Breath-holding training method, system and storage medium

Abstract

An embodiment of the present specification provides a breath-holding training system, which includes a training scanner for performing a simulated scan on a patient undergoing breath-holding training; a state detection device for collecting state data reflecting the patient's breath-holding state during the simulated scan; and a processing device for determining the patient's breath-holding duration based on the state data.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging, and in particular to a breath-holding training method, system, and storage medium for assisting a patient in holding their breath during a scan. Background Art

[0002] With the advancement of technology, medical imaging systems such as computed tomography (CT) have become widely used in clinical diagnosis. The quality of images captured in medical imaging depends not only on the performance of the device's software and hardware, but also on the patient's cooperation during system use. During the scanning process, the patient's respiratory movement can introduce artifacts, while inaccurately selected scanning parameters can hinder the patient's ability to hold their breath and easily expose the patient to excessive radiation exposure.

[0003] Therefore, it is necessary to provide a breath-holding training method, system and storage medium for performing breath-holding training on patients before a formal scan, and / or assisting users in selecting appropriate scanning parameters for a formal scan. Summary of the Invention

[0004] One embodiment of this specification provides a breath-holding training system. The system includes: a training scanner for performing a simulated scan on a patient undergoing breath-holding training; a state detection device for collecting state data reflecting the patient's breath-holding state during the simulated scan; and a processing device for determining the patient's breath-holding duration based on the state data.

[0005] In some embodiments, the state detection device includes an optical camera, and the state data includes a first image acquired at a first acquisition time and a second image acquired at a second acquisition time. In order to determine the patient's breath-holding duration based on the state data, the processing device is used to: determine the patient's movement amplitude from the first acquisition time to the second acquisition time based on the first image and the second image using a first motion detection model; and determine the patient's breath-holding duration based on the movement amplitude.

[0006] In some embodiments, the state detection device includes an optical camera, and the state data includes a first image acquired at a first acquisition time and a second image acquired at a second acquisition time. In order to determine the patient's breath-holding duration based on the state data, the processing device is used to: based on the first image and the second image, use a second motion detection model to determine whether the patient has respiratory movement from the first acquisition time to the second acquisition time; and determine the patient's breath-holding duration based on the judgment result.

[0007] In some embodiments of the present specification, the first motion detection model and / or the second motion detection model are used to determine the patient's breath-holding duration based on images captured by the optical camera, which can improve the accuracy and efficiency of the breath-holding duration determination, thereby helping to determine the optimal scanning parameters during the formal imaging scan.

[0008] In some embodiments, the state detection device includes an acceleration sensor arranged on the patient's abdomen, and the state data includes an acceleration value in at least one target direction. In order to determine the patient's breath-holding duration based on the state data, the processing device is used to: determine whether the patient's body position is a prone position based on the acceleration value in the at least one target direction; in response to the patient's body position being a prone position, determine the movement amplitude based on the acceleration value in the at least one target direction; and determine the patient's breath-holding duration based on the movement amplitude.

[0009] In some embodiments, the acceleration value in each target direction includes at least two acceleration values ​​corresponding to at least two time points, and judging whether the patient's body position is a prone position based on the acceleration value in at least one target direction includes: filtering the at least two acceleration values ​​corresponding to each target direction to obtain at least two filtered acceleration values; determining the average acceleration value of the at least two filtered acceleration values ​​corresponding to each target direction; determining the angle between the acceleration direction of the patient and a reference direction based on the average acceleration value of the at least one target direction; and judging whether the patient's body position is a prone position based on the angle between the acceleration direction of the patient and the reference direction.

[0010] In some embodiments, determining the movement amplitude based on the acceleration value in the at least one target direction includes: for each target direction, determining the maximum acceleration value and the minimum acceleration value of the at least two filtered acceleration values ​​corresponding to it; and determining the movement amplitude based on the maximum acceleration value and the minimum acceleration value of the at least one target direction.

[0011] In some embodiments of this specification, an acceleration sensor is used to obtain acceleration values ​​in at least one target direction to determine whether the patient's position is prone. Only when the patient's position is prone is the patient's breath-holding duration further determined. This method can prevent inaccurate measurement results due to incorrect patient position. At the same time, some embodiments of this specification provide methods for filtering and analyzing the acceleration values ​​collected by the acceleration sensor, which can efficiently and accurately determine the patient's movement amplitude and breath-holding duration, thereby providing a reference for setting parameters for the formal imaging scan process and facilitating setting optimal scanning parameters during the formal imaging scan process.

[0012] In some embodiments, the state detection device includes an optical camera and an acceleration sensor arranged on the patient's abdomen, and the state data includes an acceleration value in at least one target direction, a first image acquired at a first acquisition time, and a second image acquired at a second acquisition time; the patient's breath-holding duration is determined based on the state data, and the processing device is used to: determine a first movement amplitude based on the acceleration value in the at least one target direction; determine a second movement amplitude based on the first image and the second image; and determine the patient's breath-holding duration based on the first movement amplitude and the second movement amplitude.

[0013] In some embodiments of this specification, the patient's breath-holding state is analyzed based on state data collected by both an optical camera and an acceleration sensor, which can improve the accuracy of the determination result.

[0014] In some embodiments, the system further includes an imaging scanner for performing medical imaging on the patient, and the processing device is further used to: determine scanning parameters based on the patient's breath-holding time; and control the imaging scanner to scan the patient based on the scanning parameters.

[0015] One embodiment of this specification provides a breath-holding training method. The method includes: instructing a training scanner to perform a simulated scan on a patient undergoing breath-holding training; obtaining state data reflecting the patient's breath-holding state collected by a state detection device during the simulated scan; and determining the patient's breath-holding duration based on the state data.

[0016] One embodiment of the present specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a breath-holding training method.

[0017] During medical scans, patients may be asked to hold their breath to avoid respiratory artifacts. Currently, patients typically do not receive breath-holding training before the imaging scanner is controlled to perform a formal scan. Patients are unfamiliar with the breath-holding action and the scanning process, which can result in patients being unable to maintain the correct breath-holding action during the formal scan. Furthermore, technicians often rely on experience to determine scan parameters such as scan length, which may not be appropriate for the patient. This can lead to artifacts due to the patient's respiratory movement during the formal scan or exposure to additional radiation.

[0018] To avoid these issues, the present invention performs simulated scans on patients undergoing breath-holding training to determine the duration of their breath-holding. Scan parameters are then determined based on this duration. Simulated scans help patients familiarize themselves with the scanning process and master the essentials of breath-holding, ensuring optimal compliance with breath-holding requirements to obtain qualified scan images. Furthermore, based on the patient's performance during breath-holding training, appropriate scanning parameters can be determined, thus avoiding artifacts caused by respiratory motion during the actual scan and minimizing the patient's exposure to additional radiation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0020] Figure 1 is a schematic diagram of an application scenario of a breath-holding training system according to some embodiments of this specification;

[0021] Figure 2 is an exemplary flow chart of breath holding training according to some embodiments of the present specification;

[0022] Figure 3 is an exemplary flow chart of determining the breath-holding duration based on an acceleration sensor according to some embodiments of this specification;

[0023] Figure 4 is a schematic diagram of a process for determining a patient's breath-holding duration based on a first motion detection model according to some embodiments of this specification;

[0024] Figure 5 is a schematic diagram of a process for determining a patient's breath-holding duration based on a second motion detection model according to some embodiments of this specification;

[0025] Figure 6 is a schematic diagram of determining the breath-holding duration based on an optical camera and an acceleration sensor according to some embodiments of this specification;

[0026] Figure 7 is a schematic diagram of determining the angle between the acceleration direction of a patient and a reference direction according to some embodiments of this specification;

[0027] Figure 8 It is a module diagram of a breath-holding training system according to some embodiments of this specification. DETAILED DESCRIPTION

[0028] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0029] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0030] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0031] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0032] Figure 1 FIG1 is a schematic diagram of an application scenario 100 of a breath-holding training system according to some embodiments of this specification. In some embodiments, the application scenario 100 of the breath-holding training system may include a training scanner 110, a state detection device 120, a demonstration device 140, a processing device 150, and an imaging scanner 160. In some embodiments, the application scenario 100 of the breath-holding training system may also include a storage device, Bluetooth, a network, and / or a user terminal (not shown).

[0033] The training scanner 110 can be used to perform simulated scans on patients undergoing breath-holding training. In some embodiments, the training scanner 110 may include a training frame 130 and a scanning bed 170. The training frame 130 can be used to fix and support the optical camera 120-1, the demonstration device 140, the main control unit, the storage device, the Bluetooth module and / or the network module, etc. In some embodiments, the training frame 130 can have a similar shape and size to the frame of the imaging scanner 160, and its material can be organic glass (Polymethyl methacrylate, PMMA), which is only used to fix and support other components. In some embodiments, the training frame 130 can be used to determine whether the patient suffers from claustrophobia. When the patient suffers from claustrophobia, the user can be told in advance to take measures.

[0034] During the simulation scan, the patient can lie on the scanning bed 170. In some embodiments, the scanning bed 170 includes a main bed frame and a bed plate. The main bed frame can serve as a support and is provided with guide rails, and the bed plate can slide on the guide rails of the main bed frame (for example, driven by a servo motor). In some embodiments, the training scanner 110 only supports the bed's forward and backward movement functions and does not have an image scanning function. In some embodiments, the bed speed during the simulation scan can be determined based on the part of the patient undergoing breath-hold training to be scanned by the imaging scanner.

[0035] The state detection device 120 can be used to collect state data reflecting the patient's breath-holding state during the simulated scanning process. In some embodiments, the state detection device 120 may include an accelerometer 120-2 arranged on the patient's abdomen, and accordingly, the state data may include an acceleration value in at least one target direction. The accelerometer 120-2 may be an electronic device capable of measuring acceleration force, which is the force acting on an object during acceleration. In some embodiments, the accelerometer 120-2 may be a three-axis accelerometer. The at least one target direction may include at least one of the x-axis direction, the y-axis direction, and the z-axis direction. Among them, the x-axis, the y-axis, and the z-axis constitute an orthogonal coordinate system. In some embodiments, during the simulated scanning process, the accelerometer 120-2 may select a ±2g range, a 10-bit resolution, and a 25Hz sampling frequency to collect acceleration signals in three dimensions: the x-axis, the y-axis, and the z-axis.

[0036] In some embodiments, the state detection device 120 may include an optical camera 120-1. Accordingly, the state data may include image data captured by the optical camera 120-1. For example, the state data may include multiple images captured by the optical camera 120-1 at different times. In some embodiments, the optical camera 120-1 may include a 3D camera to obtain a three-dimensional image of the abdomen of a patient undergoing breath-holding training. Exemplary optical cameras 120-1 may also include structured light cameras, depth cameras, laser cameras, lidar, and the like.

[0037] In some embodiments, the state detection device 120 may include an optical camera 120-1 and an acceleration sensor 120-2 disposed on the patient's abdomen. Accordingly, the state data may include acceleration values ​​and image data in at least one target direction. For more details about the state data, see Figure 2-Figure 6 and its related descriptions.

[0038] In some embodiments, the camera in the optical camera 120-1 may be a binocular camera. The binocular camera may include a projector and two detectors, wherein the two detectors are located at different positions next to the patient's abdomen to achieve high-precision three-dimensional positioning. The projector can project a certain pattern of structured light (for example, infrared light) onto the surface of the patient's abdomen. The structured light is reflected on the surface of the patient's abdomen and received by the detector, so that three-dimensional spatial information modulated by the shape of the patient's abdominal surface can be obtained and a three-dimensional image can be generated. The structured light emitted by the projector may include stripe structured light, point structured light, checkerboard structured light, or any other form of structured light. In some embodiments, the camera in the optical camera 120-1 may include only one projector and one detector.

[0039] Demonstration device 140 can be used to demonstrate a breath-holding instructional tutorial, which can be presented in the form of video, images, text, or voice. In some embodiments, different breath-holding instructional tutorials can be presented for different scan areas. In some embodiments, demonstration device 140 can also include a simulated breath-holding button. After learning the breath-holding video, the patient can click the simulated breath-holding button and follow the voice prompts to begin a simulated scan.

[0040] The processing device 150 can be used to process data related to the breath-hold training system. For example, the processing device 150 can determine the patient's breath-hold duration based on status data reflecting the patient's breath-hold status collected by the status detection device 120. Furthermore, the processing device 150 can determine scanning parameters based on the patient's breath-hold duration and, based on the scanning parameters, control the imaging scanner 160 to scan the patient. In some embodiments, the processing device 150 can be a single server or a server group. The server group can be centralized or distributed. In some embodiments, the processing device 150 can be local or remote. In some embodiments, the processing device 150 can be implemented on a cloud platform. By way of example only, the cloud platform can include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, internal clouds, multi-layer clouds, and the like, or any combination thereof. In some embodiments, the processing device 150 can be integrated or installed on the training scanner 110. For example, the processing device 150 can be an FPGA (Field Programmable Gate Array) mounted on the training gantry 130. In some embodiments, the processing device 150 can be integrated or installed on the status detection device 120.

[0041] The imaging scanner 160 can be used to perform a formal scan on the patient. In some embodiments, the processing device 150 can determine the scanning parameters based on the patient's breath-holding time, and then control the imaging scanner 160 to scan the patient or a specific part thereof. In some embodiments, the imaging scanner 160 may include an imaging device, an interventional medical device, or a combination thereof. The imaging device can obtain a reconstructed image related to at least a part of the patient. Exemplary imaging scanners 160 may include an MRI scanner, a PET scanner, a CT scanner, a DR scanner, etc., or a combination thereof. Exemplary interventional medical devices may include radiotherapy (RT) equipment, ultrasound therapy equipment, thermal therapy equipment, surgical intervention equipment, etc., or a combination thereof.

[0042] In some embodiments, a user may also interact with the breath-hold training system via other user terminals (not shown) in addition to presentation device 140. Exemplary user terminals may include mobile devices, tablet computers, laptop computers, or any combination thereof. In some embodiments, processing device 150 may be part of presentation device 140 or other user terminals.

[0043] In some embodiments, the application scenario 100 of the breath-hold training system may further include one or more other devices, such as Bluetooth, a network, and / or a storage device. The network may include any suitable wired or wireless network that facilitates information and / or data exchange. For example, the processing device 150 and the state detection device 120 may transmit information and / or data via Bluetooth and / or a network.

[0044] The storage device may store data, instructions, and / or any other information. In some embodiments, the storage device may store data and / or instructions related to breath-hold training. For example, the storage device may store state data. As another example, the storage device may store instructions for processing the state data to determine a patient's breath-hold duration.

[0045] In some embodiments, the storage device can be connected to a network to facilitate communication with one or more other components of the breath-holding training system application scenario 100 (e.g., the state detection device 120, the presentation device 140, the processing device 150, and / or the imaging scanner 160). One or more components of the breath-holding training system application scenario 100 can access data or instructions stored in the storage device via the network. In some embodiments, the storage device can be part of the processing device 150.

[0046] Figure 2 is an exemplary flow chart of breath holding training according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, Figure 2 One or more operations of the illustrated process 200 may be performed in Figure 1 The breath holding training system is implemented in the application scenario 100 shown. For example, Figure 2 The illustrated process 200 may be stored in a storage device in the form of instructions and called and / or executed by the processing device 150 .

[0047] Step 210 , instructing the training scanner to perform a simulated scan on the patient undergoing breath-holding training. In some embodiments, step 210 may be performed by the instruction module 810 .

[0048] Breath-holding training refers to training that requires patients to hold their breath and practice breath-holding movements.

[0049] A simulation scan refers to a practice scan that the patient performs before the formal scan. In some embodiments, the simulation scan does not image the patient, but can control the scanning bed to perform the movement of moving in and out of the bed at different speeds. In some embodiments, the scanning process in the simulation scan can be the same or consistent with the formal scan. For example, the patient will be asked to lie on the scanning bed, and then the demonstration device (e.g., demonstration device 140) can play instructions asking the patient to hold his breath, and then the scanning bed will move to transport the patient to the aperture of the training frame (e.g., training frame 130). In some embodiments, the patient will be asked to hold his breath for a specific length of time during the simulation scan, and the breath-holding time required for scanning different areas of interest may be different. In some embodiments, the bed entry speeds for simulation scans corresponding to different areas of interest may be the same or different. In some embodiments, the scan length of the simulation scan may be equal to the bed entry speed multiplied by the required breath-holding time.

[0050] In some embodiments, before the simulated scan, the demonstration device can play a breath-holding instructional tutorial for the patient. For example, a professional scanning technician from a tertiary hospital and a model patient can record breath-holding demonstration videos for different scan areas. The demonstration device can then select the appropriate demonstration video to play based on the patient's scan area. In some embodiments, demonstration videos include videos for various scan areas, such as lung scans, liver scans, and combined chest and abdominal scans.

[0051] Step 220 , obtaining state data reflecting the patient's breath-holding state collected by the state detection device during the simulated scanning process. In some embodiments, step 220 may be performed by the acquisition module 820 .

[0052] The state data may include any data that can reflect the patient's breath-holding state. In some embodiments, the state data may include an acceleration value in at least one target direction collected by an acceleration sensor (such as acceleration sensor 120-2). In some embodiments, the state data may include images collected by an optical camera (such as optical camera 120-1). For example, the state data may include a first image collected by optical camera 120-1 at a first collection time and a second image collected at a second collection time. For more details about state data, see Figure 3-Figure 6 and its related descriptions.

[0053] In some embodiments, the processing device 150 may obtain the status data collected by the status detection device during the simulation scanning process from the status detection device via the network and / or Bluetooth.

[0054] Step 230 , determining the patient's breath-holding duration based on the status data. In some embodiments, step 230 may be performed by the determination module 830 .

[0055] In some embodiments, step 230 can be performed during a simulated scan. For example, during a simulated scan, the status detection device can send the collected status data to the processing device 150 in real time or intermittently (e.g., periodically). Based on the received status data, the processing device 150 can determine the duration of the patient's breath-holding state. If the duration of the patient's breath-holding state is greater than or equal to the preset breath-holding duration for the simulated scan (e.g., 30s, 35s, 40s, etc.), the presentation device 140 will instruct the patient to stop holding their breath. The patient's breath-holding duration will then be equal to the preset breath-holding duration for the simulated scan. If the patient's breath-holding state lasts for less than the preset breath-holding duration for the simulated scan but the patient has already stopped holding their breath, the patient's breath-holding duration will be equal to the patient's maximum breath-holding duration during the simulated scan. If the patient's breath-holding state lasts for less than the preset breath-holding duration for the simulated scan and the patient continues to hold their breath, the presentation device 140 may issue a prompt instructing the patient to continue holding their breath. In some embodiments, step 230 can be performed after the simulated scan concludes. For example, the processing device 150 may determine, based on all state data collected by the state detection device during the simulation scan, the length of time the patient maintains the breath-holding state during the simulation scan as the breath-holding duration.

[0056] In some embodiments, the processing device 150 may execute Figure 3 Flow 300 is shown to determine the duration of a patient's breath-hold based on acceleration values ​​in at least one target direction obtained by an acceleration sensor disposed on the patient's abdomen. For another example, processing device 150 can determine the duration of a patient's breath-hold based on a first image acquired by an optical camera at a first acquisition time and a second image acquired at a second acquisition time. For another example, processing device 150 can determine the duration of a patient's breath-hold based on acceleration values ​​in at least one target direction obtained by the optical camera and the acceleration sensor disposed on the patient's abdomen, the first image acquired at the first acquisition time, and the second image acquired at the second acquisition time.

[0057] More details on determining a patient's breath-hold duration based on state data can be found in Figure 3-Figure 6 and its related descriptions.

[0058] Step 240 , determining scanning parameters based on the patient's breath-holding duration. In some embodiments, step 240 may be performed by the determination module 830 .

[0059] Scan parameters refer to parameters related to the formal scan that will be performed on the patient. For example, scan parameters may include scan range, scan length, etc. Scan range may refer to the coverage of the scanned area. In some cases, due to the patient's limited breath-holding ability or the long length of the scanned area, multiple irradiations are required to complete the formal scan. For example, the patient may be required to hold their breath for a specific length of time during a single irradiation, and after the completion of the single scan, the patient may ventilate, and after the completion of the ventilation, the next irradiation may be performed to scan other parts of other patients. Scan length may refer to the length of the scanned area in the axial direction of the imaging scanner during a single scan.

[0060] In some embodiments, the processing device 150 can determine scanning parameters during the main scan based on the breath-holding time determined by the patient during the simulation scan. For example, the processing device 150 can determine the scan length based on the patient's breath-holding time and the preset bed speed required to scan the patient's selected region of interest. Specifically, the scan length can be equal to the patient's breath-holding time multiplied by the preset bed speed. In some embodiments, the processing device 150 can determine the final breath-holding time by taking the average of multiple breath-holding times determined by the patient during multiple simulation scans. For another example, the processing device 150 can determine the scan range based on the scan length of the patient. Specifically, the processing device 150 can select the area to be examined that has a length equal to the scan length as the scan range and prioritize scanning this scan range. This can avoid artifacts caused by the patient's respiratory motion during the main scan, avoid radiation exposure to non-regions of interest due to improper scan range settings, or avoid radiation exposure caused by secondary scans due to artifacts in the scanned image, thereby reducing the patient's radiation dose.

[0061] Step 250 , based on the scanning parameters, controls the imaging scanner to scan the patient. In some embodiments, step 250 may be performed by the instruction module 810 .

[0062] In some embodiments, the processing device 150 may control the imaging scanner to perform a formal scan on the patient using the scan parameters based on the scan parameters.

[0063] A simulated scan is performed on a patient undergoing breath-holding training to determine the patient's breath-holding duration. Scan parameters are then determined based on this duration, and the imaging scanner is controlled based on these scan parameters to scan the patient. The simulated scan helps patients become familiar with the breath-holding techniques used during the formal imaging scan, ensuring they adhere to these requirements to the greatest extent possible to obtain qualified scan images. It also helps the processing equipment set optimal scan parameters during the formal imaging scan based on the patient's breath-holding duration as reported by the breath-holding training system, thereby avoiding artifacts caused by the patient's own respiratory movement and minimizing the radiation dose from unnecessary scans.

[0064] It should be noted that the above description of process breath-hold training is for illustrative purposes only and does not limit the scope of application of this specification. Those skilled in the art will be able to make various modifications and alterations to process breath-hold training under the guidance of this specification. However, such modifications and alterations will remain within the scope of this specification.

[0065] Figure 3 This is an exemplary flow chart of determining the breath holding time based on an acceleration sensor according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps. In some embodiments, Figure 3 One or more operations of the illustrated process 300 may be performed in Figure 1 The breath holding training system is implemented in the application scenario 100 shown. For example, Figure 3 The illustrated process 300 may be stored in a storage device in the form of instructions and called and / or executed by the processing device 150 .

[0066] like Figure 2 As described above, the processing device 150 can determine the patient's breath-holding duration based on the acceleration value collected by the acceleration sensor in at least one target direction. The target direction refers to the coordinate axis direction of the coordinate system corresponding to the acceleration sensor. In some embodiments, the acceleration sensor may include a three-axis sensor. Figure 7 As shown, the acceleration sensor can be set parallel to the patient's abdomen, and the target direction can include three directions: X-axis, Y-axis and Z-axis, wherein the X-axis direction is perpendicular to the upper surface of the acceleration sensor, the Y-axis direction is parallel to the upper surface of the acceleration sensor, and the Z-axis is a direction perpendicular to the X-axis and the Y-axis.

[0067] The acceleration value refers to a physical quantity obtained by an acceleration sensor that reflects the speed of an object. In some embodiments, the acceleration sensor can collect AD values ​​and convert the AD values ​​into acceleration values ​​using the following formula (1):

[0068] x trans =x ad *3.9 / 1000*9.8 (1)

[0069] Among them, x ad is the AD value, the corresponding unit is LSB, x trans is the acceleration value, the corresponding unit is m / s 2 AD value refers to the value after converting analog quantity (such as current, voltage) into digital quantity.

[0070] In some embodiments, each acceleration value in the target direction may include at least two acceleration values ​​corresponding to at least two time points. In other words, the acceleration sensor may collect acceleration values ​​in the target direction multiple times at different time points.

[0071] In some embodiments, processing device 150 may first determine whether the patient's position is recumbent based on the acceleration value in at least one target direction. Once the patient's position is determined to be recumbent, processing device 150 may further determine the patient's breath-holding duration based on the acceleration value. For example, processing device 150 may perform steps 310-340 to determine whether the patient is recumbent.

[0072] Step 310 : For each target direction, filter at least two corresponding acceleration values ​​to obtain at least two filtered acceleration values. In some embodiments, step 310 may be performed by the determination module 830 .

[0073] For each target direction, the processing device 150 may filter at least two corresponding acceleration values ​​to obtain at least two filtered acceleration values. In some embodiments, the processing device 150 may perform a 5-point median filter on the collected acceleration values ​​of the X-axis, Y-axis, and Z-axis. For example, taking the X-axis as an example, the processing device 150 may divide the collected acceleration values ​​of the X-axis into groups of 5 points, sort the 5 points in each group, and use the median value as the filtered value of the corresponding point, that is, i_med =Med(sort(x i-2 , x i-1 , x i , x i+1 , x i+2 )) is the value after 5-point median filtering, where x i_med is the value after median filtering of the 5 points in group i, x i is x i-2 , x i-1 , x i+1 , x i+2 The processing device 150 can use a similar method to perform 5-point median filtering on the Y axis and the Z axis. Then the 5-point median filtered signal y is obtained. i_med , z i_med , so as to achieve the purpose of removing the jump singularity points.

[0074] In some embodiments, the processing device 150 may perform a trimmed mean filter on the signal after the 5-point median filtering. The filter window width of the trimmed mean filter is set to 5, and the trimming ratio coefficient is set to 0.2. For example, taking the X-axis as an example, the processing device 150 may group the acceleration values ​​of the signal after the 5-point median filtering into groups of 5 points, and sort the 5 points in each group, remove the maximum and minimum values ​​after sorting, and take the average of the remaining 3 points, that is, x-axis.i_tmf =TMF(sort(x i-2_med , x i-1_med , x i_med , x i+1_med , x i+2_med )) is the value after trimming mean filtering, where x i_tmf is the value after the trimmed mean filter of group i, x i_med is x i-2_med , x i-1_med , x i+1_med , x i+2_med The processing device 150 can use a similar method to perform trimmed mean filtering on the Y axis and the Z axis. Then the trimmed mean filtered signal y is obtained. i_tmf , z i_tmf .

[0075] It should be understood that the median filter and mean filter described above are merely exemplary filtering methods; any other feasible filtering method can also be used to filter the acceleration values ​​in the target direction to remove jump singularities. Accelerometers are unstable, and filtering the acceleration values ​​in the target direction can filter out some noise and remove jump singularities, thereby revealing characteristic acceleration trends.

[0076] Step 320 : For each target direction, determine the average acceleration value of the at least two filtered acceleration values ​​corresponding thereto. In some embodiments, step 320 may be performed by the determination module 830 .

[0077] In some embodiments, for each target direction, the processing device 150 may be based on the corresponding trimmed mean filtered signal x tmf ,y tmf , z tmf Do the average to get the average acceleration value. Just as an example, for the X axis, you can i_tmf Take the average and get x mean ; For the Y axis, you can i_tmf Take the average and get y mean ; For the Z axis, you can i_tmf Take the average and get z mean .

[0078] Step 330 : Determine the angle between the patient's acceleration direction and the reference direction based on the average acceleration value of at least one target direction. In some embodiments, step 330 may be performed by the determination module 830 .

[0079] The acceleration direction may be one or more of at least one target direction. For example, the acceleration direction may be Figure 7 The directions of the X and Y axes are shown.

[0080] The reference direction can be used to calibrate the patient's posture. Figure 7 As shown, the reference direction may be a horizontal direction, which is parallel to the plane of the scanning bed supporting the patient.

[0081] In some embodiments, the processing device 150 may determine the angle between the patient's acceleration direction and the reference direction based on equations (2) and (3).

[0082]

[0083]

[0084] Among them, x mean is the average acceleration value of the X axis, y mean is the average acceleration value of the Y axis, z mean is the average acceleration value of the Z axis, and α and β are the angles between the patient's acceleration direction and the reference direction. Figure 7 As shown, α is the angle between the X-axis and the horizontal direction, and β is the angle between the Y-axis and the horizontal direction.

[0085] Step 340 : Based on the angle between the patient's acceleration direction and the reference direction, determine whether the patient's body position is prone. In some embodiments, step 340 may be performed by the determination module 830 .

[0086] Body position refers to the patient's body posture. For example, the patient's body position may include lying down, sitting, standing, etc. Among them, lying down may include lying flat, lying on the side and / or lying prone.

[0087] In some embodiments, the processing device 150 can determine whether the patient's body position is prone based on the angle between the patient's acceleration direction and the reference direction. α And β<thres β , the processing device 150 can determine that the patient's body position is lying down. α and thres β They refer to the angle thresholds corresponding to the X-axis and Y-axis respectively.

[0088] In some embodiments, in response to the patient's body position not being a prone position, the processing device 150 may control the demonstration device 140 to instruct the patient to adjust the body position. After a certain period of time (e.g., 30 seconds, 1 minute, etc.), steps 310 to 340 are performed again to determine whether the patient's body position is a prone position after the adjustment.

[0089] In some embodiments, in response to the patient's body position being a prone position, the processing device 150 may determine the breath-holding duration based on the acceleration value in at least one target direction by executing steps 350 - 370 .

[0090] Step 350 : For each target direction, determine the maximum acceleration value and the minimum acceleration value of the at least two filtered acceleration values ​​corresponding thereto. In some embodiments, step 350 may be performed by the determination module 830 .

[0091] In some embodiments, for each target direction, the processing device 150 may calculate the maximum acceleration value and the minimum acceleration value of the at least two filtered acceleration values. In some embodiments, the processing device 150 may calculate the maximum acceleration value and the minimum acceleration value of the at least two filtered acceleration values ​​based on the trimmed mean filtered signal x. i_tmf ,y i_tmf , z i_tmf , determine the maximum acceleration value x in the X-axis direction max With the minimum acceleration value x min , the maximum acceleration value y in the Y-axis direction max With the minimum acceleration value y min , and the maximum acceleration value z in the Z-axis direction max With the minimum acceleration value z min .

[0092] Step 360 : Determine the motion amplitude based on the maximum acceleration value and the minimum acceleration value in at least one target direction. In some embodiments, step 360 may be performed by the determination module 830 .

[0093] The motion amplitude can reflect the displacement of the patient during the simulated scanning process. In some embodiments, the motion amplitude can reflect the degree of the patient's abdominal heave, and thus can reflect the amplitude of the patient's respiratory motion.

[0094] In some embodiments, the processing device 150 may determine the motion amplitude based on the maximum acceleration value and the minimum acceleration value in at least one target direction. For example, the processing device 150 may use the vector sum of the signal oscillation amplitudes as the motion amplitude. The vector sum of the signal oscillation amplitudes may be obtained based on formula (4):

[0095]

[0096] Among them, vib amp is the vector sum of the signal oscillation amplitude, x max is the maximum acceleration value in the X-axis direction, x min is the minimum acceleration value in the X-axis direction, y max is the maximum acceleration value in the Y-axis direction, y min is the minimum acceleration value in the Y-axis direction, z max is the maximum acceleration value in the Z-axis direction, zmin is the minimum acceleration value in the Z-axis direction.

[0097] Step 370 , determining the patient's breath-holding duration based on the movement amplitude. In some embodiments, step 370 may be performed by the determination module 830 .

[0098] In some embodiments, the processing device 150 may determine the duration of the patient's breath holding based on the amplitude of the movement. For example, the processing device 150 may determine the duration of the patient's breath holding based on the vector sum of the signal oscillation amplitudes. That is, when vib amp >thres amp The processing device 150 can determine whether the patient has respiratory movement, and the processing device 150 can calculate the time interval T from the patient's breath holding to the determination of the presence of respiratory movement. hold , and T hold As the patient's breath holding time. When the preset breath holding time T is reached done When it is still not able to meet vib amp >thres amp , the demonstration device (such as demonstration device 140) will instruct the patient to stop holding his breath, and the patient's breath-holding time is equal to the breath-holding time preset in the simulation scan.

[0099] In some embodiments of this specification, an acceleration sensor is used to obtain acceleration values ​​in at least one target direction to determine whether the patient's position is prone. Only when the patient's position is prone is the patient's breath-holding duration further determined. This method can prevent inaccurate measurement results due to incorrect patient position. At the same time, some embodiments of this specification provide methods for filtering and analyzing the acceleration values ​​collected by the acceleration sensor, which can efficiently and accurately determine the patient's movement amplitude and breath-holding duration, thereby providing a reference for setting parameters for the formal imaging scan process and facilitating setting optimal scanning parameters during the formal imaging scan process.

[0100] It should be noted that the above description of the process breath-holding training is for illustrative purposes only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and changes to the process breath-holding training under the guidance of this specification. However, such modifications and changes remain within the scope of this specification. In some embodiments, steps 320-340 may be omitted. In some embodiments, determining whether the patient is in a supine position may be based on other methods, such as by analyzing the patient's optical image.

[0101] In some embodiments, the state detection device includes an optical camera, and the state data includes a first image captured by the optical camera at a first acquisition time and a second image captured by the optical camera at a second acquisition time. In some embodiments, the processing device 150 can use a first motion detection model to determine the patient's motion amplitude from the first acquisition time to the second acquisition time based on the first and second images, and then determine the patient's breath-holding duration based on the motion amplitude. In some embodiments, the processing device 150 can use a second motion detection model to determine whether the patient experienced respiratory motion from the first acquisition time to the second acquisition time based on the first and second images, and then determine the patient's breath-holding duration based on the determination result.

[0102] In some embodiments, the first image and the second image may be three-dimensional images, such as depth images. In some embodiments, the first acquisition time may be earlier than the second acquisition time. In some embodiments, the two three-dimensional image frames corresponding to the first acquisition time and the second acquisition time may be adjacent or non-adjacent. For example, the following description uses two frames with the first acquisition time and the second acquisition time being adjacent to each other as an example.

[0103] Figure 4 4 is a schematic diagram of a process 400 for determining a patient's breath-holding duration based on a first motion detection model according to some embodiments of this specification.

[0104] In some embodiments, the first motion detection model 420 may be a deep learning neural network model. Exemplary deep learning neural network models may include convolutional neural networks (CNN), deep neural networks (DNN), recurrent neural networks (RNN), etc., or a combination thereof.

[0105] In some embodiments, as Figure 4 As shown, the input of the first motion detection model 420 can be the first image 410-1 and the second image 410-2. In some embodiments, the output of the first motion detection model 420 is a motion magnitude 430. For example, the motion magnitude 430 can be represented by a motion field from the first image 410-1 to the second image 410-2. The motion field can include multiple motion vectors, each of which can represent the amount and direction of movement from a point in the first image 410-1 to its corresponding point in the second image 410-2.

[0106] In some embodiments, as Figure 4As shown, the model parameters of the first motion detection model 420 can be obtained by training the first initial model 450 using multiple first training samples. For example, multiple first training samples can be obtained. Each training sample can include a sample first image 440-1 and a sample second image 440-2 of a sample patient.

[0107] The training of the first initial model 450 may include one or more iterations. By way of example only, in the current iteration, for each first training sample, the processing device 150 may use the first intermediate model to determine the motion field from the sample first image 440-1 to the sample second image 440-2 of the first training sample. If the current iteration is the first iteration, the first intermediate model may be the first initial model 450. If the current iteration is any other iteration, the first intermediate model may be a model generated in the previous iteration. The processing device 150 may transform the sample first image 440-1 based on the motion field. The processing device 150 may further determine the value of the loss function based on the similarity between the transformed sample first images and the sample second image 440-2 of the plurality of first training samples, and update the first intermediate model based on the value of the loss function.

[0108] In some embodiments, the parameters of the first initial model 450 can be iteratively updated based on the plurality of first training samples so that the loss function of the first intermediate model satisfies a preset condition. For example, the loss function converges, or the loss function value is less than a preset value. When the loss function satisfies the preset condition, model training is complete, and the trained first initial model 450 can be used as the first motion detection model.

[0109] In some embodiments, processing device 150 can determine the patient's breath-holding duration based on the motion amplitude output by the first motion detection model. For example, for all frames captured by the optical camera, processing device 150 can determine the motion amplitude between each pair of adjacent frames and determine the patient's breath-holding duration based on the sum of the determined motion amplitudes. Specifically, when the sum of the motion amplitudes is greater than a preset threshold, processing device 150 can determine that the patient has respiratory motion and calculate the time interval from the start of breath-holding to the current frame as the patient's breath-holding duration. If the preset breath-holding duration is reached but the sum of the motion amplitudes is still less than the preset threshold, the presentation device (such as presentation device 140) will instruct the patient to stop holding their breath, and the patient's breath-holding duration will then be equal to the preset breath-holding duration for the simulated scan. For another example, processing device 150 can determine the patient's breath-holding duration based on the motion amplitudes of the current frame and the previous frame. Specifically, when the motion amplitudes of the current frame and the previous frame are greater than a preset threshold, processing device 150 can determine that the patient has respiratory motion and calculate the time interval from the start of breath-holding to the current frame as the patient's breath-holding duration. When the preset breath-holding time is reached, but the motion amplitude of the current frame and the previous frame is still less than the preset threshold, the demonstration device (such as demonstration device 140) will instruct the patient to stop holding his breath, and the patient's breath-holding time is equal to the breath-holding time preset for the simulated scan.

[0110] In some embodiments of the present specification, the first motion detection model is used to determine the motion amplitude and then determine the patient's breath-holding time, which can quickly and accurately obtain the patient's breath-holding time, thereby helping the processing device 150 to set the optimal scanning parameters during the formal imaging scan according to the patient's breath-holding time determined by the optical camera.

[0111] Figure 5 5 is a schematic diagram of a process 500 for determining a patient's breath-holding duration based on a second motion detection model according to some embodiments of this specification.

[0112] In some embodiments, the second motion detection model 420 may be a deep learning neural network model. Exemplary deep learning neural network models may include CNN, DNN, RNN, etc., or a combination thereof.

[0113] In some embodiments, as Figure 5 As shown, the input of the second motion detection model 510 may be the first image 410 - 1 and the second image 410 - 2 . In some embodiments, the output of the second motion detection model 510 is a determination result 520 of whether respiratory motion occurs.

[0114] In some embodiments, as Figure 5As shown, the second motion detection model 510 can be generated by training a second initial model 540 using a plurality of positive samples 530-1 and negative samples 530-2. The positive samples 530-1 include image pairs collected from a sample patient in a breath-holding state, and the negative samples 530-2 include image pairs collected from a sample patient in a respiratory motion state (e.g., adjacent frames captured by an optical camera).

[0115] The training of the second initial model 540 may include one or more iterations. As an example only, in the current iteration, for each second training sample, the processing device 150 may use the second intermediate model to determine whether the positive sample 530-1 and the negative sample 530-2 of the second training sample have respiratory motion. If the current iteration is the first iteration, the second intermediate model may be the second initial model 540. If the current iteration is another iteration, the second intermediate model may be a model generated in the previous iteration. The processing device 150 may determine the value of the loss function based on the accuracy of the result of whether the positive sample 530-1 and the negative sample 530-2 of the second training sample have respiratory motion, and update the second intermediate model based on the value of the loss function.

[0116] In some embodiments, the parameters of the second initial model 540 can be iteratively updated based on the plurality of second training samples so that the loss function of the second intermediate model satisfies a preset condition. For example, the loss function converges, or the loss function value is less than a preset value. When the loss function satisfies the preset condition, model training is complete, and the trained second initial model 540 can be used as the second motion detection model.

[0117] In some embodiments, the processing device 150 can determine the patient's breath-holding duration 460 based on whether respiratory movement 520 occurs in the output of the second motion detection model 510. For example, the processing device 150 can determine the patient's breath-holding duration based on whether respiratory movement occurs in the current frame relative to the previous frame. That is, when respiratory movement occurs in the current frame relative to the previous frame, the processing device 150 can determine that the patient has respiratory movement and calculate the time interval from the start of the patient's breath-holding to the current frame as the patient's breath-holding duration. When the preset breath-holding duration is reached, but respiratory movement still does not occur in the current frame relative to the previous frame, the presentation device (such as the presentation device 140) will instruct the patient to stop holding his breath, and the patient's breath-holding duration is equal to the breath-holding duration preset for the simulation scan.

[0118] Processing device 150 can calculate the time interval from the patient's breath-holding to the determination of respiratory movement as the patient's breath-holding duration. If, after reaching the preset breath-holding duration, the motion amplitude of the current frame and the previous frame still does not exceed the preset threshold, the presentation device (such as presentation device 140) will instruct the patient to stop breath-holding, and the patient's breath-holding duration will be equal to the preset breath-holding duration of the simulated scan.

[0119] In some embodiments, processing device 150 may utilize other methods to determine the duration of the patient's breath-hold based on first image 410-1 and second image 410-2. For example, processing device 150 may utilize an image similarity algorithm to determine the similarity between first image 410-1 and second image 410-2. If the similarity is less than a similarity threshold, processing device 150 may determine that the patient has experienced respiratory motion. For another example, processing device 150 may determine the motion field between first image 410-1 and second image 410-2 by registering first image 410-1 and second image 410-2, as the motion amplitude.

[0120] In some embodiments of this specification, a second motion detection model is used to determine whether respiratory movement has occurred, and thus to determine the patient's breath-holding duration. This allows for faster acquisition of the patient's breath-holding duration, thereby facilitating the processing device 150 to set optimal scanning parameters during the actual imaging scan based on the patient's breath-holding duration determined by the optical camera. Furthermore, the label acquisition method for the second motion detection model is simple, which can improve training efficiency.

[0121] Figure 6 This is a schematic diagram of determining a breath-holding duration 600 based on an optical camera and an acceleration sensor according to some embodiments of this specification.

[0122] like Figure 6 As shown, the state detection device includes an optical camera 120-1 and an acceleration sensor 120-2 disposed on the patient's abdomen. The state data includes an acceleration value 610 in at least one target direction, a first image 410-1 acquired at a first acquisition time, and a second image 410-2 acquired at a second acquisition time. The processing device 150 can determine a second motion amplitude 610-2 based on the acceleration value 610 in the at least one target direction; then determine a first motion amplitude 620-2 based on the first image 410-1 and the second image 410-2; and further determine the duration of the patient's breath-holding based on the second motion amplitude 620-1 and the first motion amplitude 620-2.

[0123] For example, processing device 150 may use the average or weighted average of second movement amplitude 620-1 and first movement amplitude 620-2 as the final movement amplitude. The patient's breath-holding duration 630 is then determined based on the final movement amplitude. For more details on determining the patient's breath-holding duration based on the movement amplitude, see step 370 and its related description.

[0124] In some embodiments, the processing device 150 can determine whether the patient has experienced respiratory movement based on the second movement amplitude 620-1 and the first movement amplitude 620-2. For example, when the second movement amplitude 620-1 and the first movement amplitude 620-2 simultaneously determine that the patient has experienced respiratory movement, the processing device 150 can determine that the patient has experienced respiratory movement, and the processing device 150 can calculate the patient's breath-holding duration 630 from the start of breath-holding to the current moment. For another example, when the preset breath-holding duration is reached, but the second movement amplitude 620-1 and the first movement amplitude 620-2 do not simultaneously determine that the patient has experienced respiratory movement, the presentation device (such as the presentation device 140) will instruct the patient to stop holding his breath, and the patient's breath-holding duration 630 will be equal to the breath-holding duration preset for the simulated scan.

[0125] In some embodiments of this specification, the patient's breath-holding state is analyzed based on state data collected by both an optical camera and an acceleration sensor, which can improve the accuracy of the determination result.

[0126] Figure 8 800 is a module diagram of a breath-holding training system according to some embodiments of the present specification.

[0127] In some embodiments, the module diagram 800 of the breath-hold training system may include an indication module 810 , an acquisition module 820 , and a determination module 830 .

[0128] The instruction module 810 may be used to instruct the training scanner to perform a simulated scan on a patient who has received breath-holding training.

[0129] The acquisition module 820 can be used to acquire state data reflecting the patient's breath-holding state collected by the state detection device during the simulated scanning process. In some embodiments, the state detection device includes an optical camera, and the state data includes a first image collected at a first acquisition time and a second image collected at a second acquisition time. In some embodiments, the state detection device includes an acceleration sensor disposed on the patient's abdomen, and the state data includes an acceleration value in at least one target direction. In some embodiments, the state detection device includes an optical camera and an acceleration sensor disposed on the patient's abdomen, and the state data includes an acceleration value in at least one target direction, a first image collected at a first acquisition time, and a second image collected at a second acquisition time.

[0130] The determination module 830 can be used to determine the breath-holding duration of the patient based on the status data. In some embodiments, the determination module 830 can determine the breath-holding duration of the patient based on the first image and the second image using a first motion detection model or a second motion detection model. In some embodiments, the determination module 830 can determine whether the patient's body position is a prone position based on the acceleration value in the at least one target direction, and in response to the patient's body position being a prone position, determine the movement amplitude, and determine the breath-holding duration of the patient based on the movement amplitude. In some embodiments, the determination module 830 can determine a first movement amplitude based on the acceleration value in the at least one target direction; determine a second movement amplitude based on the first image and the second image; and determine the breath-holding duration of the patient based on the first movement amplitude and the second movement amplitude.

[0131] For more details about the indication module 810, the acquisition module 820 and the determination module 830, see Figure 2-Figure 7 and its related descriptions.

[0132] It should be understood that Figure 8 The system and its modules shown can be implemented in various ways. It should be noted that the above description of the candidate display and determination system and its modules is only for the convenience of description and does not limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principles of the system, it is possible to arbitrarily combine the modules or form subsystems to connect with other modules without deviating from this principle. In some embodiments, Figure 8 The indication module, acquisition module, and determination module disclosed herein may be different modules within a system, or a single module may implement the functions of two or more of the aforementioned modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0133] In some embodiments, a breath-holding training device includes a processor and a memory; the memory is used to store instructions, and when the instructions are executed by the processor, the device implements the breath-holding training method.

[0134] In some embodiments, a computer-readable storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the breath-holding training method.

[0135] The beneficial effects that may be brought about by the embodiments of this specification include but are not limited to: (1) By performing a simulated scan on a patient who has received breath-holding training to determine the patient's breath-holding time, then determining the scanning parameters based on the patient's breath-holding time, and controlling the imaging scanner to scan the patient based on the scanning parameters. The simulated scan helps the patient become familiar with the breath-holding essentials during the formal imaging scan and to comply with the breath-holding requirements to the greatest extent possible to obtain qualified scanned images. At the same time, it helps the processing device to set the optimal scanning parameters during the formal imaging scan based on the patient's breath-holding time as fed back by the breath-holding training system, thereby avoiding artifacts caused by the patient's own respiratory movement and also avoiding the patient from experiencing radiation doses caused by unnecessary scans. (2) Obtaining an acceleration value in at least one target direction through an acceleration sensor, and then determining whether the patient's body position is a prone position. Only when the patient's body position is a prone position will the patient's breath-holding time be further determined. This method can prevent inaccurate measurement results due to incorrect patient position. At the same time, some embodiments of this specification provide methods for filtering and analyzing the acceleration values ​​collected by the acceleration sensor, which can efficiently and accurately determine the patient's movement amplitude and breath-holding duration, thereby providing a reference for setting the parameters of the formal imaging scan process and helping to set the optimal scanning parameters during the formal imaging scan process. (3) By determining the movement amplitude through the first motion detection model and then determining the patient's breath-holding duration, the patient's breath-holding duration can be quickly and accurately obtained, thereby helping the processing device to set the optimal scanning parameters during the formal imaging scan process based on the breath-holding duration. (4) By determining whether respiratory movement occurs through the second motion detection model and then determining the patient's breath-holding duration, the patient's breath-holding duration can be obtained more quickly, thereby helping the processing device to set the optimal scanning parameters during the formal imaging scan process based on the patient's breath-holding duration determined by the optical camera. In addition, the label acquisition method of the second motion detection model is simple and can improve the efficiency of training. (5) Analyzing the patient's breath-holding state based on the state data collected by the optical camera and the acceleration sensor at the same time can improve the accuracy of the determination result.

[0136] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0137] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0138] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0139] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0140] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0141] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0142] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A breath-holding training system, characterized in that: include: a training scanner, used to perform simulated scans on patients undergoing breath-holding training; a state detection device for collecting state data reflecting the patient's breath-holding state during the simulated scanning process; The state detection device includes an optical camera and an acceleration sensor provided on the patient's abdomen, and the state data includes an acceleration value in at least one target direction, a first image acquired at a first acquisition time, and a second image acquired at a second acquisition time; as well as a processing device for determining a breath-holding duration of the patient based on the status data; The processing equipment is further configured to: determining whether the patient's body position is a prone position based on the acceleration value in the at least one target direction; In response to the patient being in a prone position, determining a first motion amplitude based on the acceleration value; determining a second motion magnitude based on the first image and the second image; as well as The breath-holding duration of the patient is determined based on the first movement amplitude and the second movement amplitude.

2. The system according to claim 1, wherein To determine the breath-holding time of the patient based on the status data, the processing device is configured to: determining, based on the first image and the second image, a motion amplitude of the patient from the first acquisition time to the second acquisition time using a first motion detection model; as well as Based on the movement amplitude, a breath-holding duration of the patient is determined.

3. The system according to claim 1, wherein: To determine the breath-holding time of the patient based on the status data, the processing device is configured to: determining, based on the first image and the second image, using a second motion detection model whether the patient has respiratory motion from the first acquisition time to the second acquisition time; Based on the judgment result, the breath-holding time of the patient is determined.

4. The system according to claim 1, wherein: The acceleration value in each target direction includes at least two acceleration values ​​corresponding to at least two time points, and judging whether the patient's body position is a prone position based on the acceleration value in at least one target direction includes: For each target direction, filtering the at least two acceleration values ​​corresponding thereto to obtain at least two filtered acceleration values; For each target direction, determining an average acceleration value of at least two filtered acceleration values ​​corresponding thereto; determining an angle between the acceleration direction of the patient and a reference direction based on the average acceleration value of the at least one target direction; and Based on the angle between the acceleration direction of the patient and the reference direction, it is determined whether the patient's body position is a prone position.

5. The system according to claim 4, wherein: Determining the first motion amplitude based on the acceleration value in the at least one target direction includes: For each target direction, determining a maximum acceleration value and a minimum acceleration value of the at least two filtered acceleration values ​​corresponding thereto; and The first motion amplitude is determined based on the maximum acceleration value and the minimum acceleration value in the at least one target direction.

6. The system according to claim 1, wherein: The system further comprises an imaging scanner for performing medical imaging on the patient, The processing equipment is further configured to: determining scanning parameters based on the breath-holding time of the patient; and Based on the scanning parameters, the imaging scanner is controlled to scan the patient.

7. A breath-holding training method, characterized in that: The method comprises: Instruct the training scanner to perform a simulated scan of the patient undergoing breath-holding training; acquiring state data reflecting the patient's breath-holding state collected by a state detection device during the simulated scanning process; and Determining the breath-holding duration of the patient based on the status data includes: determining whether the patient's body position is a prone position based on an acceleration value in at least one target direction; In response to the patient being in a prone position, determining a first motion amplitude based on the acceleration value; determining a second motion magnitude based on a first image acquired at a first acquisition time and a second image acquired at a second acquisition time; and The breath-holding duration of the patient is determined based on the first movement amplitude and the second movement amplitude.

8. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the breath-holding training method according to claim 7.

Images