Automatic measurement method of bile volume, ultrasonic imaging system and storage medium

Abstract

The present application provides an automatic measurement method for bile capacity, an ultrasonic imaging system and a storage medium, the method comprising: automatically collecting gallbladder ultrasonic images at multiple measurement time points by fixing an ultrasonic probe at the position of the gallbladder on the patient's body surface; segmenting the gallbladder area in the gallbladder ultrasonic image; determining the gallbladder volume according to the segmented gallbladder area, thereby determining the bile capacity. The solution of the present application can regularly collect gallbladder ultrasonic images and determine the bile capacity, reduce user operations, and improve the accuracy of bile capacity measurement.

Description

Technical Field

[0001] The present application relates to the technical field of ultrasonic imaging, and more specifically to an automatic measurement method for bile capacity, an ultrasonic imaging system and a storage medium. Background Art

[0002] The accurate measurement of bile volume is of great value in evaluating the contractile and diastolic function of the gallbladder, studying the causes of gallstones or other diseases of the gallbladder, etc. Ultrasonic diagnosis has become one of the most widely used and frequently used methods for measuring bile volume because of its advantages of being non-invasive, radiation-free, convenient to examine, real-time imaging, and suitable for reexamination.

[0003] In actual diagnosis, doctors usually need to measure bile volume multiple times at fixed time intervals within a certain period of time in order to evaluate the bile excretion status. Current ultrasound equipment can only provide doctors with the function of manually measuring bile volume. Each time the bile volume is manually measured, the doctor needs to first capture the image, then freeze the image, select the appropriate image frame, and then calculate the bile volume. The operation steps are very cumbersome, especially for multiple measurements in a short period of time. Moreover, since the measurement needs to be fully manual, the doctor may not be able to measure the bile volume on time every time, resulting in deviations in the measurement time. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further described in detail in the Detailed Description of the Invention section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] A first aspect of an embodiment of the present application provides an automatic measurement method for bile capacity, the method comprising: automatically and regularly acquiring gallbladder ultrasound images at multiple measurement time points using an ultrasound probe fixed at the gallbladder position on the patient's body surface; segmenting a gallbladder area from the gallbladder ultrasound image; and determining the gallbladder volume based on the segmented gallbladder area, thereby determining the bile capacity.

[0006] In one embodiment, the method further comprises: generating a variation curve of bile capacity over time according to the bile capacity measured at the plurality of measurement time points; and outputting the variation curve.

[0007] In one embodiment, the method further comprises: when the bile capacity exceeds a threshold, outputting a prompt message.

[0008] In one embodiment, the timed automatic acquisition of gallbladder ultrasound images at multiple measurement time points includes: automatically acquiring the gallbladder ultrasound image once at each of the measurement time points; or continuously acquiring gallbladder ultrasound video images over a period of time, and extracting the gallbladder ultrasound images at the multiple measurement time points from the gallbladder ultrasound video images.

[0009] In one embodiment, the gallbladder ultrasound image is a two-dimensional gallbladder ultrasound image or a three-dimensional gallbladder ultrasound image.

[0010] In one embodiment, the timed automatic acquisition of gallbladder ultrasound images at multiple measurement time points includes: acquiring one frame of the two-dimensional gallbladder ultrasound image or one volume of the three-dimensional gallbladder ultrasound image at each measurement time point; or acquiring multiple frames of the two-dimensional gallbladder ultrasound image or multiple volumes of the three-dimensional gallbladder ultrasound image around each measurement time point.

[0011] In one embodiment, when multiple frames of the two-dimensional gallbladder ultrasound images or multiple volumes of the three-dimensional gallbladder ultrasound images are acquired around each of the measurement time points, segmenting the gallbladder region in the gallbladder ultrasound images includes: segmenting the gallbladder region in the multiple frames of the two-dimensional gallbladder ultrasound images, and selecting the gallbladder region of one of the two-dimensional gallbladder ultrasound images according to a predetermined criterion for determining the gallbladder volume; or, segmenting the gallbladder region in the multiple volumes of the three-dimensional gallbladder ultrasound images, and selecting the gallbladder region of one of the three-dimensional gallbladder ultrasound images according to a predetermined criterion for determining the gallbladder volume.

[0012] In one embodiment, selecting the gallbladder region of one frame of the two-dimensional gallbladder ultrasound image according to a predetermined criterion for determining the gallbladder volume includes: selecting the gallbladder region with the largest area among the segmented gallbladder regions for determining the gallbladder volume.

[0013] In one embodiment, selecting the gallbladder region of one of the three-dimensional gallbladder ultrasound images according to a predetermined criterion for determining the gallbladder volume includes: selecting the gallbladder region having the largest three-dimensional gallbladder contour among the segmented gallbladder regions for determining the gallbladder volume.

[0014] In one embodiment, when multiple frames of the two-dimensional gallbladder ultrasound images or multiple volumes of the three-dimensional gallbladder ultrasound images are acquired around each of the measurement time points, the method further includes: using a machine learning algorithm to score the degree of standardization of each frame of the two-dimensional gallbladder ultrasound image or each volume of the three-dimensional gallbladder ultrasound image, and selecting the frame of the two-dimensional gallbladder ultrasound image or the volume of the three-dimensional gallbladder ultrasound image with the highest score for segmenting the gallbladder region.

[0015] In one embodiment, the use of a machine learning algorithm to score the degree of standardization of each frame of the two-dimensional gallbladder ultrasound image or each volume of the three-dimensional gallbladder ultrasound image includes: constructing a database, the database containing multiple gallbladder regions and a score of the degree of standardization of each gallbladder region; using the database to train a machine learning algorithm so that the machine learning algorithm can extract features of the gallbladder region associated with the score; using the trained machine learning algorithm to extract features of the gallbladder region in the gallbladder ultrasound image, and using a classifier to classify the extracted features to obtain a score of the degree of standardization of the gallbladder ultrasound image.

[0016] In one embodiment, segmenting the gallbladder region in the gallbladder ultrasound image includes: automatically segmenting the gallbladder region in the gallbladder ultrasound image; or interactively segmenting the gallbladder region in the gallbladder ultrasound image in combination with user input.

[0017] In one embodiment, automatically segmenting the gallbladder region in the gallbladder ultrasound image includes: automatically segmenting the gallbladder region in the gallbladder ultrasound image using an image segmentation algorithm.

[0018] In one embodiment, the automatic segmentation of the gallbladder area in the gallbladder ultrasound image includes: extracting features from image blocks in a predetermined neighborhood around each pixel point in the gallbladder ultrasound image; classifying the extracted features using a classifier to determine the category of the image block corresponding to the feature; and dividing the pixel points corresponding to the image block into pixel points of the gallbladder area or pixel points of the background area according to the category of the image block, thereby dividing the gallbladder ultrasound image into the gallbladder area and the background area.

[0019] In one embodiment, automatically segmenting the gallbladder region in the gallbladder ultrasound image includes: segmenting the gallbladder region in the gallbladder ultrasound image using a trained deep learning neural network.

[0020] In one embodiment, the interactively segmenting the gallbladder region in the gallbladder ultrasound image in combination with user input includes: determining a preliminary segmentation range in the gallbladder ultrasound image according to a user's frame selection operation; and automatically segmenting the gallbladder region within the preliminary segmentation range.

[0021] In one embodiment, the interactively segmenting the gallbladder region in the gallbladder ultrasound image in combination with user input includes: segmenting the gallbladder region using an interactive segmentation algorithm according to points or lines drawn by the user on the gallbladder region.

[0022] In one embodiment, when the gallbladder ultrasound image is a two-dimensional gallbladder ultrasound image, determining the gallbladder volume based on the segmented gallbladder region includes: identifying two mutually perpendicular radial lines in the gallbladder region; and determining the gallbladder volume based on the two mutually perpendicular radial lines.

[0023] In one embodiment, when the gallbladder ultrasound image is a three-dimensional gallbladder ultrasound image, determining the gallbladder volume according to the segmented gallbladder region includes: determining the gallbladder volume according to a three-dimensional contour of the gallbladder segmented in the gallbladder ultrasound image.

[0024] In one embodiment, the method further comprises: determining the measurement time point or the time interval between adjacent measurement time points according to user input.

[0025] A second aspect of an embodiment of the present application provides an automatic measurement method for bile capacity, comprising:

[0026] By using an ultrasound probe fixed at the gallbladder position on the patient's body surface, the gallbladder ultrasound images at multiple measurement time points are automatically acquired;

[0027] determining a gallbladder region in the gallbladder ultrasound image;

[0028] The gallbladder volume is determined based on the determined gallbladder area, thereby determining the bile capacity.

[0029] A third aspect of an embodiment of the present application provides an ultrasound imaging system, comprising: an ultrasound probe, which can be fixed on the surface of a patient's body at the location of the gallbladder; a transmitting circuit, used to excite the probe to transmit ultrasound waves to the patient's gallbladder region at a certain time at a plurality of measurement time points; a receiving circuit, used to control the probe to receive ultrasound echoes returned from the gallbladder region to obtain ultrasound echo signals; a processor, used to: process the ultrasound echo signals to obtain gallbladder ultrasound images at the plurality of measurement time points; segment the gallbladder region in the gallbladder ultrasound image; determine the gallbladder volume based on the segmented gallbladder region, thereby determining the bile capacity; and a memory, used to store a program executed by the processor.

[0030] In one embodiment, the ultrasound imaging system further includes: a display for displaying the gallbladder ultrasound image.

[0031] In one embodiment, the processor is further used to: generate a variation curve of bile capacity over time according to the bile capacity measured at a plurality of measurement time points; and the display is further used to display the variation curve.

[0032] A fourth aspect of the embodiments of the present application provides an ultrasound imaging system, comprising:

[0033] An ultrasound probe, which can be fixed on the patient's body surface at the location of the gallbladder;

[0034] A transmitting circuit, used for stimulating the probe to transmit ultrasonic waves to the gallbladder area of ​​the patient at multiple measurement time points;

[0035] A receiving circuit, used for controlling the probe to receive the ultrasonic echo returned from the gallbladder area to obtain an ultrasonic echo signal;

[0036] Processor for:

[0037] Processing the ultrasonic echo signal to obtain the gallbladder ultrasonic images at the multiple measurement time points;

[0038] determining a gallbladder region in the gallbladder ultrasound image;

[0039] The gallbladder volume is determined based on the determined gallbladder area, thereby determining the bile capacity.

[0040] A fifth aspect of an embodiment of the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a computer or a processor, the steps of the method described in the first aspect of the embodiment of the present application are implemented.

[0041] The automatic bile capacity measurement method, ultrasound imaging system and storage medium according to the embodiments of the present application can regularly acquire gallbladder ultrasound images and determine the bile capacity, thereby reducing user operations and improving the accuracy of bile capacity measurement. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0043] Figure 1 A schematic block diagram of an ultrasound imaging system according to an embodiment of the present application is shown;

[0044] Figure 2 A schematic flow chart showing a method for automatically measuring bile capacity according to an embodiment of the present application;

[0045] Figure 3 A schematic flow chart showing a method for automatically measuring bile capacity according to another embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present application more obvious, the example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the scope of protection of the present application.

[0047] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present application. However, it is apparent to those skilled in the art that the present application can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present application, some technical features well known in the art are not described.

[0048] It should be understood that the present application can be implemented in different forms and should not be interpreted as being limited to the embodiments set forth herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0049] The purpose of the terms used herein is only to describe specific embodiments and is not intended to be limiting of the present application. When used herein, the singular forms "one", "an" and "said / the" are also intended to include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "consisting of" and / or "comprising", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0050] In order to thoroughly understand the present application, a detailed structure will be proposed in the following description to illustrate the technical solution proposed by the present application. The optional embodiments of the present application are described in detail as follows, but in addition to these detailed descriptions, the present application may also have other implementation methods.

[0051] Next, first refer to Figure 1 An ultrasound imaging system according to an embodiment of the present application is described. Figure 1 A schematic structural block diagram of an ultrasound imaging system 100 according to an embodiment of the present application is shown.

[0052] like Figure 1As shown, the ultrasound imaging system 100 includes an ultrasound probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 118, a display 120, and a memory 124. Further, the ultrasound imaging system may also include a beamforming circuit 116 and a transmit / receive selection switch 122, and the transmitting circuit 112 and the receiving circuit 114 may be connected to the ultrasound probe 110 through the transmit / receive selection switch 122.

[0053] Among them, the ultrasonic probe 110 generally includes an array of multiple array elements. Each time an ultrasonic wave is emitted, all or part of the array elements of the ultrasonic probe 110 participate in the emission of the ultrasonic wave. At this time, each array element or each part of the array elements participating in the ultrasonic emission is excited by the emission pulse and emits an ultrasonic wave respectively. The ultrasonic waves emitted by these array elements are superimposed during the propagation process to form a synthetic ultrasonic beam emitted to the target object. In the embodiment of the present application, the synthetic ultrasonic beam is the ultrasonic wave emitted to the gallbladder part of the target object. The ultrasonic probe 100 can be fixed at the gallbladder position on the patient's body surface by a fixing device.

[0054] The transmit / receive selection switch 122 may also be referred to as a transmit / receive controller, which may include a transmit controller and a receive controller. The transmit controller is used to stimulate the ultrasound probe 110 to transmit ultrasonic waves to the target object (e.g., the human body) via the transmit circuit 112 at regular intervals; the receive controller is used to receive ultrasonic echoes returned from the target object via the receive circuit 114 through the ultrasound probe 110.

[0055] The processor 118 can obtain an ultrasonic echo signal based on the ultrasonic echo, and process the ultrasonic echo signal to obtain a gallbladder ultrasonic image of the target object. For example, the ultrasonic echo signal is processed by a beamforming module. The gallbladder ultrasonic image obtained by the processor 118 can be stored in a memory. In addition, the gallbladder ultrasonic image can be displayed on the display 120. For a more detailed description, please refer to the subsequent embodiments of this specification.

[0056] The display 120 is connected to the processor 118, and the display 120 may be a touch screen, a liquid crystal display, etc.; or the display 120 may be an independent display device such as a liquid crystal display, a television, etc., which is independent of the ultrasound data processing system 100; or the display 120 may be a display screen of an electronic device such as a smart phone, a tablet computer, etc. The number of the displays 120 may be one or more. For example, the display 120 may include a main screen and a touch screen, wherein the main screen is mainly used to display ultrasound images, and the touch screen is mainly used for human-computer interaction.

[0057] The display 120 can display the gallbladder ultrasound image obtained by the processor 118. The display 120 can also display a curve of bile capacity changing over time. In addition, while displaying the ultrasound image, the display 120 can also provide the user with a graphical interface for human-computer interaction, and one or more controlled objects are set on the graphical interface, providing the user with a human-computer interaction device to input operation instructions to control these controlled objects, thereby performing corresponding control operations. For example, an icon is displayed on the graphical interface, and the icon can be operated using the human-computer interaction device to perform a specific function, such as drawing points, lines or boxes on the gallbladder ultrasound image to interactively segment the gallbladder area in the gallbladder ultrasound image.

[0058] Optionally, the ultrasound data processing system 100 may further include other human-computer interaction devices in addition to the display 120, which are connected to the processor 118. For example, the processor 118 may be connected to the human-computer interaction device via an external input / output port, and the external input / output port may be a wireless communication module, or a wired communication module, or a combination of the two. The external input / output port may also be implemented based on USB, bus protocols such as CAN, and / or wired network protocols.

[0059] The human-computer interaction device may include an input device for detecting user input information, which may be, for example, a control instruction for ultrasound transmission / reception timing, an operation input instruction for drawing points, lines or frames on a gallbladder ultrasound image, or other instruction types. The input device may include a keyboard, a mouse, a scroll wheel, a trackball, a mobile input device (such as a mobile device with a touch screen, a mobile phone, etc.), a multi-function knob, etc., or a combination of multiple thereof. The human-computer interaction device may also include an output device such as a printer.

[0060] The memory 124 may be used to store instructions executed by the processor, to store received ultrasound echoes, to store ultrasound images, etc. The memory 124 may be a flash memory card, a solid-state memory, a hard disk, etc. It may be a volatile memory and / or a non-volatile memory, a removable memory and / or a non-removable memory, etc.

[0061] Optionally, the processor 118 in the ultrasound data processing system 100 can be implemented by software, hardware, firmware or any combination thereof, and can use circuits, single or multiple application-specific integrated circuits (ASICs), single or multiple general-purpose integrated circuits, single or multiple microprocessors, single or multiple programmable logic devices, or any combination of the aforementioned circuits and / or devices, or other suitable circuits or devices, so that the processor 118 can execute the corresponding steps of the methods in the various embodiments of the present specification.

[0062] It should be understood that Figure 1 The components included in the ultrasound data processing system 100 are only exemplary, and the system may include more or fewer components, which is not limited in the present application.

[0063] Next, we will refer to Figure 2 The automatic measurement method of bile capacity according to an embodiment of the present application is described. Figure 2 It is a schematic flow chart of the automatic bile capacity measurement method 200 according to an embodiment of the present application.

[0064] like Figure 2 As shown, the method 200 includes the following steps:

[0065] In step S210, an ultrasound probe fixed at the position of the gallbladder on the patient's body surface is used to automatically and regularly collect ultrasound images of the gallbladder at multiple measurement time points.

[0066] The ultrasound probe can be fixed to the patient's gallbladder in any suitable manner to transmit ultrasound to the patient's gallbladder. For example, the ultrasound probe can be fixed to the patient's body surface by a fixing device such as a bracket, or can be directly attached to the patient's body surface.

[0067] For example, in combination Figure 1 In step S210, the transmit / receive selection switch 122 may stimulate the ultrasonic probe 110 to transmit ultrasonic waves to the gallbladder of the target object (e.g., human body) via the transmitting circuit 112 at a fixed time, and the ultrasonic probe 110 may receive the ultrasonic echoes returned from the gallbladder of the target object via the receiving circuit 114 and convert them into ultrasonic echo signals. The beamforming module 116 may perform signal processing, and then send the beamformed ultrasonic echo data to the processor 118 for related processing, thereby obtaining a gallbladder ultrasonic image.

[0068] According to different imaging modes required by the user, the processor 118 can process the ultrasound echo signal differently to obtain ultrasound data of different modes, such as two-dimensional ultrasound data or three-dimensional ultrasound data. Then, after logarithmic compression, dynamic range adjustment, digital scan conversion and other processing, ultrasound image data of different modes are formed, such as two-dimensional gallbladder ultrasound image data including B image, C image, D image, etc., and three-dimensional gallbladder ultrasound image data that can be sent to a display device for three-dimensional image or spatial stereoscopic image display.

[0069] In step S210, there are multiple ways to determine the measurement time point. For example, the specific time of multiple measurement time points preset by the user may be received, such as 9:00, 9:05, 9:10, etc.; or the time interval between adjacent measurement time points preset by the user may be received, such as a measurement time point every 5 minutes. At this time, the measurement start time, measurement number or measurement time period set by the user may also be received, such as starting from 9:00, collecting 10 times in total, or collecting for 50 minutes in total, etc.

[0070] In an embodiment of the present application, the timed automatic acquisition of the gallbladder ultrasound images at multiple measurement time points may be to automatically acquire the gallbladder ultrasound image once at each of the measurement time points, for example, to perform a scan every 5 minutes; or, it may be to continuously acquire the gallbladder ultrasound video image over a period of time, and to extract the gallbladder ultrasound images at multiple measurement time points from the gallbladder ultrasound video image, for example, to acquire a 50-minute ultrasound video image, and to extract therefrom a plurality of two-dimensional gallbladder ultrasound images or three-dimensional gallbladder ultrasound images at preset measurement time points.

[0071] Taking a two-dimensional gallbladder ultrasound image as an example, a frame of a two-dimensional gallbladder ultrasound image can be automatically acquired at each measurement time point, or a frame of a two-dimensional gallbladder ultrasound image can be extracted from an ultrasound video image. Since a two-dimensional gallbladder ultrasound image shows a section of the gallbladder, and the gallbladder section acquired at the measurement time point may not be a standard long-axis section of the gallbladder, a non-standard section may lead to an erroneous measurement result. Therefore, in one embodiment, multiple frames of two-dimensional gallbladder ultrasound images can be acquired or extracted within a period of time around the measurement time point, so as to select a frame of the most standard section for subsequent bile volume measurement.

[0072] For three-dimensional gallbladder ultrasound images, one or more volumes of three-dimensional gallbladder ultrasound images can also be automatically collected at each measurement time point. The three-dimensional gallbladder ultrasound image can be collected by a volume probe, or it can be reconstructed based on the Freehand three-dimensional ultrasound reconstruction technology using a convex array or linear array probe with a magnetic navigation device, or it can be scanned by an area array probe, and this application does not limit this. Alternatively, as described above, multiple volumes of three-dimensional images can be continuously scanned over a period of time, that is, one four-dimensional image, that is, a three-dimensional ultrasound video image. Afterwards, one or more volumes of three-dimensional gallbladder ultrasound images are extracted at each measurement time point for the measurement of bile capacity.

[0073] In one embodiment, each time a gallbladder ultrasound image is obtained at a measurement time point, subsequent steps S220 and S230 are executed to segment the gallbladder region and calculate the bile capacity, so that the interval time can be effectively utilized and prompt information can be generated in time when the bile capacity exceeds the threshold. Of course, in other embodiments, the subsequent steps can also be executed after all gallbladder ultrasound images are obtained.

[0074] In step S220, a gallbladder region is segmented from the gallbladder ultrasound image.

[0075] Among them, when the gallbladder ultrasound image is a two-dimensional gallbladder ultrasound image, the gallbladder area segmented in the gallbladder ultrasound image refers to the gallbladder section in the two-dimensional gallbladder ultrasound image. When the gallbladder ultrasound image is a three-dimensional gallbladder ultrasound image, the gallbladder area segmented in the gallbladder ultrasound image refers to the three-dimensional contour of the gallbladder in the three-dimensional gallbladder ultrasound image. Generally speaking, a normal gallbladder has clear contours, smooth and neat cystic walls, no echoes in the cystic cavity, and enhanced posterior echoes in the ultrasound image. The gallbladder area is generally a typical cystic structure, with a pear-shaped longitudinal section and a circular or elliptical cross-section.

[0076] In one embodiment, the gallbladder region in the gallbladder ultrasound image can be segmented fully automatically, thereby reducing user operations and eliminating the need for the user to wait beside the patient during the entire measurement process.

[0077] As an example, whether for the segmentation of a two-dimensional gallbladder ultrasound image or a three-dimensional gallbladder ultrasound image, the automatic segmentation method may include but is not limited to the following:

[0078] The first segmentation method is to automatically segment the gallbladder region in the gallbladder ultrasound image using an image segmentation algorithm, wherein the image segmentation algorithm may include various applicable image segmentation algorithms such as a Snake algorithm, a Graph Cut algorithm, a Level Set algorithm, and a Random Walker algorithm.

[0079] The second segmentation method is an image segmentation method based on machine learning, which specifically includes: first, using a machine learning method to extract features from image blocks in a predetermined neighborhood around each pixel point in the gallbladder ultrasound image. The feature extraction method used can be traditional PCA (principal component analysis), LDA (linear discriminant analysis), Harr feature extraction, texture feature extraction, etc., or a deep neural network can be used for feature extraction; then, the extracted features are matched with the features in a pre-constructed database, and the extracted features are classified using classifiers such as KNN (K-nearest neighbor classifier), SVM (support vector machine), random forest, neural network, etc. to determine the category of the image block corresponding to the feature, that is, the image block is divided into an image block of the gallbladder area or an image block of the background area according to the feature of the image block; then, according to the category of the image block, the pixel points corresponding to the image block are divided into pixel points of the gallbladder area or pixel points of the background area, thereby dividing the gallbladder ultrasound image into the gallbladder area and the background area.

[0080] The third segmentation method is an end-to-end semantic segmentation network method based on deep learning. This type of method uses a trained deep learning neural network to segment the gallbladder area in the gallbladder ultrasound image. This type of method learns the features of a pre-built database by stacking convolutional layers and fully connected layers, and adds upsampling or deconvolution layers to make the input and output sizes the same, so as to directly obtain the region of interest (i.e., gallbladder area) of the input image and its corresponding category. The deep learning networks used include FCN (Fully Convolutional Neural Network), U-Net (U-Net), Mask R-CNN (Mask Candidate Region Neural Network), etc.

[0081] In another embodiment, the segmentation range can be narrowed in a semi-automatic manner, or more accurate segmentation can be guided according to user input. In the segmentation process, adding user interaction as algorithm input can enable objects with high-level semantics in the image to be completely extracted.

[0082] For example, the preliminary segmentation range can be determined in the gallbladder ultrasound image according to the user's frame selection operation, that is, the user can draw a ROI (region of interest) frame on the user interaction interface so that the gallbladder area is included in the ROI frame, and the ROI frame includes but is not limited to a rectangular frame; then, the gallbladder area is automatically segmented within the preliminary segmentation range, and the automatic segmentation includes but is not limited to the above three automatic segmentation methods.

[0083] For another example, another interactive segmentation method may include: the user draws some points or lines on the gallbladder region, and the gallbladder region is segmented using an interactive segmentation algorithm based on the points or lines drawn by the user on the gallbladder region. For example, the interactive segmentation algorithm obtains the points or lines drawn by the user as input, and automatically establishes a weighted graph of the similarity between each pixel and the foreground or background, and distinguishes the foreground and background by solving the minimum cut. The interactive segmentation algorithm includes but is not limited to Graph Cut, Random Walker, etc.

[0084] As described above, in step S210, one or more frames of two-dimensional gallbladder ultrasound images, or one or more volumes of three-dimensional gallbladder ultrasound images, may be collected at each measurement time point. When only one frame of two-dimensional gallbladder ultrasound image or one volume of three-dimensional gallbladder ultrasound image is collected at each measurement time point, the gallbladder ultrasound image may be directly segmented as described above to obtain the gallbladder region therein. When multiple frames of two-dimensional gallbladder ultrasound images or multiple volumes of three-dimensional gallbladder ultrasound images are collected around each measurement time point, one frame or one volume of better gallbladder ultrasound images is automatically selected therefrom for subsequent calculation of bile volume.

[0085] In one embodiment, when selecting the gallbladder ultrasound image, all gallbladder ultrasound images obtained at each time point may be segmented, and selection may be made based on the segmentation results.

[0086] Taking a two-dimensional gallbladder ultrasound image as an example, when multiple frames of two-dimensional gallbladder ultrasound images are collected around each measurement time point, the gallbladder region can be segmented out in the multiple frames of two-dimensional gallbladder ultrasound images, and the gallbladder region of one frame of the image can be selected according to a predetermined standard to determine the gallbladder volume. Among them, since the long axis section of the gallbladder is the section with the largest gallbladder display among all sections, the gallbladder region with the largest area among the segmented gallbladder regions can be selected to determine the gallbladder volume.

[0087] Taking a three-dimensional gallbladder ultrasound image as an example, when multiple volumes of three-dimensional gallbladder ultrasound images are collected around each measurement time point, the gallbladder region can be segmented out in the multiple volumes of three-dimensional gallbladder ultrasound images, and the gallbladder region of one of the volumes of images can be selected according to a predetermined standard for determining the gallbladder volume. Similarly, the selection standard of the three-dimensional gallbladder ultrasound image can also be to select the gallbladder region with the largest gallbladder three-dimensional contour among the segmented gallbladder regions for determining the gallbladder volume, for example, calculating the volumes of all gallbladder three-dimensional contours, and taking the largest volume as the final calculation result.

[0088] In another embodiment, a machine learning algorithm may be used to score each frame of a two-dimensional gallbladder ultrasound image or each volume of a three-dimensional gallbladder ultrasound image, and the gallbladder ultrasound image with the highest score is selected for segmentation. In this method, it is not necessary to segment all gallbladder ultrasound images, thereby increasing the calculation speed.

[0089] Specifically, using a machine learning algorithm to score gallbladder ultrasound images may include the following steps:

[0090] First, a database is constructed, which contains multiple gallbladder regions and the standard degree scores of each gallbladder region. Among them, multiple gallbladder region images can be collected in advance and manually scored by the user. The scoring criteria may include: whether the gallbladder collected in the image is complete, whether the gallbladder section in the image is the largest section of the gallbladder, whether there is no interference from other tissues or large blood vessels in the image, etc. The scoring criteria may also include image quality, for example, images with rich grayscale, high contrast, and delicate structure have better quality and correspondingly higher scores.

[0091] After the database is constructed, the database can be used to train a machine learning algorithm so that the machine learning algorithm can extract features of the gallbladder region associated with the score. The feature extraction method can be traditional PCA, LDA, Harr feature extraction, texture feature extraction, etc., or a deep neural network such as a VGG model, MobileNet (mobile neural network), or ResNet (residual network) can be used for feature extraction.

[0092] Next, the trained machine learning algorithm is used to extract features of the gallbladder region in the gallbladder ultrasound image, and the extracted features are classified using a classifier, that is, the extracted features are matched with the database to obtain a standard degree score of the gallbladder ultrasound image. Among them, various suitable classifiers such as KNN, SVM, random forest, neural network, etc. can be used for classification.

[0093] According to the scores of multiple frames of two-dimensional gallbladder ultrasound images or multiple volumes of three-dimensional gallbladder ultrasound images at each measurement time point, the gallbladder ultrasound image with the highest score can be selected for segmentation to ensure the accuracy of subsequent measurement results.

[0094] In step S230, the gallbladder volume is determined according to the segmented gallbladder region, thereby determining the bile capacity.

[0095] If a two-dimensional gallbladder ultrasound image is acquired in step S210, two vertical radial lines can be automatically measured in the gallbladder section segmented in step S220, and the gallbladder is assumed to be a certain approximate regular set shape, such as an ellipsoid or a cone, and then the corresponding empirical formula is used to estimate the gallbladder volume, thereby obtaining the bile capacity.

[0096] If the three-dimensional gallbladder ultrasound image is acquired in step S210, the gallbladder volume can be calculated based on the three-dimensional contour of the gallbladder segmented in step S220, thereby obtaining the bile capacity. For example, the volume measurement software provided by the ultrasound imaging system can be used to obtain the gallbladder volume based on the three-dimensional contour of the gallbladder. When measuring the gallbladder volume based on the three-dimensional contour of the gallbladder, the volume of all pixels in the three-dimensional contour of the gallbladder can be directly accumulated, which is less affected by the geometric shape, so the measurement result is more accurate.

[0097] In one embodiment, the method 200 further includes: generating a change curve of the bile capacity over time from the bile capacity measured at the multiple measurement time points, that is, combining the bile capacity measured at each measurement time point according to the time dimension. Afterwards, the change curve is output, for example, the change curve is displayed on the display 120 or the change curve is added to the inspection report. The change curve can be a line graph such as a curve graph or a line graph, but can also be a bar graph or other forms of graphs, as long as it can reflect the change relationship of the bile capacity over time.

[0098] In one embodiment, the method 200 further includes: when the bile capacity exceeds a threshold, outputting a prompt message. The prompt message may include information displayed on a display interface, or may include sound prompt information, which is not limited in this embodiment of the present application.

[0099] Next, combine Figure 2 For the example shown, see Figure 3 , describing the automatic measurement method of bile capacity according to an embodiment of the present application. Figure 3 It is a schematic flow chart of the automatic bile capacity measurement method 300 according to an embodiment of the present application.

[0100] like Figure 3 As shown, the method 300 includes the following steps:

[0101] In step 310, an ultrasound probe fixed at the position of the gallbladder on the patient's body surface is used to automatically acquire gallbladder ultrasound images at multiple measurement time points.

[0102] There are many ways to automatically acquire gallbladder ultrasound images at multiple measurement time points. In addition to the above-mentioned method of automatically acquiring gallbladder ultrasound images at multiple measurement time points, other methods may also be used. For example, a large number of gallbladder ultrasound images are first acquired continuously or discontinuously, and then the gallbladder ultrasound images at the multiple measurement times are determined among the large number of gallbladder ultrasound images. The multiple measurement time points may be determined after the image acquisition or before the image acquisition, and may be determined by user definition or by system default, which is not specifically limited here. Regarding the determination of the gallbladder ultrasound images at multiple measurement times, which is the same or similar to the above-mentioned step S210, please refer to the description in the above-mentioned step S210 for details, which will not be repeated here.

[0103] In step 320, a gallbladder region is determined in the gallbladder ultrasound image.

[0104] There are many ways to determine the gallbladder area in the gallbladder ultrasound image. In addition to the above-mentioned determination based on segmentation, there may be other ways, such as determining the approximate gallbladder area in the gallbladder ultrasound image by fitting, etc., which are not specifically limited here.

[0105] The specific process of fitting can be: taking the ultrasound image as a two-dimensional ultrasound image as an example, the gallbladder includes some key structural positions, therefore, these key structural positions are detected in the ultrasound image, for example, if three non-collinear key structural positions in the ultrasound image are known, a plane where the three points are located can be determined according to three non-collinear points in space, and the mathematical equation of the plane can be solved to obtain the gallbladder region; for another example, if multiple (greater than three) key structural positions in the ultrasound image are known, a plane equation can be fitted by a fitting method to obtain the gallbladder region, and there are many fitting methods, such as least squares estimation, Hough transform, etc. In this embodiment, the section adopts the expression of the plane equation, and other equivalent expressions can also be used, such as a point in space plus a normal vector can also represent the section. In addition, the gallbladder region in a multi-dimensional ultrasound image of more than two dimensions can be fitted based on a similar method (for example, the key structural position of the gallbladder in space), which will not be repeated here.

[0106] Of course, the method of determining the gallbladder area in the gallbladder ultrasound image is the same or similar to the above step S220. For details, please refer to the description of the above step S220, which will not be repeated here.

[0107] In step 330, the gallbladder volume is determined according to the determined gallbladder area, thereby determining the bile capacity.

[0108] The process of determining the gallbladder volume according to the determined gallbladder area, thereby determining the bile capacity, is identical or similar to the above step S230. For details, please refer to the description of the above step S230, which will not be repeated here.

[0109] Based on the above description, the automatic bile capacity measurement method according to the embodiment of the present application regularly acquires gallbladder ultrasound images and determines the bile capacity, which reduces user operations and improves the accuracy of bile capacity measurement.

[0110] Now re-refer to Figure 1 The embodiment of the present application further provides an ultrasound imaging system 100, which can be used to implement the above method 200 or method 300. The ultrasound imaging system 100 may include an ultrasound probe 110, a transmitting circuit 112, a receiving circuit 114, a beamforming module 116, a processor 118, a display 120, a transmitting / receiving selection switch 122, and some or all of the components in the memory 124. The relevant description of each component can refer to the above. The following only describes the main functions of the ultrasound imaging system 100, and omits the details described above.

[0111] Among them, the ultrasonic probe 110 can be fixed on the patient's body surface at the gallbladder position; the transmitting circuit 112 is used to stimulate the ultrasonic probe 110 to transmit ultrasonic waves to the patient's gallbladder area at multiple measurement time points; the receiving circuit 114 is used to control the ultrasonic probe 110 to receive the ultrasonic echo returned from the gallbladder area to obtain an ultrasonic echo signal; the processor 118 is used to: process the ultrasonic echo signal to obtain the gallbladder ultrasonic image at the multiple measurement time points; segment the gallbladder area in the gallbladder ultrasonic image; determine the gallbladder volume based on the segmented gallbladder area, thereby determining the bile capacity; the memory 124 is used to store the program executed by the processor.

[0112] In one embodiment, the ultrasound imaging system 100 further includes a display 120 for displaying the gallbladder ultrasound image.

[0113] In one embodiment, the processor 118 is further used to: generate a curve showing the change of bile capacity over time according to the bile capacity measured at a plurality of measurement time points; and the display 120 is further used to display the change curve.

[0114] In addition, according to an embodiment of the present application, a storage medium is also provided, on which program instructions are stored, and when the program instructions are executed by a computer or a processor, the corresponding steps of the automatic measurement method of bile capacity of the embodiment of the present application are executed. The storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disk read-only memory (CD-ROM), a USB memory, or any combination of the above storage media.

[0115] In addition, according to an embodiment of the present application, a computer program is also provided, which can be stored in a cloud or local storage medium. When the computer program is executed by a computer or a processor, it is used to execute the corresponding steps of the automatic measurement method of bile capacity of the embodiment of the present application.

[0116] Based on the above description, the automatic bile capacity measurement method, ultrasound imaging system and storage medium according to the embodiments of the present application can regularly acquire gallbladder ultrasound images and determine the bile capacity, reduce user operations, and improve the accuracy of bile capacity measurement.

[0117] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application to this. Those of ordinary skill in the art may make various changes and modifications therein without departing from the scope and spirit of the present application. All these changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0118] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0119] 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 only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0120] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0121] Similarly, it should be understood that in order to streamline the present application and help understand one or more of the various inventive aspects, in the description of the exemplary embodiments of the present application, the various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, the method of the present application should not be interpreted as reflecting the following intention: the claimed application requires more features than the features clearly stated in each claim. More specifically, as reflected in the corresponding claims, the inventive point is that the corresponding technical problem can be solved with features less than all the features of a single disclosed embodiment. Therefore, the claims following the specific embodiment are hereby explicitly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present application.

[0122] It will be understood by those skilled in the art that, except for mutually exclusive features, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this specification may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0123] In addition, those skilled in the art will appreciate that, although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0124] The various component embodiments of the present application can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules in the article analysis device according to the embodiment of the present application. The present application can also be implemented as a device program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0125] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and that those skilled in the art may design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets should not be constructed as a limitation to the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of multiple such elements. The present application may be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim that lists several devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0126] The above is only a specific implementation or description of a specific implementation of the present application, and the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for automatically measuring bile capacity, characterized in that: The method comprises: Determine a plurality of measurement time points or time intervals between adjacent measurement time points according to user input; Automatically and regularly acquiring ultrasound images of the gallbladder at the plurality of measurement time points by means of an ultrasound probe fixed at the position of the gallbladder on the patient's body surface; Segmenting a gallbladder region in the gallbladder ultrasound image; Determining the gallbladder volume according to the segmented gallbladder region, thereby determining the bile capacity; generating a curve showing the bile capacity changing over time according to the bile capacity measured at the plurality of measurement time points; and Outputting the change curve to evaluate the excretion status of bile; The step of automatically and regularly acquiring gallbladder ultrasound images at a plurality of measurement time points and segmenting the gallbladder region from the gallbladder ultrasound images includes: Acquire multiple frames of two-dimensional gallbladder ultrasound images around each measurement time point, segment the gallbladder region from the multiple frames of the two-dimensional gallbladder ultrasound images, and select the gallbladder region with the largest area among the segmented gallbladder regions to determine the gallbladder volume; or, A plurality of volumes of three-dimensional gallbladder ultrasound images are acquired around each measurement time point, the gallbladder region is segmented out from the plurality of volumes of the three-dimensional gallbladder ultrasound images, and the gallbladder region having the largest three-dimensional gallbladder contour among the segmented gallbladder regions is selected for determining the gallbladder volume.

2. The automatic measurement method according to claim 1, characterized in that: Also includes: When the bile capacity exceeds a threshold, a prompt message is output.

3. The automatic measurement method according to claim 1, characterized in that: Segmenting the gallbladder region in the gallbladder ultrasound image includes: Automatically segmenting the gallbladder region in the gallbladder ultrasound image; or In combination with user input, the gallbladder region in the gallbladder ultrasound image is interactively segmented.

4. The automatic measurement method according to claim 3, characterized in that: The step of automatically segmenting the gallbladder region in the gallbladder ultrasound image comprises: The gallbladder region in the gallbladder ultrasound image is automatically segmented using an image segmentation algorithm.

5. The automatic measurement method according to claim 3, characterized in that: The step of automatically segmenting the gallbladder region in the gallbladder ultrasound image comprises: Performing feature extraction on image blocks in a predetermined neighborhood around each pixel point in the gallbladder ultrasound image; Using a classifier to classify the extracted features to determine the category of the image block corresponding to the features; According to the category of the image block, the pixel points corresponding to the image block are divided into the pixel points of the gallbladder area or the pixel points of the background area, so that the gallbladder ultrasound image is divided into the gallbladder area and the background area.

6. The automatic measurement method according to claim 3, characterized in that: The step of automatically segmenting the gallbladder region in the gallbladder ultrasound image comprises: The gallbladder region in the gallbladder ultrasound image is segmented using a trained deep learning neural network.

7. The automatic measurement method according to claim 3, characterized in that: The step of interactively segmenting the gallbladder region in the gallbladder ultrasound image in combination with user input comprises: Determining a preliminary segmentation range in the gallbladder ultrasound image according to a user's frame selection operation; The gallbladder region is automatically segmented within the preliminary segmentation range.

8. The automatic measurement method according to claim 3, characterized in that: The step of interactively segmenting the gallbladder region in the gallbladder ultrasound image in combination with user input comprises: The gallbladder region is segmented out using an interactive segmentation algorithm according to points or lines drawn on the gallbladder region by the user.

9. The automatic measurement method according to claim 1, characterized in that: When the gallbladder ultrasound image is a two-dimensional gallbladder ultrasound image, determining the gallbladder volume according to the segmented gallbladder region includes: Two mutually perpendicular radial lines are identified in the gallbladder region; The gallbladder volume is determined according to the two mutually perpendicular radial lines.

10. The automatic measurement method according to claim 1, characterized in that: When the gallbladder ultrasound image is a three-dimensional gallbladder ultrasound image, determining the gallbladder volume according to the segmented gallbladder region includes: The gallbladder volume is determined according to the three-dimensional contour of the gallbladder segmented in the gallbladder ultrasound image.

11. An ultrasonic imaging system, characterized in that: include: An ultrasound probe, which can be fixed on the patient's body surface at the location of the gallbladder; A transmitting circuit, used for stimulating the probe to transmit ultrasonic waves to the gallbladder area of ​​the patient at a plurality of measuring time points in a timely manner; A receiving circuit, used for controlling the probe to receive the ultrasonic echo returned from the gallbladder area to obtain an ultrasonic echo signal; Processor for: Determine the multiple measurement time points or the time intervals between adjacent measurement time points according to user input; Processing the ultrasonic echo signal to obtain the gallbladder ultrasonic images at the multiple measurement time points; Segmenting a gallbladder region in the gallbladder ultrasound image; Determining the gallbladder volume according to the segmented gallbladder region, thereby determining the bile capacity; Generating a curve of bile capacity changing with time according to the bile capacity measured at the multiple measurement time points; Outputting the change curve to evaluate the excretion status of bile; as well as A memory, used for storing a program executed by the processor; The step of obtaining the gallbladder ultrasound images at multiple measurement time points and segmenting the gallbladder region from the gallbladder ultrasound images includes: Acquire multiple frames of two-dimensional gallbladder ultrasound images around each measurement time point, segment the gallbladder region from the multiple frames of the two-dimensional gallbladder ultrasound images, and select the gallbladder region with the largest area among the segmented gallbladder regions to determine the gallbladder volume; or, A plurality of volumes of three-dimensional gallbladder ultrasound images are acquired around each measurement time point, the gallbladder region is segmented out from the plurality of volumes of the three-dimensional gallbladder ultrasound images, and the gallbladder region having the largest three-dimensional gallbladder contour among the segmented gallbladder regions is selected for determining the gallbladder volume.

12. The ultrasonic imaging system according to claim 11, characterized in that: Also includes: A display is used to display the gallbladder ultrasound image and the change curve.

13. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a computer or a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images