Ultrasonic probe navigation method, device, equipment and medium

Abstract

The present disclosure provides an ultrasound probe navigation method, device, equipment and medium, which relates to the field of data processing technology, especially to the field of artificial intelligence and AI medical technology. The specific implementation scheme is: obtain a first ultrasound section image acquired by the ultrasound probe at the first moment and a second ultrasound section image acquired at the second moment; determine the first posture change value based on the first posture offset and the second posture offset; based on the first ultrasound section image, the second ultrasound section image and the posture of the ultrasound probe at the first moment and the second moment, correct the first posture change value to obtain a corrected posture change value; correct the second posture offset based on the corrected posture change value to generate navigation information of the ultrasound probe. Even if the operator does not have rich experience, high-quality ultrasound section images can be obtained.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to the field of artificial intelligence and AI medical technology. Background Art

[0002] Ultrasound imaging is a medical imaging technology that uses high-frequency sound wave technology to capture images in real time. Since ultrasound imaging does not produce ionizing radiation, it can be used for health checks of pregnant women and infants. This technology plays an important role in the field of medical examinations. Summary of the invention

[0003] The present disclosure provides an ultrasound probe navigation method, device, equipment and medium.

[0004] In a first aspect, the present disclosure provides an ultrasound probe navigation method, comprising:

[0005] During scanning by the ultrasonic probe, the operator obtains a first ultrasonic section image acquired by the ultrasonic probe at a first moment and a second ultrasonic section image acquired at a second moment;

[0006] Determine the first pose change value based on the first pose offset and the second pose offset; wherein the first pose offset is the pose offset between the pose of the ultrasound probe and the target pose when acquiring the first ultrasound section image, the second pose offset is the pose offset between the pose of the ultrasound probe and the target pose when acquiring the second ultrasound section image, and the target pose is the standard pose of the ultrasound probe when scanning the target scanning position;

[0007] Based on the first ultrasonic cross-sectional image, the second ultrasonic cross-sectional image, and the position and posture of the ultrasonic probe at the first moment and the second moment, correcting the first position and posture change value to obtain a corrected position and posture change value;

[0008] The second posture offset is corrected based on the corrected posture change value, and navigation information of the ultrasound probe is generated based on the corrected second posture offset.

[0009] In a second aspect, the present disclosure provides an ultrasound probe navigation device, comprising:

[0010] An acquisition module, used for acquiring a first ultrasonic section image acquired by the ultrasonic probe at a first moment and a second ultrasonic section image acquired at a second moment during a scanning process performed by an operator using the ultrasonic probe;

[0011] A determination module, configured to determine a first posture change value based on a first posture offset and a second posture offset; wherein the first posture offset is a posture offset between a posture of the ultrasound probe and a target posture when acquiring the first ultrasound section image, the second posture offset is a posture offset between a posture of the ultrasound probe and a target posture when acquiring the second ultrasound section image, and the target posture is a standard posture when the ultrasound probe scans a target scanning position;

[0012] a correction module, configured to correct the first posture change value based on the first ultrasonic section image, the second ultrasonic section image, and the posture of the ultrasonic probe at the first moment and the second moment to obtain a corrected posture change value;

[0013] A correction module is used to correct the second posture offset based on the corrected posture change value, and generate navigation information of the ultrasound probe based on the corrected second posture offset.

[0014] In a third aspect, the present disclosure provides an electronic device, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect above.

[0018] In a fourth aspect, the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method described in the first aspect above.

[0019] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, wherein the computer program implements the method described in the first aspect when executed by a processor.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flow chart of an ultrasound probe navigation method provided by an embodiment of the present disclosure;

[0023] Figure 2 is a flow chart of another ultrasound probe navigation method provided by an embodiment of the present disclosure;

[0024] Figure 3 is a schematic diagram of an ultrasound probe equipped with an optical marker and an IMU provided by an embodiment of the present disclosure;

[0025] Figure 4 is a schematic diagram of a process for obtaining a second posture change value provided by an embodiment of the present disclosure;

[0026] Figure 5 is a schematic diagram of a process for obtaining a first pose offset and a second pose offset provided by an embodiment of the present disclosure;

[0027] Figure 6 is a schematic diagram of a process for obtaining a third posture change value provided by an embodiment of the present disclosure;

[0028] Figure 7 is a schematic diagram of a process for obtaining a corrected posture change value provided by an embodiment of the present disclosure;

[0029] Figure 8 is a flow chart of another ultrasound probe navigation method provided by an embodiment of the present disclosure;

[0030] Fig. 9 is a schematic diagram of an exemplary flow chart of an ultrasound probe navigation method provided by an embodiment of the present disclosure;

[0031] Fig.10 is a structural schematic diagram of an ultrasound probe navigation device provided by an embodiment of the present disclosure;

[0032] Fig.11 It is a block diagram of an electronic device used to implement the ultrasound probe navigation method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0034] In the related art, the use of ultrasound equipment to collect high-quality ultrasound section images is highly dependent on the skilled operation of doctors. Ultrasound section images are collected in a 2D dynamic imaging manner. In order to conduct a comprehensive examination of human organs with three-dimensional structures, dynamic images of human organs in different section directions need to be collected. The operator of the ultrasound equipment needs to know how to place and move the ultrasound probe to obtain ultrasound section images in different section directions, and the operator needs to determine the location of the ultrasound probe based on the currently scanned ultrasound section image, as well as how to move the ultrasound probe to obtain the required ultrasound section image. This requires the operator to have a thorough understanding of the anatomical structure of human organs and the characteristics of ultrasound section images corresponding to the anatomical structure of human organs. Inexperienced operators find it difficult to obtain high-quality ultrasound section images.

[0035] It can be seen that currently obtaining high-quality ultrasound cross-sectional images depends on the operator's experience, and operators who have not received professional training cannot obtain high-quality ultrasound cross-sectional images.

[0036] The ultrasound device in the embodiment of the present disclosure may be a desktop ultrasound device, a portable ultrasound device, or a handheld ultrasound device.

[0037] Among them, desktop ultrasound equipment is the largest in size and has the best imaging quality, but it is expensive.

[0038] Portable ultrasound devices are medium-sized, provide better image quality, and are less expensive than desktop ultrasound devices.

[0039] Handheld ultrasound devices are the smallest in size and have average imaging quality, but the devices are inexpensive. Their main application scenarios include bedside diagnosis, out-of-hospital emergency care, and primary medical screening.

[0040] In order to solve the above technical problems, an embodiment of the present disclosure provides an ultrasound probe navigation method, which can be performed by an electronic device that can communicate with an ultrasound device. The electronic device can be a smart phone, a desktop computer, or a tablet computer, etc. The electronic device and the ultrasound device can be connected by a wire, or the electronic device and the ultrasound device can be connected wirelessly via WiFi, Bluetooth, or other technologies.

[0041] like Figure 1 As shown, the method includes:

[0042] S101 . During a scanning process using an ultrasonic probe, an operator obtains a first ultrasonic section image acquired by the ultrasonic probe at a first moment and a second ultrasonic section image acquired at a second moment.

[0043] The operator places the ultrasound probe on the skin surface of the human organ that needs to be scanned, controls the movement of the ultrasound probe to scan the human organ, and during the scanning process, the ultrasound probe will collect ultrasound cross-sectional images in real time.

[0044] During the scanning process using the ultrasound probe, the electronic device can obtain the ultrasound section image collected by the ultrasound probe once every fixed time, and the first moment and the second moment are two adjacent collection moments. For example, the preset time can be set to 2S.

[0045] S102, determining a first pose change value based on the first pose offset and the second pose offset.

[0046] The first pose offset is the pose offset between the pose of the ultrasound probe and the target pose when acquiring the first ultrasound section image, the second pose offset is the pose offset between the pose of the ultrasound probe and the target pose when acquiring the second ultrasound section image, and the target pose is the standard pose when the ultrasound probe scans the target scanning position. The target scanning position is the preset scanning end position of this scan.

[0047] The first pose change value is the difference between the first pose offset and the second pose offset.

[0048] The method for obtaining the first pose offset and the second pose offset will be described in detail below.

[0049] S103, based on the first ultrasonic section image, the second ultrasonic section image, and the position and posture of the ultrasonic probe at the first moment and the second moment, correct the first position and posture change value to obtain a corrected position and posture change value.

[0050] In the embodiment of the present disclosure, the first posture change value is corrected to obtain a corrected posture change value of the ultrasound probe between the first moment and the second moment.

[0051] S104. Correct the second posture offset based on the corrected posture change value, and generate navigation information of the ultrasound probe based on the corrected second posture offset.

[0052] By adopting the embodiment of the present disclosure, the first posture change value can be obtained by the posture offset between the posture of the ultrasound probe when collecting ultrasound section images at two moments and the target posture. Then, the first posture change value is corrected by the ultrasound section images collected by the ultrasound probe at two moments and the posture of the ultrasound probe at two moments to obtain a corrected posture change value, so that the obtained corrected posture change value can accurately represent the actual posture change of the ultrasound probe. Furthermore, the second posture offset is corrected based on the corrected posture change value, and accurate navigation information of the ultrasound probe can be generated based on the corrected second posture offset. In this way, the operator can move the ultrasound probe according to the navigation information to obtain high-quality ultrasound section images, and even if the operator does not have rich experience, high-quality ultrasound section images can be obtained.

[0053] In another embodiment of the present disclosure, Figure 2 As shown, the above S103, based on the first ultrasonic section image, the second ultrasonic section image and the position and posture of the ultrasonic probe at the first moment and the second moment, corrects the first position change value to obtain the corrected position change value, which can be specifically implemented as follows:

[0054] S1031. Obtain the position and posture of the ultrasonic probe at the first moment and the second moment measured by an inertial measurement unit (IMU) installed in the ultrasonic probe.

[0055] Among them, the IMU is installed on the ultrasonic probe, and the IMU can measure the position and posture of the ultrasonic probe during the scanning process in real time.

[0056] like Figure 3 As shown, Figure 3 A schematic diagram of an ultrasonic probe equipped with an IMU provided in an embodiment of the present disclosure, Figure 3 The ultrasound probe in t 1 ,t 2 …t N The ultrasound section images collected at each moment are I(t 1 )、、I(t 2 )…I(t N ), IMU can collect the ultrasonic probe at t 1 ,t 2 …t N The position U(t 1 )、U(t 2 ),…U(t N ).

[0057] S1032. Calculate the difference between the position and posture of the ultrasonic probe at the first moment and the position and posture of the ultrasonic probe at the second moment to obtain a second position and posture change value.

[0058] For example, in Figure 3 Zhong RuoT 1 is the first moment, t 2 is the second moment, then the second posture change value ΔP IMU =U(t 1 )-U(t 1 ).

[0059] S1033. Determine a third posture change value based on the first ultrasound section image, the second ultrasound section image, and the posture of the ultrasound probe at the first moment and the second moment.

[0060] The method for determining the third posture change value will be introduced in subsequent embodiments.

[0061] S1034. Based on the second posture change value and the third posture change value, correct the first posture change value to obtain a corrected posture change value.

[0062] Using the embodiment of the present disclosure, the second posture change value is obtained by measuring the posture of the ultrasound probe at two times through the IMU. Then, the third posture change value is obtained by synthesizing the ultrasound section images collected by the ultrasound probe at two times and the posture of the ultrasound probe measured by the IMU at two times. The first posture change value is corrected based on the second posture change value and the third posture change value to obtain a corrected posture change value, which is equivalent to fusing and complementing the posture change values ​​obtained by three different motion estimation methods, so that the corrected posture change value obtained can accurately represent the actual posture change of the ultrasound probe. Furthermore, the second posture offset is corrected based on the corrected posture change value, and the corrected second posture offset can generate accurate navigation information, so that the operator can obtain high-quality ultrasound section images based on the navigation information without rich experience.

[0063] For S1031-S1032, Figure 4 As shown, Figure 4 A schematic diagram of a process for obtaining a second posture change value provided in an embodiment of the present disclosure.

[0064] S401, IMU collects the position and posture of the ultrasonic probe in real time.

[0065] S402, obtaining the ultrasonic probe collected by the IMU at the first moment t j The pose U(t j ).

[0066] S403, obtaining the ultrasonic probe collected by the IMU at the second time t j+1 The pose U(t j+1 ).

[0067] S404, calculating the second posture change value ΔP IMU .

[0068] Among them, ΔP iMU =U(t j )-U(t j+1 ).

[0069] It is understandable that through Figure 4 The process shown can obtain the second posture change value at every two adjacent moments.

[0070] In one embodiment of the present disclosure, the first pose offset and the second pose offset in the above embodiment are obtained by:

[0071] The first ultrasonic section image is input into the first estimation model to obtain the first posture offset output by the first estimation model; the second ultrasonic section image is input into the first estimation model to obtain the second posture offset output by the first estimation model.

[0072] Among them, the first estimation model is a regression model obtained by training with a first preset training set, and the first preset training set includes multiple sample ultrasound section images and a posture offset between the ultrasound probe's posture and the target posture when collecting each sample ultrasound section image; the ultrasound probe's posture is obtained using an optical positioning tracking device or a magnetic positioning tracking device.

[0073] The first estimation model may be any type of regression model, for example, a logistic regression model.

[0074] Take the example of an ultrasound probe equipped with an optical positioning tracking device. Figure 3 As shown, Figure 3 Also shown is an optical marker installed on the ultrasound probe. The disclosed embodiment can pre-use an ultrasound probe installed with an optical marker to collect multiple frames of sample ultrasound section images. The optical positioning tracking device can obtain the position and posture of the ultrasound probe when collecting each frame of sample ultrasound section image through the optical marker. Experienced doctors can observe multiple frames of sample ultrasound section images and select standard section images from them. The electronic device can calculate the position and posture offset between the position and posture of the ultrasound probe when collecting each sample ultrasound section image and the target position and posture of the ultrasound probe when collecting the standard section image, as a label for each sample ultrasound section image.

[0075] In this way, a first preset training set can be obtained, and the first estimation model can be trained by the first preset training set. Specifically, each sample ultrasound section image can be input into the first estimation model, and the predicted posture offset output by the first estimation model for each sample ultrasound section image can be obtained. The loss function value is calculated based on the predicted posture offset and the label of the sample ultrasound section image, and the parameters of the first estimation model are adjusted based on the loss function value until the first estimation model converges, and it is determined that the training of the first estimation model is completed.

[0076] like Figure 5 As shown, Figure 5 This is a flow chart of obtaining the first pose offset and the second pose offset through the trained first estimation model. Figure 5 A method for obtaining a first pose offset and a second pose offset through a first estimation model is introduced.

[0077] S501, the ultrasound probe collects ultrasound cross-sectional images in real time.

[0078] S502: Obtain the ultrasound probe at the first moment t j The first ultrasound section image I(t j).

[0079] S503: Obtain the ultrasound probe at the second time t j+1 The second ultrasound section image I(t j+1 ).

[0080] S504: Input the first ultrasonic section image and the second ultrasonic section image into the first estimation model F respectively. 1 ().

[0081] S505, obtaining the first pose offset D(t j ).

[0082] Among them, D(t j )=F 1 (I(t j )).

[0083] S506, obtaining the second posture offset D(t j+1 ).

[0084] Among them, D(t j+1 )=F 1 (I(t j+1 )).

[0085] It can be understood that the first position change value in the above embodiment is:

[0086] ΔP IMG =D(t j )-D(t j+1 ).

[0087] By adopting the embodiment of the present disclosure, the first estimation model can be used to perform posture estimation on the first ultrasonic section image and the second ultrasonic section image respectively, thereby obtaining the first posture offset and the second posture offset. Since the first estimation model is pre-trained using the first preset training set, and since the labels of each sample ultrasonic section image included in the first training set are obtained by using an optical positioning tracking device or a magnetic positioning tracking device, the label can accurately represent the posture offset of the ultrasonic probe when collecting the sample ultrasonic section image and when collecting the standard section image. Therefore, the trained first estimation model can accurately obtain the first posture offset and the second posture offset, thereby improving the accuracy of the ultrasonic probe motion estimation, so that the navigation information finally obtained based on the first posture offset and the second posture offset is more accurate, thereby guiding the operator to collect high-quality ultrasonic section images.

[0088] In another embodiment of the present disclosure, the above S1033, based on the first ultrasonic section image, the second ultrasonic section image and the position and posture of the ultrasonic probe at the first moment and the second moment, determines the third position and posture change value, which can be specifically implemented as follows:

[0089] The first ultrasonic cross-sectional image, the second ultrasonic cross-sectional image, and the position and posture of the ultrasonic probe at the first moment and the second moment are input into the second estimation model to obtain a third position and posture change value output by the second estimation model.

[0090] Among them, the second estimation model is a regression model trained by the second preset training set, the second preset training set includes multiple groups of sample data, and the posture change value of the ultrasound probe during the collection of each group of sample data; each group of sample data includes two ultrasound slice images collected at two adjacent moments, and the posture of the ultrasound probe collected by the IMU at two adjacent moments; the posture change value of the ultrasound probe is obtained by using an optical positioning tracking device or a magnetic positioning tracking device.

[0091] In the embodiment of the present disclosure, the second estimation model may be various types of regression models, for example, a logistic regression model.

[0092] Similar to the method of obtaining the first preset training set, the two ultrasonic cross-sectional images at adjacent moments in each set of sample data in the second preset training set can also be acquired by an ultrasonic probe equipped with an optical marker. In addition, the position and posture of the ultrasonic probe when acquiring two ultrasonic cross-sectional images at adjacent moments can be acquired by an optical positioning and tracking device, and the difference between the position and posture of the ultrasonic probe at two adjacent moments can be calculated to obtain the position and posture change value of the ultrasonic probe during the acquisition of each set of sample data, that is, the label of each set of sample data is the position and posture change value of the ultrasonic probe when acquiring the two ultrasonic cross-sectional images included in the set of sample data.

[0093] In this way, the second estimation model is trained by the second preset training set, each group of sample data is input into the second estimation model, and the predicted pose change value of each group of sample data output by the second estimation model is obtained. The loss function value between the predicted pose change value of each group of sample data and the label of the sample data is calculated, and the parameters of the second estimation model are adjusted based on the calculated loss function value until the second estimation model converges, and it is determined that the training of the second estimation model is completed.

[0094] like Figure 6 As shown, Figure 6 A schematic diagram of a process for obtaining a third posture change value through a trained second estimation model provided in an embodiment of the present disclosure.

[0095] S601, the ultrasound probe collects ultrasound cross-sectional images in real time.

[0096] S602: Obtain the ultrasound probe at the first moment t j The first ultrasound section image I(t j ).

[0097] S603: Obtain the ultrasound probe at the second time t j+1The second ultrasound section image I(t j+1 ).

[0098] S604, the IMU obtains the position and posture of the ultrasound probe in real time.

[0099] S605: Obtain the ultrasonic probe collected by the IMU at the first moment t j The pose U(t j ).

[0100] S606: Obtain the ultrasonic probe collected by the IMU at the second time t j+1 The pose U(t j+1 ).

[0101] Among them, S601-S603 and S604-S606 can be executed in parallel.

[0102] S607: The first ultrasonic section image I(t j ), the second ultrasound section image I(t j+1 ), the first moment t j The pose U(t j ) and the second moment t j+1 The pose U(t j+1 ) Input the second estimation model F 2 ().

[0103] S608: Obtain a third posture change value ΔP output by the second estimation model AI .

[0104] Among them, ΔP AI =F 2 ({I(t j ), I(t j+1 )},{U(t j )), U(t j+1 )}).

[0105] By adopting the embodiment of the present disclosure, the third posture change value can be estimated by the second estimation model based on the first ultrasonic section image, the second ultrasonic section image, and the posture of the ultrasonic probe collected by the IMU at the first moment and the second moment. Because the second estimation model is pre-trained using the second training set, and because the labels of each group of sample data included in the second training set are obtained by using an optical positioning device or a magnetic positioning tracking device, the accuracy is high, so that the label can accurately represent the posture change value of the ultrasonic probe, so that the trained second estimation model can accurately predict the posture change value of the ultrasonic probe at the first moment and the second moment. In addition, the second estimation model can combine the posture of the ultrasonic probe collected by the IMU device with the ultrasonic section image analysis, so that the obtained posture change value is more accurate, the error of the ultrasonic probe motion estimation is reduced, and more accurate navigation information can be obtained, thereby guiding the operator to collect high-quality ultrasonic section images.

[0106] In another embodiment of the present disclosure, S1034, based on the second posture change value and the third posture change value, the first posture change value is corrected to obtain a corrected posture change value, which can be specifically implemented as follows:

[0107] The first posture change value, the second posture change value and the third posture change value are filtered based on the indirect Kalman filtering method to obtain the corrected posture change value.

[0108] like Figure 7 As shown, Figure 7 A flowchart of a method for obtaining a corrected posture change value provided in an embodiment of the present disclosure.

[0109] S701, obtain the first position change value ΔP IMG .

[0110] S702, obtaining a second posture change value ΔP IMU . .

[0111] S703, obtaining the third posture change value ΔP AI .

[0112] The method for obtaining the first pose change value, the second pose change value and the third pose change value in S701-S703 can refer to the relevant description in the above embodiment and will not be repeated here.

[0113] S704, filtering the first posture change value, the second posture change value and the third posture change value by indirect Kalman filtering technology to obtain a corrected posture change value ΔP K .

[0114] Optionally, the first pose change value, the second pose change value and the third pose change value can be filtered using a Kalman filter implemented by an indirect method to obtain the first pose change value, the second pose change value and the third pose change value for correction to reduce the error of the pose change value and obtain the corrected pose change value. The Kalman filter can be any Kalman filter implemented by an indirect method in the relevant technology.

[0115] By adopting the embodiment of the present disclosure, the first pose change value obtained based on the ultrasonic section image, the second pose change value obtained based on the IMU technology, and the third pose change value obtained based on the second estimation model are filtered through the indirect Kalman filtering technology, that is, the results of the three different navigation technologies are fused and corrected, which solves the problem of large errors in navigation using only ultrasonic section image analysis technology or IMU technology, and improves the accuracy of ultrasonic probe navigation.

[0116] In another embodiment of the present disclosure, the above S104, correcting the second posture offset based on the corrected posture change value, can be specifically implemented as follows: calculating the difference between the first posture offset and the corrected posture change value to obtain the corrected second posture offset.

[0117] The corrected second posture offset is: D(t j+1 ) K =D(t j )-ΔP K (t j , t j+1 ).

[0118] By adopting this method, after obtaining the accurate corrected posture change value, the posture offset at the first moment is subtracted from the corrected posture change value, so as to obtain the theoretical posture offset of the second sample section image at the second moment, thereby generating navigation information based on the corrected second posture offset, which can guide the operator to move the scanning probe toward the target scanning position without relying on the operator's personal experience.

[0119] In another embodiment of the present disclosure, Figure 8 As shown, the method includes S801-S807.

[0120] Among them, S801-S803 are the same as S101-S103, and the relevant description of S101-S103 in the above embodiment can be referred to, which will not be repeated here.

[0121] S804: Correct the second posture offset based on the corrected posture change value.

[0122] S805: Determine whether the corrected second posture deviation is less than a first preset threshold.

[0123] The first preset threshold may be a threshold set in advance according to an actual scenario.

[0124] If the judgment result is yes, execute S806; if the judgment result is no, execute S807.

[0125] S806: Determine that the ultrasound probe has been moved to the target scanning position.

[0126] If the corrected second posture offset is less than the first preset threshold, it means that the difference between the posture of the ultrasound probe at the second moment and the target posture is small, and the second ultrasound section image collected at the second moment can be regarded as a standard ultrasound section image, that is, it is determined that the ultrasound probe has been moved to the target scanning position and no further movement is required.

[0127] It can be understood that when the corrected second posture deviation is less than the first preset threshold, a prompt message to stop moving the ultrasound probe can be sent to the operator.

[0128] S807, generate navigation information of the ultrasound probe based on the corrected second posture offset, and obtain the ultrasound section image collected by the ultrasound probe at the next moment, take the current second moment as the first moment, take the next moment as the second moment, return to S802, and determine the first posture change value based on the first posture offset and the second posture offset, until the corrected second posture offset is less than the first preset threshold.

[0129] If the corrected second posture offset is not less than the first preset threshold, it means that the difference between the posture of the ultrasound probe at the second moment and the target posture is large. At this time, the distance between the ultrasound probe and the target scanning position is still large, and the ultrasound probe needs to be moved further.

[0130] By adopting the embodiment of the present disclosure, by generating navigation information, the operator can be guided to gradually move the ultrasound probe to the target scanning position to complete the scanning of the target scanning position and obtain the ultrasound section image of the target scanning position. The operator does not need to judge whether the target scanning position has been moved based on experience, thereby reducing the requirements for the operator.

[0131] In another embodiment of the present disclosure, the corrected second posture offset includes an offset distance and an offset angle. The above S104, generating navigation information of the ultrasound probe based on the corrected second posture offset, can be specifically implemented as follows:

[0132] If the offset distance is greater than the second preset threshold, the offset distance is converted into a moving direction to obtain navigation information; if the offset distance is less than or equal to the second preset threshold, the offset angle is converted into a rotation direction to obtain navigation information.

[0133] In the disclosed embodiment, when the offset distance included in the corrected second posture offset is greater than the second preset threshold, that is, the current ultrasound probe is far away from the target scanning position, the operator can be guided to move the ultrasound probe to the target scanning position first, so the offset angle of the ultrasound probe can be ignored, and only the offset distance can be converted into the moving direction. If the offset distance included in the second posture offset is less than or equal to the second preset threshold, it means that the ultrasound probe has moved to the vicinity of the target scanning position. At this time, the offset angle can be converted into a rotation direction to guide the operator to adjust the posture of the ultrasound probe, thereby scanning a high-quality ultrasound section image.

[0134] If the offset distance is a positive number, the moving direction is upward; if the offset distance is a negative number, the moving direction is downward.

[0135] If the offset angle is a positive number, the rotation direction is right; if the offset angle is a negative number, the rotation direction is left.

[0136] For example, the second preset threshold can be set to 1 cm. If the second posture offset includes an offset distance of +2 cm and an offset angle of +90 degrees, and the offset distance is greater than the second preset threshold, the offset distance +2 cm can be converted into an upward movement to obtain navigation information.

[0137] If the second posture offset includes an offset distance of +0.1 cm, an offset angle of +90 degrees, and the offset distance is less than a second preset threshold, the offset angle of +90 degrees may be converted to a right rotation to obtain navigation information.

[0138] In the disclosed embodiment, fine-grained navigation information can also be generated based on the corrected second posture offset, that is, if the offset distance is greater than the second preset threshold, the offset distance can be converted into a moving direction and a moving distance to obtain navigation information; if the offset distance is less than or equal to the second preset threshold, the offset angle can be converted into a rotation direction and a rotation angle to obtain navigation information.

[0139] For example, the second preset threshold can be set to 1 cm. If the second posture offset includes an offset distance of +2 cm and an offset angle of +90 degrees, and the offset distance is greater than the second preset threshold, the offset distance +2 cm can be converted into an upward movement of 2 cm to obtain navigation information.

[0140] If the second posture offset includes an offset distance of +0.1 cm, an offset angle of +90 degrees, and the offset distance is less than a second preset threshold, the offset angle of +90 degrees may be converted to a right rotation of 90 degrees to obtain navigation information.

[0141] By adopting the embodiment of the present disclosure, a second preset threshold can be set. When the offset distance included in the corrected second posture offset is greater than the second preset threshold, navigation information for only moving the ultrasound probe is generated; when the offset distance included in the corrected second posture offset is less than or equal to the second preset threshold, navigation information for rotating the ultrasound probe is generated. That is, the ultrasound probe needs to be rotated only when it is moved to a position closer to the target scanning position. This can simplify the operator's operation of the ultrasound probe based on the navigation information and avoid the operator repeatedly rotating the ultrasound probe multiple times at a position far away from the target scanning position.

[0142] like Fig. 9 As shown, Fig. 9 A schematic diagram of an ultrasound probe navigation process provided by an embodiment of the present disclosure is shown below. Fig. 9 Provide explanation.

[0143] S901. The operator places the ultrasound probe on the skin surface of the target scanning organ of the human body.

[0144] S902, obtaining t through an ultrasonic probe 0 Ultrasound section image at time I(t 0 ).

[0145] S903, will t 0 Ultrasound section image at time I(t 0 ) Input displacement deviation estimation model F 1 ().

[0146] Among them, the displacement deviation estimation model F 1 () is the first estimation model in the above embodiment.

[0147] S904, obtaining displacement deviation estimation model F 1 The output of the ultrasonic probe is at t 0 The pose offset D(t 0 ).

[0148] S905, offset the posture D(t 0 ) is converted into navigation information.

[0149] S906: The operator controls the ultrasound probe to move according to the navigation information.

[0150] S907, obtain t 1 Ultrasound section image at time I(t 1 ), t 0 and t 1 The position U(t 0 ) and U(t 1 ).

[0151] S908, will t 1 The displacement deviation estimation model F of the ultrasonic section image input at time 1 (), get the ultrasonic probe at t 1 The pose offset D(t 1 ).

[0152] S909, calculate t 0 and t 1 The difference of the posture offset at the moment is used to obtain the first posture change value ΔP IMG .

[0153] Among them, ΔP IMG =D(t 0 )-D(t 1 ).

[0154] S910, calculate t 0 and t 1 The difference in posture collected by IMU at the moment is used to obtain the second posture change value ΔP IMU .

[0155] Among them, ΔP IMU =U(t 0 )-U(t 1 ).

[0156] S911, will 0 Ultrasound section image at time I(t 0 ), t 1 Ultrasound section image at time I(t 1 )、U(t 0 ) and U(t 1 ) Input estimation model F 2 (), and obtain the third posture change value ΔP AI .

[0157] Among them, the estimated model F 2 It is the second estimation model in the above embodiment.

[0158] ΔP AI =F 2 ({I(t 0 ), I(t 1 )},{U(t 0 )), U(t 1 )}).

[0159] S912, through the indirect Kalman filtering technology, the first position change value ΔP IMG , the second posture change value ΔP IMU And the third posture change value ΔP AI Filtering is performed to obtain t0 and t 1 The correction value of ultrasound probe posture change at time ΔP K (0).

[0160] S913, the ultrasonic probe is 1 The pose offset D(t 1 ) to obtain the corrected t 1 The posture deviation D(t 1 ) K .

[0161] Among them, D(t 1 ) K =D(t 0 )-ΔP K (0).

[0162] S914, D(t 1 ) K Converted to navigation information.

[0163] S915: The operator controls the ultrasound probe to move according to the navigation information.

[0164] S916, get t j ,t j+1 Ultrasound cross-sectional image at the moment and ultrasound probe posture collected by IMU.

[0165] You can get t later j ,t j+1 The first posture change value, the second posture change value and the third posture change value at time t are corrected. 0 and t 1 The processing methods of the three posture change values ​​at the moment are the same, and the specific implementation process is omitted here.

[0166] S917, get t j ,t j+1 The corrected position change value of the ultrasonic probe at time ΔP K (j).

[0167] S918, to t j+1 The posture offset at the moment is corrected to obtain the corrected posture offset D(t j+1 ) K =D(t j )-ΔP K (j).

[0168] S919, determine D(t j+1 ) K Is it less than a first preset threshold?

[0169] If the judgment result is yes, execute S920; if the judgment result is no, return to S915.

[0170] S920: The ultrasonic probe stops moving and reaches the target scanning position.

[0171] The navigation solution provided by the disclosed embodiment can be applied to an ultrasound scanning system, which can reduce the difficulty of using ultrasound equipment, enable operators to quickly master the use of ultrasound equipment, and make the application scenarios of ultrasound equipment more extensive, so that operators in grassroots medical institutions can also use ultrasound equipment skillfully. It can also be applied to the training scenarios of ultrasound doctors to reduce the training time of ultrasound doctors.

[0172] Based on the same inventive concept, the present disclosure also provides an ultrasound probe navigation device, such as Fig.10 As shown, the device comprises:

[0173] An acquisition module 1001 is used to acquire a first ultrasonic section image acquired by the ultrasonic probe at a first moment and a second ultrasonic section image acquired at a second moment during a scanning process performed by an operator using the ultrasonic probe;

[0174] A determination module 1002 is used to determine a first posture change value based on a first posture offset and a second posture offset; wherein the first posture offset is a posture offset between a posture of the ultrasound probe and a target posture when acquiring a first ultrasound section image, the second posture offset is a posture offset between a posture of the ultrasound probe and a target posture when acquiring a second ultrasound section image, and the target posture is a standard posture when the ultrasound probe scans a target scanning position;

[0175] The correction module 1003 is further used to correct the first posture change value based on the first ultrasonic section image, the second ultrasonic section image and the posture of the ultrasonic probe at the first moment and the second moment to obtain a corrected posture change value;

[0176] The correction module 1004 is used to correct the second posture offset based on the corrected posture change value, and generate navigation information of the ultrasound probe based on the corrected second posture offset.

[0177] Optionally, the correction module 1003 is specifically used for:

[0178] Obtaining the position and posture of the ultrasonic probe at a first moment and a second moment measured by an inertial measurement unit (IMU) installed in the ultrasonic probe;

[0179] Calculate the difference between the position and posture of the ultrasonic probe at the first moment and the position and posture of the ultrasonic probe at the second moment to obtain a second position and posture change value;

[0180] Determine a third posture change value based on the first ultrasonic section image, the second ultrasonic section image, and the posture of the ultrasonic probe at the first moment and the second moment;

[0181] Based on the second posture change value and the third posture change value, the first posture change value is corrected to obtain a corrected posture change value.

[0182] Optionally, the device further comprises:

[0183] A judging module, used to judge whether the corrected second posture deviation is less than a first preset threshold;

[0184] The determination module 1002 is further configured to determine that the ultrasound probe has been moved to the target scanning position if the determination result of the determination module is yes;

[0185] The correction module 1003 is also used to execute the step of generating navigation information of the ultrasound probe based on the corrected second posture offset if the judgment result of the judgment module is no, and trigger the acquisition module 1001 to acquire the ultrasound section image collected by the ultrasound probe at the next moment, take the current second moment as the first moment, take the next moment as the second moment, and trigger the determination module 1002 to execute the step of determining the first posture change value based on the first posture offset and the second posture offset, until the judgment module determines that the corrected second posture offset is less than the first preset threshold.

[0186] Optionally, the determination module 1002 is further configured to obtain the first pose offset and the second pose offset in the following manner:

[0187] Inputting the first ultrasonic section image into the first estimation model to obtain the first pose offset output by the first estimation model;

[0188] Inputting the second ultrasonic section image into the first estimation model to obtain a second posture offset output by the first estimation model;

[0189] Among them, the first estimation model is a regression model obtained by training with a first preset training set, and the first preset training set includes multiple sample ultrasound section images and a posture offset between the ultrasound probe's posture and the target posture when collecting each sample ultrasound section image; the ultrasound probe's posture is obtained using an optical positioning tracking device or a magnetic positioning tracking device.

[0190] Optionally, the correction module 1003 is specifically used for:

[0191] Inputting the first ultrasonic section image, the second ultrasonic section image, and the postures measured by the ultrasonic probe at the first moment and the second moment into a second estimation model, and obtaining a third posture change value output by the second estimation model;

[0192] Among them, the second estimation model is a regression model trained by the second preset training set, the second preset training set includes multiple groups of sample data, and the posture change value of the ultrasound probe during the collection of each group of sample data; each group of sample data includes two ultrasound slice images collected at two adjacent moments, and the posture of the ultrasound probe collected by the IMU at two adjacent moments; the posture change value of the ultrasound probe is obtained by using an optical positioning tracking device or a magnetic positioning tracking device.

[0193] Optionally, the correction module 1003 is specifically used for:

[0194] The first posture change value, the second posture change value and the third posture change value are filtered based on the indirect Kalman filtering method to obtain the corrected posture change value.

[0195] Optionally, the correction module 1004 is specifically used for:

[0196] The difference between the first pose offset and the corrected pose change value is calculated to obtain the corrected second pose offset.

[0197] Optionally, the corrected second posture offset includes an offset distance and an offset angle;

[0198] The correction module 1004 is specifically used for:

[0199] If the offset distance is greater than a second preset threshold, converting the offset distance into a moving direction to obtain navigation information;

[0200] If the offset distance is less than or equal to the second preset threshold, the offset angle is converted into a rotation direction to obtain navigation information.

[0201] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0202] It should be noted that the ultrasound cross-sectional images in this embodiment are from a public data set.

[0203] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0204] Fig.11A schematic block diagram of an example electronic device 1100 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0205] like Fig.11 As shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0206] A number of components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0207] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1101 performs the various methods and processes described above, such as the ultrasound probe navigation method. For example, in some embodiments, the ultrasound probe navigation method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the ultrasound probe navigation method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to execute the ultrasound probe navigation method in any other appropriate manner (eg, by means of firmware).

[0208] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0209] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0210] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0211] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0212] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0213] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0214] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0215] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An ultrasound probe navigation method, include: During scanning by the ultrasonic probe, the operator obtains a first ultrasonic section image acquired by the ultrasonic probe at a first moment and a second ultrasonic section image acquired at a second moment; Determine the first pose change value based on the first pose offset and the second pose offset; wherein the first pose offset is the pose offset between the pose of the ultrasound probe and the target pose when acquiring the first ultrasound section image, the second pose offset is the pose offset between the pose of the ultrasound probe and the target pose when acquiring the second ultrasound section image, and the target pose is the standard pose of the ultrasound probe when scanning the target scanning position; Based on the first ultrasonic cross-sectional image, the second ultrasonic cross-sectional image, and the position and posture of the ultrasonic probe at the first moment and the second moment, correcting the first position and posture change value to obtain a corrected position and posture change value; The difference between the first posture offset and the corrected posture change value is calculated to obtain a corrected second posture offset, and the navigation information of the ultrasound probe is generated based on the corrected second posture offset.

2. The method according to claim 1, in, The method of correcting the first posture change value based on the first ultrasonic cross-section image, the second ultrasonic cross-section image, and the posture of the ultrasonic probe at the first moment and the second moment to obtain a corrected posture change value includes: Acquire the position and posture of the ultrasonic probe at the first moment and the second moment measured by an inertial measurement unit IMU installed in the ultrasonic probe; Calculating the difference between the position and posture of the ultrasonic probe at the first moment and the position and posture of the ultrasonic probe at the second moment to obtain a second position and posture change value; Determine a third posture change value based on the first ultrasound cross-section image, the second ultrasound cross-section image, and the posture of the ultrasound probe at the first moment and the second moment; Based on the second posture change value and the third posture change value, the first posture change value is corrected to obtain the corrected posture change value.

3. The method according to claim 1, after obtaining the corrected second posture offset, the method further include: Determining whether the corrected second posture deviation is less than a first preset threshold; If yes, it is determined that the ultrasound probe has been moved to the target scanning position; If not, execute the step of generating the navigation information of the ultrasound probe based on the corrected second posture offset, and obtain the ultrasound section image collected by the ultrasound probe at the next moment, take the current second moment as the first moment, take the next moment as the second moment, and return to the step of determining the first posture change value based on the first posture offset and the second posture offset until the corrected second posture offset is less than the first preset threshold.

4. The method according to any one of claims 1 to 3, in, The first posture offset and the second posture offset are obtained by: Inputting the first ultrasonic section image into a first estimation model to obtain the first posture offset output by the first estimation model; Inputting the second ultrasound section image into the first estimation model to obtain the second posture offset output by the first estimation model; Among them, the first estimation model is a regression model trained by a first preset training set, and the first preset training set includes multiple sample ultrasound section images, and the posture offset between the posture of the ultrasound probe and the target posture when each sample ultrasound section image is collected; the posture of the ultrasound probe is obtained by using an optical positioning tracking device or a magnetic positioning tracking device.

5. The method according to claim 2, in, The determining a third posture change value based on the first ultrasonic cross-section image, the second ultrasonic cross-section image, and the posture of the ultrasonic probe at the first moment and the second moment includes: Inputting the first ultrasonic cross-sectional image, the second ultrasonic cross-sectional image, and the position and posture of the ultrasonic probe at the first moment and the second moment into a second estimation model, and obtaining the third position and posture change value output by the second estimation model; Among them, the second estimation model is a regression model trained by a second preset training set, and the second preset training set includes multiple groups of sample data, and the posture change value of the ultrasound probe during the collection of each group of sample data; each group of sample data includes two ultrasound slice images collected at two adjacent moments, and the posture of the ultrasound probe collected by the IMU at the two adjacent moments; the posture change value of the ultrasound probe is obtained by using an optical positioning tracking device or a magnetic positioning tracking device.

6. The method according to claim 2, in, The method of correcting the first posture change value based on the second posture change value and the third posture change value to obtain the corrected posture change value includes: The first posture change value, the second posture change value and the third posture change value are filtered based on an indirect Kalman filtering method to obtain the corrected posture change value.

7. The method according to claim 1, in, The corrected second posture offset includes an offset distance and an offset angle; The generating the navigation information of the ultrasound probe based on the corrected second posture offset includes: If the offset distance is greater than a second preset threshold, converting the offset distance into a moving direction to obtain the navigation information; If the offset distance is less than or equal to the second preset threshold, the offset angle is converted into a rotation direction to obtain the navigation information.

8. An ultrasound probe navigation device, include: An acquisition module, used for acquiring a first ultrasonic section image acquired by the ultrasonic probe at a first moment and a second ultrasonic section image acquired at a second moment during a scanning process performed by an operator using the ultrasonic probe; A determination module, configured to determine a first posture change value based on a first posture offset and a second posture offset; wherein the first posture offset is a posture offset between a posture of the ultrasound probe and a target posture when acquiring the first ultrasound section image, the second posture offset is a posture offset between a posture of the ultrasound probe and a target posture when acquiring the second ultrasound section image, and the target posture is a standard posture when the ultrasound probe scans a target scanning position; a correction module, configured to correct the first posture change value based on the first ultrasonic section image, the second ultrasonic section image, and the posture of the ultrasonic probe at the first moment and the second moment to obtain a corrected posture change value; A correction module is used to calculate the difference between the first posture offset and the corrected posture change value to obtain a corrected second posture offset, and generate navigation information of the ultrasound probe based on the corrected second posture offset.

9. The device according to claim 8, in, The correction module is specifically used for: Acquire the position and posture of the ultrasonic probe at the first moment and the second moment measured by an inertial measurement unit IMU installed in the ultrasonic probe; Calculating the difference between the position and posture of the ultrasonic probe at the first moment and the position and posture of the ultrasonic probe at the second moment to obtain a second position and posture change value; Determine a third posture change value based on the first ultrasound cross-section image, the second ultrasound cross-section image, and the posture of the ultrasound probe at the first moment and the second moment; Based on the second posture change value and the third posture change value, the first posture change value is corrected to obtain the corrected posture change value.

10. The device according to claim 8, further comprising: include: A judging module, used to judge whether the corrected second posture deviation is less than a first preset threshold; The determining module is further configured to determine that the ultrasonic probe has been moved to the target scanning position if the determination result of the determining module is yes; The correction module is also used to execute the step of generating the navigation information of the ultrasound probe based on the corrected second posture offset if the judgment result of the judgment module is no, and trigger the acquisition module to acquire the ultrasound section image collected by the ultrasound probe at the next moment, take the current second moment as the first moment, take the next moment as the second moment, and trigger the determination module to execute the step of determining the first posture change value based on the first posture offset and the second posture offset, until the judgment module determines that the corrected second posture offset is less than the first preset threshold.

11. The device according to any one of claims 8 to 10, in, The determining module is further configured to obtain the first posture offset and the second posture offset in the following manner: Inputting the first ultrasonic section image into a first estimation model to obtain the first posture offset output by the first estimation model; Inputting the second ultrasound section image into the first estimation model to obtain the second posture offset output by the first estimation model; Among them, the first estimation model is a regression model trained by a first preset training set, and the first preset training set includes multiple sample ultrasound section images, and the posture offset between the posture of the ultrasound probe and the target posture when each sample ultrasound section image is collected; the posture of the ultrasound probe is obtained by using an optical positioning tracking device or a magnetic positioning tracking device.

12. The device according to claim 9, in, The correction module is specifically used for: Inputting the first ultrasonic cross-sectional image, the second ultrasonic cross-sectional image, and the position and posture of the ultrasonic probe at the first moment and the second moment into a second estimation model, and obtaining the third position and posture change value output by the second estimation model; Among them, the second estimation model is a regression model trained by a second preset training set, and the second preset training set includes multiple groups of sample data, and the posture change value of the ultrasound probe during the collection of each group of sample data; each group of sample data includes two ultrasound slice images collected at two adjacent moments, and the posture of the ultrasound probe collected by the IMU at the two adjacent moments; the posture change value of the ultrasound probe is obtained by using an optical positioning tracking device or a magnetic positioning tracking device.

13. The device according to claim 9, in, The correction module is specifically used for: The first posture change value, the second posture change value and the third posture change value are filtered based on an indirect Kalman filtering method to obtain the corrected posture change value.

14. The device according to claim 8, in, The corrected second posture offset includes an offset distance and an offset angle; The correction module is specifically used for: If the offset distance is greater than a second preset threshold, converting the offset distance into a moving direction to obtain the navigation information; If the offset distance is less than or equal to the second preset threshold, the offset angle is converted into a rotation direction to obtain the navigation information.

15. An electronic device, include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

17. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images