistency of the candidate abnormal connected regions in a series of ultrasound contrast images is verified to obtain the initial screening of candidate abnormal connected regions. The initial screening candidate abnormal connected regions are subjected to spatial continuity verification, and the initial screening candidate abnormal connected regions that pass the spatial continuity verification are determined as stable abnormal connected structures.

6. The method for identifying abnormal connected structures in dynamic ultrasound contrast images according to claim 5, characterized in that, The temporal consistency of the candidate abnormal connected regions in a series of consecutive ultrasound contrast images is verified. The initial screening of candidate abnormal connected regions yielded the following: The candidate abnormal connected regions in a series of consecutive ultrasound contrast images are compared and verified. Adjacent regions in the series of consecutive ultrasound contrast images are all considered as candidate abnormal connected regions and are determined as initial screening candidate abnormal connected regions. The step of performing spatial continuity verification on the initially screened candidate abnormal connected regions, and determining the initially screened candidate abnormal connected regions that pass the spatial continuity verification as stable abnormal connected structures, includes: The morphological features of the initial screening candidate abnormal connected regions are judged, and the initial screening candidate abnormal connected regions that meet the morphological features of abnormal connected regions are determined as stable abnormal connected structures.

7. The method for identifying abnormal connected structures in dynamic ultrasound contrast images according to claim 1, characterized in that, The process involves comparing and verifying candidate abnormal connected regions in consecutive multi-frame ultrasound contrast images, determining stable abnormal connected structures from these candidate abnormal connected regions, and then further including: Calculate the spatial location, start and end points, and length of the abnormal connectivity structure in the ultrasound contrast image; The orientation angle of the abnormal connectivity structure is determined based on the start and end points of the abnormal connectivity structure in the ultrasound contrast image. Extract the development start time and duration of the abnormal connectivity structure; The spatial location, length, orientation angle, development start time, and duration of the abnormal connected structure are output as parameters.

8. A device for identifying abnormal connectivity structures in dynamic ultrasound contrast images, characterized in that, include: The sequence acquisition unit is used to acquire dynamic image sequences of ultrasound contrast imaging. The feature extraction unit is used to extract the imaging features of each frame of ultrasound contrast imaging image; The imaging features are used to determine how the imaging intensity of each region in an ultrasound contrast image changes over time. A time difference calculation unit is used to determine the imaging time difference between adjacent regions in the ultrasound contrast image based on the imaging characteristics. The first screening unit is used to determine the corresponding adjacent region as a candidate abnormal connected region when the development time difference is less than a preset threshold. The second screening unit is used to compare and verify the candidate abnormal connected regions in a series of ultrasound contrast images, and to determine stable abnormal connected structures from the candidate abnormal connected regions.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which is executed by the at least one processor to enable the at least one processor to perform the method for identifying abnormal connectivity structures in dynamic ultrasound contrast images according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for identifying abnormal connectivity structures in dynamic ultrasound contrast images according to any one of claims 1-7.

Images