WO2023216594A1 - Ultrasonic imaging system and method - Google Patents

Abstract

An ultrasonic imaging system and method. The method comprises: acquiring three-dimensional volume data containing the volume of the endometrium, automatically determining, on the basis of the three-dimensional volume data, an endometrial receptivity result, and then controlling to output the endometrial receptivity result, so as to automatically evaluate the endometrial receptivity.

Description

Ultrasound imaging system and method Technical field

The present invention relates to an ultrasound imaging system and method.

Background technique

Ultrasound technology, as one of the main means of modern medical imaging examination, is also widely used in reproductive medicine. Among them, endometrial receptivity analysis is a hot issue in reproductive medicine. Endometrial receptivity refers to the ability of the endometrium to accept fertilized eggs. It is one of the main factors affecting the success rate of in vitro artificial fertilization (IVF). Patients with poor endometrial receptivity will not be able to accept fertilized eggs after fertilized egg transplantation. There is a high probability of pregnancy failure. Ultrasound imaging is mainly used clinically to assess endometrial receptivity.

Contents of the invention

In order to use ultrasound images to evaluate the receptivity of the endometrium, the present invention proposes an ultrasound imaging system and an ultrasound imaging method, which are described in detail below.

According to a first aspect, an embodiment provides an ultrasound imaging system, including:

a probe for transmitting ultrasound waves to the tissue of interest including the endometrium and receiving corresponding ultrasound echo signals;

A transmitting and receiving control circuit, used to control the probe to transmit ultrasonic waves and receive ultrasonic echo signals;

a tolerance evaluation key that generates tolerance evaluation instructions in response to user operations;

A processor, configured to process the corresponding ultrasound echo signal to obtain three-dimensional volume data including the endometrium; in response to the receptivity assessment instruction:

The processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium;

The processor automatically calculates volume-related measurement items and non-volume-related measurement items based on the segmented endometrium; the volume-related measurement items include endometrial thickness, endometrial volume, and endometrial blood perfusion. Any one or more of the indicators, the non-volume related measurement items include any one or more of endometrial classification and endometrial myometrium echo uniformity;

The processor automatically determines the results of the receptivity evaluation-related measurement items based on the volume-related measurement items and non-volume-related measurement items;

The processor determines the receptivity result of the endometrium based on the results of the measurement items related to the receptivity evaluation.

In one embodiment, the processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium, including:

The processor segments the three-dimensional volume data containing the endometrium through feature detection based on the difference in image characteristics between the endometrium and the uterine basal tissue and/or the periodically changing morphological characteristics of the endometrium. endometrium;

or,

A model trained by machine learning is obtained, and the endometrium is segmented from the three-dimensional volume data containing the endometrium based on the model.

In one embodiment, the processor determines the endometrial receptivity result based on the results of the receptivity evaluation-related measurement items, including:

The processor calculates a score of the endometrial receptivity based on the results of the measurement items related to the receptivity evaluation;

The processor determines an endometrial receptivity result based on the endometrial receptivity score.

According to a second aspect, an embodiment provides an ultrasound imaging system, comprising:

a probe for transmitting ultrasound waves to the tissue of interest including the endometrium and receiving corresponding ultrasound echo signals;

A transmitting and receiving control circuit, used to control the probe to transmit ultrasonic waves and receive ultrasonic echo signals;

A processor configured to process the corresponding ultrasonic echo signal to obtain three-dimensional volume data containing the endometrium, and automatically determine the receptivity result of the endometrium based on the three-dimensional volume data, and control Outputs the endometrial receptivity results.

In one embodiment, the processor automatically determines the receptivity result of the endometrium based on the three-dimensional volume data, including:

The processor automatically determines the results of measurement items related to the receptivity evaluation based on the three-dimensional volume data;

The processor determines the receptivity result of the endometrium based on the results of the measurement items related to the receptivity evaluation.

In one embodiment, the processor automatically determines the results of the receptivity evaluation-related measurement items based on the three-dimensional volume data, including: the processor automatically determines at least the results of the volume-related measurement items based on the three-dimensional volume data, so The volume-related measurement items include any one or more of endometrial thickness, endometrial volume, and endometrial blood perfusion indicators.

In one embodiment, the processor automatically determines at least the results of volume-related measurement items based on the three-dimensional volume data, including:

The processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium; and calculates the volume-related measurement results based on the segmented endometrium; or,

A mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the volume-related measurement items is established in advance; the processor identifies the preset features in the acquired three-dimensional volume data containing the endometrium, and performs the mapping according to the obtained three-dimensional volume data containing the endometrium. Describe the mapping relationship and calculate the results of volume-related measurement items.

In one embodiment, the processor calculates the volume-related measurement results based on the segmented endometrium, including:

Based on the segmented endometrium, the processor counts the number of pixels belonging to the endometrium to obtain the pixel volume of the endometrium; the processor uses the conversion relationship between the pixel distance and the actual physical distance , convert the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrial volume;

and / or,

The processor locates the sagittal plane of the endometrium based on the segmented endometrium, and calculates the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrial thickness;

and / or,

The processor counts the color Doppler blood flow signal intensity and the number of pixels in the endometrium area based on the segmented endometrium to calculate the blood perfusion index of the endometrium.

In one embodiment, the processor automatically determines the results of receptivity evaluation-related measurement items based on the three-dimensional volume data, including: the processor automatically determines at least the results of non-volume-related measurement items based on the three-dimensional volume data, The non-volume-related measurement items include any one or more of endometrial classification and endometrial myometrial echo uniformity.

In one embodiment, the processor automatically determines at least the results of non-volume-related measurement items based on the three-dimensional volume data, including:

The processor calculates results of non-volume-related measurement items through a classification algorithm based on the three-dimensional volume data;

or,

A mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the non-volume-related measurement items is established in advance; the processor identifies the preset features in the acquired three-dimensional volume data containing the endometrium, and performs the mapping according to The mapping relationship calculates the results of non-volume related measurement items.

In one embodiment, the processor automatically determines the receptivity result of the endometrium based on the three-dimensional volume data, including:

A mapping relationship between preset characteristics and receptivity results including the three-dimensional volume data of the endometrium is established in advance;

The processor identifies preset features in the acquired three-dimensional volume data including endometrium, and calculates receptivity results based on the mapping relationship.

According to a third aspect, an embodiment provides an ultrasound imaging method, including:

Obtain three-dimensional volumetric data containing the endometrium;

Automatically segment the three-dimensional volume data containing the endometrium to segment the endometrium;

According to the segmented endometrium, volume-related measurement items and non-volume-related measurement items are automatically calculated; the volume-related measurement items include any of endometrial thickness, endometrial volume, and endometrial blood perfusion indicators. One or more, the non-volume related measurement items include any one or more of endometrial classification and endometrial myometrium echo uniformity;

Automatically determine the results of the receptivity evaluation-related measurement items based on the volume-related measurement items and non-volume-related measurement items;

The endometrial receptivity result is determined based on the results of the measurement items related to the receptivity evaluation.

In one embodiment, the automatic segmentation of the three-dimensional volume data containing the endometrium to segment the endometrium includes:

Segment the endometrium from the three-dimensional volume data containing the endometrium through feature detection based on the difference in image characteristics between the endometrium and the uterine basal tissue and/or the cyclically changing morphological characteristics of the endometrium;

or,

A model trained by machine learning is obtained, and the endometrium is segmented from the three-dimensional volume data containing the endometrium based on the model.

In one embodiment, determining the endometrial receptivity result based on the results of measurement items related to the receptivity evaluation includes:

Calculate a score of the endometrial receptivity based on the results of the measurement items related to the receptivity evaluation;

Endometrial receptivity results are determined based on the endometrial receptivity score.

According to a fourth aspect, an embodiment provides an ultrasound imaging method, including:

Obtain three-dimensional volumetric data containing the endometrium;

Automatically determine the endometrial receptivity result based on the three-dimensional volumetric data;

Control output of the endometrial receptivity results.

In one embodiment, the volume of the endometrium is automatically determined based on the three-dimensional volume data.

Tolerance results, including:

Automatically determine the results of measurement items related to receptivity evaluation based on the three-dimensional volume data;

The endometrial receptivity result is determined based on the results of the measurement items related to the receptivity evaluation.

In one embodiment, the automatic determination of the results of the receptivity evaluation-related measurement items based on the three-dimensional volume data includes: at least automatically determining the results of the volume-related measurement items based on the three-dimensional volume data, and the volume-related measurement items include Any one or more of endometrial thickness, endometrial volume, and endometrial blood perfusion indicators.

In one embodiment, the results of at least automatically determining volume-related measurement items based on the three-dimensional volume data include:

Automatically segment the three-dimensional volume data containing the endometrium to segment the endometrium; calculate the results of the volume-related measurement based on the segmented endometrium; or,

Establish in advance a mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the volume-related measurement items; identify the preset features in the acquired three-dimensional volume data containing the endometrium, and based on the mapping relationship, Calculates the results of volume-related measurements.

In one embodiment, calculating the volume-related measurement results based on the segmented endometrium includes:

Based on the segmented endometrium, the number of pixels belonging to the endometrium is counted to obtain the pixel volume of the endometrium; through the conversion relationship between the pixel distance and the actual physical distance, the endometrium is calculated The pixel volume is converted into the actual physical volume of the endometrium as the endometrial volume;

and / or,

Based on the segmented endometrium, locate the sagittal plane of the endometrium, and calculate the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrial thickness;

and / or,

Based on the segmented endometrium, the color Doppler blood flow signal intensity and the number of pixels in the endometrium area are counted to calculate the blood perfusion index of the endometrium.

In one embodiment, automatically determining the results of receptivity evaluation-related measurement items based on the three-dimensional volume data includes: automatically determining at least the results of non-volume-related measurement items based on the three-dimensional volume data, and the non-volume-related measurement The terms include any one or more of endometrial classification and endometrial myometrial echogenicity.

In one embodiment, the results of automatically determining at least non-volume-related measurement items based on the three-dimensional volume data include:

Calculate results of non-volume-related measurement items based on the three-dimensional volumetric data through a classification algorithm;

or,

Establish in advance a mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the non-volume-related measurement items; identify the preset features in the acquired three-dimensional volume data containing the endometrium, and use the mapping relationship according to the , calculates the results of non-volume-related measurements.

In one embodiment, the automatic determination of the endometrial receptivity result based on the three-dimensional volume data includes:

A mapping relationship between preset characteristics and receptivity results including the three-dimensional volume data of the endometrium is established in advance;

Preset features in the acquired three-dimensional volume data containing the endometrium are identified, and the receptivity result is calculated based on the mapping relationship.

According to a fifth aspect, an embodiment provides a computer-readable storage medium storing a program, and the program can be executed by a processor to implement the method as described in any embodiment herein. .

According to the ultrasound imaging system, ultrasound imaging method and computer-readable storage medium of the above embodiments, three-dimensional volume data including the endometrium are obtained, and then the receptivity result of the endometrium is automatically determined based on the three-dimensional volume data, and then the output of the uterus is controlled. Endometrial receptivity results, thereby enabling automated endometrial receptivity assessment.

Description of the drawings

Figure 1 is a schematic structural diagram of an ultrasound imaging system according to an embodiment;

Figure 2 is a schematic diagram of the conversion relationship between measured values and scores of measurement items related to tolerance evaluation;

Figure 3 is a flow chart of an ultrasound imaging method according to an embodiment;

Figure 4 is a flow chart for automatically determining endometrial receptivity results based on three-dimensional volume data according to an embodiment;

Figure 5 is a flow chart for automatically determining endometrial receptivity results based on three-dimensional volume data according to an embodiment;

Figure 6 is a flow chart of an ultrasound imaging method according to an embodiment.

Detailed ways

The present invention will be further described in detail below through specific embodiments in conjunction with the accompanying drawings. Similar elements in different embodiments use associated similar element numbers. In the following embodiments, many details are described in order to make the present application better understood. However, those skilled in the art can readily recognize that some of the features may be omitted in different situations, or may be replaced by other elements, materials, and methods. In some cases, some operations related to the present application are not shown or described in the specification. This is to avoid the core part of the present application being overwhelmed by excessive descriptions. For those skilled in the art, it is difficult to describe these in detail. The relevant operations are not necessary, and they can fully understand the relevant operations based on the descriptions in the instructions and general technical knowledge in the field.

Additionally, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. At the same time, each step or action in the method description can also be sequentially exchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the description and drawings are only for clearly describing a certain embodiment, and do not imply a necessary sequence, unless otherwise stated that a certain sequence must be followed.

The serial numbers assigned to components in this article, such as "first", "second", etc., are only used to distinguish the described objects and do not have any sequential or technical meaning. The terms "connection" and "connection" mentioned in this application include direct and indirect connections (connections) unless otherwise specified.

This application addresses the problem of endometrial receptivity assessment. In some embodiments, measurement items related to receptivity evaluation are proposed, such as volume-related measurement items and/or non-volume-related measurement items; in some embodiments, volume-related measurement items The terms include any one or more of endometrial thickness, endometrial volume and endometrial blood perfusion index, where the endometrial blood perfusion index can be, for example, vascular index VI, blood flow index FI, Vessel-blood flow index VFI, etc.; in some embodiments, the non-volume related measurement items include any one or more of endometrial classification and endometrial myometrium echo uniformity.

In some solutions, doctors can use ultrasound imaging systems to obtain the results of the above-mentioned measurement items related to receptivity evaluation. In particular, volume-related measurement items also need to be obtained based on the three-dimensional segmentation results of the endometrium. For example, the doctor manually performs three-dimensional segmentation on the endometrium. Manually outline the outline of the endometrium on multiple sections of the volume data to perform three-dimensional segmentation of the endometrium. Only in this way can the three-dimensional segmentation results be obtained. Moreover, the more outlines the doctor outlines, the more accurate the three-dimensional segmentation results will be. After obtaining the above After obtaining the results of these receptivity evaluation-related measurement items, the doctor then manually summarizes the results of these receptivity evaluation-related measurement items to comprehensively evaluate the endometrial receptivity; therefore, it is necessary to obtain accurate endometrial receptivity. Evaluating the results often consumes a lot of time and energy from doctors.

In other solutions, a solution for automatic assessment of endometrial receptivity is proposed. For example, after completing the 3D/4D ultrasound endometrial data collection, only one function button (physical button or virtual button) is needed. The imaging system can automatically calculate and obtain the endometrial receptivity assessment results; in some embodiments, during this process, the endometrium is automatically segmented from the volume data to obtain the thickness, volume, and blood perfusion of the endometrium. and multiple receptivity evaluation-related measurement items to achieve automatic endometrial receptivity assessment, which can greatly reduce the time doctors spend manually measuring each measurement item, improve doctors' work efficiency, and ensure the accuracy of assessment results. sex and stability.

The solution of this application can be implemented on an ultrasonic imaging system. Please refer to Figure 1. The ultrasonic imaging system in some embodiments includes a probe 10, a transmitting and receiving control circuit 20, an echo processing module 30, a processor 40 and a display module 50. Each component is explained below.

The probe 10 can be a matrix probe or a four-dimensional probe with a mechanical device. The present invention is not limited to this, as long as the ultrasonic probe used can obtain the ultrasonic echo signal or data of the target area of the subject. In some embodiments, the ultrasound probe acquires a set of four-dimensional image data (ie, a dynamic three-dimensional ultrasound image) or acquires a volume of three-dimensional ultrasound image data. In some specific embodiments, the probe 10 includes a plurality of array elements, which are used to realize mutual conversion of electrical pulse signals and ultrasonic waves, thereby realizing detection of the biological tissue 60 (biological tissue in the human body or animal body, such as the endometrium). The tissue of interest) emits ultrasonic waves and receives the ultrasonic echoes reflected back from the tissue to obtain ultrasonic echo signals. The multiple array elements included in the probe 10 can be arranged in a row to form a linear array, or arranged in a two-dimensional matrix to form an area array. The multiple array elements can also form a convex array. The array element can emit ultrasonic waves according to the excitation electrical signal, or convert the received ultrasonic waves into electrical signals. Therefore, each array element can be used to transmit ultrasonic waves to the biological tissue in the area of interest, and can also be used to receive ultrasonic echoes returned by the tissue. When performing ultrasonic testing, the transmitting sequence and the receiving sequence can be used to control which array elements are used to transmit ultrasonic waves and which array elements are used to receive ultrasonic waves, or the array elements can be controlled to transmit ultrasonic waves or receive ultrasonic echoes in time slots. All array elements participating in ultrasonic emission can be excited by electrical signals at the same time, thereby emitting ultrasonic waves at the same time; or the array elements participating in ultrasonic emission can also be excited by several electrical signals with a certain time interval, thereby continuously emitting ultrasonic waves with a certain time interval.

The transmitting and receiving control circuit 20 is used to control the probe 10 to transmit ultrasonic waves and receive ultrasonic echo signals. Specifically, the transmitting and receiving control circuit 20 is used to control the probe 10 to sense the biological tissue 60, such as the endometrium, on the one hand. The tissue of interest emits an ultrasound beam, and on the other hand, it is used to control the probe 10 to receive the ultrasound echo reflected by the tissue. In a specific embodiment, the transmitting and receiving control circuit 20 is used to generate a transmitting sequence and a receiving sequence, and output them to the probe 10 . The transmission sequence is used to control some or all of the multiple array elements in the probe 10 to transmit ultrasound waves to the biological tissue 60, such as the tissue of interest including the endometrium. The parameters of the transmission sequence include the number of array elements for transmission and the ultrasound transmission parameters (such as Amplitude, frequency, number of waves, launch interval, launch angle, wave type and/or focus position, etc.). The receiving sequence is used to control some or all of the multiple array elements to receive the echo after the ultrasonic waves are transmitted through the tissue. The parameters of the receiving sequence include the number of receiving array elements and the receiving parameters of the echo (such as receiving angle, depth, etc.). Depending on the use of the ultrasonic echo or the images generated based on the ultrasonic echo, the ultrasonic parameters in the transmitting sequence and the echo parameters in the receiving sequence are also different.

The echo processing module 30 is used to process the ultrasonic echo signals received by the probe 10, such as filtering, amplifying, and beamforming the ultrasonic echo signals to obtain ultrasonic echo data. In a specific embodiment, the echo processing module 30 can output the ultrasonic echo data to the processor 40, or can first store the ultrasonic echo data in a memory. When it is necessary to perform operations based on the ultrasonic echo data, the processor 40 Read the ultrasonic echo data from the memory. Persons skilled in the art should understand that in some embodiments, when there is no need to perform filtering, amplification, beamforming and other processing on the ultrasonic echo signal, the echo processing module 30 can also be omitted.

The processor 40 is used to obtain ultrasonic echo data or signals, and use related algorithms to obtain required parameters or images. For example, the probe 10 transmits ultrasonic waves to the tissue of interest including the endometrium, and receives corresponding ultrasonic echo signals; the processor 40 processes the corresponding ultrasonic echo signals to obtain three-dimensional volume data including the endometrium.

The display module 50 may be used to display information, such as parameters and images calculated by the processor 40 . Those skilled in the art should understand that in some embodiments, the ultrasound imaging system itself may not integrate a display module, but may be connected to a computer device (such as a computer) to display information through the display module (such as a display screen) of the computer device.

Ultrasound imaging systems in some embodiments can perform assessment of endometrial receptivity. Specifically, the probe 10 transmits ultrasonic waves to the tissue of interest including the endometrium, and receives corresponding ultrasonic echo signals; the processor 40 is used to process the corresponding ultrasonic echo signals to obtain a three-dimensional volume including the endometrium. data, automatically determine the endometrial receptivity result based on the three-dimensional volume data, and control the output of the endometrial receptivity result, for example, output it to the display module 50 for display. In some embodiments, the processor 40 automatically determines the endometrial receptivity results based on the three-dimensional volume data, including: the processor 40 automatically determines the results of measurement items related to receptivity evaluation based on the three-dimensional volume data, such as receptivity evaluation. The measured value of the relevant measurement item or the score converted from the measured value; the processor 40 evaluates the result of the relevant measurement item according to the receptivity to determine the endometrial receptivity result.

A more detailed description will be given below of the results of the processor 40 automatically determining measurement items related to the receptivity evaluation based on the three-dimensional volume data.

In some embodiments, the measurement items related to tolerance evaluation include volume-related measurement items and/or non-volume-related measurement items. In addition to calculating volume-related measurement items such as endometrial volume, endometrial thickness, and endometrial blood perfusion based on the three-dimensional endometrial segmentation based on the three-dimensional volume data containing the endometrium, it can also be based on the uterus and intrauterine Ultrasound imaging features of the membrane use machine learning or deep learning algorithms to measure non-volume-related measurement items such as endometrial classification and echo uniformity of the myometrium.

In some specific embodiments, the volume-related measurement items can be calculated as follows: the volume-related measurement items (volume, thickness, blood flow, etc.) can be obtained through accurate three-dimensional segmentation of the endometrium, or can be directly returned to the corresponding measurements through an algorithm. The measure or score (score) of the item.

The calculation of volume-related measurement items through accurate three-dimensional segmentation of the endometrium will be explained first.

The purpose of accurate 3D segmentation is to determine whether each volume pixel in the 3D volume data belongs to the endometrium. According to the results of three-dimensional segmentation, the number of voxels belonging to the endometrium can be counted to obtain measurement items such as endometrial volume and thickness. After obtaining the endometrial volume, the proportion of blood flow signals can also be calculated to obtain blood flow perfusion correlation. measurement items. The direct regression method is to directly predict a final measurement item value or score value through an algorithm. Both of the above implementation solutions can be implemented using image algorithms or deep learning algorithms.

Take the image algorithm to achieve three-dimensional endometrium segmentation as an example: In the three-dimensional volume data of the endometrium, there are obvious differences between the echo of the endometrium and the echo of the surrounding tissue. At the same time, as the female menstrual cycle changes, the endometrium The shape of the endometrium also changes periodically. Based on these image features, traditional grayscale and/or morphological methods can be used to segment the endometrium, such as Otsu threshold (OTSU), level set (LevelSet), and graph cut (Graph). Cut), snake model (Snake) and other segmentation methods.

Taking the endometrial segmentation based on concentration learning method as an example: first learn the features or rules in the database that can distinguish target areas and non-target areas, and then locate and identify key anatomical parts of other images based on the learned features or rules. It includes the following main steps:

Step 1, build database steps

The database usually contains multiple sets of endometrial body data and calibration results of key anatomical structures. Among them, the calibration results can be set according to the actual task needs. For segmentation tasks, the calibration is usually a Mask for accurately segmenting the endometrium area.

Step 2, positioning and identification steps

After the database is constructed, a deep learning network algorithm is designed to learn the characteristics or rules in the database that can distinguish the target area (endometrial area) and non-target area (background area) to achieve accurate segmentation of the endometrium. This implementation step includes but is not limited to the following situations.

The first case is an end-to-end semantic segmentation network method based on deep learning. Semantic segmentation needs to classify each pixel of the input image and determine which category each pixel in the image belongs to. In the present invention, it is to determine which category each pixel belongs to. Whether a pixel belongs to the endometrium; the form of this method can be: learning features of the constructed database by stacking base convolutional layers and fully connected layers; adding an upsampling or deconvolution layer behind the feature extraction network, Restore the extracted features to a resolution close to or the same as the original image, and output the segmentation Mask. The values at different positions in the Mask represent the category of the corresponding position in the original image (whether it belongs to the endometrium), thereby directly obtaining the input image. The pixel position belonging to the endometrium; some networks can be FCN, U-Net, deeplab series, etc.

The second case is an end-to-end instance segmentation network based on deep learning; this type of method is similar to the first type of semantic segmentation method, and is implemented by stacking different deep learning network layers. The difference is that instance segmentation also needs to distinguish the same category. Different goals. A common way to implement the instance segmentation algorithm of deep learning is to combine it with the target detection network. By detecting and locating different targets of different categories in the image, the location and size of the target are obtained, and then two-category semantic segmentation is performed in each target area. , determine whether each pixel in the target area belongs to the target or the background. Endometrium segmentation can also be achieved using instance segmentation networks. Instance segmentation network algorithms include Mask-RCNN, FCIS, etc.

The third case is a method that combines deep learning with image segmentation; for example, using a deep learning algorithm to obtain an initial segmentation result or feature, and then using a traditional segmentation algorithm to further optimize the result; in addition, a deep learning algorithm can also be used to predict the segmentation of a traditional segmentation algorithm. Parameters, for example, deep learning algorithms can be used to predict the initial contour of the traditional level set algorithm and optimized parameters to obtain better segmentation results.

Use image segmentation methods or deep learning algorithms to determine which pixels of volume data belong to the endometrium, thereby obtaining multiple related measurement items; specifically, after obtaining the three-dimensional segmentation results of the endometrium, the volume of the endometrium can be measured as follows: The pixel volume of the endometrium can be obtained by counting the number of pixels belonging to the endometrium, and then through the conversion relationship between the pixel distance and the actual physical distance during scanning and reconstruction by the ultrasound imaging system, the actual physical volume of the endometrium can be obtained. Volume; endometrial thickness can be measured as follows: position the endometrial three-dimensional segmentation result in the sagittal plane, and calculate the thickest part of the sagittal plane segmentation result to obtain the endometrial thickness; blood perfusion can be measured in this way Measurement: For color Doppler 3D data, the blood perfusion of the endometrium can be calculated based on the three-dimensional segmentation results of the endometrium; it can be obtained by counting the intensity and number of color Doppler blood flow signals in the endometrium area. The vascular index VI, blood flow index FI, and vascular-blood flow index VFI on the endometrium; vascular index (VI), blood flow index (FI), and vascular blood flow index (VFI) are important indicators for evaluating blood flow; among them , the vascular index (VI) is the blood fluid volume in the area of interest/the total pixel value in the area of interest, which refers to the proportion of pixels of blood vessels to the total number of pixels in the endometrium, representing the area of interest (such as the uterus Intimal area) The number of blood vessels per unit volume indicates the abundance or sparseness of blood vessels in the tissue; the blood flow index (FI) is the average of blood fluid voxels (excluding voxels with no blood flow signal) in the area of interest. Intensity, that is, the average signal intensity of pixels with blood flow in the endometrium, is the average value or blood flow density of all blood flows in the area of interest, and represents the average intensity of the blood flow signal in the target volume; vascularized blood flow index (VFI) is the average blood flow signal of all voxels (including voxels without blood flow signals) in the area of interest, and is a combination of blood vessel information and blood flow information existing in the target tissue.

The above describes the calculation of volume-related measurement items through accurate three-dimensional segmentation of the endometrium, and then explains the direct regression of the measurement value or score (score) of the corresponding measurement item through the algorithm.

The direct regression solution uses an algorithm to identify the features of volume data and establish a mapping relationship between the features and the corresponding measurement values (or score values). When a piece of data is input, the algorithm predicts specific measurements based on the characteristics of the data. Similar to the aforementioned segmentation methods, direct regression solutions can also be implemented using deep learning algorithms and/or image methods. The implementation steps of the parameter regression scheme based on deep learning are similar to the implementation method of three-dimensional segmentation of endometrium. They can be divided into steps such as building a database and designing and training a regression network. The deep learning network used can be a convolutional neural network (CNN). , three-dimensional convolutional neural network (3D-CNN) and recurrent neural network (RNN), etc. Traditional regression methods require manual design of feature extraction methods to extract features from the data. Commonly used features include grayscale features, texture features, pixel gradients, statistical features of pixel distribution, etc.; after the features are extracted, linear regression and other algorithms can be used to establish features. Correspondence between specific measured values to obtain regression results. Similar to the segmentation scheme, the regression scheme can also be implemented by combining traditional methods and deep learning methods.

The above describes the measurement of volume-related measurement items through three-dimensional segmentation of the endometrium, and the direct regression of the measurement values or scores of the corresponding measurement items through algorithms; the measurement of non-volume-related measurement items will be explained below.

As mentioned above, in addition to the measurement items related to endometrial volume, there are also some parameters for endometrial receptivity assessment that do not need to rely on the calculation results of endometrial volume, such as endometrial classification and endometrial muscle. Layer echo uniformity. Such non-volume-related measures can be calculated by classification or direct regression.

Classification calculation: Automatic classification of endometrial body data through algorithms can determine the type of endometrium and whether the echo of the endometrium is uniform. The classification method can be implemented based on a deep learning algorithm or a traditional machine learning algorithm; the classification based on the deep learning algorithm is similar to the implementation steps of the deep learning segmentation algorithm described above and will not be described again here. Traditional machine learning classification algorithms include: Adaboost algorithm, support vector machine (SVM), random forest (Random Forest), etc.; the above classification process can be implemented based on three-dimensional volume data or based on two-dimensional slices one by one. After the classification results are obtained, specific measurement scores can also be mapped according to the classification results.

Regression calculation: The regression calculation of other types of parameters is similar to the regression method of volume-related parameters described above, and will not be repeated here.

In some embodiments, when the image quality is poor and the endometrial volume segmentation results calculated by the algorithm are biased, the user can also use the keyboard, mouse and other tools to delete, recalibrate and other modification operations on the segmentation results to achieve semi-automatic Calculation of measurement items.

The above describes the measurement or calculation of measurements related to receptivity evaluation.

When applied to an ultrasound imaging system, in some embodiments, the processor 40 at least automatically determines the results of volume-related measurement items based on the three-dimensional volume data, where the volume-related measurement items include endometrial thickness, endometrial volume, and endometrial blood flow. any one or more of the flow perfusion indicators. In some embodiments, the processor 40 may automatically determine at least the results of the volume-related measurement items based on the above three-dimensional volume data:

(1) The processor 40 automatically segments the three-dimensional volume data including the endometrium to segment the endometrium; the processor 40 calculates the above volume-related measurement results based on the segmented endometrium; for example, by calculating the uterine lining. Taking the endometrial volume as an example, the processor 40 counts the number of pixels belonging to the endometrium based on the segmented endometrium to obtain the pixel volume of the endometrium. The processor 40 calculates the pixel distance between the pixel distance and the actual physical distance. The conversion relationship between the pixel volume of the endometrium is converted into the actual physical volume of the endometrium as the endometrial volume; taking the calculation of the thickness of the endometrium as an example, the processor 40 is based on the segmented endometrium. , locate the sagittal plane of the endometrium, and calculate the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the thickness of the endometrium; taking the calculation of blood perfusion index as an example, the processor 40 Based on the segmented endometrium, count the color Doppler blood flow signal intensity and number of pixels in the endometrium area to calculate the endometrium blood perfusion index;

Alternatively, the processor 40 can also automatically determine at least the results of the volume-related measurement items based on the above three-dimensional volume data:

(2) Establish in advance a mapping relationship between the preset features of the three-dimensional volume data containing the endometrium and the results of the volume-related measurement items; the processor 40 identifies the preset features in the acquired three-dimensional volume data containing the endometrium, and According to the above mapping relationship, the results of the volume-related measurement items are calculated.

In some embodiments, the processor at least automatically determines results of non-volume-related measurement items based on the three-dimensional volume data, wherein the non-volume-related measurement items include any one or more of endometrial classification and endometrial myometrial echo uniformity. . In some embodiments, the processor 40 may automatically determine at least the results of the non-volume-related measurement items based on the three-dimensional volume data as follows:

(1) The processor 40 calculates the results of non-volume-related measurement items through a classification algorithm based on the three-dimensional volume data;

Alternatively, the processor 40 may also automatically determine at least the results of the non-volume-related measurement items based on the three-dimensional volume data:

(2) Establish in advance a mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of non-volume-related measurement items; the processor 40 identifies the preset features in the acquired three-dimensional volume data containing the endometrium, And according to the mapping relationship between the preset characteristics of the three-dimensional volume data including the endometrium and the results of the non-volume-related measurement items, the results of the non-volume-related measurement items are calculated.

After automatically determining the results of the measurement items related to the receptivity evaluation based on the three-dimensional volume data, the processor 40 determines the endometrial receptivity results based on the results of the measurement items related to the receptivity evaluation. The results of the measurement items related to the tolerance evaluation mentioned above may be the measured values of the measurement items related to the tolerance evaluation, or may be scores (scores) converted from the measured values. For example, Figure 2 is an example of the conversion relationship between the measurement values and scores of the measurement items related to the receptivity evaluation; it should be noted that Figure 2 only shows the measurement values and scores (scores) of some of the measurement items related to the receptivity evaluation. The corresponding relationship between them, and the corresponding specific values can be set and modified according to different clinical standards.

When the result of the measurement item related to the receptivity evaluation is a measurement value, the processor 40 can calculate a score based on the result of the measurement item related to the receptivity evaluation as the endometrial receptivity result; when the result of the receptivity evaluation-related measurement item is When the result of the measurement item is a score, the processor 40 can perform a weighted summation of these scores to obtain the endometrial receptivity result.

In some embodiments, obtaining the receptivity results of the endometrium can also be achieved by using regression; in the above-mentioned solution of regressing the measured values of relevant measurement items for receptivity evaluation, the regression of the measured values is replaced by Direct score regression; for example, the step of regressing the endometrial volume value in the previous protocol can be replaced by regressing the endometrial volume score. The solution to directly use the algorithm to regress the score actually skips the step of regression measurement items and directly uses the algorithm to learn the mapping relationship between image features and specific tolerance scores.

The endometrial receptivity result can also be directly a receptivity grade. For example, the processor 40 can set a threshold, and after obtaining the endometrial receptivity score, compare it with the threshold to classify it into different grades; some In an embodiment, the measured values and corresponding scores of the measurement items related to the receptivity evaluation may also be displayed, and these may be displayed as endometrial receptivity results, and the doctor will specifically judge the results of the receptivity analysis.

In some other embodiments, the processor 40 automatically determines the receptivity result of the endometrium based on the three-dimensional volume data, including: pre-establishing a mapping between preset characteristics and receptivity results including the three-dimensional volume data of the endometrium. relationship; the processor 40 identifies the preset features in the acquired three-dimensional volume data including the endometrium, and calculates the receptivity based on the mapping relationship between the preset features of the three-dimensional volume data including the endometrium and the receptivity result. result. Similarly, the tolerance result here can be a score or a tolerance level, etc.

An operation process can be like this;

The doctor generates and displays a two-dimensional ultrasound image through the ultrasound imaging system, and then selects the area of interest in the two-dimensional ultrasound image using input tools such as the mouse. For example, the doctor draws a box with the mouse to select the area of interest containing the endometrium, or also The area of interest can be automatically selected through the ultrasound imaging system. For example, the area of interest including the endometrium is identified on the two-dimensional ultrasound image through the ultrasound imaging system. Then the user manually or the ultrasound imaging system automatically starts the three-dimensional ultrasound data collection. The imaging system scans and collects the three-dimensional volume data including the endometrium. After the ultrasound imaging system obtains the three-dimensional volume data including the endometrium, it automatically determines the receptivity result of the endometrium and displays it.

The ultrasound imaging system in some embodiments may also include a susceptibility evaluation key. The susceptibility evaluation key may be a physical structure or a virtual key. When the susceptibility evaluation key is a virtual key, it can be passed by the user. Mouse ready to click. In some embodiments, the receptivity evaluation key can generate a receptivity evaluation instruction in response to a user operation; in response to the receptivity evaluation instruction, the processor 40 obtains three-dimensional volume data including the endometrium, and based on the three-dimensional volume data To determine the receptivity result of the endometrium; how the processor 40 determines the receptivity result of the endometrium based on the three-dimensional volume data has been described in detail above and will not be described again here.

An operation process can be like this;

The doctor generates and displays a two-dimensional ultrasound image through the ultrasound imaging system, and then selects the area of interest in the two-dimensional ultrasound image using input tools such as the mouse. For example, the doctor draws a box with the mouse to select the area of interest containing the endometrium, or also The area of interest can be automatically selected through the ultrasound imaging system. For example, the area of interest including the endometrium is identified on the two-dimensional ultrasound image through the ultrasound imaging system. Then the user manually or the ultrasound imaging system automatically starts the three-dimensional ultrasound data collection. The imaging system scans and collects the three-dimensional volume data containing the endometrium, and then the user can trigger the receptivity assessment button, so that the ultrasound imaging system automatically determines the endometrium after acquiring the three-dimensional volume data containing the endometrium. The tolerance results are displayed.

The above is some description of the ultrasound imaging system. Some embodiments also disclose an ultrasound imaging method, which is described in detail below.

Referring to Figure 3, the ultrasound imaging method of some embodiments includes the following steps:

Step 100: Obtain three-dimensional volume data including endometrium.

Step 110: Automatically determine the endometrial receptivity result based on the three-dimensional volume data.

In some embodiments, please refer to Figure 4. Step 110 automatically determines the above-mentioned endometrial receptivity result based on three-dimensional volume data including the following steps:

Step 111: Automatically determine the results of relevant measurement items for receptivity evaluation based on the above three-dimensional volume data.

For example, step 111 at least automatically determines the results of volume-related measurement items based on the above three-dimensional volume data, where the volume-related measurement items include any one or more of endometrial thickness, endometrial volume, and endometrial blood perfusion indicators. .

In some specific embodiments, step 111 automatically segments the above-mentioned three-dimensional volume data including the endometrium to segment the endometrium; based on the segmented endometrium, calculates the above-mentioned volume-related measurement results. For example, taking the calculation of the endometrial volume as an example, step 111 counts the number of pixels belonging to the endometrium based on the segmented endometrium to obtain the pixel volume of the endometrium. Step 111 uses the pixel distance and the actual physical The conversion relationship between the distances is to convert the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrial volume; taking the calculation of the thickness of the endometrium as an example, step 111 is based on the segmented endometrium. membrane, locate the sagittal plane of the endometrium, and calculate the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrial thickness; for another example, take the calculation of blood perfusion index as an example, step 111 Based on the segmented endometrium, the color Doppler blood flow signal intensity and number of pixels in the endometrium area are counted to calculate the endometrium blood perfusion index.

In some specific embodiments, a mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the volume-related measurement items is established in advance; step 111 identifies the preset features in the acquired three-dimensional volume data containing the endometrium. , and calculate the results of the volume-related measurement items based on the pre-established mapping relationship between the preset features including the three-dimensional volume data of the endometrium and the results of the volume-related measurement items.

For another example, step 111 automatically determines at least the results of non-volume-related measurement items based on the above three-dimensional volume data, where the non-volume-related measurement items include any one or more of endometrial classification and endometrial myometrium echo uniformity.

In some specific embodiments, step 111 calculates the results of non-volume-related measurement items through a classification algorithm based on the above-mentioned three-dimensional volume data.

In some specific embodiments, a mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of non-volume-related measurement items is established in advance; step 111 identifies the preset features in the acquired three-dimensional volume data containing the endometrium. Features, and calculate the results of the non-volume-related measurement items based on the pre-established mapping relationship between the preset features including the three-dimensional volume data of the endometrium and the results of the non-volume-related measurement items.

Step 113: Determine the endometrial receptivity result based on the results of the above-mentioned receptivity evaluation related measurement items.

In some embodiments, please refer to Figure 5. Step 110 automatically determines the above-mentioned endometrial receptivity result based on three-dimensional volume data including the following steps:

Step 115: Preliminarily establish a mapping relationship between preset features including the three-dimensional volume data of the endometrium and the receptivity results;

Step 117: Identify the preset features in the obtained three-dimensional volume data containing the endometrium, and calculate the receptivity result based on the mapping relationship between the preset features of the three-dimensional volume data containing the endometrium and the receptivity result.

Step 120: Control and output the above endometrial receptivity result.

The above are some descriptions of ultrasound imaging methods.

Referring to Figure 6, in some specific embodiments, the ultrasound imaging method includes the following steps:

Step 200: Obtain three-dimensional volume data including endometrium.

Step 210: Automatically segment the above three-dimensional volume data containing the endometrium to segment the endometrium. For example, step 210 is based on the difference in image features between the endometrium and the uterine basal tissue, and/or the cyclically changing morphological characteristics of the endometrium, and uses feature detection to segment the uterus from the above three-dimensional volume data containing the endometrium. membrane. For another example, step 210 obtains a model trained by machine learning, and segments the endometrium from the above three-dimensional volume data containing the endometrium based on the model.

Step 220: Automatically calculate volume-related measurement items and non-volume-related measurement items based on the segmented endometrium; the volume-related measurement items include endometrial thickness, endometrial volume, and endometrial blood perfusion indicators. Any one or more of the above non-volume-related measurement items include any one or more of endometrial classification and endometrial myometrial echo uniformity.

Step 230: Automatically determine the results of the receptivity evaluation-related measurement items based on the above volume-related measurement items and non-volume-related measurement items.

Step 240: Determine the endometrial receptivity result based on the results of the measurement items related to the receptivity evaluation. For example, step 240 calculates the score of the above-mentioned endometrial receptivity based on the results of the above-mentioned measurement items related to the receptivity evaluation, and then determines the endometrial receptivity result based on the above-mentioned endometrial receptivity score.

This document is described with reference to various exemplary embodiments. However, those skilled in the art will recognize that changes and modifications can be made to the exemplary embodiments without departing from the scope herein. For example, the various operational steps, as well as the components used to perform the operational steps, may be implemented in different ways (e.g., one or more steps may be eliminated, modified or incorporated into other steps).

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. Additionally, as will be understood by those skilled in the art, the principles herein may be reflected in a computer program product on a computer-readable storage medium preloaded with computer-readable program code. Any tangible, non-transitory computer-readable storage medium may be used, including magnetic storage devices (hard disk, floppy disk, etc.), optical storage devices (CD to ROM, DVD, Blu Ray disk, etc.), flash memory and/or the like . These computer program instructions may be loaded onto a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to form a machine, such that the instructions executed on the computer or other programmable data processing apparatus may generate a device that implements the specified functions. These computer program instructions may also be stored in a computer-readable memory, which may instruct a computer or other programmable data processing device to operate in a specific manner, such that the instructions stored in the computer-readable memory may form a Manufactured articles include devices that perform specified functions. Computer program instructions may also be loaded onto a computer or other programmable data processing device to perform a series of operating steps on the computer or other programmable device to produce a computer-implemented process such that the execution on the computer or other programmable device Instructions can provide steps for implementing a specified function.

Although the principles herein have been illustrated in various embodiments, many modifications of structure, arrangement, proportion, elements, materials and parts as are particularly suited to particular circumstances and operating requirements may be made without departing from the principles and scope of the disclosure. use. The above modifications and other changes or revisions are intended to be included within the scope of this document.

The foregoing detailed description has been described with reference to various embodiments. However, those skilled in the art will recognize that various modifications and changes can be made without departing from the scope of the disclosure. Accordingly, this disclosure is to be considered in an illustrative and not a restrictive sense, and all such modifications are to be included within its scope. Likewise, advantages, other advantages, and solutions to problems with respect to various embodiments have been described above. However, benefits, advantages, solutions to problems, and any elements that create these, or make the solution more explicit, should not be construed as critical, required, or essential. As used herein, the term "comprises" and any other variations thereof are intended to be non-exclusively inclusive such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also those not expressly listed or otherwise not part of the process , methods, systems, articles or other elements of equipment. Furthermore, the term "coupled" and any other variations thereof as used herein refers to physical connection, electrical connection, magnetic connection, optical connection, communication connection, functional connection and/or any other connection.

Those skilled in the art will recognize that many changes may be made in the details of the embodiments described above without departing from the basic principles of the invention. Therefore, the scope of the invention should be determined solely by the claims.

Claims (23)

1. An ultrasound imaging system, characterized by including:

   a probe for transmitting ultrasound waves to the tissue of interest including the endometrium and receiving corresponding ultrasound echo signals;

   A transmitting and receiving control circuit, used to control the probe to transmit ultrasonic waves and receive ultrasonic echo signals;

   a tolerance evaluation key that generates tolerance evaluation instructions in response to user operations;

   A processor, configured to process the corresponding ultrasound echo signal to obtain three-dimensional volume data including the endometrium; in response to the receptivity assessment instruction:

   The processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium;

   The processor automatically calculates volume-related measurement items and non-volume-related measurement items based on the segmented endometrium; the volume-related measurement items include endometrial thickness, endometrial volume, and endometrial blood perfusion. Any one or more of the indicators, the non-volume related measurement items include any one or more of endometrial classification and endometrial myometrium echo uniformity;

   The processor automatically determines the results of the receptivity evaluation-related measurement items based on the volume-related measurement items and non-volume-related measurement items;

   The processor determines the receptivity result of the endometrium based on the results of the measurement items related to the receptivity evaluation.
2. The ultrasound imaging system of claim 1, wherein the processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium, including:

   The processor segments the three-dimensional volume data containing the endometrium through feature detection based on the difference in image characteristics between the endometrium and the uterine basal tissue and/or the periodically changing morphological characteristics of the endometrium. endometrium;

   or,

   A model trained by machine learning is obtained, and the endometrium is segmented from the three-dimensional volume data containing the endometrium based on the model.
3. The ultrasonic imaging method according to claim 1, wherein the processor determines the receptivity result of the endometrium based on the results of the receptivity evaluation related measurement items, including:

   The processor calculates a score of the endometrial receptivity based on the results of the measurement items related to the receptivity evaluation;

   The processor determines an endometrial receptivity result based on the endometrial receptivity score.
4. An ultrasound imaging system, characterized by including:

   a probe for transmitting ultrasound waves to the tissue of interest including the endometrium and receiving corresponding ultrasound echo signals;

   A transmitting and receiving control circuit, used to control the probe to transmit ultrasonic waves and receive ultrasonic echo signals;

   A processor configured to process the corresponding ultrasonic echo signal to obtain three-dimensional volume data containing the endometrium, and automatically determine the receptivity result of the endometrium based on the three-dimensional volume data, and control Outputs the endometrial receptivity results.
5. The ultrasound imaging system of claim 4, wherein the processor automatically determines the endometrial receptivity result based on the three-dimensional volume data, including:

   The processor automatically determines the results of measurement items related to the receptivity evaluation based on the three-dimensional volume data;

   The processor determines the receptivity result of the endometrium based on the results of the measurement items related to the receptivity evaluation.
6. The ultrasonic imaging system of claim 5, wherein the processor automatically determines the results of receptivity evaluation-related measurement items based on the three-dimensional volume data, including: the processor at least Results of volume-related measurement items are automatically determined, and the volume-related measurement items include any one or more of endometrial thickness, endometrial volume, and endometrial blood perfusion indicators.
7. The ultrasonic imaging system of claim 6, wherein the processor automatically determines at least the results of volume-related measurement items based on the three-dimensional volume data, including:

   The processor automatically segments the three-dimensional volume data containing the endometrium to segment the endometrium; and calculates the volume-related measurement results based on the segmented endometrium; or,

   A mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the volume-related measurement items is established in advance; the processor identifies the preset features in the acquired three-dimensional volume data containing the endometrium, and performs the mapping according to the obtained three-dimensional volume data containing the endometrium. Describe the mapping relationship and calculate the results of volume-related measurement items.
8. The ultrasound imaging system of claim 7, wherein the processor calculates the volume-related measurement results based on the segmented endometrium, including:

   Based on the segmented endometrium, the processor counts the number of pixels belonging to the endometrium to obtain the pixel volume of the endometrium; the processor uses the conversion relationship between the pixel distance and the actual physical distance , convert the pixel volume of the endometrium into the actual physical volume of the endometrium as the endometrial volume;

   and / or,

   The processor locates the sagittal plane of the endometrium based on the segmented endometrium, and calculates the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrial thickness;

   and / or,

   The processor counts the color Doppler blood flow signal intensity and the number of pixels in the endometrium area based on the segmented endometrium to calculate the blood perfusion index of the endometrium.
9. The ultrasonic imaging system of claim 5, wherein the processor automatically determines the results of receptivity evaluation-related measurement items based on the three-dimensional volume data, including: the processor at least Automatically determine results of non-volume-related measurements, including any one or more of endometrial classification and endometrial myometrium echogenicity.
10. The ultrasound imaging system of claim 9, wherein the processor automatically determines at least the results of non-volume-related measurement items based on the three-dimensional volume data, including:

    The processor calculates results of non-volume-related measurement items through a classification algorithm based on the three-dimensional volume data;

    or,

    A mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the non-volume-related measurement items is established in advance; the processor identifies the preset features in the acquired three-dimensional volume data containing the endometrium, and performs the mapping according to The mapping relationship calculates the results of non-volume related measurement items.
11. The ultrasound imaging system of claim 4, wherein the processor automatically determines the endometrial receptivity result based on the three-dimensional volume data, including:

    A mapping relationship between preset characteristics and receptivity results including the three-dimensional volume data of the endometrium is established in advance;

    The processor identifies preset features in the acquired three-dimensional volume data including endometrium, and calculates receptivity results based on the mapping relationship.
12. An ultrasound imaging method, characterized by including:

    Obtain three-dimensional volumetric data containing the endometrium;

    Automatically segment the three-dimensional volume data containing the endometrium to segment the endometrium;

    According to the segmented endometrium, volume-related measurement items and non-volume-related measurement items are automatically calculated; the volume-related measurement items include any of endometrial thickness, endometrial volume, and endometrial blood perfusion indicators. One or more, the non-volume related measurement items include any one or more of endometrial classification and endometrial myometrium echo uniformity;

    Automatically determine the results of the receptivity evaluation-related measurement items based on the volume-related measurement items and non-volume-related measurement items;

    The endometrial receptivity result is determined based on the results of the measurement items related to the receptivity evaluation.
13. The ultrasonic imaging method according to claim 12, wherein the automatic segmentation of the three-dimensional volume data containing the endometrium to segment the endometrium includes:

    Segment the endometrium from the three-dimensional volume data containing the endometrium through feature detection based on the difference in image characteristics between the endometrium and the uterine basal tissue and/or the cyclically changing morphological characteristics of the endometrium;

    or,

    A model trained by machine learning is obtained, and the endometrium is segmented from the three-dimensional volume data containing the endometrium based on the model.
14. The ultrasonic imaging method according to claim 12, wherein determining the endometrial receptivity result based on the results of the receptivity evaluation related measurement items includes:

    Calculate a score of the endometrial receptivity based on the results of the measurement items related to the receptivity evaluation;

    Endometrial receptivity results are determined based on the endometrial receptivity score.
15. An ultrasound imaging method, characterized by including:

    Obtain three-dimensional volumetric data containing the endometrium;

    Automatically determine the endometrial receptivity result based on the three-dimensional volumetric data;

    Control output of the endometrial receptivity results.
16. The ultrasonic imaging method according to claim 15, wherein the automatic determination of the endometrial receptivity result based on the three-dimensional volume data includes:

    Automatically determine the results of measurement items related to receptivity evaluation based on the three-dimensional volume data;

    The endometrial receptivity result is determined based on the results of the measurement items related to the receptivity evaluation.
17. The ultrasonic imaging method of claim 16, wherein automatically determining the results of receptivity evaluation-related measurement items based on the three-dimensional volume data includes: automatically determining at least volume-related measurement items based on the three-dimensional volume data. As a result, the volume-related measurement items include any one or more of endometrial thickness, endometrial volume, and endometrial blood perfusion indicators.
18. The ultrasonic imaging method according to claim 17, wherein the result of automatically determining at least volume-related measurement items based on the three-dimensional volume data includes:

    Automatically segment the three-dimensional volume data containing the endometrium to segment the endometrium; calculate the volume-related measurement results based on the segmented endometrium; or, pre-establish a three-dimensional volume data containing the endometrium. The mapping relationship between the preset characteristics of the volume data and the results of the volume-related measurement items; identifying the preset characteristics in the acquired three-dimensional volume data including the endometrium, and calculating the results of the volume-related measurement items based on the mapping relationship.
19. The ultrasonic imaging method of claim 18, wherein calculating the volume-related measurement results based on the segmented endometrium includes:

    Based on the segmented endometrium, the number of pixels belonging to the endometrium is counted to obtain the pixel volume of the endometrium; through the conversion relationship between the pixel distance and the actual physical distance, the endometrium is calculated The pixel volume is converted into the actual physical volume of the endometrium as the endometrial volume;

    and / or,

    Based on the segmented endometrium, locate the sagittal plane of the endometrium, and calculate the thickness of the thickest part of the endometrium in the sagittal plane of the endometrium as the endometrial thickness;

    and / or,

    Based on the segmented endometrium, the color Doppler blood flow signal intensity and the number of pixels in the endometrium area are counted to calculate the blood perfusion index of the endometrium.
20. The ultrasonic imaging method of claim 16, wherein automatically determining results of receptivity evaluation-related measurement items based on the three-dimensional volume data includes: automatically determining at least non-volume-related measurements based on the three-dimensional volume data. The non-volume-related measurement items include any one or more of endometrial classification and endometrial myometrial echo uniformity.
21. The ultrasonic imaging method according to claim 20, wherein the automatically determining results of at least non-volume-related measurement items based on the three-dimensional volume data includes:

    Calculate results of non-volume-related measurement items based on the three-dimensional volumetric data through a classification algorithm;

    or,

    Establish in advance a mapping relationship between preset features of the three-dimensional volume data containing the endometrium and the results of the non-volume-related measurement items; identify the preset features in the acquired three-dimensional volume data containing the endometrium, and use the mapping relationship according to the , calculates the results of non-volume-related measurements.
22. The ultrasonic imaging method according to claim 15, wherein the automatic determination of the endometrial receptivity result based on the three-dimensional volume data includes:

    A mapping relationship between preset characteristics and receptivity results including the three-dimensional volume data of the endometrium is established in advance;

    Preset features in the acquired three-dimensional volume data containing the endometrium are identified, and the receptivity result is calculated based on the mapping relationship.
23. A computer-readable storage medium, characterized in that a program is stored on the computer-readable storage medium, and the program can be executed by a processor to implement the method according to any one of claims 12 to 22.

Images