Alarm method and device of medical equipment, computer program and computer readable storage medium

Abstract

The invention discloses a medical equipment alarm method and device, a computer program and a computer readable storage medium. The alarm method of the medical equipment comprises the following steps: providing a default attention part and an attention range on an image of an object according to a machine learning result; acquiring and storing acceptance or change of the attention part and the attention range; according to the change of the concerned part and the concerned range on the image of the object in a preset time interval, judging whether abnormity exists or not through machine learning; giving an alarm according to a judgment result; and receiving a response to the alarm, and storing the images of the object at the beginning and the end of the preset time interval and the response. According to the invention, the abnormity can be automatically identified and the alarm can be given in a machine learning mode, and the selection of the attention range and the response to the alarm by a doctor can be used for machine learning, so that the abnormity identification is more accurate, and the alarm prompt is more in line with the actual danger degree.

Description

[0001] Nouns and pronouns relating to persons in this patent application are not limited to a specific gender. Technical Field

[0002] The invention relates to medical equipment, in particular to information processing of a camera. Background Art

[0003] Since the advent of CT, due to continuous technological innovation and advantages such as intuitiveness and high efficiency, more and more hospitals choose to use CT machines to diagnose patients' lesions. At the same time, as CT scanning technology becomes more mature and widely used, how to avoid some injuries to patients during scanning (such as the needle of the enhancement agent falling off or the patient having an allergic reaction to the scanning or enhancement drug) and at the same time, how to not increase the scanning burden of doctors have gradually become the concerns of scanning doctors.

[0004] In order to keep an eye on the patient's status during the scan, many hospitals have installed probes in the CT room, and some manufacturers have also installed cameras on the CT rack so that doctors can better observe the patient. However, this requires doctors to care about the patient's scan imaging and the patient's own condition. For example, for patients who need enhanced scanning, whether the blood vessels injected with injections have swelling and other drug reactions, whether the needle has fallen off, or when doing a biopsy, whether the inserted biopsy needle is abnormal, whether the patient with claustrophobia is already very nervous, etc. Therefore, although these camera probes have greatly increased the safety factor during the scanning process, they still make the scanning doctor busy and overwhelmed during the scanning process. As long as there is a slight negligence, the needle will still fall off and the enhancement solution will leak during the scanning process, and even some unnecessary medical accidents that could have been avoided in time will occur. Therefore, dynamic judgment of the camera screen has become an urgent need for doctors. Summary of the invention

[0005] In view of this, the present invention proposes an alarm method, device, computer program, and computer-readable storage medium for medical equipment.

[0006] According to a first aspect of the present invention, there is provided an alarm method for a medical device, comprising:

[0007] Providing a default focus area and focus range on the image of the object according to the machine learning result;

[0008] Acquiring and storing acceptance or modification of the concerned part and concerned range;

[0009] According to the changes of the focus area and focus range on the image of the object during the preset time interval, determining whether there is an abnormality through machine learning;

[0010] Based on the judgment result, an alarm is issued;

[0011] A response to the alert is received and images of the object at the beginning and end of a preset time interval and the response are stored.

[0012] In one embodiment, the areas of concern include face, elbows, and backs of hands.

[0013] In one embodiment, the warning is a pop-up box or a prompt in a status bar.

[0014] In one embodiment, the responses include handle and ignore.

[0015] According to a second aspect of the present invention, a computer program is provided, which can implement the steps of the above method when executed by a processor.

[0016] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program can implement the steps of the above-described method when executed by a processor.

[0017] According to a fourth aspect of the present invention, there is provided an alarm device for medical equipment, comprising:

[0018] A recommendation unit configured to provide a default focus area and focus range on the image of the object according to the machine learning result;

[0019] a range determination unit configured to obtain and store acceptance or modification of the focus site and focus range;

[0020] a determination unit configured to determine whether there is an abnormality through machine learning according to changes in the focus area and focus range on the image of the object during a preset time interval;

[0021] An alarm unit, configured to issue an alarm according to the judgment result;

[0022] A storage unit is configured to receive a response to the alarm and store images of the object at the beginning and end of a preset time interval and the response.

[0023] In one embodiment, the areas of concern include face, elbows, and backs of hands.

[0024] In one embodiment, the warning is a pop-up box or a prompt in a status bar.

[0025] In one embodiment, the responses include handle and ignore.

[0026] The alarm method, device, computer program, and computer-readable storage medium of the medical equipment of the present invention can automatically identify abnormalities and issue alarms through machine learning. The doctor's selection of the scope of attention and the response to the alarm will also be used for machine learning. Therefore, the identification of abnormalities is more accurate and the alarm prompt is more in line with the actual degree of danger. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings so that the above and other features and advantages of the present invention will be more apparent to those skilled in the art. In the accompanying drawings:

[0028] Figure 1 The figure is a schematic flow chart of an alarm method for a medical device according to an embodiment of the present invention.

[0029] Figure 2 The figure is a schematic structural block diagram of an alarm device for medical equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail with reference to the following embodiments.

[0031] This application starts from the actual needs of doctors and uses machine learning methods to identify the patient's current scanning status. First, the doctor draws the detection range of his concern on the monitoring screen, and the system monitors the detection range in real time, that is, the system compares the detection screen with the previous screen in real time from the beginning of monitoring. When the comparison results find abnormalities, such as the enhancement needle falling off, or the enhancement agent extravasation, or the patient reacts to the drug, the skin color changes, etc., the system will automatically pop up an information box to prompt the operating doctor. At this time, the doctor can carefully observe the monitoring to confirm whether the scan needs to be paused, and the doctor's operation, that is, pausing or continuing the scan, and the corresponding monitoring screen, will be learned by the system as new data, that is, the machine will learn to judge whether the user needs to be prompted to pause or continue the scan under this change.

[0032] At the same time, the monitoring range that the doctor is concerned about will also be learned by the system as new data. For example, the machine learns that the arm with a needle, or when there is no needle, the face is the point of concern for the doctor. In addition, the machine can also learn how large its focus range is for different focus points. Of course, the system's comparison frequency, the sensitivity of the frame when an abnormality occurs, and even whether to prompt the user with a frame or a status bar message can all be configured by the user.

[0033] Figure 1 FIG. 1 is a schematic flow chart of an alarm method 100 for a medical device according to an embodiment of the present invention. Figure 1As shown, the alarm method 100 for medical equipment includes step S102, step S104, step S106, step S108, and step S110. The medical equipment is, for example, a CT machine, an MR machine, and the like.

[0034] In step S102, a default focus area and focus range are provided on the image of the object according to the machine learning result. The image of the object can be obtained, for example, by a camera. The focus area may include the face, elbow, and back of the hand.

[0035] In step S104, the acceptance or change of the concerned part and concerned range is obtained and stored. The doctor can accept or change the concerned part and concerned range provided by the system, and the operation will be recorded for subsequent machine learning.

[0036] In step S106, according to the changes of the focus area and the focus range on the image of the object during the preset time interval, it is determined by machine learning whether there is an abnormality. The preset time interval can be, for example, 1 second. These abnormalities may include the fall-off of the enhancement needle, the extravasation of the enhancement agent, the abnormal reaction of the patient to the drug, and the abnormal expression of the patient.

[0037] Step S108: According to the judgment result, an alarm is issued, which may be a pop-up box or a prompt in the status bar.

[0038] Step S110, receiving a response to the alarm and storing the images of the object at the beginning and end of the preset time interval and the aforementioned response. The response may include treatment and ignore, and the doctor may choose to continue scanning or terminate the scan according to the actual situation. These images and responses will be used for subsequent machine learning.

[0039] According to a second aspect of the present invention, a computer program is provided, which can implement the steps of the alarm method 100 for a medical device when executed by a processor.

[0040] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein the program can implement the steps of the alarm method 100 for a medical device when executed by a processor.

[0041] Figure 2 FIG. 2 is a schematic structural block diagram of an alarm device 200 for medical equipment according to an embodiment of the present invention. Figure 2 As shown, the alarm device 200 for medical equipment includes a recommendation unit 202, a range determination unit 204, a judgment unit 206, an alarm unit 208, and a storage unit 210. The medical equipment is, for example, a CT machine, an MR machine, and the like.

[0042] The recommendation unit 202 provides a default focus area and focus range on the image of the object according to the machine learning result. The image of the object can be obtained by a camera, for example. The focus area may include the face, elbow, and back of the hand.

[0043] The range determination unit 204 obtains and stores the acceptance or change of the concerned part and concerned range. The doctor can accept or change the concerned part and concerned range provided by the system, and the operation will be recorded for subsequent machine learning.

[0044] The judgment unit 206 judges whether there is an abnormality through machine learning according to the changes of the object's image annotation part and the focus range during the preset time interval. The preset time interval can be, for example, 1 second. These abnormalities may include the fall-off of the enhancement needle, the extravasation of the enhancement agent, the patient's abnormal reaction to the drug, and the patient's abnormal expression.

[0045] The alarm unit 208 issues an alarm based on the judgment result. The alarm may be a pop-up box or a prompt in the status bar.

[0046] The storage unit 210 receives the response to the alarm and stores the images of the object at the beginning and end of the preset time interval and the aforementioned response. The response may include treatment and neglect, and the doctor may choose to continue scanning or terminate scanning according to the actual situation. These images and responses will be used for subsequent machine learning.

[0047] The alarm method, device, computer program, and computer-readable storage medium of the medical equipment of the present invention can automatically identify abnormalities and issue alarms through machine learning. The doctor's selection of the scope of attention and the response to the alarm will also be used for machine learning. Therefore, the identification of abnormalities is more accurate and the alarm prompt is more in line with the actual degree of danger.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A medical device alarm method (100), comprising: Step S102, providing a default focus area and focus range on the image of the object according to the machine learning result; Step S104, obtaining and storing the acceptance or change of the concerned part and concerned range; Step S106, judging whether there is an abnormality through machine learning according to changes in the focus area and focus range on the image of the object during a preset time interval; Step S108, issuing an alarm according to the judgment result; Step S110, receiving a response to the alarm and storing images of the object at the beginning and end of a preset time interval and the response.

2. The method according to claim 1, characterized in that: The areas of concern include face, elbows, and backs of hands.

3. The method according to claim 1, characterized in that: The warning is a prompt in a pop-up box or in a status bar.

4. The method according to claim 1, characterized in that: The responses include act and ignore.

5. A computer program, which, when executed by a processor, can implement the steps of the method according to any one of claims 1 to 5.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 5 can be implemented.

7. An alarm device (200) for medical equipment, comprising: A recommendation unit (202), configured to provide a default focus area and focus range on the image of the object according to the machine learning result; A range determination unit (204) configured to obtain and store acceptance or modification of the focus site and focus range; A judgment unit (206) is configured to judge whether there is an abnormality through machine learning according to changes in the focus area and focus range on the image of the object during a preset time interval; An alarm unit (208), which is configured to issue an alarm according to the judgment result; A storage unit (210) is configured to receive a response to the alarm and store images of the object at the beginning and end of a preset time interval and the response.

8. The device according to claim 7, characterized in that: The areas of concern include face, elbows, and backs of hands.

9. The device according to claim 7, characterized in that: The warning is a prompt in a pop-up box or in a status bar.

10. The device according to claim 7, characterized in that: The responses include act and ignore.

Images