WO2021249048A1

WO2021249048A1 - Coronavirus disease 2019 (covid-19) risk prompt apparatus, method and system based on ultrasonic imaging

Info

Publication number: WO2021249048A1
Application number: PCT/CN2021/089803
Authority: WO
Inventors: 王臻; 安广福; 周田; 杨勇; 刘慕魁
Original assignee: 北京核信锐视安全技术有限公司
Priority date: 2020-06-10
Filing date: 2021-04-26
Publication date: 2021-12-16
Also published as: CN111643118A; CN111643118B

Abstract

A COVID-19 risk prompt apparatus, method and system based on ultrasonic imaging. The method comprises: obtaining a recognition result by means of a pre-trained recognition model, wherein the recognition result comprises a B line and/or a lung consolidation area recognized from each lung area of a lung; and according to epidemiological information and symptom information of an inspected person and the recognition result output by the recognition model, determining a risk level of the inspected person suffering from the COVID-19. The level of the probability of an inspected person suffering from the COVID-19 can be confirmed according to a risk level, worries can be eliminated or correct prevention and treatment measures can be taken, and inspected people do not need to be checked one by one, thereby greatly reducing the workload of doctors, and improving the utilization rate of medical resources. Furthermore, the time consumed for the process of acquiring an ultrasonic image and the determination of a risk level of suffering from the COVID-19 is relatively short, so that worries of an inspected person with a relatively low risk of suffering from the COVID-19 can be eliminated as soon as possible, and influence on normal life is avoided.

Description

New coronary pneumonia risk notification device, method and system based on ultrasound imaging

Cross-references to related applications

This application claims the priority of the Chinese patent application whose application number is 202010521182.2 filed on June 10, 2020, and the invention title is "Ultrasound imaging-based new coronary pneumonia risk warning device, method and system", which is fully incorporated by reference This article.

Technical field

This application relates to the field of epidemic prevention and computer technology, and in particular to a new coronary pneumonia risk warning device, method and system based on ultrasound imaging.

Background technique

New type of coronavirus pneumonia (new coronary pneumonia for short, COVID-19 for short) is highly infectious and progresses quickly. Clinically, there is an urgent need for simple and practical methods for early screening and dynamic monitoring of it. At present, patients with new coronary pneumonia need to undergo a step-by-step examination under the guidance of a doctor to get the results of the examination. Among them, the workload of doctors and the risk of infection have been increased, and a lot of medical resources have also been taken up. In addition, the existing diagnosis process also takes a long time to get the test results, which brings great inconvenience to people who do not actually have new coronary pneumonia. At the same time, the poor timeliness of the test results is also not conducive to Prevention and control.

It can be seen that for the current new coronary pneumonia, doctors have undertaken a lot of work due to the need to conduct one-by-one investigations on the testees.

Summary of the invention

The embodiments of this application provide a new coronary pneumonia risk warning device, method and system based on ultrasound imaging to solve the current problem of new coronary pneumonia, due to the need to investigate the subjects one by one, the doctor has undertaken a large workload .

In view of the above technical problems, in the first aspect, an embodiment of the present application provides a new coronary pneumonia risk warning device based on ultrasound imaging, including:

The acquisition module is used to acquire the epidemiological information and symptom information of the examinee, as well as the ultrasound image obtained by performing an ultrasound scan on the lungs of the examinee; wherein the epidemiological information includes presets before the current moment During the time period, contact information with patients with new coronary pneumonia and/or information about living in areas affected by new coronary pneumonia; symptom information includes symptoms caused by abnormal respiratory system;

The recognition module is used to input the ultrasound image into a pre-trained recognition model, and the recognition model outputs a recognition result; wherein, the recognition result includes the B-line and/or recognized from each lung area of the lung Lung consolidation area; lung area is the area divided into lungs according to the surface marking lines of the lungs;

The prompt module is used to prompt the test subject to the risk level of new coronary pneumonia according to the recognition result, the epidemiological information, and the symptom information;

Wherein, the recognition module takes a sample ultrasound image obtained by performing an ultrasound scan of the lung as an input, and takes a sample recognition result marked on the sample ultrasound image as an output, which is obtained through machine learning training; the sample recognition result is included in the sample ultrasound image, B line and/or lung consolidation area marked from each lung area of the lung.

In the second aspect, an embodiment of the present application provides a new coronary pneumonia risk warning method based on ultrasound imaging, including:

Obtain epidemiological information and symptom information of the subject, as well as ultrasound images obtained by ultrasound scanning of the lungs of the subject; wherein the epidemiological information includes the pre-set time period from the current moment, and Contact information of patients with new coronary pneumonia and/or information about living in areas affected by new coronary pneumonia; symptom information includes symptoms caused by abnormalities in the respiratory system;

Inputting the ultrasound image into a pre-trained recognition model, and outputting a recognition result from the recognition model; wherein the recognition result includes the B-line and/or lung consolidation regions recognized from each lung area of the lung; The lung area is the area divided into the lungs according to the surface marking lines of the lungs;

According to the recognition result, the epidemiological information, and the symptom information, prompt the test subject to have the risk level of new coronary pneumonia;

In a third aspect, an embodiment of the present application provides a new coronary pneumonia risk warning system based on ultrasound imaging, including a processing device connected to an ultrasound device that performs ultrasound scanning on the lungs to receive the ultrasound device’s Ultrasound images obtained by ultrasound scanning of the examinee’s lungs;

The processing equipment includes the ultrasound imaging-based risk prompting device for new coronary pneumonia described in any one of the above.

The embodiments of the present application provide a new coronary pneumonia risk warning device, method and system based on ultrasound imaging. The recognition result is obtained through a pre-trained recognition model. The recognition result includes the B line and the B line identified from each lung area of the lung. / Or lung consolidation area. According to the epidemiological information and symptom information of the testee, as well as the recognition result output by the recognition model, the risk level of the testee for new coronary pneumonia is determined. According to the risk level, it can confirm the possibility of the testee suffering from new coronary pneumonia, dispel worries or take correct preventive treatment measures, without having to check the testees one by one, which greatly reduces the workload of doctors and improves the utilization of medical resources Rate. At the same time, the acquisition process of ultrasound images and the determination of the risk level of new coronary pneumonia take a shorter time, so that subjects with a lower risk of developing new coronary pneumonia can dispel their worries as soon as possible and avoid affecting their normal life.

Description of the drawings

In order to more clearly explain the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a structural block diagram of a new coronary pneumonia risk notification device based on ultrasound imaging provided by an embodiment of the present application;

2 is a schematic flowchart of a new coronary pneumonia risk notification method based on ultrasound imaging provided by another embodiment of the present application;

FIG. 3 is a schematic diagram of the physical structure of an electronic device provided by another embodiment of the present application.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the drawings in the embodiments of this application. Obviously, the described embodiments These are a part of the embodiments of this application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative work shall fall within the protection scope of this application.

FIG. 1 is a structural block diagram of a new coronary pneumonia risk notification device based on ultrasound imaging provided by this embodiment. Referring to FIG. 1, the ultrasound imaging-based new coronary pneumonia risk notification device includes an acquisition module 101, an identification module 102, and a prompt module 103, in,

The acquiring module 101 is used to acquire the epidemiological information and symptom information of the examinee, as well as the ultrasound images obtained by performing ultrasound scanning on the lungs of the examinee; wherein, the epidemiological information includes the predictions from the current moment. Set time period, contact information with patients with new coronary pneumonia and/or information on living in areas affected by new coronary pneumonia; symptom information includes symptoms caused by abnormal respiratory system;

The recognition module 102 is configured to input the ultrasound image into a pre-trained recognition model, and output the recognition result from the recognition model; wherein, the recognition result includes the B-line and/or identified from each lung area of the lung Or the lung consolidation area; the lung area is the area divided into the lungs according to the surface marking lines of the lungs;

The prompting module 103 is configured to prompt the risk level of the testee to have new coronary pneumonia according to the recognition result, the epidemiological information, and the symptom information;

Among them, obtaining the epidemiological information and symptom information of the tested person specifically includes: obtaining the epidemiological information and symptom information input through the interactive interface.

The testee can be anyone. This embodiment aims to determine the risk level of the testee suffering from the new coronary pneumonia through the new coronary pneumonia risk notification device based on ultrasound imaging, and the risk level makes the testees with a lower risk of developing new coronary pneumonia unnecessary Carry out the investigation of new coronary pneumonia, thereby reducing the workload of doctors in the investigation of new coronary pneumonia.

Wherein, the recognition module may be a convolutional neural network model.

The division of the lung area includes: taking the parasternal line, anterior axillary line, posterior axillary line, and paraspine line as the boundary, divide each side of the lung into three areas, front, side, and back, namely, the front chest area, the side chest area, and the back chest area. . Each side is divided into upper and lower parts based on the level of the nipple connection, so each lung can be divided into upper anterior area, lower anterior area, upper lateral area, lower lateral area, upper posterior area, and lower posterior area. There are a total of 12 lungs. Lung area.

Among them, the B-line refers to the band-like strong echo perpendicular to the pleural line (or A-line), also called the "rocket" sign, which radiates radially to the deep lung field.

Among them, lung consolidation (ie subpleural lung consolidation) is manifested as subpleural hypoechoic area or tissue-like echo structure area, which is the change that occurs after lung tissue loses air. In lung ultrasound, most lung consolidation (consolidation within the lung lobes) is characterized by "fragments", that is, the boundary between the consolidated lung tissue and the aerated lung tissue is irregular, showing the shape of torn fragments. Consolidation between lung lobes showed echoes of liver and spleen tissues. Visible dynamic bronchial "inflation sign" in lung consolidation can be used as an important evidence to determine pneumonia and can rule out obstructive atelectasis. Pulmonary consolidation is often accompanied by pleural effusion, and ultrasound is very sensitive and accurate to pleural effusion, and a very small amount of fluid in the pleural cavity can be found.

Therefore, the B-line (radially diverging to the deep lung field) and the lung consolidation area (fragmented area) have their own characteristics, so these abnormal information can be marked from the ultrasound image. In the process of training the model, these B-lines and lung consolidation regions can be marked in advance from the sample ultrasound image, so that the trained recognition model can identify the B-line and lung consolidation regions from the input ultrasound image , To provide a basis for the subsequent determination of the risk level of new coronary pneumonia.

This embodiment provides a new coronary pneumonia risk notification device based on ultrasound imaging. The recognition result is obtained through a pre-trained recognition model. The recognition result includes the B-line and/or lung consolidation area identified from each lung area of the lung . According to the epidemiological information and symptom information of the testee, as well as the recognition result output by the recognition model, the risk level of the testee for new coronary pneumonia is determined. According to the risk level, it can confirm the possibility of the testee suffering from new coronary pneumonia, dispel worries or take correct preventive treatment measures, without having to check the testees one by one, which greatly reduces the workload of doctors and improves the utilization of medical resources Rate. At the same time, the acquisition process of ultrasound images and the determination of the risk level of new coronary pneumonia take a shorter time, so that subjects with a lower risk of developing new coronary pneumonia can dispel their worries as soon as possible and avoid affecting their normal life.

In one embodiment, on the basis of the above-mentioned embodiment, a model training module is further included, and the model training module is used for:

For any lung area in any sample ultrasound image, if there is a B-line in the any lung area, mark the B-line in the any lung area, and/or if the any lung area If there is a lung consolidation area in any lung area, mark the lung consolidation area in any one of the lung areas to obtain a sample recognition result marked by the ultrasound image of any one of the samples;

Taking any of the sample ultrasound images as the input of the pre-built training model, and taking the sample recognition result of the label of any sample ultrasound image as the output, the training model is trained, and all the samples will be tested by a number of sample ultrasound images. The model obtained after the training model is trained is used as the recognition model.

Among them, several sample ultrasound images include sample ultrasound images in which there is no B-line and lung consolidation area in each lung area, as well as sample ultrasound images in which there is at least one lung area with B-line, and at least one lung area has lung solids. Change the sample ultrasound image of the variable area to improve the comprehensiveness of the sample ultrasound image.

In the process of training the recognition model in this embodiment, the abnormal information is marked according to the lung area, so that the output recognition result also marks the abnormal information according to the lung area, which is convenient for the B line and/or the identification of each lung area. The area of lung consolidation determines the risk level of new coronary pneumonia.

In an embodiment, on the basis of the foregoing embodiments, the prompt module is further used for:

According to the recognition result, determine whether there is a B-line abnormality and/or lung consolidation abnormality in each side of the lung, according to whether there is a B-line abnormality and/or lung consolidation abnormality in each side of the lung, and the epidemiological information And the symptom information, suggesting the risk level of the testee suffering from new coronary pneumonia;

Wherein, for either side of the lung, if it is determined that the multiple B-line lung regions in any side of the lung are greater than or equal to the first threshold value according to the B-line identified from each lung region of the lung, then There is a B-line abnormality in either side of the lung; wherein multiple B-line lung areas are lung areas that contain more than or equal to the preset number of B-lines in at least one ultrasound image;

For either side of the lung, if it is judged that the number of lung regions with lung consolidation regions in the lungs on either side is greater than or equal to the second threshold based on the lung consolidation regions identified from the lung regions of the lungs , Then there is an abnormal pulmonary consolidation in either side of the lung.

Among them, the preset number of B lines is 3 or more, the first threshold is two or more, and the second threshold is 1 or more.

In this embodiment, the recognition result is used to determine whether there is abnormal B-line and/or lung consolidation in each lung of both lungs, and then according to the abnormality of B-line and/or lung consolidation in each lung The situation, as well as epidemiological information and symptom information determine the risk level of the tested person for new coronary pneumonia.

In one embodiment, on the basis of the foregoing embodiments, according to the presence or absence of B-line abnormalities and/or pulmonary consolidation abnormalities in each side of the lung, the epidemiological information and the symptom information, prompt The risk level of the tested person suffering from new coronary pneumonia includes:

If there are no B-line abnormalities and lung consolidation abnormalities in both lungs, and the epidemiological information and the symptom information are both positive results, it indicates that the risk level of the testee suffering from new coronary pneumonia is First level

If there are no B-line abnormalities and lung consolidation abnormalities in both lungs, and the epidemiological information or the symptom information is a negative result, it indicates that the risk level of the testee suffering from new coronary pneumonia is the first Second grade

If there are no B-line abnormalities and lung consolidation abnormalities in the lungs on both sides, and the epidemiological information and the symptom information are negative results, it indicates that the risk level of the testee suffering from new coronary pneumonia is The third level; or, if there is a B-line abnormality and/or lung consolidation abnormality in the unilateral lung, and the epidemiological information or the symptom information is a negative result, it indicates that the subject has a new crown The risk level of pneumonia is the third level;

If there are abnormal B-line and/or lung consolidation abnormalities in both lungs, and the epidemiological information or the symptom information is a negative result, it indicates that the risk level of the testee suffering from new coronary pneumonia is The fourth level; or, if there is abnormal B-line and/or lung consolidation abnormality in the unilateral lung, and the epidemiological information and the symptom information are both negative results, it indicates that the subject has The risk level of new coronary pneumonia is the fourth level;

If there are B-line abnormalities and/or lung consolidation abnormalities in both lungs, and the epidemiological information and the symptom information are negative results, it indicates the risk level of the testee suffering from new coronary pneumonia Is the fifth level;

Wherein, the positive result of the epidemiological information is that there is no history of contact with patients with new coronary pneumonia and the history of residence in a new coronary pneumonia-affected area, and the negative result of the epidemiological information is that there is a history of contact with patients with new coronary pneumonia. And/or the history of residence in a new coronary pneumonia epidemic area; the positive result of the symptom information is that there are no symptoms caused by abnormal respiratory system, and the negative result of the symptom information is that there are symptoms caused by abnormalities of the respiratory system; The fifth grade has a higher risk of COVID-19 than the fourth grade, the fourth grade has a higher risk of COVID-19 than the third grade, and the third grade has a higher risk of COVID-19 than the second grade. The risk of pneumonia is high, and the second grade has a higher risk of suffering from new coronary pneumonia than the first grade.

This embodiment divides four risk levels of suffering from new coronary pneumonia, and the probability of suffering from new coronary pneumonia can be judged through the risk level, so as to take timely measures to avoid spread.

If the risk level of the testee suffering from new coronary pneumonia is the third level, the fourth level or the fifth level, a first prompt message is issued, and the first prompt information is used to prompt the testee to have the new coronary pneumonia The possibility of pneumonia is higher, and there is a risk of infecting others.

Wherein, the first prompt information may be sent to a first terminal, which is owned by the testee, or is a terminal set in a public area for the testee to make inquiries.

Wherein, the first prompt information may also include measures to be taken by the detected person, such as avoiding going to public areas, not having close contact with anyone, wearing a mask and wearing protective glasses before contact with people, and so on.

In this embodiment, the first prompt message can prompt the examinee to pay attention to infection protection in a timely manner, which is beneficial to assist the examinee in the protection work and reduce the possible infectivity.

If the risk level of the testee suffering from new coronary pneumonia is the third level, the fourth level, or the fifth level, after detecting the appointment information of the testee’s appointment with a doctor, the test will be obtained. The diagnosed doctor information, the identification result, the epidemiological information, and the symptom information are sent according to the doctor information, and second prompt information is issued; the second prompt information is used to prompt the doctor to the subject The possibility of suffering from new coronary pneumonia is higher, and there is a risk of infecting others.

Wherein, the first prompt information may be sent to a second terminal, and the second terminal is owned by a doctor who diagnoses the subject, or is a terminal set in a public area for the doctor to make inquiries.

Wherein, the second prompt information may also include measures to be taken when diagnosing the subject, for example, wearing a mask and protective glasses before contact with the subject.

In this embodiment, the second prompt message can prompt the doctor to prevent infection in time and reduce the possible infectivity.

The risk level of the testee suffering from new coronary pneumonia and the personal information of the testee are sent to the epidemic prevention supervision department.

Among them, the risk level and personal information of the tested person are sent to the epidemic prevention supervision department, so that the epidemic prevention supervision department can take corresponding supervision measures against the detected person. The person who was in close contact with the tested person organized the spread of new coronary pneumonia in time.

In this embodiment, by sending information such as the risk level to the epidemic prevention supervision department, it is beneficial to further enhance the protection against new coronary pneumonia and improve the protection effect.

Figure 2 is a schematic flow chart of the method for prompting a risk of new coronary pneumonia based on ultrasound imaging provided by this embodiment. See Figure 2. The method for prompting a risk of new coronary pneumonia based on ultrasound imaging includes:

Step 201: Obtain epidemiological information and symptom information of the subject, and ultrasound images obtained by performing an ultrasound scan on the lungs of the subject; wherein the epidemiological information includes a preset time period before the current moment Inside, contact information with patients with new coronary pneumonia and/or information about living in areas affected by new coronary pneumonia; symptom information includes symptoms caused by abnormalities in the respiratory system;

Step 202: Input the ultrasound image into a pre-trained recognition model, and output the recognition result from the recognition model; wherein, the recognition result includes the B-line and/or lung solids identified from each lung area of the lung. Change area; lung area is the area divided into the lungs according to the surface marking lines of the lungs;

Step 203: According to the recognition result, the epidemiological information, and the symptom information, prompt the test subject to have a risk level of new coronary pneumonia;

The method for prompting the risk of new coronary pneumonia based on ultrasound imaging provided in this embodiment is applicable to the apparatus for prompting the risk of new coronary pneumonia based on ultrasound imaging provided in the foregoing embodiments, and will not be repeated here.

This embodiment provides a new coronary pneumonia risk notification method based on ultrasound imaging. The recognition result is obtained through a pre-trained recognition model. The recognition result includes the B-line and/or lung consolidation area identified from each lung area of the lung . According to the epidemiological information and symptom information of the testee, as well as the recognition result output by the recognition model, the risk level of the testee for new coronary pneumonia is determined. According to the risk level, it can confirm the possibility of the testee suffering from new coronary pneumonia, dispel worries or take correct preventive treatment measures, without having to check the testees one by one, which greatly reduces the workload of doctors and improves the utilization of medical resources Rate. At the same time, the acquisition process of ultrasound images and the determination of the risk level of new coronary pneumonia take a short time, so that subjects with a lower risk of new coronary pneumonia can dispel their worries as soon as possible and avoid affecting their normal life.

This embodiment provides a new coronary pneumonia risk warning system based on ultrasound imaging, including a processing device that is connected to an ultrasound device that performs ultrasound scanning on the lungs to receive the ultrasound device’s response to the lungs of a subject. Ultrasound images obtained by ultrasound scanning of the department;

This embodiment provides a new coronary pneumonia risk prompt system based on ultrasound imaging. The recognition result is obtained through a pre-trained recognition model. The recognition result includes the B-line and/or lung consolidation area identified from each lung area of the lung . According to the epidemiological information and symptom information of the testee, as well as the recognition result output by the recognition model, the risk level of the testee for new coronary pneumonia is determined. According to the risk level, it can confirm the possibility of the testee suffering from new coronary pneumonia, dispel worries or take correct preventive treatment measures, without having to check the testees one by one, which greatly reduces the workload of doctors and improves the utilization of medical resources Rate. At the same time, the acquisition process of ultrasound images and the determination of the risk level of new coronary pneumonia take a short time, so that subjects with a lower risk of new coronary pneumonia can dispel their worries as soon as possible and avoid affecting their normal life.

In one embodiment, on the basis of the above-mentioned embodiment, it further includes a first terminal, the first terminal is configured to display the first prompt information sent by the processing device, and the first prompt information is used to prompt the The testee is more likely to have new coronary pneumonia and has a higher risk of infecting others (or the first prompt information is used to remind the testee that there is a risk of infecting others); wherein, the first terminal is controlled by all Said that the testee owns or is a terminal set up in a public area for the testee to make inquiries; and/or,

It also includes a second terminal, the second terminal is used to display the second prompt information sent by the processing device, the second prompt information prompts the doctor that the testee is more likely to have new coronary pneumonia, the infection The risk of others is higher (or the second prompt information is used to remind the doctor that the subject is at risk of infecting others); wherein, the second terminal is owned by the doctor who diagnosed the subject, or It is a terminal set up in the public area for doctors to make inquiries.

Fig. 3 illustrates a schematic diagram of the physical structure of an electronic device. As shown in Fig. 3, the electronic device may include: a processor 301, a communications interface 302, a memory 303, and a communication bus 304, Among them, the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304. The processor 301 can call the logic instructions in the memory 303 to execute the following method: obtain the epidemiological information and symptom information of the subject, and the ultrasound image obtained by performing an ultrasound scan on the lung of the subject; wherein, Epidemiological information includes information about contact with patients with new coronary pneumonia and/or information about living in areas affected by new coronary pneumonia within a preset time period from the current moment; symptom information includes symptoms caused by abnormalities in the respiratory system; and the ultrasound image Input the pre-trained recognition model, and output the recognition result from the recognition model; wherein, the recognition result includes the B-line and/or lung consolidation area recognized from each lung area of the lung; the lung area is based on the lung According to the recognition result, the epidemiological information, and the symptom information, it is suggested that the subject has a risk level of new coronary pneumonia; wherein, the identification The module takes the sample ultrasound image obtained from the ultrasound scan of the lungs as input, and takes the sample recognition result marked on the sample ultrasound image as the output, which is obtained through machine learning training; the sample recognition result is included in the sample ultrasound image, from each of the lungs. B-line and/or lung consolidation area marked in the lung area.

In addition, the above-mentioned logical instructions in the memory 303 can be implemented in the form of a software functional unit and when sold or used as an independent product, they can be stored in a computer readable storage medium. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. .

Further, an embodiment of the present application discloses a computer program product, the computer program product includes a computer program stored on a non-transitory readable storage medium, the computer program includes program instructions, when the program instructions are executed by a computer When time, the computer can execute the methods provided in the above method embodiments, for example, including: obtaining epidemiological information and symptom information of the subject, and ultrasound images obtained by performing ultrasound scanning on the lungs of the subject; wherein , Epidemiological information includes contact information with patients with new coronary pneumonia and/or information on living in areas affected by new coronary pneumonia within a preset period of time before the current moment; symptom information includes symptoms caused by abnormalities in the respiratory system; The image is input to the pre-trained recognition model, and the recognition result is output by the recognition model; wherein, the recognition result includes the B-line and/or lung consolidation area recognized from each lung area of the lung; the lung area is based on The area of the lung divided by the body surface marking line of the lung; according to the recognition result, the epidemiological information, and the symptom information, the risk level of the testee with new coronary pneumonia is prompted; wherein, the The recognition module takes the sample ultrasound image obtained from the ultrasound scan of the lung as input, and takes the sample recognition result marked on the sample ultrasound image as the output, which is obtained through machine learning training; the sample recognition result is included in the sample ultrasound image, from the lung B line and/or lung consolidation area marked in each lung area.

On the other hand, the embodiments of the present application also provide a non-transitory readable storage medium on which a computer program is stored. The computer program is implemented when executed by a processor to perform the transmission method provided in the foregoing embodiments, for example, including: Obtain epidemiological information and symptom information of the subject, as well as ultrasound images obtained by ultrasound scanning of the lungs of the subject; wherein the epidemiological information includes the pre-set time period from the current moment, and Contact information of patients with new coronary pneumonia and/or living information in areas affected by new coronary pneumonia; symptom information includes symptoms caused by abnormalities in the respiratory system; input the ultrasound image into a pre-trained recognition model, and the recognition model outputs the recognition result; Wherein, the recognition result includes the B-line and/or lung consolidation area recognized from each lung area of the lung; the lung area is the area divided into the lung according to the surface marking line of the lung; according to the recognition The result, the epidemiological information, and the symptom information indicate the risk level of the subject suffering from new coronary pneumonia; wherein, the recognition module takes the sample ultrasound image obtained by performing an ultrasound scan of the lung as input, and The sample recognition result marked on the sample ultrasound image is used as an output, which is obtained through machine learning training; the sample recognition result is included in the sample ultrasound image, and the B line and/or lung consolidation area marked from each lung area of the lung are included.

The device embodiments described above are merely illustrative, where the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement without creative work.

Through the description of the above implementation manners, those skilled in the art can clearly understand that each implementation manner can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product can be stored in a readable storage medium, such as ROM/RAM, magnetic disk , CD-ROM, etc., including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiment.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the application, not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions recorded in the foregoing embodiments are modified, or some of the technical features are equivalently replaced; these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

A new coronary pneumonia risk warning device based on ultrasound imaging, which is characterized in that it comprises:

The acquisition module is used to acquire the epidemiological information and symptom information of the examinee, as well as the ultrasound image obtained by performing an ultrasound scan on the lungs of the examinee; wherein the epidemiological information includes presets before the current moment During the time period, contact information with patients with new coronary pneumonia and/or information about living in areas affected by new coronary pneumonia; symptom information includes symptoms caused by abnormal respiratory system;

The recognition module is used to input the ultrasound image into a pre-trained recognition model, and the recognition model outputs a recognition result; wherein, the recognition result includes the B-line and/or recognized from each lung area of the lung Lung consolidation area; lung area is the area divided into lungs according to the surface marking lines of the lungs;

The prompt module is used to prompt the test subject to the risk level of new coronary pneumonia according to the recognition result, the epidemiological information, and the symptom information;

Wherein, the recognition module takes a sample ultrasound image obtained by performing an ultrasound scan of the lung as an input, and takes a sample recognition result marked on the sample ultrasound image as an output, which is obtained through machine learning training; the sample recognition result is included in the sample ultrasound image, B line and/or lung consolidation area marked from each lung area of the lung.
The new coronary pneumonia risk notification device based on ultrasound imaging according to claim 1, further comprising a model training module, the model training module being used for:

For any lung area in any sample ultrasound image, if there is a B-line in the any lung area, mark the B-line in the any lung area, and/or if the any lung area If there is a lung consolidation area in any lung area, mark the lung consolidation area in any one of the lung areas to obtain a sample recognition result marked by the ultrasound image of any one of the samples;

Taking any of the sample ultrasound images as the input of the pre-built training model, and taking the sample recognition result of the label of any sample ultrasound image as the output, the training model is trained, and all the samples will be tested by a number of sample ultrasound images. The model obtained after the training model is trained is used as the recognition model.
The new coronary pneumonia risk prompting device based on ultrasound imaging according to claim 1, wherein the prompting module is further used for:

According to the recognition result, determine whether there is a B-line abnormality and/or lung consolidation abnormality in each side of the lung, according to whether there is a B-line abnormality and/or lung consolidation abnormality in each side of the lung, and the epidemiological information And the symptom information, suggesting the risk level of the testee suffering from new coronary pneumonia;

Wherein, for either side of the lung, if it is determined that the multiple B-line lung regions in any side of the lung are greater than or equal to the first threshold value according to the B-line identified from each lung region of the lung, then There is a B-line abnormality in either side of the lung; wherein multiple B-line lung areas are lung areas that contain more than or equal to the preset number of B-lines in at least one ultrasound image;

For either side of the lung, if it is judged that the number of lung regions with lung consolidation regions in the lungs on either side is greater than or equal to the second threshold based on the lung consolidation regions identified from the lung regions of the lungs , Then there is an abnormal pulmonary consolidation in either side of the lung.
The new coronary pneumonia risk prompting device based on ultrasound imaging according to claim 3, characterized in that, according to whether there are B-line abnormalities and lung consolidation abnormalities in each side of the lung, the epidemiological information and the The symptom information, which indicates the risk level of the tested person suffering from new coronary pneumonia, including:

If there are no B-line abnormalities and lung consolidation abnormalities in both lungs, and the epidemiological information and the symptom information are both positive results, it indicates that the risk level of the testee suffering from new coronary pneumonia is First level

If there are no B-line abnormalities and lung consolidation abnormalities in both lungs, and the epidemiological information or the symptom information is a negative result, it indicates that the risk level of the testee suffering from new coronary pneumonia is the first Second grade

If there are no B-line abnormalities and lung consolidation abnormalities in the lungs on both sides, and the epidemiological information and the symptom information are negative results, it indicates that the risk level of the testee suffering from new coronary pneumonia is The third level; or, if there is a B-line abnormality and/or lung consolidation abnormality in the unilateral lung, and the epidemiological information or the symptom information is a negative result, it indicates that the subject has a new crown The risk level of pneumonia is the third level;

If there are abnormal B-line and/or lung consolidation abnormalities in both lungs, and the epidemiological information or the symptom information is a negative result, it indicates that the risk level of the testee suffering from new coronary pneumonia is The fourth level; or, if there is abnormal B-line and/or lung consolidation abnormality in the unilateral lung, and the epidemiological information and the symptom information are both negative results, it indicates that the subject has The risk level of new coronary pneumonia is the fourth level;

If there are B-line abnormalities and/or lung consolidation abnormalities in both lungs, and the epidemiological information and the symptom information are negative results, it indicates the risk level of the testee suffering from new coronary pneumonia Is the fifth level;

Wherein, the positive result of the epidemiological information is that there is no history of contact with patients with new coronary pneumonia and the history of residence in a new coronary pneumonia-affected area, and the negative result of the epidemiological information is that there is a history of contact with patients with new coronary pneumonia. And/or the history of residence in a new coronary pneumonia epidemic area; the positive result of the symptom information is that there are no symptoms caused by abnormal respiratory system, and the negative result of the symptom information is that there are symptoms caused by abnormalities of the respiratory system; The fifth grade has a higher risk of COVID-19 than the fourth grade, the fourth grade has a higher risk of COVID-19 than the third grade, and the third grade has a higher risk of COVID-19 than the second grade. The risk of pneumonia is high, and the second grade has a higher risk of suffering from new coronary pneumonia than the first grade.
The new coronary pneumonia risk prompting device based on ultrasound imaging according to claim 1, wherein the prompting module is further used for:

If the risk level of the testee suffering from new coronary pneumonia is the third level, the fourth level or the fifth level, a first prompt message is issued, and the first prompt information is used to prompt the testee to have the new coronary pneumonia The possibility of pneumonia is higher, and the risk of infecting others is higher.
The new coronary pneumonia risk prompting device based on ultrasound imaging according to claim 1, wherein the prompting module is further used for:

If the risk level of the testee suffering from new coronary pneumonia is the third level, the fourth level, or the fifth level, after detecting the appointment information of the testee’s appointment with a doctor, the test will be obtained. The diagnosed doctor information, the identification result, the epidemiological information, and the symptom information are sent according to the doctor information, and second prompt information is issued; the second prompt information is used to prompt the doctor to the subject The possibility of suffering from new coronary pneumonia is higher, and the risk of infecting others is higher.
The new coronary pneumonia risk prompting device based on ultrasound imaging according to claim 1, wherein the prompting module is further used for:

The risk level of the testee suffering from new coronary pneumonia and the personal information of the testee are sent to the epidemic prevention supervision department.
A new coronary pneumonia risk notification method based on ultrasound imaging, which is characterized in that it includes:

Obtain epidemiological information and symptom information of the subject, as well as ultrasound images obtained by ultrasound scanning of the lungs of the subject; wherein the epidemiological information includes the pre-set time period from the current moment, and Contact information of patients with new coronary pneumonia and/or information about living in areas affected by new coronary pneumonia; symptom information includes symptoms caused by abnormalities in the respiratory system;

Inputting the ultrasound image into a pre-trained recognition model, and outputting a recognition result from the recognition model; wherein the recognition result includes the B-line and/or lung consolidation regions recognized from each lung area of the lung; The lung area is the area divided into the lungs according to the surface marking lines of the lungs;

According to the recognition result, the epidemiological information, and the symptom information, prompt the test subject to have the risk level of new coronary pneumonia;

Wherein, the recognition module takes a sample ultrasound image obtained by performing an ultrasound scan of the lung as an input, and takes a sample recognition result marked on the sample ultrasound image as an output, which is obtained through machine learning training; the sample recognition result is included in the sample ultrasound image, B line and/or lung consolidation area marked from each lung area of the lung.
A new coronary pneumonia risk warning system based on ultrasound imaging, which is characterized in that it includes a processing device connected to an ultrasound device that performs ultrasound scanning on the lungs, so as to receive the lungs of the tested person from the ultrasound device. Ultrasound images obtained by ultrasound scanning;

The processing equipment comprises the new coronary pneumonia risk notification device based on ultrasound imaging according to any one of the above claims 1 to 7.
The new coronary pneumonia risk warning system for ultrasound imaging according to claim 9, wherein:

It also includes a first terminal, where the first terminal is configured to display first prompt information sent by the processing device, and the first prompt information is used to prompt that the subject is more likely to have new coronary pneumonia; The risk of infecting others is relatively high; wherein, the first terminal is owned by the tested person, or is a terminal set up in a public area for the tested person to make inquiries; and/or,

It also includes a second terminal, the second terminal is used to display the second prompt information sent by the processing device, the second prompt information prompts the doctor that the testee is more likely to have new coronary pneumonia, the infection The risk of others is higher; wherein, the second terminal is owned by a doctor who diagnoses the subject, or is a terminal set in a public area for doctors to make inquiries.