Evaluation method based on hysterosalpingography imaging and ultrasound imaging system

Abstract

An evaluation method based on hysterosalpingography imaging and an ultrasonic imaging system, the ultrasonic imaging system comprises an ultrasonic probe, a transmitting circuit, a receiving circuit and a processor, the processor is used for: controlling the ultrasonic probe to emit ultrasonic waves to a hysterosalpingography tissue containing a contrast agent, receiving echoes of the ultrasonic waves to obtain ultrasonic echo signals, and obtaining contrast volume data based on the ultrasonic echo signals; determining feature information of key feature structures according to the contrast volume data, the key feature structures comprising at least one of a hysterosalpingography, an uterine cavity, an ovary and a pelvic cavity; obtaining evaluation results corresponding to the feature information of the at least one key feature structure based on a corresponding relationship between the feature information of the key feature structures and corresponding hysterosalpingography patency evaluation indexes; determining hysterosalpingography patency according to the at least one evaluation result, and controlling a display to display the hysterosalpingography patency. The present application automatically determines the hysterosalpingography patency based on hysterosalpingography imaging, and improves the work efficiency of doctors.

Description

Technical Field

[0001] This application relates to the field of ultrasound imaging technology, and more specifically to an evaluation method and ultrasound imaging system based on hysterosalpingography. Background Technology

[0002] According to the World Health Organization, infertility has become the third leading cause of disease affecting human health. In modern industrialized society, factors such as inflammation and infection, environmental pollution, advanced maternal age, and fast-paced lifestyles are contributing to a year-on-year increase in infertility rates and a trend towards affecting younger people. Therefore, strengthening infertility screening and assessment is crucial.

[0003] In clinical practice, fallopian tube patency testing is a crucial step in infertility diagnosis. The fallopian tubes are a major component of the female reproductive system, serving as the tubular passageway for the transport of eggs, sperm, and fertilized eggs, and the site of fertilization. Tubal-related infertility accounts for 30-50% of all infertility cases. Therefore, assessing fallopian tube patency is essential for the diagnosis of infertility.

[0004] With the development of modern medical imaging technology, transvaginal ultrasound imaging (HSI) allows for immediate and repeatable examinations without requiring a special examination environment. It enables rapid and non-invasive assessment of fallopian tube patency before, during, and after clinical treatment, and is simple, inexpensive, and easy to promote. However, in clinical practice, the fallopian tube structure is complex and tortuous. Comprehensive assessment of fallopian tube patency under HSI conditions relies heavily on the physician's diagnostic experience, is highly subjective, and is prone to misdiagnosis and missed diagnosis. Summary of the Invention

[0005] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0006] One embodiment of the present invention provides an ultrasound imaging system, the ultrasound imaging system comprising:

[0007] Ultrasonic probe;

[0008] A transmitting circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fallopian tube tissue containing contrast agent;

[0009] A receiving circuit is used to control the ultrasonic probe to receive the echo of the ultrasonic wave in order to obtain an ultrasonic echo signal;

[0010] Processor, used for:

[0011] The contrast volume data is obtained based on the ultrasound echo signal;

[0012] The feature information of key feature structures is determined based on the imaging volume data, wherein the key feature structures include at least one of the fallopian tube, uterine cavity, ovary and pelvic cavity;

[0013] Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained;

[0014] The patency of the fallopian tubes is determined based on the evaluation results corresponding to the feature information of at least one of the key feature structures, and the display is controlled to show the patency of the fallopian tubes.

[0015] In one embodiment, obtaining the evaluation result corresponding to the feature information of at least one of the key feature structures based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators includes at least one of the following:

[0016] The assessment results corresponding to the shape of the fallopian tube are obtained based on the correspondence between the preset shape and the fallopian tube patency assessment index.

[0017] The assessment results corresponding to the shape of the uterine cavity are obtained based on the correspondence between the preset shape and the fallopian tube patency assessment index.

[0018] The evaluation results corresponding to the contrast agent enhancement level around the ovary are obtained based on the correspondence between the preset contrast agent enhancement level and the fallopian tube patency assessment index.

[0019] The assessment results corresponding to the contrast agent diffusion level in the pelvic cavity are obtained based on the correspondence between the preset contrast agent diffusion level and the fallopian tube patency assessment index.

[0020] In one embodiment, the processor is further configured to: acquire the speed at which the contrast agent enters the fallopian tube from the uterine cavity; the assessment result corresponding to the shape of the uterine cavity based on the correspondence between the preset shape and the fallopian tube patency assessment index includes: acquiring the assessment result corresponding to the shape of the uterine cavity and the speed at which the contrast agent enters the fallopian tube from the uterine cavity based on the preset shape and the correspondence between the preset speed of the contrast agent entering the fallopian tube from the uterine cavity and the fallopian tube patency assessment index.

[0021] In one embodiment, obtaining the speed at which the contrast agent enters the fallopian tube from the uterine cavity includes: determining the pixel coordinates of the contrast agent signal based on the contrast volume data of the uterine cavity; determining the difference between the pixel coordinates of the contrast agent signal in adjacent frames of the contrast volume data; and determining the speed at which the contrast agent enters the fallopian tube from the uterine cavity based on the difference, the physical distance corresponding to a unit pixel, and the frame rate of the contrast volume data.

[0022] In one embodiment, obtaining the speed at which the contrast agent enters the fallopian tube from the uterine cavity includes: obtaining the speed at which the contrast agent enters the fallopian tube from the uterine cavity, as input by the user.

[0023] In one embodiment, obtaining the evaluation result corresponding to the feature information of at least one key feature structure based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators includes: determining at least one candidate region in the imaging volume data of the key feature structure; determining a sub-evaluation result for each candidate region based on the image features of each candidate region; and selecting the sub-evaluation result with the highest probability from the sub-evaluation results of the at least one candidate region as the evaluation result corresponding to the feature information of the key feature structure.

[0024] In one embodiment, obtaining the evaluation result corresponding to the feature information of at least one of the key feature structures based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators includes: classifying the imaging volume data of the key feature structure using a trained machine learning model to obtain the evaluation result corresponding to the feature information of the key feature structure.

[0025] In one embodiment, the fallopian tube patency assessment index further includes a fallopian tube patency assessment index corresponding to a preset intrauterine pressure and / or a fallopian tube patency assessment index corresponding to a preset pain level.

[0026] In one embodiment, the processor is further configured to: acquire the intrauterine pressure measured by a pressure sensor during the injection of contrast agent, obtain an assessment result of the intrauterine pressure based on a preset correspondence between intrauterine pressure and fallopian tube patency assessment index, or receive an assessment result of the intrauterine pressure input by a user based on the fallopian tube patency assessment index corresponding to the preset intrauterine pressure.

[0027] In one embodiment, the processor is further configured to: receive, by the user, an assessment result of the pain level of the subject based on the fallopian tube patency assessment index corresponding to the preset pain level.

[0028] In one embodiment, obtaining the fallopian tube patency based on the evaluation results corresponding to the feature information of the at least one key feature structure includes: classifying or regressing the evaluation results corresponding to the feature information of the at least one key feature structure using a trained classifier to obtain the fallopian tube patency.

[0029] In one embodiment, the processor is further configured to control the display to show the evaluation results corresponding to the feature information of the at least one key feature structure.

[0030] In one embodiment, displaying the evaluation results corresponding to the feature information of the at least one key feature structure includes: displaying the evaluation results corresponding to the feature information of the at least one key feature structure in a graphical or list format.

[0031] In one embodiment, the graph includes a radar chart, which comprises: a classification axis dividing the radar chart into multiple partitions, each classification axis or each partition representing a fallopian tube patency assessment index; at least one classification axis or at least one partition having a scale unit for representing a preset assessment result corresponding to the fallopian tube patency assessment index; a feature graph generated on the radar chart based on the assessment result corresponding to the feature information of the at least one key feature structure; and an identifier representing the fallopian tube patency.

[0032] In one embodiment, each classification axis is used to represent a fallopian tube patency assessment index, and the feature graph is a graph formed by connecting the coordinate points on each classification axis that represent the assessment results of the fallopian tube patency assessment index corresponding to the classification axis, and each classification axis is marked with the fallopian tube patency assessment index corresponding to the classification axis.

[0033] In one embodiment, the processor is further configured to: render the contrast volume data to obtain a contrast image, and control the display to display the contrast image.

[0034] In one embodiment, the processor is further configured to: acquire tissue volume data based on the ultrasound echo signal; render the tissue volume data to obtain a tissue image; and control the display to display the tissue image.

[0035] A second aspect of the present invention provides an ultrasound imaging system, the ultrasound imaging system comprising:

[0036] Ultrasonic probe;

[0037] A transmitting circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fallopian tube tissue containing contrast agent;

[0038] A receiving circuit is used to control the ultrasonic probe to receive the echo of the ultrasonic wave in order to obtain an ultrasonic echo signal;

[0039] Processor, used for:

[0040] Based on the ultrasound echo signal, obtain contrast volume data and tissue volume data;

[0041] The feature information of key feature structures is determined based on the contrast volume data and the tissue volume data, wherein the key feature structures include at least one of the fallopian tube, uterine cavity, ovary and pelvic cavity;

[0042] Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained;

[0043] The patency of the fallopian tubes is determined based on the evaluation results corresponding to the feature information of at least one of the key feature structures, and the patency of the fallopian tubes is displayed.

[0044] A third aspect of this invention provides an evaluation method based on hysterosalpingography (HSG), the method comprising:

[0045] The ultrasound probe is controlled to emit ultrasound waves toward the fallopian tube tissue containing contrast agent, and the echo of the ultrasound waves is received to obtain ultrasound echo signals, and the contrast volume data is obtained based on the ultrasound echo signals.

[0046] The feature information of key feature structures is determined based on the imaging volume data, wherein the key feature structures include at least one of the fallopian tube, uterine cavity, ovary and pelvic cavity;

[0047] Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained;

[0048] The patency of the fallopian tubes is determined based on the evaluation results corresponding to the feature information of at least one of the key feature structures, and the patency of the fallopian tubes is displayed.

[0049] A fourth aspect of this invention provides an evaluation method based on hysterosalpingography (HSG), the method comprising:

[0050] The ultrasound probe is controlled to emit ultrasound waves toward the fallopian tube tissue containing contrast agent, and the echo of the ultrasound waves is received to obtain ultrasound echo signals. Based on the ultrasound echo signals, contrast volume data and tissue volume data are obtained.

[0051] The feature information of key feature structures is determined based on the contrast volume data and the tissue volume data, wherein the key feature structures include at least one of the fallopian tube, uterine cavity, ovary and pelvic cavity;

[0052] Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained;

[0053] The patency of the fallopian tubes is determined based on the evaluation results corresponding to the feature information of at least one of the key feature structures, and the patency of the fallopian tubes is displayed.

[0054] The ultrasound imaging system and the assessment method based on hysterosalpingography (HSG) of this invention can automatically determine the patency of the fallopian tubes based on HSG imaging, thereby improving the efficiency of doctors' work. Attached Figure Description

[0055] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of the invention in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of the invention and form part of the specification. They are used together with the embodiments of the invention to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0056] Figure 1 A structural block diagram of an ultrasound imaging system according to an embodiment of the present invention is shown;

[0057] Figure 2 A radar chart is shown according to an embodiment of the present invention;

[0058] Figure 3 A schematic flowchart illustrating an evaluation method based on hysterosalpingography according to an embodiment of the present invention is shown.

[0059] Figure 4 A schematic flowchart illustrating an evaluation method based on hysterosalpingography according to another embodiment of the present invention is shown. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application more apparent, exemplary embodiments according to this application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are merely a part of the embodiments of this application, and not all of the embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein. Based on the embodiments of the present invention described in this application, all other embodiments obtained by those skilled in the art without inventive effort should fall within the protection scope of this application.

[0061] The following description provides numerous specific details to offer a more thorough understanding of this application. However, it will be apparent to those skilled in the art that this application can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described to avoid confusion with this application.

[0062] It should be understood that this application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. Rather, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of this application to those skilled in the art.

[0063] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. When used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising” and / or “including,” when used in this specification, identify the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups. When used herein, the term “and / or” includes any and all combinations of the associated listed items.

[0064] To fully understand this application, a detailed structure will be presented in the following description to illustrate the technical solution proposed in this application. Optional embodiments of this application are described in detail below; however, in addition to these detailed descriptions, this application may have other implementation methods.

[0065] The evaluation method and ultrasound imaging system based on hysterosalpingography provided in this application can be applied to humans and various animals.

[0066] Below, first refer to Figure 1 An ultrasound imaging system according to an embodiment of this application is described. Figure 1 A schematic structural block diagram of an ultrasound imaging system 100 according to an embodiment of the present invention is shown.

[0067] like Figure 1 As shown, the ultrasound imaging system 100 includes an ultrasound probe 110, a transmitting circuit 112, a receiving circuit 114, a processor 116, and a display 118. Further, the ultrasound imaging system may also include a transmit / receive selection switch 120 and a beamforming module 122. The transmitting circuit 112 and the receiving circuit 114 can be connected to the ultrasound probe 110 via the transmit / receive selection switch 120.

[0068] The ultrasonic probe 110 includes multiple transducer elements. These elements can be arranged in a row to form a linear array, or in a two-dimensional matrix to form a planar array. They can also form a convex array. Each transducer element is used to emit ultrasonic waves based on an excitation electrical signal, or to convert received ultrasonic waves into electrical signals. Therefore, each transducer element can be used to achieve the mutual conversion between electrical pulse signals and ultrasonic waves, thereby enabling the emission of ultrasonic waves to the target area of ​​the object being tested, and also to receive ultrasonic wave echoes reflected back from the tissue. During ultrasonic testing, the transmission and reception sequences can be used to control which transducer elements are used to emit ultrasonic waves and which are used to receive ultrasonic waves, or to control the transducer elements to be used in time-slotted manner for emitting ultrasonic waves or receiving ultrasonic wave echoes. Transducer elements participating in ultrasonic wave emission can be simultaneously excited by electrical signals, thus emitting ultrasonic waves simultaneously; alternatively, transducer elements participating in ultrasonic beam emission can be excited by several electrical signals with a certain time interval, thus continuously emitting ultrasonic waves with a certain time interval.

[0069] During ultrasound imaging, processor 116 controls transmitting circuit 112 to send a delayed-focused transmission pulse to ultrasound probe 110 via transmit / receive selection switch 120. Excited by the transmission pulse, ultrasound probe 110 emits an ultrasonic beam towards the tissue of the target area of ​​the object being measured. After a certain delay, it receives the ultrasonic echo reflecting back from the tissue of the target area, carrying tissue information, and converts this ultrasonic echo back into an electrical signal. Receiving circuit 114 receives the electrical signal generated by ultrasound probe 110, obtains the ultrasonic echo signal, and sends these ultrasonic echo signals to beamforming module 122. Beamforming module 122 performs focusing delay, weighting, and channel summation on the ultrasonic echo data before sending it to processor 116. Processor 116 performs signal detection, signal enhancement, data conversion, and logarithmic compression on the ultrasonic echo signal to form an ultrasound image. The ultrasound image obtained by processor 116 can be displayed on display 118 or stored in memory 124.

[0070] Optionally, the processor 116 can be implemented as software, hardware, firmware, or any combination thereof, and can use one or more application-specific integrated circuits (ASICs), one or more general-purpose integrated circuits, one or more microprocessors, one or more programmable logic devices, or any combination of the foregoing circuits and / or devices, or other suitable circuits or devices. Furthermore, the processor 116 can control other components in the ultrasound imaging system 100 to perform the corresponding steps of the methods in the various embodiments of this specification.

[0071] The display 118 is connected to the processor 116. The display 118 can be a touch screen, an LCD screen, etc.; or, the display 118 can be an independent display such as an LCD screen or a television, separate from the ultrasound imaging system 100; or, the display 118 can be the screen of an electronic device such as a smartphone or tablet, etc. The number of displays 118 can be one or more.

[0072] The display 118 can display the ultrasound images obtained by the processor 116. Furthermore, while displaying the ultrasound images, the display 118 can also provide a graphical user interface for human-machine interaction. One or more controlled objects can be set on the graphical interface, allowing the user to input operation commands using a human-machine interaction device to control these controlled objects and perform corresponding control operations. For example, icons can be displayed on the graphical interface, and the human-machine interaction device can be used to operate these icons to perform specific functions, such as drawing a region of interest bounding box on the ultrasound image.

[0073] Optionally, the ultrasound imaging system 100 may also include other human-machine interface devices besides the display 118, which are connected to the processor 116. For example, the processor 116 may be connected to the human-machine interface device via an external input / output port, which may be a wireless communication module, a wired communication module, or a combination of both. The external input / output port may also be based on USB, bus protocols such as CAN, and / or wired network protocols.

[0074] The human-computer interaction device may include an input device for detecting user input information. This input information may be, for example, control commands for the timing of ultrasound transmission / reception, operational input commands for drawing points, lines, or boxes on an ultrasound image, or other types of commands. The input device may include one or a combination of several of the following: a keyboard, mouse, scroll wheel, trackball, mobile input device (e.g., a mobile device with a touchscreen, a mobile phone, etc.), a multi-function knob, etc. The human-computer interaction device may also include an output device such as a printer.

[0075] The ultrasound imaging system 100 may also include a memory 124 for storing instructions executed by the processor, storing received ultrasound echoes, storing ultrasound images, etc. The memory may be a flash memory card, solid-state memory, hard disk, etc. It may be volatile and / or non-volatile memory, removable memory and / or non-removable memory, etc.

[0076] The ultrasound imaging system 100 of this invention is used to assess fallopian tube patency based on hysterosalpingography (HSG). During the process of obtaining fallopian tube patency, the transmitting circuit 112 excites the ultrasound probe 110 to emit ultrasound waves towards the fallopian tube tissue containing contrast agent; the receiving circuit 114 controls the ultrasound probe to receive the echo of the ultrasound waves to obtain an ultrasound echo signal; the processor 116 is used to: acquire HSG volume data based on the ultrasound echo signal; determine the feature information of key feature structures based on the HSG volume data, wherein the key feature structures include at least one of the fallopian tubes, uterine cavity, ovary, and pelvic cavity; obtain the assessment result corresponding to the feature information of at least one key feature structure based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators; determine the fallopian tube patency based on the assessment result corresponding to the feature information of at least one key feature structure; and control the display to show the fallopian tube patency.

[0077] For example, during hysterosalpingography (HSG), the patient is first placed in the lithotomy position for a routine transvaginal two-dimensional ultrasound scan to determine the basic features and locations of key structures within the fallopian tubes. This fallopian tube tissue includes not only the fallopian tubes themselves but also other tissues related to fallopian tube patency, such as the uterine cavity, pelvic cavity, and ovaries. Next, saline solution is injected into the uterine cavity, and the scanning angle and position of the transvaginal volume probe are set to ensure that all key structures are within the scannable range. Then, contrast agent is injected into the uterine cavity, and the fallopian tube tissue containing the contrast agent is subjected to a three-dimensional or four-dimensional volume scan.

[0078] During the scan, the transmitting circuit 112 excites the ultrasound probe 110 to emit ultrasound waves towards the fallopian tube tissue containing contrast agent; the receiving circuit 114 controls the ultrasound probe 110 to receive the echo of the ultrasound waves to obtain an ultrasound echo signal. After signal amplification and analog-to-digital conversion, the signal is transmitted to the beamforming module 122 for beamforming processing. Then, the beamformed ultrasound echo signal is sent to the processor 116, which performs three-dimensional reconstruction of the ultrasound echo signal to obtain contrast volume data. The contrast volume data may include three-dimensional contrast volume data or four-dimensional contrast volume data.

[0079] The processor 116 is also used to determine feature information of key feature structures based on the imaging volume data. Key feature structures are feature structures related to the patency of the fallopian tubes, specifically including at least one of the following: fallopian tubes, uterine cavity, ovary, and pelvic cavity.

[0080] For example, determining the feature information of key feature structures first requires detecting or segmenting the key feature structures in the contrast volume data. For instance, the detection or segmentation of key feature structures can be achieved based on traditional grayscale and morphological feature detection methods; alternatively, machine learning or deep learning methods can be used to detect or accurately segment the corresponding key feature structures in the contrast volume data.

[0081] Because the uterine cavity appears bright and its morphology is significantly different from the surrounding tissues when the contrast agent is fully infused, when detecting or segmenting key feature structures using traditional feature detection methods, the uterine cavity can first be detected in the contrast volume data using morphological and other feature detection methods. The uterine cavity consists of three parts: the uterine horn, the uterine body, and the cervix. When the uterine horn of the uterine cavity points upward and the two sides of the uterine body are symmetrical, it indicates that the uterine cavity is in a correct position. The fallopian tubes on both sides of the uterine cavity are directly connected to the uterine horn, and the ends of the fallopian tubes are the ovaries. In the contrast volume data after the uterine cavity is correctly positioned, pelvic diffusion is reflected behind the uterine cavity. Because the uterine cavity has the above-mentioned spatial relationship with other key feature structures, the detection of each key feature structure can be achieved by detecting each part of the uterine cavity.

[0082] For example, the hysterosalpingography (HSG) volume data is first binary segmented, and after some necessary morphological operations, multiple possible regions are obtained. Then, based on the shape, grayscale, brightness, and other features of each possible region, the probability that the region is the uterine cavity is determined, and the region with the highest probability is selected as the uterine cavity region. Within the detected uterine cavity region, the uterine horn is located based on its morphological features, and the HSG volume data is rotated to align the uterine horn upwards. Next, based on the symmetry of the uterine body region within the uterine cavity, the HSG volume data is further rotated to ensure the uterine cavity is in a correct position. If the HSG volume data only shows one uterine horn and the other is missing, only that uterine horn is detected, and the uterine cavity is aligned using the symmetry of the uterine body. Other key feature structures are then detected based on the aligned uterine cavity. Of course, in addition to morphological features, other traditional grayscale detection or segmentation methods can also be used to detect or segment key feature structures in the HSG volume data, such as OTSU thresholding, level set, graph cut, and Snake.

[0083] When using machine learning or deep learning methods to detect or segment key feature structures (such as the uterine cavity) in contrast imaging volume data, an expert database needs to be pre-built. This expert database refers to the labeling of key feature structures in the contrast imaging volume data based on the knowledge and experience of experts. Based on the labeling of key feature structures in the expert database, machine learning and / or deep learning algorithms are applied to learn the characteristics or patterns that distinguish key feature structures from other regions, thereby achieving automatic detection or segmentation of key feature structures.

[0084] One approach is to combine traditional image feature extraction methods with classifier classification to detect or segment key feature structures. For example, a traditional image feature extraction method might be based on a sliding window: first, image features are extracted from the region within the sliding window. These features can be traditional PCA, LDA, Haar features, texture features, etc., or deep neural networks can be used for feature extraction. Then, the extracted image features are matched against an expert database, and classifiers such as KNN, SVM, random forest, and other neural networks are used for classification to determine whether the current sliding window contains key feature structures and to obtain their specific categories.

[0085] Another approach is to use a deep learning-based bounding box method for identifying key feature structures. Specifically, a deep learning network is trained by stacking convolutional and fully connected layers to learn features and regress parameters from the constructed database. For the acquired imaging volume data, the bounding boxes of the corresponding key feature structures can be directly regressed using the deep learning network, while simultaneously obtaining the categories of the key feature structures within the bounding boxes. Optional deep learning networks include, but are not limited to, R-CNN, Fast R-CNN, Faster R-CNN, SSD, and YOLO.

[0086] In addition, key feature structures can be identified using end-to-end semantic segmentation networks based on deep learning. This approach is similar to the second implementation, except that the fully connected layers of the deep learning network are removed, and upsampling layers or deconvolution layers are added to make the input and output sizes the same. This allows the key feature structures and their corresponding categories in the input imaging volumetric data to be directly obtained. Optional semantic segmentation networks include, but are not limited to, FCN, U-Net, and Mask R-CNN.

[0087] Optionally, any one of the above methods can be used to locate the key feature structure, and then a classifier can be designed to determine its category based on the localization result. Optional classification methods include: first, extracting features from the target region, such as traditional PCA, LDA, Haar features, texture features, etc., or using deep neural networks for feature extraction; then matching the extracted features with a database and classifying them using classifiers such as KNN, SVM, random forest, or other neural networks.

[0088] It should be understood that the present invention is not limited to the specific target identification method used. Both existing target identification methods and future target identification methods can be applied to the ultrasound imaging system 100 according to the embodiments of the present invention.

[0089] The processor 116 can use a combination of one or more of the above methods to detect or segment the position of the uterine cavity in the imaging volume data. Based on this, it can combine the other key feature structures with the relative spatial position of the uterine cavity after alignment, and perform detection or segmentation of other key feature structures based on one or more of the above target recognition methods.

[0090] For four-dimensional contrast-enhanced volume data, the processor 116 or a manual operator must first select three-dimensional contrast-enhanced volume data with complete contrast agent perfusion from the four-dimensional contrast-enhanced volume data, and then detect or segment key feature structures. The specific methods for detecting or segmenting key feature structures can employ the methods described above for detecting or segmenting key feature structures in three-dimensional contrast-enhanced volume data. Similarly, the selection of three-dimensional contrast-enhanced volume data with complete contrast agent perfusion by the processor 116 from the four-dimensional contrast-enhanced volume data can also be performed using one or more of the aforementioned target detection or segmentation methods.

[0091] Subsequently, the processor 116 can also render the hysterosalpingography (HSG) volume data to obtain an HSG image, and control the display 118 to display the HSG image. After obtaining the fallopian tube patency based on the HSG volume data, the user can perform comparative analysis of the HSG image and the fallopian tube patency.

[0092] For example, for the detected or segmented uterine cavity region, the positions of the uterine horns and cervix can be identified using any of the aforementioned target recognition methods. The uterine horns are aligned upwards, the cervix downwards, and the uterine body is generally symmetrical front to back and side to side. Volumetric rendering imaging is then performed to obtain a good uterine image. Volumetric rendering imaging displays the uterine volume data within the region of interest using algorithms such as ray tracing through different imaging modes. The alignment of the uterine volume data can be achieved by the processor 116. That is, after detecting or segmenting key feature structures such as the uterine cavity, the orientation of the uterine volume data can be automatically adjusted according to the relative positions of the various parts of the uterine cavity. Simultaneously, for cases with poor image quality or deviations in the positions of key feature structures detected by the algorithm, the user can manually adjust the angle of the uterine volume data by rotation.

[0093] During contrast imaging, the ultrasound probe 110 receives ultrasound echo signals including ultrasound echo signals carrying tissue information and ultrasound echo signals reflected by the contrast agent. Optionally, the processor 116 can also acquire tissue volume data based on the ultrasound echo signals, render the tissue volume data to obtain a tissue image, and control the display 118 to display the tissue image. The tissue image can provide more information about tissue structure than the contrast image.

[0094] The processor 116 is also used to obtain an evaluation result corresponding to the feature information of at least one key feature structure based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators. This evaluation result can be a specific score value.

[0095] Optionally, for the four key feature structures of fallopian tubes, uterine cavity, ovary and pelvis, the preset feature information related to fallopian tube patency is the preset morphology of the fallopian tubes, the preset morphology of the uterine cavity, the preset contrast agent enhancement level around the ovary and the preset contrast agent diffusion level in the pelvis. Therefore, the assessment result corresponding to the feature information of at least one key feature structure obtained based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators may include at least one of the following: the assessment result corresponding to the fallopian tube morphology determined by the contrast volume data based on the correspondence between preset morphology (i.e., preset morphology of the fallopian tube) and fallopian tube patency assessment indicators; the assessment result corresponding to the uterine cavity morphology determined by the contrast volume data based on the correspondence between preset morphology (i.e., preset morphology of the uterine cavity) and fallopian tube patency assessment indicators; the assessment result corresponding to the contrast agent enhancement level around the ovary determined by the contrast volume data based on the correspondence between preset contrast agent enhancement level (i.e., preset contrast agent enhancement level around the ovary) and fallopian tube patency assessment indicators; and the assessment result corresponding to the contrast agent diffusion level in the pelvis determined by the contrast volume data based on the correspondence between preset contrast agent diffusion level (i.e., preset contrast agent diffusion level in the pelvis) and fallopian tube patency assessment indicators.

[0096] See Table 1. The first four columns of Table 1 show the correspondence between the preset morphology of the fallopian tubes and the fallopian tube patency assessment index based on fallopian tube morphology, the preset morphology of the uterine cavity and the fallopian tube patency assessment index based on uterine cavity morphology, the preset contrast agent enhancement level around the ovary and the fallopian tube patency assessment index based on the contrast agent enhancement level around the ovary, and the preset contrast agent diffusion level in the pelvis and the fallopian tube patency assessment index based on the contrast agent diffusion level in the pelvis.

[0097] Taking the fallopian tube patency assessment indicators based on fallopian tube morphology as an example, the preset morphology of the fallopian tube mainly includes whether the fallopian tube runs smoothly, whether its shape is excessively tortuous, the continuity of visualization on both sides of the fallopian tube, and the visualization of the fimbriae. If the fallopian tube morphology in the hysterosalpingography (HSG) volume data matches the preset morphology corresponding to a certain preset assessment result, then that preset assessment result is taken as the assessment result corresponding to the fallopian tube in the HSG volume data. According to the fallopian tube patency assessment indicators in Table 1, the correspondence between the preset morphology of the fallopian tube and the fallopian tube patency assessment indicators based on fallopian tube morphology includes:

[0098] 1) If the pre-defined shape of the fallopian tube is natural, smooth, and has a smooth diameter, the corresponding pre-defined assessment result is 1 point;

[0099] 2) If the preset morphology of the fallopian tube is rigid, tortuous, coiled, angularly reflected, dilated and / or with little contrast agent leakage at the fimbriae and / or delayed visualization of the fallopian tube, the corresponding preset assessment result is 2 points.

[0100] 3) If the preset morphology of the fallopian tube is no contrast material throughout and / or no contrast material in the mid-distal section and / or no contrast material leakage at the fimbriae, the corresponding preset assessment result is 3 points.

[0101] Table 1. Indicators for assessing fallopian tube patency

[0102]

[0103] Similarly, the assessment indicators for the patency of the other key structural features of the fallopian tubes can also be evaluated according to Table 1.

[0104] In one embodiment, obtaining the evaluation result corresponding to the feature information of at least one key feature structure based on the correspondence between preset feature information and the corresponding fallopian tube patency assessment index includes: determining at least one candidate region in the imaging volume data of the key feature structure; determining a sub-evaluation result for each candidate region based on the image features of each candidate region; and selecting the sub-evaluation result with the highest probability from the sub-evaluation results of at least one candidate region as the evaluation result corresponding to the feature information of the key feature structure.

[0105] Specifically, candidate regions can be identified in the contrast volume data of key feature structures based on traditional grayscale and / or morphological target detection or segmentation methods. For example, the proximal and distal regions of the fallopian tube can be further detected or segmented. Then, after performing necessary morphological operations on the detected or segmented candidate regions, each candidate region is evaluated based on features such as shape and grayscale brightness to obtain sub-evaluation results. Simultaneously, the probability of each candidate region's sub-evaluation result is obtained, and the sub-evaluation result with the highest probability is taken as the final evaluation result.

[0106] In another embodiment, an evaluation result corresponding to the feature information of at least one key feature structure is obtained based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators. This includes: classifying the imaging volume data of the key feature structure using a trained machine learning model to obtain the evaluation result corresponding to the feature information of the key feature structure. The implementation of the machine learning model is similar to the machine learning model used to identify key feature structures described above. Specifically, features can be extracted based on traditional methods such as sliding windows and / or deep neural networks, and then classified using a classifier; a bounding box-based deep learning network can also be used to classify key feature structures; or a deep learning end-to-end semantic segmentation network can be used to directly classify key feature structures.

[0107] In one embodiment, referring to Table 1, the evaluation results can be obtained by combining the uterine cavity morphology with the speed at which the contrast agent enters the fallopian tubes from the uterine cavity. Therefore, the processor 116 is also used to obtain the speed at which the contrast agent enters the fallopian tubes from the uterine cavity. The evaluation results corresponding to the uterine cavity morphology based on the correspondence between preset morphology and fallopian tube patency evaluation indicators include: obtaining the evaluation results corresponding to the uterine cavity morphology and the speed at which the contrast agent enters the fallopian tubes from the uterine cavity based on the preset morphology and the correspondence between preset speed and fallopian tube patency evaluation indicators. For example, if the uterine cavity is smooth and the contrast agent moves quickly from the uterine horn into the fallopian tube, the evaluation result is 1 point; if the uterine cavity has high tension and the contrast agent enters the fallopian tubes slowly, the evaluation result is 2 points; if the uterine cavity is distended and the contrast agent rolls within the uterine cavity, the evaluation result is 3 points.

[0108] In one embodiment, the speed at which contrast agent enters the fallopian tubes from the uterine cavity can be obtained through motion detection based on four-dimensional contrast volume data. Motion detection refers to determining the pixel coordinates of the contrast agent signal based on the uterine cavity structure detected in the contrast volume data; determining the difference in pixel coordinates of the contrast agent signal in adjacent frames of the contrast volume data; and determining the speed at which the contrast agent enters the fallopian tubes from the uterine cavity based on the difference in pixel coordinates, the physical distance per unit pixel, and the frame rate of the contrast volume data. Specifically, the speed value can be obtained by calculating the product of the difference in pixel coordinates of the contrast agent signal in adjacent frames, the physical distance per unit pixel, and the frame rate.

[0109] If 4D imaging volume data is unavailable, the assessment result corresponding to the uterine cavity shape can be obtained solely based on the correspondence between the preset uterine cavity shape and fallopian tube patency assessment indicators. Alternatively, the speed at which the contrast agent enters the fallopian tubes from the uterine cavity, as manually input by the user, can also be obtained.

[0110] In one embodiment, in addition to the fallopian tube patency assessment indicators that can be evaluated based on imaging volume data, as shown in the last two columns of Table 1, the fallopian tube patency assessment indicators also include at least one of the fallopian tube patency assessment indicators corresponding to a preset intrauterine pressure and a fallopian tube patency assessment indicator corresponding to a preset pain level. These two assessment indicators can be evaluated based on user input.

[0111] In one embodiment, the processor 116 can acquire the intrauterine pressure measured by a pressure sensor during the contrast agent injection process, and obtain an assessment result of the intrauterine pressure based on a preset correspondence between intrauterine pressure and fallopian tube patency assessment indicators. Optionally, the processor can also directly receive the assessment result of the intrauterine pressure input by the user, based on the fallopian tube patency assessment indicators corresponding to the preset intrauterine pressure. The assessment result can be obtained based on the resistance felt by the user during the contrast agent injection process. Exemplarily, the processor 116 can control the display 118 to display the preset correspondence between intrauterine pressure and fallopian tube patency assessment indicators, so that the user can refer to the correspondence to assess the intrauterine pressure and obtain an assessment result of the intrauterine pressure.

[0112] Referring to Table 1, the fallopian tube patency assessment index based on intrauterine pressure is divided into three levels: If the preset intrauterine pressure is no resistance during injection, the pressure curve is a gentle slope, and the pressure is <40 kPa, the corresponding preset assessment result is 1 point; if the preset intrauterine pressure is resistance during injection, the pressure curve is a steep slope, and the pressure is 40-60 kPa, the corresponding preset assessment result is 2 points; if the preset intrauterine pressure is high resistance during injection, the pressure curve is a steep slope, and the pressure is >60 kPa, the corresponding preset assessment result is 3 points. The presence or absence of resistance during injection is the assessment standard used when obtaining the assessment result based on the resistance felt by the user during the injection of the contrast agent. The pressure curve and pressure value are the assessment standards used when obtaining the assessment result based on the intrauterine pressure measured by the pressure sensor during the injection of the contrast agent.

[0113] In one embodiment, the processor 116 can receive user input based on an assessment of the subject's pain level. The subject's pain level needs to be manually input by the user based on the subject's feedback. For example, the processor 116 can control the display 118 to display a preset correspondence between pain level and fallopian tube patency assessment indicators, so that the user can refer to this correspondence to assess the subject's pain level and obtain an assessment result of the subject's pain level.

[0114] The pain levels in Table 1 are classified according to the World Health Organization (WHO) standards and clinical manifestations. According to the WHO standards, pain levels are divided into four grades: 0, 1, 2, and 3. Based on the clinical manifestations of the subjects during the imaging process, this embodiment of the application classifies the fallopian tube patency assessment index related to the subjects' pain levels into three categories: For preset pain levels of 0 and 1, where the patient reports no pain, is quiet and cooperative, or experiences mild pain, the corresponding preset assessment result is 1 point; for preset pain levels of 2, moderate pain, where the patient reports unbearable pain, groaning and restlessness, the corresponding preset assessment result is 2 points; and for preset pain levels of 3, severe pain, where the patient reports unbearable pain, shouting, and non-cooperation, the corresponding preset assessment result is 3 points.

[0115] The embodiments of this application may also include the aforementioned fallopian tube patency assessment indicators. For example, if the volume data of the four-dimensional hysterosalpingography (HSG) is missing, and the speed at which the contrast agent enters the fallopian tube from the uterine cavity cannot be obtained under the three-dimensional HSG volume data, then the indicator regarding the contrast agent entry speed may not be used, or this indicator may be converted to user input. Alternatively, if the subject cannot describe the degree of pain, the fallopian tube patency assessment indicator regarding the subject's pain level may not be used.

[0116] The processor 116 is also configured to determine the patency of the fallopian tubes based on the evaluation results corresponding to the feature information of the at least one of the key feature structures.

[0117] In one embodiment, obtaining the fallopian tube patency based on at least one assessment result includes: classifying or regressing the at least one assessment result using a trained classifier to obtain a classification of fallopian tube patency. The fallopian tube patency can be divided into three categories: patent, partially patent, and blocked. Specifically, the assessment results corresponding to the aforementioned fallopian tube patency assessment indicators can be used as features to design a classifier to classify or regress the degree of fallopian tube patency and output the fallopian tube patency score. The classifier can employ KNN, SVM, random forest, neural network, or other similar classifiers.

[0118] Generally, the higher the score for each fallopian tube patency assessment indicator, the lower the fallopian tube patency. Therefore, in some embodiments, the scores corresponding to each fallopian tube patency assessment indicator can be weighted and summed according to preset weights, and the sum can be compared with the preset threshold corresponding to each fallopian tube patency category to obtain the classification result of fallopian tube patency.

[0119] The detection or segmentation of the aforementioned key feature structures, the evaluation of various fallopian tube patency assessment indicators, and the classification or regression of fallopian tube patency can be fully automated by the processor 116, or semi-automatically based on user input. Semi-automatic implementation allows users to delete, modify, or re-enter results using tools such as a keyboard and mouse, even when the quality of the imaging volume data is poor or the results obtained through intelligent algorithms are biased.

[0120] The processor 116 is also used to control the display 118 to show the patency of the fallopian tubes. Furthermore, in one embodiment, the processor 116 can also control the display 118 to show the evaluation results corresponding to feature information of at least one key feature structure.

[0121] The processor 116 can control the display 118 to display the evaluation results corresponding to the feature information of at least one key feature structure in a graphical or list manner.

[0122] In one embodiment, the graph used to display the evaluation results corresponding to the feature information of at least one key feature structure can be in the form of a radar chart. For example... Figure 2 As shown, the radar chart includes a classification axis and feature graphs. The classification axis divides the radar chart into multiple partitions, and each classification axis or each partition represents one of the fallopian tube patency assessment indicators. At least one classification axis or at least one partition has a scale unit for representing a preset assessment result. The feature graphs are generated on the radar chart based on the assessment results obtained from each fallopian tube patency assessment indicator.

[0123] exist Figure 2 In the radar chart shown, each classification axis represents a fallopian tube patency assessment index, and each classification axis is labeled with the fallopian tube patency assessment index corresponding to that axis. For example, the uppermost classification axis represents a fallopian tube patency assessment index related to fallopian tube morphology, the lowermost classification axis represents a fallopian tube patency assessment index related to the diffusion level of pelvic contrast agent, and so on. The feature graph is a graph formed by connecting the coordinate points on each classification axis that represent the assessment results of the fallopian tube patency assessment index corresponding to that axis. Figure 2 It is manifested as an irregular hexagon. Although Figure 2 A radar chart is typically represented as a hexagon, but its shape is not limited to this. For example, if a particular indicator of fallopian tube patency is missing, the radar chart can be presented as a pentagon. Alternatively, a radar chart can also be presented as a circle.

[0124] As another form of radar chart, when each partition is used to represent one of the fallopian tube patency assessment indicators, the assessment result obtained according to the corresponding fallopian tube patency assessment indicator can be represented by the area of ​​the feature graph.

[0125] Optionally, the radar chart may also include indicators representing the patency of the fallopian tubes. These indicators may be displayed as text at the edge of the radar chart, or the patency of the fallopian tubes may be represented by different colors on the radar chart. For example, if the fallopian tubes are patent, the feature graphic may be displayed in green, and if the fallopian tubes are blocked, the feature graphic may be displayed in red.

[0126] Based on the above description, the ultrasound imaging system 100 of this embodiment of the invention automatically completes a quantitative assessment based on the fallopian tube patency assessment index after completing the acquisition of the hysterosalpingography volume data, and obtains the fallopian tube patency based on the assessment results, thus standardizing the fallopian tube patency assessment process and effectively improving the efficiency and quality of doctors' work.

[0127] Below, we will refer to Figure 3 This application describes an evaluation method based on hysterosalpingography (HSG) imaging according to one embodiment of the present application. Figure 3 This is a schematic flowchart of an evaluation method 300 based on hysterosalpingography (HSG) imaging according to an embodiment of the present invention. The evaluation method 300 based on HSG imaging can be implemented by the ultrasound imaging system 100 described above. The following only describes the main steps of the evaluation method 300 based on HSG imaging, while omitting the details already described above.

[0128] like Figure 3 As shown, the evaluation method 300 based on hysterosalpingography (HSG) imaging according to an embodiment of the present invention includes the following steps:

[0129] In step S310, the ultrasound probe is controlled to emit ultrasound waves toward the fallopian tube tissue containing contrast agent, and the echo of the ultrasound waves is received to obtain ultrasound echo signals, and the contrast volume data is obtained based on the ultrasound echo signals.

[0130] In step S330, feature information of key feature structures is determined based on the contrast volume data, wherein the key feature structures include at least one of the fallopian tubes, uterine cavity, ovary and pelvic cavity;

[0131] In step S330, an evaluation result corresponding to the feature information of at least one of the key feature structures is obtained based on the correspondence between preset feature information and the corresponding fallopian tube patency assessment index.

[0132] In step S340, the patency of the fallopian tubes is determined based on the evaluation results corresponding to the feature information of at least one of the key feature structures, and the patency of the fallopian tubes is displayed.

[0133] The evaluation method 300 based on hysterosalpingography in this invention automatically performs a quantitative evaluation based on the fallopian tube patency evaluation indicators after collecting the hysterosalpingography volume data, and obtains the fallopian tube patency based on the evaluation results, thus standardizing the fallopian tube patency evaluation process and effectively improving the efficiency and quality of doctors' work.

[0134] Another aspect of this invention provides an ultrasound imaging system for implementing an evaluation method based on hysterosalpingography (HSG) imaging. Continuing with... Figure 1 The ultrasound imaging system of this invention includes: an ultrasound probe 110; a transmitting circuit 112 for exciting the ultrasound probe 110 to emit ultrasound waves toward fallopian tube tissue containing contrast agent; a receiving circuit 114 for controlling the ultrasound probe to receive the echo of the ultrasound waves to obtain an ultrasound echo signal; and a processor 116 for: acquiring contrast volume data and tissue volume data based on the ultrasound echo signal; determining feature information of key feature structures based on the contrast volume data and the tissue volume data, wherein the key feature structures include at least one of fallopian tubes, uterine cavity, ovary, and pelvic cavity; obtaining an evaluation result corresponding to the feature information of at least one key feature structure based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators; determining fallopian tube patency based on the evaluation result corresponding to the feature information of at least one key feature structure; and controlling a display 118 to display the fallopian tube patency.

[0135] The ultrasound imaging system in this embodiment is largely similar to the ultrasound imaging system described above. The main difference lies in that the processor 116 acquires not only contrast volume data but also tissue volume data. The contrast volume data provides more information about the contrast agent, while the tissue volume data provides more information about the tissue. The contrast volume data and tissue volume data can be obtained based on the same set of ultrasound echo signals or on different ultrasound echo signals.

[0136] Furthermore, the processor 116 determines not only the feature structure information of key feature structures based on contrast volume data, but also the feature information of key feature structures based on tissue volume data. Since tissue volume data can provide more information about tissue structure, the feature information of key feature structures regarding tissue structure can be determined based on tissue volume data, and the feature information regarding contrast agent information can be determined based on contrast volume data, thereby improving the accuracy of the determined feature information of key feature structures.

[0137] Apart from the above, the ultrasound imaging system in this embodiment is generally similar to the ultrasound imaging system described above. For details, please refer to the relevant description above. For the sake of brevity, the same details will not be repeated here.

[0138] Below, we will refer to Figure 4 This application describes an evaluation method based on hysterosalpingography (HSG) imaging according to another embodiment of the present application. Figure 4 This is a schematic flowchart of an evaluation method 400 based on hysterosalpingography (HSG) imaging according to an embodiment of the present invention. The following description focuses only on the main steps of the evaluation method 400 based on HSG imaging, omitting the details already described above.

[0139] like Figure 4 As shown, the evaluation method 400 based on hysterosalpingography includes the following steps:

[0140] In step S410, the ultrasound probe is controlled to emit ultrasound waves toward the fallopian tube tissue containing contrast agent, and the echo of the ultrasound waves is received to obtain ultrasound echo signals. Based on the ultrasound echo signals, contrast volume data and tissue volume data are obtained.

[0141] In step S420, feature information of key feature structures is determined based on the contrast volume data and the tissue volume data, wherein the key feature structures include at least one of the fallopian tube, uterine cavity, ovary and pelvic cavity;

[0142] In step S430, an evaluation result corresponding to the feature information of at least one of the key feature structures is obtained based on the correspondence between the preset feature information and the corresponding fallopian tube patency assessment index.

[0143] In step S440, the patency of the fallopian tubes is determined based on the evaluation results corresponding to the feature information of at least one of the key feature structures, and the patency of the fallopian tubes is displayed.

[0144] Based on the above description, the ultrasound imaging system and the evaluation method 400 based on hysterosalpingography according to embodiments of the present invention automatically determine the patency of the fallopian tubes based on hysterosalpingography, thereby improving the work efficiency of doctors.

[0145] Furthermore, according to embodiments of the present invention, a computer storage medium is provided, on which program instructions are stored. When executed by a computer or processor, the program instructions are used to perform corresponding steps of the evaluation method 200 or 400 based on hysterosalpingography (HSG) imaging according to embodiments of the present invention. The storage medium may, for example, include a memory card of a smartphone, 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 disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0146] Furthermore, according to embodiments of the present invention, a computer program is also provided, which can be stored on a cloud or local storage medium. When this computer program is run by a computer or processor, it is used to perform the corresponding steps of the evaluation method based on hysterosalpingography (HSG) imaging according to embodiments of the present invention.

[0147] Although exemplary embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above exemplary embodiments are merely illustrative and are not intended to limit the scope of this application. Various changes and modifications can be made therein by those skilled in the art without departing from the scope and spirit of this application. All such changes and modifications are intended to be included within the scope of this application as claimed in the appended claims.

[0148] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0149] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0150] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0151] Similarly, it should be understood that, in order to streamline this application and aid in understanding one or more of the various inventive aspects, features of this application may sometimes be grouped together in a single embodiment, figure, or description thereof in the description of exemplary embodiments of this application. However, this approach should not be construed as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the corresponding claims, its inventive point lies in solving the corresponding technical problem with features fewer than all features of a single disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this application.

[0152] Those skilled in the art will understand that, apart from the mutual exclusion of features, all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or apparatus so disclosed can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0153] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of this application and form different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0154] The various component embodiments of this application can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some modules according to embodiments of the present invention. This application can also be implemented as an apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such an implementation of this application can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0155] It should be noted that the above embodiments are illustrative of this application and not limiting of it, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. This application can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.

[0156] The above description is merely a specific embodiment or illustration of the embodiments of this application. The scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. The scope of protection of this application shall be determined by the scope of the claims.

Claims

1. An ultrasound imaging system, characterized in that, The ultrasound imaging system includes: Ultrasonic probe; A transmitting circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fallopian tube tissue containing contrast agent; A receiving circuit is used to control the ultrasonic probe to receive the echo of the ultrasonic wave in order to obtain an ultrasonic echo signal; Processor, used for: The contrast volume data is obtained based on the ultrasound echo signal; Key feature structures are detected or segmented in the contrast volume data, and feature information of the key feature structures is determined. The key feature structures include fallopian tubes, uterine cavity, ovary and pelvic cavity. The feature information of the key feature structures includes at least one of the following: the morphology of the fallopian tubes, the morphology of the uterine cavity, the contrast agent enhancement level around the ovary and the contrast agent diffusion level in the pelvic cavity. Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained, including at least one of the following: The assessment results corresponding to the shape of the fallopian tube are obtained based on the correspondence between the preset shape of the fallopian tube and the fallopian tube patency assessment index. The assessment results corresponding to the shape of the uterine cavity are obtained based on the correspondence between the preset shape of the uterine cavity and the fallopian tube patency assessment index. The assessment results corresponding to the contrast agent enhancement level around the ovary are obtained based on the correspondence between the preset contrast agent enhancement level around the ovary and the fallopian tube patency assessment index. The assessment result corresponding to the contrast agent diffusion level in the pelvis is obtained based on the correspondence between the preset contrast agent diffusion level in the pelvis and the fallopian tube patency assessment index. The fallopian tube patency is determined based on the assessment result corresponding to the feature information of at least one of the key feature structures, and the fallopian tube patency is displayed on the monitor. The assessment result includes a score; the scores corresponding to each fallopian tube patency assessment index are weighted and summed according to preset weights, and the sum is compared with a preset threshold corresponding to each fallopian tube patency classification to obtain the fallopian tube patency classification result. Alternatively, a trained classifier is used to classify or regress the assessment result corresponding to the feature information of at least one of the key feature structures to obtain the fallopian tube patency.

2. The ultrasound imaging system according to claim 1, characterized in that, The processor is also used to: obtain the speed at which the contrast agent enters the fallopian tube from the uterine cavity; The correlation between the preset uterine cavity shape and the fallopian tube patency assessment index yields the assessment results corresponding to the uterine cavity shape, including: The evaluation results corresponding to the morphology of the uterine cavity and the speed at which the contrast agent enters the fallopian tube from the uterine cavity are obtained based on the preset shape and preset speed of the contrast agent entering the fallopian tube from the uterine cavity.

3. The ultrasound imaging system according to claim 2, characterized in that, The speed at which the contrast agent enters the fallopian tube from the uterine cavity includes: The pixel coordinates of the contrast agent signal are determined based on the contrast volume data of the uterine cavity; Determine the difference in pixel coordinates of the contrast agent signal in the contrast volume data of adjacent frames; The speed at which the contrast agent enters the fallopian tube from the uterine cavity is determined based on the difference, the physical distance corresponding to a unit pixel, and the frame rate of the contrast volume data.

4. The ultrasound imaging system according to claim 2, characterized in that, The speed at which the contrast agent enters the fallopian tube from the uterine cavity includes: The speed at which the contrast agent enters the fallopian tube from the uterine cavity, as input by the user, is obtained.

5. The ultrasound imaging system according to claim 1, characterized in that, The assessment result corresponding to the feature information of at least one of the key feature structures is obtained based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, including: At least one candidate region is identified in the contrast volume data of the key feature structure; A sub-evaluation result for each candidate region is determined based on the image features of each candidate region; The sub-evaluation result with the highest probability is selected from the sub-evaluation results of the at least one candidate region and used as the evaluation result corresponding to the feature information of the key feature structure.

6. The ultrasound imaging system according to claim 1, characterized in that, The assessment result corresponding to the feature information of at least one of the key feature structures is obtained based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, including: The trained machine learning model is used to classify the contrast volume data of the key feature structure in order to obtain the evaluation results corresponding to the feature information of the key feature structure.

7. The ultrasound imaging system according to claim 1, characterized in that, The fallopian tube patency assessment indicators also include fallopian tube patency assessment indicators corresponding to preset intrauterine pressure and / or fallopian tube patency assessment indicators corresponding to preset pain level.

8. The ultrasound imaging system according to claim 7, characterized in that, The processor is also used for: The intrauterine pressure during the contrast agent injection process is obtained from the pressure sensor. The assessment result of the intrauterine pressure is obtained according to the preset correspondence between intrauterine pressure and fallopian tube patency assessment index. Alternatively, the system may receive the assessment result of the intrauterine pressure obtained by the user based on the fallopian tube patency assessment index corresponding to the preset intrauterine pressure.

9. The ultrasound imaging system according to claim 7, characterized in that, The processor is also used for: The system receives the assessment result of the subject's pain level based on the fallopian tube patency assessment index corresponding to the preset pain level, which is input by the user.

10. The ultrasound imaging system according to claim 1, characterized in that, The processor is also configured to control the display to show the evaluation results corresponding to the feature information of the at least one of the key feature structures.

11. The ultrasound imaging system according to claim 10, characterized in that, The evaluation result that displays the feature information corresponding to at least one of the key feature structures includes: The evaluation results corresponding to the feature information of at least one of the key feature structures are displayed in a graphical or list format.

12. The ultrasound imaging system according to claim 11, characterized in that, The graphic includes a radar chart, which includes: A classification axis divides the radar chart into multiple partitions. Each classification axis or each partition is used to represent a fallopian tube patency assessment index. At least one classification axis or at least one partition has a scale unit for representing a preset assessment result corresponding to the fallopian tube patency assessment index. A feature graph is generated on the radar chart based on the evaluation result corresponding to the feature information of at least one of the key feature structures; And, an indicator representing the patency of the fallopian tubes.

13. The ultrasound imaging system according to claim 12, characterized in that, Each of the classification axes is used to represent a fallopian tube patency assessment index. The feature graph is a graph formed by connecting the coordinate points on each classification axis that represent the assessment results of the fallopian tube patency assessment index corresponding to the classification axis. Each classification axis is marked with the fallopian tube patency assessment index corresponding to the classification axis.

14. The ultrasound imaging system according to claim 1, characterized in that, The processor is also used for: The contrast volume data is rendered to obtain a contrast image, and the display is controlled to show the contrast image.

15. The ultrasound imaging system according to claim 1, characterized in that, The processor is also used for: Tissue volume data are obtained based on the ultrasound echo signal; The tissue volume data is rendered to obtain a tissue image, and the display is controlled to show the tissue image.

16. An ultrasound imaging system, characterized in that, The ultrasound imaging system includes: Ultrasonic probe; A transmitting circuit is used to excite the ultrasound probe to emit ultrasound waves toward the fallopian tube tissue containing contrast agent; A receiving circuit is used to control the ultrasonic probe to receive the echo of the ultrasonic wave in order to obtain an ultrasonic echo signal; Processor, used for: Based on the ultrasound echo signal, obtain contrast volume data and tissue volume data; Key feature structures are detected or segmented from the contrast volume data and the tissue volume data, and feature information of the key feature structures is determined. The key feature structures include fallopian tubes, uterine cavity, ovary and pelvic cavity. The feature information of the key feature structures includes at least one of the following: the morphology of the fallopian tubes, the morphology of the uterine cavity, the contrast agent enhancement level around the ovary and the contrast agent diffusion level in the pelvic cavity. Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained, including at least one of the following: The assessment results corresponding to the shape of the fallopian tube are obtained based on the correspondence between the preset shape of the fallopian tube and the fallopian tube patency assessment index. The assessment results corresponding to the shape of the uterine cavity are obtained based on the correspondence between the preset shape of the uterine cavity and the fallopian tube patency assessment index. The assessment results corresponding to the contrast agent enhancement level around the ovary are obtained based on the correspondence between the preset contrast agent enhancement level around the ovary and the fallopian tube patency assessment index. The assessment result corresponding to the contrast agent diffusion level in the pelvis is obtained based on the correspondence between the preset contrast agent diffusion level in the pelvis and the fallopian tube patency assessment index. The fallopian tube patency is determined and displayed based on the assessment result corresponding to the feature information of at least one of the key feature structures. The assessment result includes a score, and the scores corresponding to each fallopian tube patency assessment index are weighted and summed according to preset weights. The sum is then compared with a preset threshold corresponding to each fallopian tube patency classification to obtain the fallopian tube patency classification result. Alternatively, a trained classifier is used to classify or regress the assessment result corresponding to the feature information of at least one of the key feature structures to obtain the fallopian tube patency.

17. An evaluation method based on hysterosalpingography (HSG), characterized in that, The method includes: The ultrasound probe is controlled to emit ultrasound waves toward the fallopian tube tissue containing contrast agent, and the echo of the ultrasound waves is received to obtain ultrasound echo signals, and the contrast volume data is obtained based on the ultrasound echo signals. Key feature structures are detected or segmented in the contrast volume data, and feature information of key feature structures is determined. The key feature structures include fallopian tubes, uterine cavity, ovary and pelvic cavity. The feature information of key feature structures includes at least one of the following: the morphology of the fallopian tubes, the morphology of the uterine cavity, the contrast agent enhancement level around the ovary and the contrast agent diffusion level in the pelvic cavity. Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained, including at least one of the following: The assessment results corresponding to the shape of the fallopian tube are obtained based on the correspondence between the preset shape of the fallopian tube and the fallopian tube patency assessment index. The assessment results corresponding to the shape of the uterine cavity are obtained based on the correspondence between the preset shape of the uterine cavity and the fallopian tube patency assessment index. The assessment results corresponding to the contrast agent enhancement level around the ovary are obtained based on the correspondence between the preset contrast agent enhancement level around the ovary and the fallopian tube patency assessment index. The assessment results corresponding to the contrast agent diffusion level in the pelvic cavity are obtained based on the correspondence between the preset contrast agent diffusion level in the pelvic cavity and the fallopian tube patency assessment index. The patency of the fallopian tubes is determined and displayed based on the evaluation results corresponding to the feature information of at least one of the key feature structures. The evaluation results include scores, which are weighted and summed according to preset weights for each fallopian tube patency evaluation index. The sum is then compared with a preset threshold corresponding to each fallopian tube patency category to obtain the fallopian tube patency classification result. Alternatively, a trained classifier can be used to classify or regress the evaluation results corresponding to the feature information of at least one of the key feature structures to obtain the fallopian tube patency.

18. An evaluation method based on hysterosalpingography (HSG), characterized in that, The method includes: The ultrasound probe is controlled to emit ultrasound waves toward the fallopian tube tissue containing contrast agent, and the echo of the ultrasound waves is received to obtain ultrasound echo signals. Based on the ultrasound echo signals, contrast volume data and tissue volume data are obtained. Key feature structures are detected or segmented from the contrast volume data and the tissue volume data, and feature information of the key feature structures is determined. The key feature structures include fallopian tubes, uterine cavity, ovary and pelvic cavity. The feature information of the key feature structures includes at least one of the following: the morphology of the fallopian tubes, the morphology of the uterine cavity, the contrast agent enhancement level around the ovary and the contrast agent diffusion level in the pelvic cavity. Based on the correspondence between preset feature information and corresponding fallopian tube patency assessment indicators, an assessment result corresponding to the feature information of at least one of the key feature structures is obtained, including at least one of the following: The assessment results corresponding to the shape of the fallopian tube are obtained based on the correspondence between the preset shape of the fallopian tube and the fallopian tube patency assessment index. The assessment results corresponding to the shape of the uterine cavity are obtained based on the correspondence between the preset shape of the uterine cavity and the fallopian tube patency assessment index. The assessment results corresponding to the contrast agent enhancement level around the ovary are obtained based on the correspondence between the preset contrast agent enhancement level around the ovary and the fallopian tube patency assessment index. The assessment results corresponding to the contrast agent diffusion level in the pelvic cavity are obtained based on the correspondence between the preset contrast agent diffusion level in the pelvic cavity and the fallopian tube patency assessment index. The patency of the fallopian tubes is determined and displayed based on the evaluation results corresponding to the feature information of at least one of the key feature structures. The evaluation results include scores, which are weighted and summed according to preset weights for each fallopian tube patency evaluation index. The sum is then compared with a preset threshold corresponding to each fallopian tube patency category to obtain the fallopian tube patency classification result. Alternatively, a trained classifier can be used to classify or regress the evaluation results corresponding to the feature information of at least one of the key feature structures to obtain the fallopian tube patency.

Images