Methods for measuring fetal ventricle ratio and ultrasound imaging systems

Abstract

This application provides a method for measuring fetal ventricular ratio and an ultrasound imaging system. The method is applied to an ultrasound imaging system, which includes a processor. The processor acquires an ultrasound image of a cross-section of the fetal lateral ventricle; the processor determines the midline of the brain based on the ultrasound image of the cross-section of the lateral ventricle; the processor acquires a first farthest point on the lateral wall of the lateral ventricle in the ultrasound image that is farthest from the midline of the brain, and acquires the length of a first perpendicular line from the first farthest point to the midline of the brain; the processor acquires a second farthest point on the medial side of the skull in the ultrasound image that is farthest from the midline of the brain, and acquires the length of a second perpendicular line from the second farthest point to the midline of the brain; the processor determines the fetal ventricular ratio based on the lengths of the first and second perpendicular lines. This application improves the efficiency of doctors and increases the accuracy of the obtained ventricular ratio.

Description

Technical Field

[0001] This application relates to the field of ultrasound imaging technology, and more specifically to a method for measuring the fetal ventricle ratio and an ultrasound imaging system. Background Technology

[0002] In modern obstetric examinations, ultrasound technology has become the most widely used examination method due to its safety, convenience, non-invasiveness, and low cost. In particular, it can avoid the potential harm to the mother and fetus caused by X-rays, making its application value in obstetrics significantly superior to other examinations. It has become one of the main auxiliary means for obstetricians to make diagnoses.

[0003] In diagnosing fetal neurological developmental abnormalities, the lateral ventricles are a crucial examination component. Located deep within the cerebral hemispheres, there are two lateral ventricles, one on each side, shaped like a "C" and filled with cerebrospinal fluid. A lateral ventricle width greater than 10 mm is called lateral ventricle enlargement, often caused by excessive fetal cerebrospinal fluid, central nervous system abnormalities such as midline brain structure developmental abnormalities or localized space-occupying lesions, or it may be an intracranial manifestation of abnormalities in other systems, such as chromosomal abnormalities or viral infections. Therefore, changes in the lateral ventricles during fetal development are important indicators for doctors to assess the severity and extent of fetal neurological diseases, and even crucial factors in deciding whether to continue the pregnancy.

[0004] Besides directly measuring the width of the lateral ventricles, the ventricle ratio is also widely used to determine whether there are lateral ventricle abnormalities. During the measurement of the fetal ventricle ratio, doctors often need to manually measure the distance from the midline of the brain to the lateral wall of the lateral ventricle and the distance from the midline of the brain to the inner surface of the fetal skull. This involves manually drawing a vertical line from the point on the lateral wall of the lateral ventricle furthest from the midline of the brain to the midline of the brain, and a vertical line from the point on the inner surface of the skull furthest from the midline of the brain to the midline of the brain.

[0005] However, without the aid of other tools, it is very difficult for doctors to draw accurate vertical lines by hand. As a result, in actual clinical practice, measuring and calculating the ventricular ratio often consumes too much time and effort, resulting in low efficiency and low accuracy.

[0006] In view of at least one of the above problems, this application proposes a new method for measuring fetal ventricle ratio and an ultrasound imaging system. Summary of the Invention

[0007] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. The summary section of this invention is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0008] This application provides a method for measuring the fetal ventricle ratio, applied to an ultrasound imaging system, the ultrasound imaging system including a processor, and the measurement method including:

[0009] The processor acquires ultrasound images of a cross-section of the fetal lateral ventricle;

[0010] The processor determines the midline of the brain based on the ultrasound image of the transverse section of the lateral ventricle;

[0011] The processor acquires the first farthest point on the lateral wall of the lateral ventricle in the ultrasound image that is farthest from the midline of the brain, and acquires the length of the first perpendicular line from the first farthest point to the midline of the brain.

[0012] The processor acquires the second farthest point on the inner side of the skull in the ultrasound image that is farthest from the midline of the brain, and acquires the length of the second perpendicular line from the second farthest point to the midline of the brain.

[0013] The processor determines the ventricle ratio of the fetus based on the lengths of the first and second vertical lines.

[0014] In one example, the processor acquires the first farthest point on the lateral ventricular wall of the lateral cerebral ventricle in the ultrasound image that is farthest from the midline of the brain, including:

[0015] The processor, in response to an operation command for the ultrasound image, acquires the first farthest point in the ultrasound image where the lateral ventricular wall is furthest from the midline of the brain; or

[0016] The processor automatically acquires the first farthest point in the ultrasound image where the lateral wall of the lateral ventricle is furthest from the midline of the brain.

[0017] In one example, the processor automatically acquires the first farthest point in the ultrasound image where the lateral wall of the lateral ventricle is furthest from the midline of the brain, including:

[0018] Identify and acquire the posterior horn region of the lateral ventricle in the ultrasound image;

[0019] Calculate the distance from each pixel in the posterior horn region of the lateral ventricle to the midline of the brain;

[0020] The pixel furthest from the brain midline is selected as the first farthest point.

[0021] In one example, the processor acquires the second farthest point on the medial side of the skull in the ultrasound image, which is furthest from the midline of the brain, including:

[0022] The processor, in response to an operation command for the ultrasound image, acquires the second farthest point in the ultrasound image on the medial side of the skull, which is furthest from the midline of the brain; or

[0023] The processor automatically acquires the second farthest point on the inner side of the skull in the ultrasound image that is farthest from the midline of the brain.

[0024] In one example, the processor automatically acquires the second farthest point on the medial side of the skull in the ultrasound image that is furthest from the midline of the brain, including:

[0025] Identify and acquire the region of strong echogenic rings in the cranial cavity within the ultrasound image;

[0026] Calculate the distance from each pixel of the inner edge of the hyperechoic ring region of the brain to the midline of the brain;

[0027] The pixel furthest from the brain midline is selected as the second farthest point.

[0028] In one example, the processor determines the midline of the brain based on an ultrasound image of a cross-section of the lateral ventricle, including:

[0029] The processor, in response to an operation command for the ultrasound image, determines the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle; or

[0030] The processor determines the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle using an intelligent recognition method.

[0031] In one example, the measurement method further includes:

[0032] The processor automatically generates a first perpendicular line from the first farthest point to the midline of the brain.

[0033] The first vertical line is displayed in the ultrasound image; and / or

[0034] The processor automatically generates a second perpendicular line from the second farthest point to the midline of the brain.

[0035] The second vertical line is shown in the ultrasound image.

[0036] In one example, the measurement method further includes:

[0037] The ultrasound image displays the brain midline and / or the ventricular ratio.

[0038] In one example, the measurement method further includes:

[0039] Obtain a first adjustment instruction for adjusting the position of the first farthest point, and adjust the position of the first farthest point based on the first adjustment instruction; and / or

[0040] Obtain a second adjustment instruction for adjusting the position of the second farthest point, and adjust the position of the second farthest point based on the second adjustment instruction.

[0041] In one example, the measurement method further includes:

[0042] The processor determines whether the fetus has lateral ventricle abnormalities based on the threshold range of the ventricle ratio, and outputs a prompt message when an abnormality is found in the lateral ventricle.

[0043] The aforementioned prompt message will be displayed.

[0044] Another aspect of this application provides an ultrasound imaging system, the ultrasound imaging system comprising:

[0045] Ultrasonic probe;

[0046] A transmitting circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus;

[0047] A receiving circuit is used to receive ultrasound echoes based on the ultrasound waves returned from the fetus, and to obtain an ultrasound echo signal;

[0048] The processor is configured to: obtain an ultrasound image of a cross-section of the lateral ventricle of the fetus based on the ultrasound echo signal;

[0049] The processor is also used to perform the aforementioned method for measuring the fetal ventricle ratio;

[0050] A monitor is used to display various visual information.

[0051] The fetal ventricle ratio measurement method and ultrasound imaging system described in this application optimize the doctor's workflow, improve the doctor's work efficiency, and increase the accuracy of the final obtained fetal ventricle ratio. The obtained ventricle ratio has good repeatability, providing doctors with a better basis for diagnosing the development of the fetal lateral ventricles. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the 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.

[0053] In the attached diagram:

[0054] Figure 1 A schematic block diagram of an ultrasound imaging system according to an embodiment of this application is shown;

[0055] Figure 2 An ultrasound image of a lateral ventricle cross section showing a manually measured fetal ventricle ratio;

[0056] Figure 3 An ultrasound image of a lateral ventricle cross section measuring the fetal ventricle ratio according to an embodiment of this application is shown.

[0057] Figure 4 A schematic flowchart illustrating a method for measuring the fetal ventricle ratio according to an embodiment of this application is shown. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application more apparent, exemplary embodiments according to this application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein. Based on the embodiments of this application described herein, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of this application.

[0059] The following description provides numerous specific details to offer a more thorough understanding of this application. However, it will be apparent to those skilled in the art that this application can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described to avoid confusion with this application.

[0060] It should be understood that this application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of this application to those skilled in the art.

[0061] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0062] To fully understand this application, a detailed structure will be presented in the following description to illustrate the technical solution proposed in this application. Optional embodiments of this application are described in detail below; however, in addition to these detailed descriptions, this application may have other implementation methods.

[0063] Below, first refer to Figure 1 An ultrasound imaging system according to an embodiment of this application is described. Figure 1 A schematic structural block diagram of an ultrasound imaging system 100 according to an embodiment of this application is shown.

[0064] like Figure 1 As shown, the ultrasound imaging system 100 includes an ultrasound probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116, and a display 118. Further, the ultrasound imaging system 100 may also include a transmit / receive selection switch 120 and a beamforming module 122. The transmitting circuit 112 and the receiving circuit 114 can be connected to the ultrasound probe 110 via the transmit / receive selection switch 120.

[0065] The ultrasound probe 110 includes multiple transducer elements. These elements can be arranged in a row to form a linear array, or in a two-dimensional matrix to form a planar array, or in a convex array. The transducer elements are used to emit ultrasound waves based on excitation electrical signals, or to convert received ultrasound waves into electrical signals. Therefore, each transducer element can be used to achieve the mutual conversion between electrical pulse signals and ultrasound waves, thereby enabling the emission of ultrasound waves to the brain of the fetus being tested, or to receive ultrasound echoes reflected back from the fetus's brain. During ultrasound detection, the transmission and reception sequences can be used to control which transducer elements are used to emit ultrasound waves and which are used to receive ultrasound waves, or to control the transducer elements to be used in time-slotted manner for emitting or receiving ultrasound echoes. Transducer elements involved in ultrasound emission can be simultaneously excited by electrical signals to emit ultrasound waves simultaneously; alternatively, transducer elements involved in ultrasound beam emission can be excited by several electrical signals with a certain time interval to continuously emit ultrasound waves with a certain time interval.

[0066] During ultrasound imaging, the transmitting circuit 112 excites the ultrasound probe to emit ultrasound waves toward the fetus. The transmitting circuit 112 sends the delayed-focused transmission pulse to the ultrasound probe 110 via the transmit / receive selection switch 120. Excited by the transmission pulse, the ultrasound probe 110 emits corresponding ultrasound waves along the corresponding two-dimensional (2D) scanning plane toward the tissue being tested. After a certain delay, the receiving circuit 114 receives the ultrasound echo reflecting back from the tissue, carrying tissue information, and converts this ultrasound echo back into an electrical signal. The receiving circuit 114 receives the electrical signal generated by the ultrasound probe 110, obtains the ultrasound echo signal, and sends these ultrasound echo signals to the beamforming module 122. The beamforming module 122 performs focusing delay, weighting, and channel summation on the ultrasound echo data, and then sends it to the processor 116. The signal processing module of the processor 116 processes the signal. The processor 116 obtains an ultrasound image of the transverse section of the lateral ventricle of the fetus based on the ultrasound echo signal. Specifically, the processor 116 reconstructs the corresponding two-dimensional ultrasound image based on the spatial position relationship of each transmitted / received signal. After denoising, smoothing, enhancement and other corresponding partial or complete image post-processing steps, the processor 116 obtains two-dimensional ultrasound data of the tested body tissue, such as an ultrasound image.

[0067] Optionally, the processor 116 can be implemented as software, hardware, firmware, or any combination thereof, and can use one or more application-specific integrated circuits (ASICs), one or more general-purpose integrated circuits, one or more microprocessors, one or more programmable logic devices, or any combination of the foregoing circuits and / or devices, or other suitable circuits or devices. Furthermore, the processor 116 can control other components in the ultrasound imaging system 100 to perform corresponding steps of the fetal ventricle ratio measurement methods in the various embodiments of this specification, the details of which will be described below.

[0068] The display 118 is connected to the processor 116. The display 118 can be a touch screen, an LCD screen, etc.; or, the display 118 can be an independent display such as an LCD screen or a television, separate from the ultrasound imaging system 100; or, the display 118 can be the screen of an electronic device such as a smartphone or tablet, etc. The number of displays 118 can be one or more.

[0069] The display 118 is used to display various visual information, including ultrasound images obtained by the processor 116. Furthermore, while displaying ultrasound images, the display 118 can also provide a graphical interface for human-computer interaction. One or more controlled objects can be set on the graphical interface, allowing the user to input operation commands via a human-computer interaction device to control these controlled objects and execute corresponding control operations. For example, icons can be displayed on the graphical interface, and the human-computer interaction device can be used to operate these icons to perform specific functions, such as drawing the brain midline, first distal point, first vertical line, second distal point, and second vertical line on the ultrasound image.

[0070] Optionally, the ultrasound imaging system 100 may also include other human-machine interface devices besides the display 118, which are connected to the processor 116. For example, the processor 116 may be connected to the human-machine interface device via an external input / output port, which may be a wireless communication module, a wired communication module, or a combination of both. The external input / output port may also be based on USB, bus protocols such as CAN, and / or wired network protocols.

[0071] The human-computer interaction device may include an input device for detecting user input information. This input information may be, for example, control commands for the timing of ultrasound transmission / reception, operational input commands for drawing points, lines, or boxes on an ultrasound image, or other types of commands. The input device may include one or a combination of several of the following: a keyboard, mouse, scroll wheel, trackball, mobile input device (e.g., a mobile device with a touchscreen, a mobile phone, etc.), a multi-function knob, etc. The human-computer interaction device may also include an output device such as a printer.

[0072] The ultrasound imaging system 100 may also include a memory 124 for storing instructions executed by the processor 116, storing received ultrasound echoes, etc. The memory may be a flash memory card, solid-state memory, hard disk, etc. It may be volatile and / or non-volatile memory, removable memory and / or non-removable memory, etc.

[0073] It should be understood that Figure 1 The components included in the ultrasound imaging system 100 shown are merely illustrative and may include more or fewer components. This application is not limiting in this regard.

[0074] Ultrasound image of a transverse section of the fetal lateral ventricle, as shown below Figure 2As shown, in the transverse image of the lateral ventricle, the strong echoic ring of the skull appears elliptical, the posterior horn of the lateral ventricle is clearly visible, containing a strong echoic choroid plexus. Part of the thalamus is visible in the center of the image, and the midline of the brain, cavum septum pellucidum, and lateral fissure of the brain are also visible. This transverse image of the lateral ventricle can be a cross-sectional view obtained from a two-dimensional ultrasound scan or a three-dimensional ultrasound cross-section. In the image, vertical lines A and B are the perpendicular lines drawn manually by the doctor from the point furthest from the midline of the lateral ventricle to the midline of the brain, and from the point furthest from the midline of the brain on the medial side of the skull to the midline of the brain, respectively. This method is not only time-consuming and laborious, but also difficult to guarantee accuracy, resulting in poor reproducibility of the obtained results.

[0075] In view of the above problems, this application provides some methods for measuring fetal ventricle ratio, which will be explained and described one by one below.

[0076] The following reference Figure 4 This application describes a method for measuring the fetal ventricle ratio according to embodiments. Figure 4 This is a schematic flowchart of a method for measuring the fetal ventricle ratio according to an embodiment of this application. The method for measuring the fetal ventricle ratio according to this application is used in an ultrasound imaging system, which includes an ultrasound probe, a processor, and a display. This ultrasound imaging system can be implemented as the ultrasound imaging system 100 described above. Specifically, the method for measuring the fetal ventricle ratio according to an embodiment of this application includes the following steps:

[0077] In step S410, the processor acquires an ultrasound image of a cross-section of the fetal lateral ventricle;

[0078] In step S420, the processor determines the midline of the brain based on the ultrasound image of the transverse section of the lateral ventricle;

[0079] In step S430, the processor obtains the first farthest point of the lateral ventricular wall of the lateral cerebral ventricle in the ultrasound image that is farthest from the midline of the brain, and obtains the length of the first perpendicular line from the first farthest point to the midline of the brain.

[0080] In step S440, the processor obtains the second farthest point on the inner side of the skull in the ultrasound image that is farthest from the midline of the brain, and obtains the length of the second farthest point to the second perpendicular line from the midline of the brain;

[0081] In step S450, the processor determines the ventricle ratio of the fetus based on the lengths of the first vertical line and the second vertical line.

[0082] The method for measuring fetal ventricle ratio according to this application optimizes the doctor's workflow, improves the doctor's work efficiency, and increases the accuracy of the final measured fetal ventricle ratio. The obtained ventricle ratio has good repeatability, providing doctors with a better basis for diagnosing the development of the fetal lateral ventricles.

[0083] Specifically, in step S410, an ultrasound image can be acquired using the aforementioned ultrasound imaging system 100. This ultrasound image can be a two-dimensional ultrasound image or a three-dimensional ultrasound image, etc. During the ultrasound imaging process, the transmitting circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetal brain. The transmitting circuit sends the delayed-focused transmission pulse to the ultrasound probe through a transmit / receive selection switch. Excited by the transmission pulse, the ultrasound probe emits a corresponding ultrasound wave along the corresponding two-dimensional (2D) scanning plane toward the tissue being tested. After a certain delay, the receiving circuit receives the ultrasound echo reflecting back from the fetal brain, carrying brain information, and converts this ultrasound echo back into an electrical signal. The receiving circuit receives the electrical signal generated by the ultrasound probe, obtains the ultrasound echo signal, and sends these ultrasound echo signals to the beamforming module. The beamforming module performs focusing delay, weighting, and channel summation on the ultrasound echo data, and then sends it to the processor. The processor's signal processing module processes the signal. The processor also performs corresponding two-dimensional ultrasound image reconstruction on the signal processed by the signal processing module according to the spatial position relationship of each transmitted / received signal. After denoising, smoothing, enhancement and other corresponding partial or complete image post-processing steps, the two-dimensional ultrasound data of the transverse section of the fetal lateral ventricle is obtained, such as a two-dimensional ultrasound image.

[0084] Optionally, the ultrasound image in this application can be a static ultrasound image or a dynamic ultrasound image (such as a video / 4D image). Alternatively, a frame from the dynamic image can be selected from the acquired ultrasound data and used as a static image input.

[0085] In determining the midline of the brain in a transverse ultrasound image of the lateral ventricle, step S420 can be performed in a variety of ways.

[0086] For example, the midline of the brain can be determined in an ultrasound image of a transverse section of the lateral ventricle using a combination of manual and automatic methods. In some embodiments, step S420 may include: the processor determining the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle in response to an operation command for the ultrasound image. The operation command may be two non-coincident points marked by the user in the ultrasound image of the transverse section of the lateral ventricle, and the processor determines a straight line passing through these two points, which is the midline of the brain; or the operation command may be a straight line marked by the user in the ultrasound image of the transverse section of the lateral ventricle, and the processor identifies this straight line and uses it as the midline of the brain.

[0087] It is worth mentioning that, in this application, the operation instructions may be generated by detecting the marking operation on the transverse section of the lateral ventricle. This operation includes, but is not limited to, sliding the trackball (a direction indicator similar to a mouse wheel on an ultrasound imaging system) marking, sliding and clicking the mouse marking, the user touching the marking on the touch screen, pressing the up, down, left and right arrow keys on the keyboard marking, etc.

[0088] The midline of the brain can also be determined in ultrasound images of a transverse section of the lateral ventricle through automatic recognition. For example, the processor determines the midline of the brain based on the ultrasound image of the transverse section of the lateral ventricle, including: the processor determines the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle through an intelligent recognition method. Automatically determining the midline of the brain in the ultrasound image of a transverse section of the lateral ventricle through intelligent recognition can reduce the error caused by user marking of the midline, improve the accuracy of the determined midline, reduce the need for manual marking of the midline, avoid mechanized labor, optimize the workflow of doctors in determining the midline of the brain, effectively improve work efficiency, and make the diagnostic process of doctors faster and smoother.

[0089] It should be understood that, in this application, various intelligent recognition methods such as line detection algorithms, structure detection algorithms, machine learning methods, and deep learning algorithms can be used to determine the brain midline in ultrasound images of transverse sections of the lateral ventricle.

[0090] In some embodiments, a line detection algorithm is used to determine the midline of the brain in an ultrasound image of a transverse section of the lateral ventricle. Since the midline of the brain is a linear structure located on the axis of symmetry of a transverse section of the skull, its echo is clearly distinguishable from surrounding tissues, so a line detection algorithm can be used to detect it. For example, a line detection algorithm can be used to detect all straight lines in an ultrasound image of a transverse section of the lateral ventricle, and the line closest to the long axis of the transverse section of the skull is selected as the midline of the brain. Line detection algorithms include, but are not limited to, Hough transform, Radon transform, LSD fast line detection algorithm, FLD line detection algorithm, EDlines line detection algorithm, LSWMS line detection algorithm, and CannyLines line detection algorithm.

[0091] In some embodiments, the midline of the brain is determined in ultrasound images of transverse sections of the lateral ventricle using a structure detection algorithm. For example, the midline is obtained by detecting characteristic anatomical structures located along the midline of the brain based on the structure detection algorithm and then fitting these characteristic anatomical structures with a straight line. Specifically, when the acquired ultrasound image is a cerebellar section of the fetal brain, the specific anatomical structures located along the midline include the cerebellum, cavum septum pellucidum, and cerebellar vermis; when the acquired ultrasound image is a thalamic section, the specific anatomical structures located along the midline include the thalamus and cavum septum pellucidum. The midline is obtained by fitting a straight line to points on the obtained cerebellum, cavum septum pellucidum, and cerebellar vermis, or thalamus and cavum septum pellucidum. Commonly used structure detection methods include, but are not limited to, the Otsu thresholding algorithm (OSTU) and level set algorithms.

[0092] In some embodiments, the midline of the brain is determined in ultrasound images of a transverse section of the lateral ventricle using machine learning methods or deep learning algorithms. The machine learning methods or deep learning algorithms learn features or patterns in a database used to distinguish target regions, and then locate and identify targets in other images based on these learned features or patterns, thereby achieving automatic determination of the midline of the brain. For example, ultrasound images of a transverse section of the lateral ventricle are used as input data to a pre-trained machine learning model or deep learning model for computation to obtain the linear equation of the midline of the brain as output data. The pre-trained machine learning model or deep learning model is trained using a preset database of calibrated ultrasound images, including at least one calibrated linear equation of the midline of the brain. During the training process, the calibrated ultrasound images are used as input data, the linear equation of the midline of the brain in the calibrated ultrasound images is used as output data, and the parameters of the model are optimized during the training of the machine learning model or deep learning model.

[0093] Taking the determination of the brain midline in a two-dimensional image as an example, the steps to train a deep learning model to obtain a pre-trained deep learning model can include: 1. Constructing a training sample database: The training sample database includes a large amount of labeled fetal lateral ventricle cross-sectional data. The specific labeling can be set according to the actual task, and can be the positions of the left and right endpoints of the brain midline, or a mask for precise segmentation of the brain midline region. 2. Localization and recognition: After constructing the training sample database, a deep learning algorithm is designed to learn the features or patterns in the training sample database used to distinguish target regions to achieve the localization of the brain midline. Specific implementations include, but are not limited to, the following: For example, the positions of the left and right endpoints of the brain midline or the endpoints of the long axis of the cranial cross-section can be detected and recognized based on deep learning methods. Typically, a generative network can be generated by stacking convolutional layers, fully connected layers, etc., to perform feature learning and parameter regression on the endpoint coordinates in the training sample database. For an input image, the coordinates of the endpoints can be obtained through network regression, thereby determining the position of the brain midline. Common networks include R-CNN, Fast R-CNN, Faster R-CNN, SSD, YOLO, etc. For example, an end-to-end semantic segmentation method based on deep learning can be used to accurately segment the brain midline region. The specific process can be found in the description above, but the difference lies in removing fully connected layers and adding upsampling or deconvolution to make the input and output sizes the same, thereby obtaining the brain midline region of the input image and determining the position of the midline line based on the segmentation result. Common networks include FCN, U-Net, and Mask R-CNN.

[0094] Furthermore, after determining the brain midline using the above method, the brain midline can be displayed in ultrasound images, allowing doctors to intuitively understand the condition of the brain midline from the ultrasound images. For example, in Figure 3 In the ultrasound image, line segment C is the identified brain midline.

[0095] In addition, to facilitate obtaining the first farthest point and the length of the first perpendicular line from the first farthest point to the midline of the brain, step S430 can be implemented in several ways.

[0096] For example, the first farthest point of the lateral ventricle's external wall from the midline of the brain can be obtained in an ultrasound image of a transverse section of the lateral ventricle using a combination of manual and automatic methods. In some embodiments, the processor obtaining the first farthest point of the lateral ventricle's external wall from the midline of the brain in the ultrasound image includes: the processor, in response to an operation command for the ultrasound image, obtaining the first farthest point of the lateral ventricle's external wall from the midline of the brain in the ultrasound image. The operation command may be a point marking operation performed by a user in the ultrasound image of a transverse section of the lateral ventricle, and the processor determines the first farthest point based on the point marking operation.

[0097] It is worth mentioning that, in this application, the operation instructions may be generated by detecting the marking operation on the transverse section of the lateral ventricle. This operation includes, but is not limited to, sliding the trackball (a direction indicator similar to a mouse wheel on an ultrasound imaging system) marking, sliding and clicking the mouse marking, the user touching the marking on the touch screen, pressing the up, down, left and right arrow keys on the keyboard marking, etc.

[0098] The processor can also automatically identify the first farthest point of the lateral wall of the lateral ventricle in a transverse section of ultrasound images to obtain the point farthest from the midline of the brain. For example, the processor obtaining the first farthest point of the lateral wall of the lateral ventricle in the ultrasound image to obtain the point farthest from the midline of the brain includes: the processor automatically obtaining the first farthest point of the lateral wall of the lateral ventricle in the ultrasound image to obtain the point farthest from the midline of the brain. By automatically obtaining the first farthest point of the lateral wall of the lateral ventricle in a transverse section of ultrasound images, the error caused by the user marking the first farthest point can be reduced, the accuracy of the first farthest point can be improved, the scenario of the user manually marking the first farthest point can be reduced, mechanical labor can be avoided, the workflow of doctors obtaining the first farthest point can be optimized, and work efficiency can be effectively improved, making the doctor's diagnostic process faster and smoother.

[0099] It should be understood that, in this application, various recognition methods such as machine learning algorithms and deep learning methods can be used to automatically obtain the first farthest point of the lateral wall of the lateral ventricle from the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle.

[0100] In some embodiments, the processor automatically acquires the first farthest point of the lateral wall of the lateral ventricle in the ultrasound image that is farthest from the midline of the brain, including: identifying and acquiring the posterior horn region of the lateral ventricle in the ultrasound image; calculating the distance from each pixel in the posterior horn region of the lateral ventricle to the midline of the brain; and selecting the pixel farthest from the midline of the brain as the first farthest point. For example, the step of training a deep learning model to obtain a pre-trained deep learning model by acquiring the first farthest point of the lateral wall of the lateral ventricle in a two-dimensional image may include: 1. Constructing a training sample database: The training sample database includes a large number of posterior horn region calibration results of fetal cranial cross-sections, which are the masks of the posterior horn region of the lateral ventricle (including the lateral wall of the posterior horn of the lateral ventricle). 2. Precise segmentation: Similar to the process of determining the midline of the brain through a deep learning algorithm, a semantic segmentation network is constructed and the features or patterns used to distinguish the lateral ventricle region in the training sample database are learned, so that the network can acquire the position of all pixels in the posterior horn region of the lateral ventricle in the input image. 3. Steps to determine the location of the farthest point of the lateral ventricle ventricular wall from the brain midline: Based on the location of the brain midline determined above, calculate the distance from the pixel in the posterior horn region of the lateral ventricle to the brain midline, and select the pixel with the largest distance as the first farthest point of the lateral ventricle ventricular wall from the brain midline.

[0101] After generating the first farthest point as described above, a vertical line from the first farthest point to the midline of the brain determined in step S420 is generated using a combination of manual and automatic methods, or automatically. This generated vertical line is the first perpendicular line. Figure 3 The vertical line A is shown in the image. In some embodiments, the processor automatically generates a first vertical line from the first farthest point to the midline of the brain and displays the first vertical line in the ultrasound image.

[0102] The length of the first perpendicular line is determined by measuring it, or the vertical distance from the first farthest point to the midline of the brain is calculated directly, and this vertical distance is the length of the first perpendicular line.

[0103] In addition, to facilitate obtaining the second farthest point and the length of the second perpendicular line from the second farthest point to the midline of the brain, step S440 can be implemented in several ways.

[0104] For example, the second farthest point on the medial side of the skull from the midline of the brain can be obtained in an ultrasound image of a transverse section of the lateral ventricle using a combination of manual and automatic methods. In some embodiments, the processor obtaining the second farthest point on the medial side of the skull from the midline of the brain in the ultrasound image includes: the processor, in response to an operation command for the ultrasound image, obtaining the second farthest point on the medial side of the skull from the midline of the brain in the ultrasound image. The operation command may be a point marking operation performed by a user in the ultrasound image of a transverse section of the lateral ventricle, and the processor determines the second farthest point based on the point marking operation.

[0105] It is worth mentioning that, in this application, the operation instructions may be generated by detecting the marking operation on the transverse section of the lateral ventricle. This operation includes, but is not limited to, sliding the trackball (a direction indicator similar to a mouse wheel on an ultrasound imaging system) marking, sliding and clicking the mouse marking, the user touching the marking on the touch screen, pressing the up, down, left and right arrow keys on the keyboard marking, etc.

[0106] The second farthest point on the medial side of the skull from the midline of the brain can also be obtained in an ultrasound image of a transverse section of the lateral ventricle through automatic identification. For example, the processor obtaining the second farthest point on the medial side of the skull from the midline of the brain in the ultrasound image includes: the processor automatically obtaining the second farthest point on the medial side of the skull from the midline of the brain in the ultrasound image. By automatically obtaining the second farthest point on the medial side of the skull from the midline of the brain in an ultrasound image of a transverse section of the lateral ventricle through the processor, the error caused by the user marking the second farthest point can be reduced, the accuracy of the second farthest point can be improved, the scenario of the user manually marking the second farthest point can be reduced, mechanical labor can be avoided, the workflow of doctors obtaining the second farthest point can be optimized, and work efficiency can be effectively improved, making the doctor's diagnostic process faster and smoother.

[0107] It should be understood that in this application, various identification methods such as machine learning algorithms and deep learning methods can be used to automatically identify the second farthest point on the medial side of the skull from the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle.

[0108] In some embodiments, the processor automatically acquires the second farthest point on the medial side of the skull in the ultrasound image that is farthest from the midline of the brain, including: identifying and acquiring a strong echoic ring region of the brain in the ultrasound image; calculating the distance from each pixel of the inner edge of the strong echoic ring region of the brain to the midline of the brain; and selecting the pixel farthest from the midline of the brain as the second farthest point. That is, in the ultrasound image, the second farthest point refers to the pixel with the maximum distance from the inner edge pixel of the strong echoic ring region of the brain to the midline of the brain. For example, the step of training a deep learning model to obtain a pre-trained deep learning model by acquiring the second farthest point on the medial side of the skull that is farthest from the midline of the brain in a two-dimensional image may include: 1. Constructing a training sample database: The training sample database includes a large number of calibration results of strong echoic ring regions of the brain from cross-sections of the fetal skull, which are the masks of the strong echoic ring regions of the brain. 2. Precise Segmentation Step: Similar to the process of determining the brain midline using deep learning algorithms, a semantic segmentation network is constructed and learns the features or patterns in the training sample database used to distinguish the strong echo loop region of the cranium. This allows the network to acquire the pixel positions of all pixels in the strong echo loop region of the cranium in the input image. 3. Determining the Position of the Farthest Point from the Midline of the Brain at the Middle Edge of the Strong Echo Loop Region: Combining the position of the straight line containing the brain midline determined above, the distance from the pixels at the middle edge of the strong echo loop region of the cranium to the brain midline is calculated. The pixel with the largest distance is selected as the second farthest point on the inner side of the skull from the brain midline.

[0109] After generating the second farthest point as described above, a vertical line from the second farthest point to the brain midline determined in step S420 is generated using a combination of manual and automatic methods, or automatically. This generated vertical line is the second perpendicular line. Figure 3 The vertical line B is shown in the image. In some embodiments, the processor automatically generates a second vertical line from the second farthest point to the midline of the brain and displays the second vertical line in the ultrasound image.

[0110] The length of the generated second perpendicular line is determined by measuring it, or the vertical distance from the second farthest point to the midline of the brain is directly calculated, and this vertical distance is the length of the second perpendicular line.

[0111] It is worth noting that neither a combination of manual and automatic methods nor an automatic method can guarantee that the positions of the first and second farthest points will be absolutely accurate. Therefore, in this application, after obtaining the first and second farthest points, their positions can be adjusted using adjustment commands to make the obtained first and second farthest points as accurate as possible.

[0112] In some embodiments, a first adjustment instruction for adjusting the position of the first farthest point is obtained, and the position of the first farthest point is adjusted based on the first adjustment instruction. The first adjustment instruction may be a point marking operation, coordinate adjustment operation, etc., performed by the user in an ultrasound image of a transverse section of the lateral ventricle. The processor adjusts the position of the first farthest point according to the point marking operation, coordinate adjustment operation, etc. Taking the coordinate adjustment operation as an example, after obtaining the first farthest point in step S430, the user can input adjustment coordinates (X, Y). The first farthest point is displaced by a distance X along the x-axis and a distance Y along the y-axis according to the adjustment coordinates (X, Y), thereby obtaining the adjusted position of the first farthest point.

[0113] In some embodiments, a second adjustment instruction for adjusting the position of the second farthest point is obtained, and the position of the second farthest point is adjusted based on the second adjustment instruction. The second adjustment instruction may be a point marking operation, coordinate adjustment operation, etc., performed by the user in an ultrasound image of a transverse section of the lateral ventricle. The processor adjusts the position of the second farthest point according to the point marking operation, coordinate adjustment operation, etc. Taking the coordinate adjustment operation as an example, after obtaining the second farthest point in step S430, the user can input adjustment coordinates (X, Y). The second farthest point is displaced by a distance X along the x-axis and a distance Y along the y-axis according to the adjustment coordinates (X, Y), thereby obtaining the adjusted position of the second farthest point.

[0114] It is worth mentioning that, in this application, the first adjustment instruction and the second adjustment instruction can be generated by detecting the user's operation, which includes, but is not limited to, point marking operations (such as sliding trackball (a direction indicator similar to a mouse wheel on an ultrasound imaging system) marking, sliding and clicking mouse marking, user hand-touching marking on a touch screen, pressing up, down, left and right arrow keys on a keyboard marking, etc.), data input operations, etc.

[0115] In some embodiments, location markers, such as graphic markers, corresponding to the first farthest point and / or the second farthest point can also be displayed on the ultrasound image so that the user can intuitively observe whether the first farthest point or the second farthest point has shifted.

[0116] In some embodiments, the corresponding lengths may also be displayed around the first vertical line and / or the second vertical line so that the user can visually see the lengths of both, or the lengths of both may be displayed in a concentrated manner in other areas of the ultrasound image.

[0117] Furthermore, after obtaining the lengths of the first and second vertical lines, the ventricular ratio of the fetus can be determined based on these lengths. Assuming the length of the first vertical line is *a* and the length of the second vertical line is *b*, the ventricular ratio of the fetus can be calculated using the following formula:

[0118]

[0119] In some embodiments, to facilitate doctors' intuitive understanding of the ventricular ratio from ultrasound images, the method further includes displaying the ventricular ratio in the ultrasound images.

[0120] After calculating the ventricle ratio, the presence of lateral ventricle abnormalities in the fetus can be determined based on the ventricle ratio. In some embodiments, the processor determines whether the fetus has lateral ventricle abnormalities based on a threshold range of the ventricle ratio, and outputs a prompt message when an abnormality is found in the lateral ventricle. The prompt message can be text, image, sound, or any combination thereof. For example, an abnormality warning image and sound can be output when an abnormality is found in the lateral ventricle. When the image information includes displayable information such as text or images, the prompt message can be displayed on a monitor such as a mobile phone screen or computer screen.

[0121] In some embodiments, the ventricular ratio is defined as the ratio of the distance between the midline of the brain and the lateral wall of the lateral ventricle (i.e., the length of the first vertical line) to the distance between the midline of the brain and the inner surface of the fetal skull (i.e., the length of the second vertical line). The threshold range for the ventricular ratio of a normal fetus also depends on the gestational age of the fetus. This threshold range may vary with different gestational ages. For example, the average ventricular ratio of a normal fetus at 12 weeks of gestation is 0.7, at 15 weeks it is 0.56, and at 30 weeks it is 0.3. Based on this data, the threshold range for the ventricular ratio of a normal fetus at different gestational ages can be determined. The processor then determines whether the fetus has lateral ventricular abnormalities based on the threshold range of the ventricular ratio. More specifically, the processor further includes: acquiring gestational age data of the fetus; acquiring the corresponding threshold range for the ventricular ratio of a normal fetus based on the gestational age data; comparing the ventricular ratio of the fetus being tested with the threshold range; if it falls within the threshold range, it indicates that the ventricular ratio of the fetus is normal, and its lateral ventricles are also normal; if it exceeds the threshold range, it indicates that the lateral ventricles may be abnormal, thereby outputting a prompt message.

[0122] The method for measuring fetal ventricle ratio and the ultrasound imaging system described in this application optimize the doctor's workflow, improve the doctor's work efficiency, and increase the accuracy of the final measured fetal ventricle ratio. The obtained ventricle ratio has good repeatability, providing doctors with a better basis for diagnosing the development of the fetal lateral ventricles.

[0123] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of this application. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of this application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.

[0124] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0126] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0127] Similarly, it should be understood that, in order to streamline this application and aid in understanding one or more of the various inventive aspects, features of this application may sometimes be grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of this application. However, this approach should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with features fewer than all features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0128] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0129] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0130] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules according to the embodiments of this application. This application can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0131] It should be noted that the above embodiments are illustrative of this application and not limiting of it, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0132] The above description is merely a specific embodiment or illustration of the embodiments of this application. The scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. The scope of protection of this application shall be determined by the scope of the claims.

Claims

1. A method for measuring the fetal ventricle ratio, characterized in that, The measurement method is applied to an ultrasound imaging system, the ultrasound imaging system including a processor, and the measurement method includes: The processor acquires ultrasound images of a cross-section of the fetal lateral ventricle; The processor determines the midline of the brain based on the ultrasound image of the transverse section of the lateral ventricle; The processor identifies the posterior horn region of the lateral ventricle in the ultrasound image of the transverse section of the lateral ventricle; calculates the distance from each pixel in the posterior horn region of the lateral ventricle to the midline of the brain; selects the pixel farthest from the midline of the brain as the first farthest point; and obtains the length of the first perpendicular line from the first farthest point to the midline of the brain. The processor automatically acquires the second farthest point on the medial side of the skull from the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle, and acquires the length of the second perpendicular line from the second farthest point to the midline of the brain. Specifically, acquiring the second farthest point on the medial side of the skull from the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle includes: Identify and acquire the region of strong echogenic rings in the cranial cavity within the ultrasound image; Calculate the distance from each pixel of the inner edge of the hyperechoic ring region of the brain to the midline of the brain; The pixel furthest from the brain midline is selected as the second farthest point; The processor determines the ventricle ratio of the fetus based on the length of the first vertical line and the length of the second vertical line; Obtain fetal gestational age data, obtain the corresponding threshold range of ventricular ratio for a normal fetus based on the gestational age data, compare the fetal ventricular ratio with the threshold range, and output a prompt message when the fetal ventricular ratio exceeds the threshold range.

2. The measurement method as described in claim 1, characterized in that, The processor determines the midline of the brain based on the ultrasound image of the transverse section of the lateral ventricle, including: The processor, in response to an operation command for the ultrasound image, determines the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle; or The processor determines the midline of the brain in the ultrasound image of the transverse section of the lateral ventricle using an intelligent recognition method.

3. The measurement method according to any one of claims 1 to 2, characterized in that, The measurement method further includes: The processor automatically generates a first perpendicular line from the first farthest point to the midline of the brain. The first vertical line is displayed in the ultrasound image; and / or The processor automatically generates a second perpendicular line from the second farthest point to the midline of the brain. The second vertical line is shown in the ultrasound image.

4. The measurement method according to any one of claims 1 to 2, characterized in that, The measurement method further includes: The ultrasound image displays the brain midline and / or the ventricular ratio.

5. The measurement method according to any one of claims 1 to 2, characterized in that, The measurement method further includes: Obtain a first adjustment instruction for adjusting the position of the first farthest point, and adjust the position of the first farthest point based on the first adjustment instruction; and / or Obtain a second adjustment instruction for adjusting the position of the second farthest point, and adjust the position of the second farthest point based on the second adjustment instruction.

6. The measurement method according to any one of claims 1 to 2, characterized in that, The measurement method further includes: The aforementioned prompt message will be displayed.

7. An ultrasound imaging system, characterized in that, The ultrasound imaging system includes: Ultrasonic probe; A transmitting circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fetus; A receiving circuit is used to receive ultrasound echoes based on ultrasound waves returned from the fetus, and to obtain an ultrasound echo signal; The processor is configured to: obtain an ultrasound image of a cross-section of the lateral ventricle of the fetus based on the ultrasound echo signal; The processor is also used to perform the method for measuring the fetal ventricle ratio as described in any one of claims 1 to 6; A monitor is used to display various visual information.

Images