Intelligent breathing navigation method, device and storage medium

Abstract

An embodiment of the present specification provides a method for intelligent breathing navigation based on a patient's breathing frequency, the method comprising the following steps: obtaining the patient's free breathing information before scanning, and predicting the patient's scanning state breathing frequency based on the patient's free breathing information before scanning; determining the patient's guidance breathing frequency during actual scanning based on the free breathing information, the scanning state breathing frequency, the scanning required breathing frequency, and the scan type; determining a navigation voice based on the guidance breathing frequency, and navigating the patient's breathing during actual scanning based on the navigation voice, thereby providing different breathing guidance for each patient's breathing condition and improving the efficiency of breathing navigation.

Description

Technical Field

[0001] This specification relates to the field of medical assistance technology, and in particular to a method, device, and computer-readable storage medium for performing intelligent respiratory navigation based on a patient's respiratory rate. Background Art

[0002] There are two modes for respiratory gating in CT scans: free breathing mode and breath-holding mode. Free breathing mode is more commonly used. Free breathing requires the patient to breathe regularly. However, when the patient is alone in the scanning room, they may not be able to breathe regularly and within the specified range, thus failing to meet the respiratory requirements during the scan.

[0003] Therefore, it is hoped to provide a voice navigation solution that can intelligently guide patients to breathe regularly based on their respiratory rate. Summary of the Invention

[0004] One of the embodiments of this specification provides a method for intelligent breathing navigation based on a patient's breathing frequency, the method comprising the following steps: obtaining the patient's free breathing information before scanning, and predicting the patient's scanning state breathing frequency based on the patient's free breathing information before scanning; determining the patient's guidance breathing frequency during actual scanning based on the free breathing information, the scanning state breathing frequency, the scanning required breathing frequency, and the scan type; determining a navigation voice based on the guidance breathing frequency, and navigating the patient's breathing during actual scanning based on the navigation voice.

[0005] In some embodiments, predicting the patient's scanning state respiratory frequency in the scanning state based on the patient's free breathing information before the scan includes: determining the patient's scanning state respiratory frequency in the scanning state based on the patient's free breathing information before the scan using a first deep learning model, wherein the first deep learning model is trained based on free breathing information training data of multiple historical patients.

[0006] In some embodiments, determining the patient's guide respiratory rate during actual scanning based on the free breathing information, the scanning state respiratory rate, the scanning required respiratory rate, and the scan type includes:

[0007] Based on the free breathing information, the scanning state respiratory frequency, the scanning required respiratory frequency and the scanning type, a second deep learning model is used to determine the patient's guidance respiratory frequency during the actual scanning, wherein the second deep learning model is trained based on training data of the free breathing information, the scanning state respiratory frequency, the scanning required respiratory frequency and the scanning type of multiple historical patients.

[0008] In some embodiments, the method further includes: acquiring the patient's free breathing information based on a patient status acquisition device, wherein the patient's free breathing information includes one or more combinations of the following: the patient's respiratory frequency, the patient's respiratory amplitude, the patient's sound information, the patient's image information, and the patient's personal information.

[0009] In some embodiments, the patient's respiratory rate is acquired based on a pressure sensor or a camera.

[0010] In some embodiments, the patient's guided breathing rate during the actual scan is determined by the following steps: judging whether intelligent voice navigation is required based on the scan type; in response to the need for intelligent voice navigation, judging whether the patient's free breathing information obtained before the scan meets the scanning breathing rate requirements; in response to the breathing rate meeting the scanning requirements, determining the patient's guided breathing rate during the actual scan; in response to the breathing rate not meeting the scanning requirements, performing breathing training on the patient.

[0011] In some embodiments, the determining of the navigation voice based on the guiding breathing frequency, and navigating the patient's breathing during actual scanning based on the navigation voice, include: judging whether the determined guiding breathing frequency of the patient during actual scanning meets the scanning required breathing frequency; in response to meeting the scanning required breathing frequency, determining the navigation voice based on the guiding breathing frequency; in response to not meeting the scanning required breathing frequency, performing breathing training on the patient.

[0012] In some embodiments, the method further includes: providing an abnormal prompt when abnormal breathing occurs in the patient during the actual scan.

[0013] One of the embodiments of this specification provides a device for performing intelligent breathing navigation based on a patient's breathing frequency, including: a breathing prediction module, used to obtain the patient's free breathing information before scanning, and predict the patient's scanning state breathing frequency based on the patient's free breathing information before scanning; a breathing determination module, used to determine the patient's guidance breathing frequency during actual scanning based on the free breathing information, the scanning state breathing frequency, the scanning required breathing frequency and the scan type; a breathing navigation module, used to determine a navigation voice based on the guidance breathing frequency, and navigate the patient's breathing during actual scanning based on the navigation voice.

[0014] In some embodiments, one of the embodiments of the present disclosure provides a computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method described in any one of the embodiments.

[0015] The method, device, and computer-readable storage medium for performing intelligent respiratory navigation based on a patient's respiratory rate provided in the embodiments of this specification have at least the following beneficial effects:

[0016] (1) By obtaining the patient's free breathing information before scanning, the patient's breathing frequency during scanning is predicted based on the patient's free breathing information before scanning. This method can provide different breathing guidance according to each patient's breathing condition, thereby improving the efficiency of respiratory navigation;

[0017] (2) At the same time, artificial intelligence is also used to predict the patient's respiratory rate in the scanning state based on the patient's free breathing information before the scan. The respiratory rate in the scanning state is determined by combining the breathing conditions of each patient and big data. The prediction results are more accurate and more adaptable.

[0018] (3) Furthermore, when determining the patient's guided respiratory rate during actual scanning based on the free breathing information, the respiratory rate in the scanning state, the respiratory rate required by the scanning, and the scanning type, artificial intelligence is used to make the determined guided respiratory rate more scientific, not only more adapted to the patient's free breathing rate, but also in line with the respiratory rate required by the scanning;

[0019] (4) In addition, according to the determined guiding breathing frequency, voice prompts can be given to guide the patient to breathe regularly during the scan, especially when abnormalities occur, so as to guide the patient to make regular breathing that meets the scanning requirements while adapting to the patient's own breathing rhythm, thereby improving the efficiency of breathing navigation and achieving accurate cooperation with the CT scanner to complete the scan. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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:

[0021] Figure 1 The figure shows a schematic diagram of an application scenario of an intelligent breathing navigation system based on a patient's breathing frequency according to some embodiments of this specification;

[0022] Figure 2 is an exemplary flow chart of a method for performing intelligent breathing navigation based on a patient's breathing rate according to some embodiments of this specification;

[0023] Figure 3 is an exemplary flow chart of the training process of the first deep learning model according to some embodiments of this specification;

[0024] Figure 4is an exemplary flow chart of the training process of the second deep learning model according to some embodiments of this specification;

[0025] Figure 5 A schematic diagram of the structure of a device for performing intelligent breathing navigation based on a patient's breathing frequency according to some embodiments of this specification is shown. DETAILED DESCRIPTION

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 1 The figure shows a schematic diagram of an application scenario of the intelligent breathing navigation system 100 according to the patient's breathing frequency according to some embodiments of this specification.

[0031] like Figure 1 As shown, the application scenario may include a medical device 110 , a processing device 120 , a storage device 130 , a terminal 140 and / or a network 150 .

[0032] Medical device 110 can be used to scan an object for diagnostic imaging. Medical device 110 can be used to view image information of the object's internal body tissue to assist doctors in diagnosing diseases. Medical device 110 can transmit higher-frequency sound waves (e.g., ultrasound waves) to the object via a probe to produce ultrasound images. In some embodiments, the object can include biological objects and / or non-biological objects. For example, the object can include a specific part of the human body, such as a chest. For another example, the object can be a patient to be scanned by medical device 110.

[0033] The medical device 110 can be configured to scan a scanned object using high-energy radiation (e.g., X-rays, gamma rays, etc.) to collect scan data related to the scanned object. The scan data can be used to generate one or more images of the scanned object. In some embodiments, the medical device 110 can include an ultrasound imaging (US) device, a computed tomography (CT) scanner, a digital radiography (DR) scanner (e.g., mobile digital radiography), a digital subtraction angiography (DSA) scanner, a dynamic spatial reconstruction (DSR) scanner, an X-ray microscope scanner, a multimodal scanner, or the like, or a combination thereof. In some embodiments, the multimodal scanner can include a computed tomography-positron emission tomography (CT-PET) scanner or a computed tomography-magnetic resonance imaging (CT-MRI) scanner.

[0034] The medical device 110 can be used for data acquisition, processing and / or output, positioning and other functions. The medical device 110 can include one or more sub-functional devices (for example, a single sensor device or a sensor system device composed of multiple sensor devices, a pressure sensor, etc.). In some embodiments, the medical device 110 can include but is not limited to an ultrasound transmitting unit (for example, including an ultrasound transducer, etc.), an ultrasound imaging unit, a radio frequency sensing unit, an NFC communication unit, an image acquisition unit (such as a camera, etc.), an image display unit, an audio output unit, etc. or any combination thereof. For example, the image display unit can be used to display the patient's respiratory waveform, etc. For example, the medical device 110 can be composed of its pressure sensor ( Figure 1 The medical device 110 may also receive information (not shown) about the patient's free breathing, such as information about the patient's free breathing before scanning. For example, the medical device 110 may also receive information about the patient's respiratory rate during scanning, the required respiratory rate during scanning, the scan type, and / or the guidance respiratory rate during scanning, etc., sent from the terminal 140 or the processing device 120 via the network 150.

[0035] The processing device 120 may include a single server, or a server group. The server group may be centralized or distributed (for example, the processing device 120 may be a distributed system). In some embodiments, the processing device 120 may be local or remote. For example, the processing device 120 may access information and / or data stored in the medical device 110, the terminal 140, and / or the storage device 130 via the network 150. For another example, the processing device 120 may be directly connected to the medical device 110, the terminal 140, and / or the storage device 130 to access the stored information and / or data. In some embodiments, the processing device 120 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof. In some embodiments, the processing device 120 may be implemented on a computing device comprising one or more components.

[0036] In some embodiments, processing device 120 can process information and / or data related to intelligent respiratory navigation to perform one or more functions described herein. In some embodiments, processing device 120 can be configured as one or more processing devices. For example, a function of processing device 120 can be implemented on multiple processing devices.

[0037] In some embodiments, the processing device 120 may include one or more processing engines (e.g., a single-core processing engine or a multi-core processing engine). The processing device 120 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), an application-specific instruction set processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, or the like, or any combination thereof. In some embodiments, the processing device 120 may be integrated into the medical device 110 and / or the terminal 140.

[0038] In some embodiments, the medical device 110, the terminal 140 and / or other possible system components may include a processing device 120. For example, the processing device 120 or a module that can implement the functions of the processing device 120 can be integrated into the medical device 110, the terminal 140 and / or other possible system components.

[0039] In some embodiments, one or more components of the medical device 110 may transmit data to other components of the medical device 110 via the network 150. For example, the processing device 120 may obtain information and / or data from the terminal 140, the medical device 110, and / or the storage device 130 via the network 150, or may transmit information and / or data to the terminal 140, the medical device 110, and / or the storage device 130 via the network 150.

[0040] The storage device 130 can be used to store data and / or instructions. Data refers to a digital representation of information and can include various types, such as binary data, text data, image data, and video data. Instructions refer to programs that control a device or component to perform a specific function. For example, the storage device 130 can store the patient's scan-state respiratory rate, scan-required respiratory rate, scan type, and / or the recommended respiratory rate during the scan.

[0041] The storage device 130 may include one or more storage components, each of which may be a standalone device or part of another device. In some embodiments, the storage device 130 may include random access memory (RAM), read-only memory (ROM), mass storage, removable memory, volatile read-write memory, or the like, or any combination thereof. Exemplarily, the mass storage may include a magnetic disk, an optical disk, a solid-state disk, or the like. In some embodiments, the storage device 130 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-layer cloud, or the like, or any combination thereof.

[0042] Terminal 140 refers to one or more terminal devices or software used by a user. Terminal 140 may include a processing unit, a display unit, an input / output unit, a sensing unit, a storage unit, etc. The sensing unit may include, but is not limited to, a light sensor, a distance sensor, an acceleration sensor, a gyroscope sensor, a sound detector, etc., or any combination thereof.

[0043] In some embodiments, terminal 140 can be any one of a mobile device 140-1, a tablet computer 140-2, a laptop computer 140-3, a desktop computer 140-4, or any combination thereof, and other devices with input and / or output capabilities. In some embodiments, terminal 140 can be used by one or more users, including those who directly use the service, such as ultrasound diagnosticians or ultrasound testing personnel, as well as other related users, such as patients and users of hospital medical systems. The above examples are intended only to illustrate the broad scope of terminal 140 devices and are not intended to limit their scope.

[0044] The network 150 can connect the various components of the system and / or connect the system with external resources. The network 150 enables communication between the various components and with other components outside the system, facilitating the exchange of data and / or information. In some embodiments, the network 150 can be any one or more of a wired network or a wireless network. For example, the network 150 can include a cable network, a fiber optic network, a telecommunications network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), a public switched telephone network (PSTN), a Bluetooth network, a ZigBee network, near-field communication (NFC), an in-device bus, an in-device line, a cable connection, or any combination thereof. The network connection between the various components can adopt one of the above methods or multiple methods. In some embodiments, the network can be a point-to-point, shared, centralized, or other topological structure, or a combination of multiple topological structures. In some embodiments, the network 150 can include one or more network access points. For example, network 150 may include wired or wireless network access points, such as base stations and / or network switching points, through which one or more components entering and exiting medical device 110 may connect to network 150 to exchange data and / or information.

[0045] It should be understood that Figure 1 The system and its modules shown can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above-mentioned methods and systems can be implemented using computer-executable instructions and / or included in processor control code, for example, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can not only be implemented by hardware circuits such as ultra-large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but can also be implemented by software executed by various types of processors, or by a combination of the above-mentioned hardware circuits and software (for example, firmware).

[0046] Also, it should be noted that for Figure 1The description of the medical device 110 is for convenience only and does not limit this specification to the exemplary embodiment. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form subsystems connected to other modules without departing from these principles.

[0047] Figure 2 This is an exemplary flow chart of a method 200 for performing intelligent breathing navigation based on a patient's respiratory rate, according to some embodiments of this specification. In some embodiments, the method 200 for performing intelligent breathing navigation based on a patient's respiratory rate can be performed by an apparatus 300 for performing intelligent breathing navigation based on a patient's respiratory rate, or by a medical device 110, a processing device 120, or a terminal 140.

[0048] Step 210 involves obtaining the patient's free breathing information before scanning. Based on this pre-scanning free breathing information, the patient's respiratory rate during scanning is predicted. This approach allows for tailored breathing guidance for each patient, improving the efficiency of respiratory navigation. In some embodiments, step 210 may be performed by the respiratory prediction module 310 of the intelligent respiratory navigation device 300. In some embodiments, pre-scan refers to the period before the scan is initiated (e.g., the scan's payout period, i.e., the period from the start of the scan to the end of the scan).

[0049] Free breathing means that the patient needs to breathe regularly. In some embodiments, the patient's free breathing information includes one or more of the following: the patient's respiratory rate, the patient's respiratory amplitude, the patient's voice information, the patient's image information, and the patient's personal information. In some embodiments, the patient's free breathing information may include the patient's respiratory rate and respiratory amplitude. In some embodiments, the patient's free breathing information can be obtained based on a patient status acquisition device.

[0050] In some embodiments, the patient status acquisition device may include a pressure sensor or a camera, for example, acquiring the patient's image information through a camera, etc. In some embodiments, the patient's image information may include image information captured of the patient in different respiratory states. In some embodiments, the image information of the patient in different respiratory states may include facial image information of the patient when holding his breath, facial image information when holding his breath, and facial image information of the patient in a free breathing state. In some embodiments, in some embodiments, the high-frequency image information and low-frequency image information in the images of the patient in different respiratory states may be processed, for example, a corresponding frequency curve may be obtained, and then the patient's respiratory frequency and respiratory amplitude may be obtained based on the frequency curve.

[0051] In some embodiments, the patient's free breathing information can be obtained based on a pressure sensor. In some embodiments, the patient's free breathing information can be collected based on a pressure sensor worn on the patient's body. In some embodiments, the patient's pressure information is first collected based on the pressure sensor worn on the patient's body, and then a corresponding pressure curve is fitted based on the patient's pressure information, and then the patient's respiratory rate and respiratory amplitude are obtained based on the pressure curve.

[0052] In some embodiments, the patient's respiratory rate in the scanning state can be predicted based on the acquired free breathing information of the patient before the scan. In some embodiments, the patient's respiratory rate in the scanning state can be determined based on the free breathing information of the patient before the scan using a first deep learning model, wherein the first deep learning model is trained based on free breathing information training data of multiple historical patients.

[0053] Figure 3 This is an exemplary flowchart of the training process of the first deep learning model in step 210 shown in some embodiments of this specification.

[0054] In some embodiments, the first deep learning model can be obtained through the following training process:

[0055] Sub-step 211: obtaining the patient's free breathing information training data, where the patient's free breathing information training data may include the patient's free breathing information training data before scanning and the patient's scanning state respiratory rate labeling data during scanning;

[0056] Sub-step 212: inputting the patient's free breathing information training data into the to-be-trained model, and outputting the patient's scanning state respiratory rate result data in the scanning state;

[0057] Sub-step 213: callback the model parameters through the scanning state respiratory rate result data of the patient in the scanning state and the scanning state respiratory rate annotation data of the patient in the scanning state to obtain the trained first deep learning model.

[0058] In some embodiments, a breathing curve of the patient holding their breath can be obtained based on the patient's breathing training process, and then the patient's respiratory rate and respiratory amplitude before scanning can be obtained based on the breathing curve. In some embodiments, a breathing test can also be performed on the patient while holding their breath, and it can be determined whether the respiratory data obtained from the breathing test matches the respiratory curve obtained during the patient's breathing training process. The test results can then be used to recall the patient's respiratory rate and respiratory amplitude before scanning obtained during the breathing training process.

[0059] In some embodiments, a free-breathing respiratory curve can be obtained based on the patient's free-breathing training process, and then the patient's pre-scan respiratory rate and respiratory amplitude can be obtained based on the free-breathing respiratory curve. In some embodiments, a free-breathing respiratory test can also be performed on the patient to determine whether the patient's free-breathing frequency is consistent each time. Based on the test results, the pre-scan respiratory rate and respiratory amplitude obtained during the call-holding and breath-holding training process can be recalled.

[0060] In some embodiments, the patient's breathing training process can be adjusted according to the patient's personal information. For example, when the age information in the patient's personal information is within a predetermined age range (e.g., 20-40 years old), the time of the patient's breathing training process can be adjusted, such as shortening the breathing training time, etc., so as to ensure the efficiency of the breathing training process, that is, to improve the efficiency of obtaining the patient's free breathing information training data. In some embodiments, the patient's breathing training process can also be adjusted in combination with the patient's historical breathing training data. For example, the respiratory frequency and respiratory amplitude of the patient obtained before the scan can be compared with the patient's historical breathing training data. When the respiratory frequency and respiratory amplitude of the patient obtained before the scan are consistent with the patient's historical breathing training data, it means that the training requirements have been met, and the patient's breathing training process can be stopped, thereby improving the efficiency of the breathing training process, that is, to improve the efficiency of obtaining the patient's free breathing information training data.

[0061] Through the artificial intelligence processing method of the first deep learning model, the patient's free breathing information is obtained before the scan. Based on the patient's free breathing information before the scan, the patient's breathing frequency in the scanning state is predicted. For example, the breathing frequency of once every 4 seconds before the scan can be predicted to be once every 3-5 seconds in the scanning state, making the prediction more accurate and adaptable, thereby guiding the breathing frequency more scientifically.

[0062] Step 220 , based on the free breathing information, the scanning state respiratory rate, the scanning required respiratory rate, and the scan type, determines the patient's guide respiratory rate during the actual scan. In some embodiments, step 220 may be performed by the breathing determination module 320 of the intelligent breathing navigation device 300 .

[0063] The "scanning state respiratory rate" refers to the free breathing rate during the scanning state. The "scanning requirement respiratory rate" refers to the respiratory rate that meets the CT scanning requirements during a CT scan. In some embodiments, the "scanning requirement respiratory rate" can be within a predetermined range that meets the scanning requirements. The average person takes a normal breath in the range of 3-6 seconds. Assuming a CT respiratory-gated scanner uses a spiral scanning method, the pitch is set based on this 3-6 second timeframe. This allows for CT scans within this respiratory rate range. Exceeding this range may result in an ineffective scan. The "scan type" refers to different scan types for different patient areas. In some embodiments, scan types may include conventional scans and CT scans for radiotherapy simulation, such as cardiac scans. For example, conventional scans are generally faster and may complete in a few seconds. For example, cardiac scans may complete in 2-3 seconds, require a lower dose, and require the patient to hold their breath during the scan to reduce artifacts caused by motion during the scan. Conventional CT scans typically complete in just a few seconds, requiring the patient to hold their breath and exhale, without the need for intelligent voice guidance tailored to each patient's individual needs. Therefore, in the embodiments of this specification, intelligent breathing navigation is mainly performed for the patient's free breathing scanning mode.

[0064] In addition, for example, during a CT scan for radiotherapy simulation, the CT scan image can guide the radiotherapy process. During the radiotherapy process, the radiotherapy equipment (such as RT equipment) needs to continuously irradiate the diseased area. The time required for one radiotherapy can reach more than 100 seconds. At this time, the patient is required to breathe regularly during the CT scan for radiotherapy simulation so that the radiotherapy machine can capture the patient's breathing pattern and start radiotherapy with each inhalation. Therefore, this process is an intermittent process, and the patient needs to continue to breathe regularly. Assuming that a breath is completed in the conventional 3-6 seconds, more than 20 regular breaths will be required for one radiotherapy scan.

[0065] In some embodiments, determining the patient's guidance breathing rate during the actual scan can be achieved through the following steps: judging whether intelligent voice navigation is required based on the scan type; in response to the need for intelligent voice navigation, judging whether the patient's free breathing information obtained before the scan meets the scan requirement breathing rate; in response to the scan requirement breathing rate being met, determining the patient's guidance breathing rate during the actual scan; in response to the scan requirement breathing rate not being met, performing breathing training on the patient. In some embodiments, the patient's guidance breathing rate during the actual scan can be determined based on the scan requirement breathing rate and the scan type. In some embodiments, determining the patient's guidance breathing rate during the actual scan based on the scan requirement breathing rate and the scan type can be implemented as the following process: judging whether intelligent voice navigation is required based on the scan type; in response to the need for intelligent voice navigation, judging whether the patient's free breathing information obtained before the scan meets the scan requirement breathing rate; in response to the scan requirement breathing rate being met, determining the patient's guidance breathing rate during the actual scan; in response to the scan requirement breathing rate not being met, performing breathing training on the patient. For example, when the patient's free breathing information obtained before scanning meets the scanning required respiratory rate, for example, in the range of 3-6 seconds, the scanning required respiratory rate can be determined as the patient's guide respiratory rate during actual scanning, and so on.

[0066] The guideline respiratory rate refers to a relatively ideal respiratory rate determined by comprehensively weighing the free breathing information, the respiratory rate in the scanning state, the required respiratory rate in the scan, and the scan type. In some embodiments, in step 220, determining the patient's guideline respiratory rate during the actual scan based on the free breathing information, the respiratory rate in the scanning state, the required respiratory rate in the scan, and the scan type can be implemented as follows: Based on the free breathing information, the respiratory rate in the scanning state, the required respiratory rate in the scan, and the scan type, a second deep learning model is used to determine the patient's guideline respiratory rate during the actual scan, wherein the second deep learning model is trained based on training data of the free breathing information, the respiratory rate in the scanning state, the required respiratory rate in the scan, and the scan type of multiple historical patients.

[0067] Figure 4 This is an exemplary flowchart of the training process of the second deep learning model in step 220 shown in some embodiments of this specification.

[0068] In some embodiments, the second deep learning model can be obtained through the following training process:

[0069] Sub-step 221 , obtaining the patient's free breathing information, respiratory rate in the scanning state, respiratory rate required for scanning, and training data of the scanning type, as well as the patient's guided respiratory rate annotation data during the actual scanning;

[0070] Sub-step 222: inputting the patient's free breathing information, scanning state respiratory rate, scanning required respiratory rate, and scanning type training data into the to-be-trained model, and outputting result data of the patient's guided respiratory rate during the actual scanning;

[0071] Sub-step 223: Using the result data of the patient's guidance respiratory rate during the actual scan and the annotation data of the patient's guidance respiratory rate during the actual scan, the model parameters are called back to obtain the trained second deep learning model.

[0072] By combining each patient's respiratory condition, big data, and the artificial intelligence algorithm of the second deep learning model, the guiding respiratory rate is determined, making the prediction results more accurate and adaptable.

[0073] Step 230: Determine a navigation voice based on the guidance breathing rate, and guide the patient's breathing during the actual scan based on the navigation voice. In some embodiments, step 220 can be performed by the breathing navigation module 330 of the intelligent breathing navigation device 300. In some embodiments, breathing navigation can be performed using the navigation voice in a free breathing scan scenario.

[0074] In some embodiments, a navigation voice is determined based on the guiding breathing rate, and the patient's breathing during the actual scan is navigated based on the navigation voice, including: determining whether the patient's guiding breathing rate during the actual scan meets the scanning required breathing rate; in response to meeting the scanning required breathing rate, determining a navigation voice based on the guiding breathing rate; in response to not meeting the scanning required breathing rate, performing breathing training on the patient. In some embodiments, the patient's guiding breathing rate during the actual scan is determined based on the scanning required breathing rate and the scan type, and can be implemented as the following process: judging whether intelligent voice navigation is needed according to the scan type; in response to requiring intelligent voice navigation, judging whether the patient's free breathing information obtained before the scan meets the scanning required breathing rate; in response to meeting the scanning required breathing rate, determining the patient's guiding breathing rate during the actual scan; in response to not meeting the scanning required breathing rate, performing breathing training on the patient. For example, if the patient's free breathing information obtained before the scan does not meet the scanning required breathing rate (for example, in the range of 3-6s), the patient can be given breathing training, and so on.

[0075] In some embodiments, the navigation voice can be used to control voice playback. The frequency of the navigation voice playback is determined based on the patient's breathing rate. For example, for the same patient, the navigation voice will play the corresponding voice guidance for exhalation and inhalation every four seconds. In some embodiments, the patient can also manually adjust the playback frequency of the navigation voice. Based on the determined guiding breathing frequency, the voice prompts instruct the patient to breathe regularly during the scan. This guides the patient to breathe regularly while adapting to their own breathing rhythm and achieves a breathing frequency that meets the scanning requirements, thereby improving the efficiency of respiratory navigation and achieving precise coordination with the CT scanner to complete the scan.

[0076] In some embodiments, the patient's free breathing state can be monitored in real time. In some embodiments, the corresponding respiratory waveform can be displayed in real time based on the real-time monitoring of the patient's free breathing state. In some embodiments, if an abnormal situation is caused by omissions in data collection or the patient's state is not adjusted in place, the abnormal signal can be removed by signal waveform editing, and the scan can be performed again when no abnormal situation occurs. In some embodiments, when the patient's free breathing during the actual scan is abnormal, an abnormal prompt can be given. In some embodiments, if the patient's breathing is always in an abnormal state during the scan, the scan can be terminated. It should be noted that the above description of process 200 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0077] Figure 5 A schematic diagram of the structure of a device 300 for performing intelligent breathing navigation based on a patient's breathing frequency according to some embodiments of this specification is shown.

[0078] In some embodiments, the intelligent breathing navigation apparatus 300 may include a breathing prediction module 310 , a breathing determination module 320 , and a breathing navigation module 330 .

[0079] In some embodiments, the breathing prediction module 310 can obtain the patient's free breathing information before scanning and, based on the patient's free breathing information before scanning, predict the patient's respiratory rate during scanning. The breathing determination module 320 can determine the patient's guidance respiratory rate during the actual scan based on the free breathing information, the scanning respiratory rate, the required scanning respiratory rate, and the scan type. The breathing navigation module 330 can determine a navigation voice based on the guidance respiratory rate and guide the patient's breathing during the actual scan based on the navigation voice.

[0080] In some embodiments, based on the patient's free breathing information before scanning, the breathing prediction module 310 can use a first deep learning model to determine the patient's scanning state breathing frequency when in the scanning state, wherein the first deep learning model is trained based on free breathing information training data of multiple historical patients.

[0081] In some embodiments, refer to Figure 3 , the first deep learning model can be obtained through the following training process:

[0082] Sub-step 211: obtaining the patient's free breathing information training data, where the patient's free breathing information training data may include the patient's free breathing information training data before scanning and the patient's scanning state respiratory rate labeling data during scanning;

[0083] Sub-step 212: inputting the patient's free breathing information training data into the to-be-trained model, and outputting the patient's scanning state respiratory rate result data in the scanning state;

[0084] Sub-step 213: callback the model parameters through the scanning state respiratory rate result data of the patient in the scanning state and the scanning state respiratory rate annotation data of the patient in the scanning state to obtain the trained first deep learning model.

[0085] In some embodiments, based on the free breathing information, the scanning state breathing frequency, the scanning required breathing frequency, and the scanning type, the breathing determination module 320 can use a second deep learning model to determine the patient's guidance breathing frequency during actual scanning, wherein the second deep learning model is trained based on training data of the free breathing information, the scanning state breathing frequency, the scanning required breathing frequency, and the scanning type of multiple historical patients.

[0086] In some embodiments, refer to Figure 4 , the second deep learning model can be obtained through the following training process:

[0087] Sub-step 221 , obtaining the patient's free breathing information, respiratory rate in the scanning state, respiratory rate required for scanning, and training data of the scanning type, as well as the patient's guided respiratory rate annotation data during the actual scanning;

[0088] Sub-step 222: inputting the patient's free breathing information, scanning state respiratory rate, scanning required respiratory rate, and scanning type training data into the to-be-trained model, and outputting result data of the patient's guided respiratory rate during the actual scanning;

[0089] Sub-step 223: Using the result data of the patient's guidance respiratory rate during the actual scan and the annotation data of the patient's guidance respiratory rate during the actual scan, the model parameters are called back to obtain the trained second deep learning model.

[0090] In some embodiments, the intelligent breathing navigation device 300 may further include an abnormality prompt module ( Figure 5 (not shown) is used to provide abnormal prompts when the patient's breathing is abnormal during the actual scan.

[0091] It should be noted that the device 300 for performing intelligent breathing navigation according to the patient's breathing frequency provided in this embodiment belongs to the same inventive concept as the method 200 for performing intelligent breathing navigation according to the patient's breathing frequency. For more implementation methods, please refer to the corresponding description of the method 200 for performing intelligent breathing navigation according to the patient's breathing frequency, which will not be repeated here.

[0092] Some embodiments of this specification also provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes, for example, method 200 for performing intelligent breathing navigation based on a patient's respiratory rate. For details, please refer to the relevant description of the embodiment of method 200 for performing intelligent breathing navigation based on a patient's respiratory rate, which will not be repeated here.

[0093] The method, device, and computer-readable storage medium for performing intelligent respiratory navigation based on a patient's respiratory rate provided in the embodiments of this specification have at least the following beneficial effects:

[0094] (1) By obtaining the patient's free breathing information before scanning, the patient's breathing frequency during scanning is predicted based on the patient's free breathing information before scanning. This method can provide different breathing guidance according to each patient's breathing condition, thereby improving the efficiency of respiratory navigation;

[0095] (2) At the same time, artificial intelligence is also used to predict the patient's respiratory rate in the scanning state based on the patient's free breathing information before the scan. The respiratory rate in the scanning state is determined by combining the breathing conditions of each patient and big data. The prediction results are more accurate and more adaptable.

[0096] (3) Furthermore, when determining the patient's guided respiratory rate during actual scanning based on the free breathing information, the respiratory rate in the scanning state, the respiratory rate required by the scanning, and the scanning type, artificial intelligence is used to make the determined guided respiratory rate more scientific, not only more adapted to the patient's free breathing rate, but also in line with the respiratory rate required by the scanning;

[0097] (4) In addition, according to the determined guiding breathing frequency, voice prompts can be given to guide the patient to breathe regularly during the scan, especially when abnormalities occur, so as to guide the patient to make regular breathing that meets the scanning requirements while adapting to the patient's own breathing rhythm, thereby improving the efficiency of breathing navigation and achieving accurate cooperation with the CT scanner to complete the scan.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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 method for intelligent breathing navigation based on a patient's breathing frequency, characterized in that: The method comprises the following steps: Acquiring free breathing information of the patient before scanning, and predicting the patient's respiratory rate in a scanning state based on the free breathing information of the patient before scanning, wherein the free breathing information of the patient before scanning includes the patient's respiratory rate before scanning; Determining the patient's guided respiratory rate during actual scanning based on the free breathing information, the scanning state respiratory rate, the scanning required respiratory rate, and the scan type; The patient's guided respiratory rate during actual scanning is obtained through the following steps: Based on the scan type, determine whether intelligent voice navigation is required; Before scanning, obtain the patient's free breathing information to see if it meets the respiratory rate requirements for scanning; In response to the respiratory rate required for the scan being met, determining a guide respiratory rate for the patient during the actual scan; A navigation voice is determined based on the guiding breathing frequency, and the breathing of the patient during the actual scan is navigated based on the navigation voice to guide the patient to make regular breathing that meets the breathing frequency required by the scan.

2. The method according to claim 1, characterized in that The predicting of the patient's respiratory rate in the scanning state based on the patient's free breathing information before the scan includes: Based on the patient's free breathing information before the scan, a first deep learning model is used to determine the patient's scanning state respiratory frequency in the scanning state, wherein the first deep learning model is trained based on free breathing information training data of multiple historical patients.

3. The method according to claim 1, characterized in that The determining of the patient's guided respiratory rate during actual scanning based on the free breathing information, the scanning state respiratory rate, the scanning required respiratory rate, and the scanning type includes: Based on the free breathing information, the scanning state respiratory frequency, the scanning required respiratory frequency and the scanning type, a second deep learning model is used to determine the patient's guidance respiratory frequency during the actual scanning, wherein the second deep learning model is trained based on training data of the free breathing information, the scanning state respiratory frequency, the scanning required respiratory frequency and the scanning type of multiple historical patients.

4. The method according to claim 1, wherein Also includes: The patient's free breathing information is obtained based on the patient status acquisition device, where the patient's free breathing information includes one or more of the following combinations: The patient's respiratory rate, the patient's respiratory amplitude, the patient's voice information, the patient's image information and the patient's personal information.

5. The method according to claim 1, characterized in that The patient's respiratory rate is obtained based on a pressure sensor or a camera.

6. The method according to claim 1, wherein The method further comprises: In response to not meeting the scanning requirement breathing rate, the patient is given breathing training.

7. The method according to claim 1, characterized in that The determining of the navigation voice based on the guiding breathing frequency, and navigating the breathing of the patient during actual scanning based on the navigation voice, includes: Determining whether the determined patient's guide respiratory rate during actual scanning meets the scanning requirement respiratory rate; In response to the respiratory rate meeting the scanning requirement, determining a navigation voice based on the guiding respiratory rate; in response to the respiratory rate not meeting the scanning requirement, performing breathing training on the patient.

8. The method according to claim 1, characterized in that Also includes: When the patient's breathing is abnormal during the actual scan, an abnormal prompt is given.

9. A device for intelligent respiratory navigation based on a patient's respiratory rate, characterized in that: include: a breathing prediction module, configured to obtain the patient's free breathing information before scanning, and predict the patient's respiratory rate in a scanning state based on the patient's free breathing information before scanning, wherein the patient's free breathing information before scanning includes the patient's respiratory rate before scanning; a breathing determination module, configured to determine a patient's guide breathing rate during actual scanning based on the free breathing information, the scanning state breathing rate, the scanning required breathing rate, and the scanning type; The patient's guided respiratory rate during actual scanning is obtained through the following steps: Based on the scan type, determine whether intelligent voice navigation is required; Before scanning, obtain the patient's free breathing information to see if it meets the respiratory rate requirements for scanning; In response to the respiratory rate required for the scan being met, determining a guide respiratory rate for the patient during the actual scan; The breathing navigation module is used to determine a navigation voice based on the guiding breathing frequency, and to navigate the patient's breathing during actual scanning based on the navigation voice, so as to guide the patient to make regular breathing that meets the breathing frequency required by the scanning.

10. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 8.

Images