System and method for safeguarding an electric device

Abstract

The invention relates to a system and a method for safeguarding an electric device. The system comprises: an image capturing device which is designed to continuously capture image data from at least one treatment region; a detection device which is designed to determine the position of the electrical device by analysing the captured image data and to identify a working region within the treatment region; an evaluation device which is designed to determine, on the basis of the determined position of the electrical device and the identified working region, whether the electrical device is located inside or outside the working region; and an output interface which is designed, when at least one predefined part of the electrical device is outside the working region, to output a first output signal which triggers an interruption of the current of the electrical device.

Description

[0001] System and procedure for securing an electrical device

[0002] Technical field of the invention

[0003] The present invention relates to a system for safeguarding an electrical device, particularly during endoscopic medical procedures and taking into account a treatment area. The invention further relates to a computer-implemented method for safeguarding an electrical device.

[0004] Background of the invention

[0005] In medical procedures and interventions, safety precautions for electrical, controllable instruments and devices are typically device-based. During a medical procedure, the operator of a device can manually adjust the parameters of the device's various operating modes as needed. For example, the operator of an RF device can control the device's power.

[0006] Adjusting a device's operating parameters depends on the specific medical procedure and the characteristics of the treatment area. For example, tissue vaporization in a child requires different operating parameters than in an adult (e.g., regarding the energy of the device used). Safe handling of a device is therefore procedure-specific. In prostate vaporization, for instance, an RF device should vaporize only specific areas of the prostate with a specific energy level. Conversely, when treating tumors within tissue, a laser must target only the tumors and operate at an appropriate energy level; otherwise, there is a risk of damaging healthy tissue. Such damage can occur due to uncontrolled movements, such as the device unexpectedly slipping.As another example, a mechanical shaver used during arthroscopy on an uneven surface can easily and accidentally move outside the area being resected. Such movements are undesirable and typically characterized by a sudden increase in the device's speed. They are sometimes uncontrolled and can lead to damage. For instance, such a jerky movement can cause tissue inflammation or even lacerations in the mechanical shaver.

[0007] It is therefore important to provide improved safeguards for electrically operated controllable instruments and devices, which can minimize the consequences of uncontrolled, jerky movements in particular and thus prevent damage.

[0008] Summary of the invention

[0009] It is therefore an object of the present invention to provide a system and a method which supports the handling of instruments in medical procedures, in particular by an analysis which combines the device with information about a medical procedure to be performed in order to be able to adapt the level of safety to each situation.

[0010] This problem is solved by the subject matter of the independent claims of the present invention.

[0011] According to a first aspect, a system for safeguarding an electrical device is provided, comprising: an image acquisition device configured to continuously acquire image data from at least one treatment area; a detection device configured to determine the position of the electrical device and identify a working area within the treatment area by analyzing the acquired image data; an evaluation device configured to determine, based on the determined position of the electrical device and the identified working area, whether the electrical device is located inside or outside the working area;and an output interface which is configured to output a first output signal, which triggers an interruption of the current to the electrical device, when at least a predefined part of the electrical device is located outside the working area.

[0012] A fundamental idea of ​​the present invention is to automatically determine the position of an electrical device relative to a work area. The system according to the invention performs device detection and identifies a work area. Should the electrical device leave the intended work area and move outside of it, the system detects this event and temporarily deactivates the device by interrupting the power supply. An advantage of the present invention is that the interruption of the power supply occurs automatically and is therefore significantly faster than a human operator's reaction.

[0013] Electrical devices include devices that are powered by electricity and can be controlled by signals. This includes, in particular, devices where an interruption of the power supply can be controlled. The predefined part of the electrical device can be, for example, a part of the device that is relevant to, or provides, the device's functionality. If the functionality is, for example, cutting or removing tissue, the predefined part can be a blade, an electrode, a laser output, or the like. The predefined part can thus be, in particular, a part that is capable of interfering with, or damaging, tissue (e.g., through contact or irradiation). In an RF device, the predefined part of the device can, for example, include the electrode. In a shaver device, the predefined part can, for example, include the blades.In other variants, the entire electrical device can be considered the predefined part of the electrical device. An electrical device can also comprise several predefined parts that are monitored according to the invention.

[0014] Determining the position of an object typically involves at least information about the location of its boundaries and / or their orientation. For example, image recording can be used to assign coordinates of a reference system to the object's boundaries. Determining the position of an electrical device specifically refers to such a determination of spatial coordinates.

[0015] Identifying the electrical device includes, for example, classifying the electrical device into a model type, including the geometric dimensions of the device and / or information about the functionality of at least the predetermined part of the electrical device.

[0016] According to the invention, the position of the electrical device in relation to the working area is used as a criterion (or trigger) to initiate the interruption of the current. A device that is "within the working area" describes a situation in which at least the part of the device that provides functionality for the medical procedure is entirely within the working area. A device that is "outside the working area" describes a situation in which at least the part of the device that provides functionality is not entirely within the working area. The part providing functionality can be, for example, the cutting edge of a scalpel, the jaw of an endoscopic device, the output of a medical laser, and / or the like.

[0017] The first output signal from the output interface, which triggers a current interruption, is any signal that can be transmitted to an actuator and cause it to interrupt the power supply to the device. Depending on the type of actuator, the signal can be an acoustic signal, an optical signal, an analog signal, a digital signal, the command line of a computer program, etc.

[0018] A treatment area is understood to be, in particular, a volume or surface encompassing tissue to be treated. The dimensions of the treatment area depend on the procedure or intervention. The treatment area may change during the course of a procedure. For example, a procedure may require any number of treatment areas, depending on the complexity of the procedure. The system of the invention can acquire information from a multitude of treatment areas. A treatment area may refer to an internal view of a patient undergoing or about to undergo a medical procedure.

[0019] The work area is to be understood as part of a treatment area. The work area is any surface or volume within which an activity is to be performed using the electrical device, particularly based on the device's medical functionality. As with treatment areas, any number of work areas may be required in a procedure, depending on its complexity.

[0020] The image data acquired by the input interface can include image data transmitted from an external imaging device. This can be raw data or pre-processed data. The image data acquired by an imaging device can, in particular, be one or more images, especially a time series of images (image sequence) of a treatment area.

[0021] Although some functions are described here, in the foregoing and below, as being performed by "devices" or "interfaces," it is understood that this does not necessarily mean that such devices or interfaces are provided as separate units. In cases where one or more devices or interfaces are provided wholly or partially as software, the devices or interfaces may be implemented by sections or snippets of program code that are distinct from one another but may also be intertwined.

[0022] Similarly, where one or more devices or interfaces are provided as hardware, the functions of one or more devices or interfaces may be provided by one and the same hardware component, or the functions of one device or interface, or the functions of several devices or interfaces, may be distributed across several hardware components, which need not necessarily correspond one-to-one with the devices or interfaces. Therefore, any device, system, method, etc., that possesses all the features and functions attributed to a particular device and / or interface is to be understood as constituting, comprising, or implementing the device and / or interface.

[0023] In particular, it is possible that all facilities and interfaces are implemented by program code that is executed by a computing facility.

[0024] The detection device and the evaluation device can be implemented as any device or means for computing, in particular for executing software, an application, or an algorithm. For example, the detection device and / or the evaluation device can include at least one processor, such as at least one central processing unit (CPU) and / or at least one graphics processing unit (GPU), and / or at least one field-programmable gate array (FPGA), and / or at least one application-specific integrated circuit (ASIC), and / or any combination thereof. The detection device and / or the evaluation device can further include main memory operationally connected to the at least one processor, and / or non-volatile memory operationally connected to the at least one processor and / or the main memory.The detection device and / or the evaluation device can be implemented partially and / or completely in a local device and / or partially and / or completely in a remote system, such as a cloud computing platform.

[0025] The image acquisition system can be configured to receive image data directly from an imaging device, particularly in real time, or alternatively from a picture archiving and communications system (PACS), the latter also potentially in real time, specifically as soon as the image data arrives in the PACS. The system can also include an imaging device, so receiving the image data can also involve capturing the image data by the imaging device. The system can include several different imaging devices, which, for example, might be designed to capture treatment areas or work areas of varying sizes or perspectives. However, the processing can always be performed using the same recognition and evaluation unit.

[0026] The output interface can include a user interface or be connected to a user interface or a central monitor. In this way, the output signal can be accompanied by a graphical representation or a message explaining the reason for the interruption of the electrical device's power supply.

[0027] Further advantages of the invention are explained below with reference to the subject matter of the dependent claims and, in particular, with reference to the description of the figures. According to some preferred embodiments, variants, or refinements of embodiments, the image acquisition device comprises a camera of an endoscopic medical device, wherein the image data includes photographs and / or video recordings of a patient's treatment area. Medical procedures and interventions in which exceeding a working area by a device or instrument can have serious or costly consequences are a preferred application area of ​​the invention.

[0028] An endoscopic medical device is broadly defined here as any device that can be used in an endoscopic medical procedure. Endoscopic medical procedures include medical interventions, examinations, or procedures that are performed at least partially inside a patient's body and are typically carried out using an endoscope.

[0029] According to some preferred embodiments, variants, or refinements of embodiments, the recognition device comprises an artificial intelligence entity trained and configured to perform object recognition, wherein the object recognition includes identification of the electrical device. In addition to determining the position of the electrical device, the system of the invention can perform recognition of the electrical device, in particular by means of the artificial intelligence entity. This allows the system to recognize which part, or parts, of the electrical device are responsible for the functionality of the device, i.e., which part(s) are the predetermined part.

[0030] With such detection of the electrical device, exceedances of the working area by parts not responsible for the functionality of the device (i.e., parts that are not the intended part), for example, exceeding the working area by the handle of the device, can be assessed as harmless and accordingly do not trigger deactivation of the device, which means that the procedure can run without unnecessary interruptions.

[0031] The artificial intelligence entity can implement one or more machine learning models, particularly image processing models, capable of image recognition. These models can also include deep learning models implementing one or more artificial neural networks. Artificial neural networks, in this context, are understood to be models with any architecture and any number of intermediate layers, such as convolutional neural networks (CNNs). The detection, or segmentation, of the electrical device's appearance can be performed using a typical state-of-the-art artificial neural network, such as a ResNet50, trained on segmented object images, particularly images of medical instruments and devices.

[0032] According to some preferred embodiments, variants, or refinements of embodiments, the recognition device comprises an artificial intelligence entity trained and designed to determine the work area based on a surgical plan. A surgical plan, in this context, refers specifically to a compilation of information that leads to the recognition of a work area. The surgical plan may thus include images of the work area to be treated or a textual description of the work area (e.g., a description of tissue surrounded by vessels). Based on this information, a work area can advantageously be determined using artificial intelligence methods.The artificial intelligence entity can, for example, be equipped with generative artificial intelligence methods so that, based on the surgical planning instructions, a work area can be recognized in real time by analyzing the captured image data of a treatment area. In these embodiments, the recognition device can further be configured to receive such surgical planning instructions, for example, from a local user interface or from a central computing unit.

[0033] In preferred embodiments, the detection device comprises a single artificial intelligence entity that performs the detection of the electrical device and the determination of the working area by applying different models.

[0034] According to some preferred embodiments, variants or refinements of embodiments, the recognition device comprises an artificial intelligence entity and an image processing database, wherein the artificial intelligence entity is designed to perform the determination of the position of the electrical device using the image processing database.

[0035] Artificial intelligence methods can require considerable resources. Therefore, to detect an event in the image stream in real time, it can be advantageous to combine or support this detection with such an image processing database. In these embodiments, the determination of the electrical device's position can be accelerated. In this way, the system according to the invention can be particularly suitable for the requirements of providing real-time support to the operator of the electrical device.

[0036] An image processing database can enable, simplify, or accelerate the determination of the position of the electrical device by evaluating at least translations, rotations, torsions, and shape changes of the electrical device.

[0037] According to some preferred embodiments, variants, or refinements of embodiments, the artificial intelligence entity is designed to detect movements of the electrical device (at speeds) above a first speed threshold using the image processing database. In this way, the system can automatically assess whether one or more machine learning models that are part of the AI ​​can provide a timely determination of the electrical device's current position, or whether additional software from an image processing database needs to be activated to determine the electrical device's current position more quickly.In some embodiments of the invention, it is conceivable that the machine learning model(s) are used to provide recognition of the electrical device and a determination of its initial position, and that the subsequent movements of the electrical device are determined using the image processing database. This process can be repeated if the working area changes.

[0038] According to some preferred embodiments, variants, or refinements of embodiments, the artificial intelligence entity is designed to transmit localization parameters of the electrical device and localization parameters of the identified work area to the image processing database. The machine learning model(s) can, for example, first decompose the temporal sequence of image data into an image sequence. Each frame of the image sequence can be represented as a grid of pixels (a pixel structure). Determining the position of the electrical device and identifying the work area involves mapping the pixels. The pixels can be mapped to the coordinates of a reference system by means of image registration. These spatial coordinates can then be transmitted to the image processing database as localization parameters.

[0039] According to some preferred embodiments, variants, or refinements of embodiments, interrupting the power includes placing the device into a standby mode. Interrupting the power does not necessarily mean switching off the electrical device. Advantageously, the device is only temporarily inactive when the power is interrupted, so that the device does not need to be switched back on when it returns to, or is to return to, the working area. This allows the operator of the electrical device to continue the procedure with minimal loss of time and effort.

[0040] According to some preferred embodiments, variants, or refinements of embodiments, the output interface is further configured to output a second output signal, which restores the power supply to the electrical device, if the device is within its operating range after a power interruption. In some embodiments of the invention, it is provided that when the evaluation unit detects that a device is back within its operating range, the electrical device is automatically reactivated. The medical procedure can thus be continued without delay. Accordingly, the output interface outputs a second output signal, which automatically restarts the device.

[0041] For example, the output interface can put the device from standby mode into normal operating mode.

[0042] According to some preferred embodiments, variants or refinements of embodiments, the evaluation device is further configured to determine a speed of the electrical device, wherein the output interface is further configured to output the first output signal when the determined speed is above a second speed threshold.

[0043] Jerky movements, even if they do not move the electrical device outside its operating range, indicate uncontrollable or uncontrolled movements. As a safety precaution, the system according to the invention can also trigger a current interruption in this case. It can also be provided that the device can be reactivated as soon as the speed has dropped below the second speed threshold. This reactivation can be carried out (in particular automatically) by outputting the second output signal. The speed of the electrical device can be determined by comparing the pixel positions of two adjacent frames in the image sequence. Each pixel is thus characterized by a flow vector from which the speed vector of the pixel can be derived.The speed of the electrical device over time can then be summarized in the form of pixel structures, each with a corresponding flow vector. To assign pixels in adjacent frames, the evaluation unit can receive information about the registered pixel structure of the electrical device from the recognition unit (for example, via the artificial intelligence entity and / or the image processing database).

[0044] According to some preferred embodiments, variants, or refinements of embodiments, the detection device is designed to visibly display the position of an electrical device and a working area within the treatment area on a user interface. Various graphical options are conceivable for this purpose. For example, the image stream can be displayed on a monitor with a superimposed representation of the working area, for instance, as an augmented reality display.

[0045] According to some preferred embodiments, variants, or refinements of embodiments, the system of the first aspect of the invention is at least partially integrated into an RF device or a mechanical shaver device. The system according to the invention can be part of an electrical device so that the safeguarding is at least partially local. This allows the safeguarding system to be purchased together with the electrical device, minimizing potential compatibility issues. In some embodiments, for example, the image acquisition device and the output interface can be integrated into the electrical device, while the detection and evaluation device are implemented in a server or a cloud computing platform. The various devices and interfaces of the system are then preferably wirelessly coupled.

[0046] According to a second aspect, the present invention provides a computer-implemented method for safeguarding an electrical device. The method comprises at least the following steps: continuously acquiring image data of at least one treatment area; determining, based on an analysis of the acquired image data, the position of the electrical device; identifying, based on an analysis of the acquired image data, a working area within the treatment area; determining, based on the determined position of the electrical device and the identified working area, whether the electrical device is inside or outside the working area; and, if the electrical device is outside the working area, outputting a first output signal that triggers an interruption of the current to the electrical device.

[0047] A signal can be output continuously, whereby, for example, the signal only assumes the characteristics of the first output signal and thus triggers the interruption of the electrical device's current if the electrical device is outside the operating range. Alternatively, a signal can be output only when the first or second output signal is to be sent.

[0048] The computer-implemented method of the second aspect can preferably be carried out using the system of the first aspect. Similarly, the various embodiments of the system can be implemented using the computer-implemented method of the second aspect.

[0049] According to a third aspect, the invention provides a computer program product comprising executable program code which, when executed by a computing device, is configured to perform the method according to an embodiment of the second aspect of the present invention.

[0050] According to a fourth aspect, the invention provides a non-volatile, computer-readable data storage medium comprising executable program code which, when executed by a computing device, is configured to carry out the method according to an embodiment of the second aspect of the present invention.

[0051] The non-volatile, computer-readable data storage medium can include or consist of any type of computer memory, in particular semiconductor memory, such as solid-state memory. The data carrier can also include or consist of a CD, DVD, Blu-ray disc, USB flash drive, or the like.

[0052] According to a fifth aspect, the invention provides a data stream comprising executable program code or configured to generate executable program code which, when executed by a computing device, is set up to perform the method according to an embodiment of the second aspect of the present invention.

[0053] Further advantageous variants, options, embodiments, and modifications will become apparent from the following figures, the detailed description, and the claims. It is understood, however, that while the detailed description and specific examples represent preferred embodiments of the invention, they are provided for illustrative purposes only, as various changes and modifications within the scope of the invention are obvious to those skilled in the art. Brief description of the figures

[0054] Individual embodiments of the present disclosure will be explained in detail with reference to the following figures. The components in the drawings are not necessarily to scale, but serve to illustrate the principles of the present invention. Parts in the various figures that correspond to the same elements or process steps have been provided with the same reference numerals in the figures. The numbering of process steps initially serves only to distinguish them and does not necessarily imply a corresponding sequence; however, it is one option to carry out the steps in the order of their numbering. Several steps can also be carried out overlapping or simultaneously. The figures show:

[0055] Fig. 1 is a schematic block diagram to illustrate a system according to an embodiment of the first aspect of the present invention;

[0056] Fig. 2 is a schematic flowchart to illustrate a computer-implemented method according to an embodiment of the second aspect of the present invention;

[0057] Fig. 3 is a schematic flowchart to illustrate a computer-implemented method according to a further embodiment of the second aspect of the present invention;

[0058] Fig. 4 is a schematic block diagram illustrating a system according to an embodiment of the first aspect of the present invention, wherein the system is partially integrated into the protected electrical device; Fig. 5 is a schematic block diagram of a computer program product according to an embodiment of the third aspect of the present invention; and

[0059] Fig. 6 shows a schematic block diagram of a non-volatile, computer-readable data storage medium according to an embodiment of the fourth aspect of the present invention.

[0060] Detailed description of the figures

[0061] Fig. 1 shows a schematic block diagram to illustrate a system 100 according to a first embodiment of the present invention, i.e., a system 100 for safeguarding an electrical device G. In Fig. 1, the electrical device G is, for example, an instrument with a spatula electrode used for high-frequency (HF) surgery. The spatula electrode may be incorporated into an endoscope. However, the electrical device G can be any electrically controllable device, for example, a shaver device, e.g., for use in resection. The electrical device G can be suitable for medical procedures or interventions, in particular for endoscopic medical procedures.

[0062] The system 100 shown in Fig. 1 comprises an image acquisition device 10, a recognition device 20, an evaluation device 30, an output interface 40, and a user interface 50.

[0063] The image acquisition device 10 is configured to continuously acquire image data BD0 from at least one treatment area (ROI). This image data BD0 can be acquired directly, via a PACS, or from another type of database. The image acquisition device 10 can include an imaging device, such as the camera of an endoscope, or receive the image data from an imaging device. The image data can include photographs and / or video recordings of a patient's treatment area. The image data BDO acquired in real time can thus advantageously comprise an image dataset or an image sequence, namely a series of temporally successive images, for example, with a frame rate between 10 and 100 Hertz, i.e., with images acquired successively at intervals of between 10 and 100 milliseconds.These can be processed well by the human eye and at the same time provide a good data basis for subsequent processing.

[0064] The detection device 20 is designed to perform an analysis of the captured image data BDO in order to determine the position of the electrical device G and to identify a working area AB within the treatment area ROI.

[0065] In the embodiment of the invention shown in Fig. 1, the recognition device comprises an artificial intelligence entity (AI) 210. This AI 210 can implement one or more machine learning models to perform, in particular, the recognition of the electrical device G and the identification of the working area AB. The AI ​​210 can also determine the position of the electrical device G. The AI ​​210 can preferably be trained to determine the working area AB based on the information compiled in a surgical plan.

[0066] The surgical plan can include images of the surgical area AB to be treated or a textual description of the surgical area AB (e.g., an anatomical description of vessels and tissue components that define the surgical area AB). The recognition device 20 can also be configured to receive such a surgical plan, for example, from a local user interface and / or from a central computing unit (not shown in Fig. 1). Coordinates of a coordinate reference system can be assigned to the surgical area AB, for example, by means of image registration. The position of the electrical device G can also be determined using image registration.

[0067] By recognizing the electrical device G, the system 100 can identify (optionally with the aid of a database) which parts of the electrical device G have which functionalities, and thus also identify the predetermined part. In combination with the surgical planning, the KIE 210 can also assess whether the electrical device G and the procedure described in the surgical plan are compatible, i.e., whether the electrical device G is needed or suitable for the described procedure.

[0068] In Fig. 1, the recognition device 20 comprises a single artificial intelligence entity 210, which performs the recognition and position of the electrical device G and the determination of the working area using various models. In other embodiments of the invention, the recognition device 20 can employ two different artificial intelligence entities that perform the different tasks separately.

[0069] The recognition device 20 in Fig. 1 further comprises an image processing database 220 containing image processing software. The artificial intelligence entity 210 is also configured to determine the position of the electrical device using the image processing database 220. Artificial intelligence methods can be very resource-intensive. Using image processing software, the determination of the position of the electrical device G can then be accelerated. Thus, the system 100 of the invention is suitable for the speed requirements of providing real-time support to the operator of the electrical device G.

[0070] An image processing database 220 can therefore include various image processing software (software that, for example, performs an evaluation of at least translations, rotations, torsions and shape changes of the electrical device G) that can be activated by the artificial intelligence entity 210.

[0071] In some embodiments, the KIE 210 is further configured to use the image processing database 220 when movements of the electrical device G exceed a first speed threshold F1. In this way, the system 100 can automatically assess whether the machine learning model(s) can provide a timely determination of the new position of the electrical device G, or whether the image processing database 220 needs to be activated to determine the position of the electrical device G more quickly.

[0072] In some embodiments of the invention, it is conceivable that the machine learning model(s) of the KIE 210 are first used to detect the electrical device G and determine its initial position, while subsequent movements of the electrical device G can be determined using the image processing database 220. This process can be repeated when the working area AB changes.

[0073] In this context, the KIE 210 can be advantageously designed to transfer localization parameters of the electrical device G and the identified work area AB to the image processing database 210. The localization parameters could, for example, be the spatial coordinates generated by image registration.

[0074] As shown in Fig. 1, the information generated by the detection unit 20, including the location of the working area AB and the electrical device G, can be transmitted to the evaluation unit 30 and the user interface 50. The evaluation unit 30 is configured to determine the relative position of the electrical device G and the working area AB. The evaluation unit 30 can use the information obtained by the detection unit 20 regarding the detection of the electrical device G to limit the (relevant) detection of the electrical device G to the detection of a predefined part of the electrical device G, where the predefined part performs the functionality of the electrical device. In the case of the spatula electrode of Fig. 1, an exceedance of the working area AB could be detected, for example, if (and only if) the electrode surface exceeds (or leaves) the working area AB.Exceeding the working area AB with only the handle of the electrical device G would be considered irrelevant.

[0075] If the evaluation unit 30 detects that the electrical device G (entirely, or at least with the part(s) providing the functionality, i.e., with the at least one predetermined part) is located outside the working area AB, a first output signal H1 is issued from the output interface 40, which triggers an interruption of the current to the electrical device G. Preferably, the evaluation unit 30 uses a detection mechanism for the electrical device G to determine whether the working area AB has been exceeded. Accordingly, the deactivation of the electrical device G can advantageously only be initiated if the predefined part of the electrical device G exceeds (or leaves) the working area AB. With this refined evaluation of an exceedance, the procedure can therefore proceed without unnecessary interruptions.

[0076] In preferred embodiments of the invention, the electrical device G is placed in a standby mode when the power is interrupted. The interruption of the power then does not mean that the electrical device G is switched off, so that the device does not need to be switched on again when (or as soon as) it (or the predefined part of it) is back within the operating range AB. This allows the operator of the electrical device G to continue the medical procedure with minimal loss of time and effort. In some embodiments of the invention, the speed of the electrical device G is determined, for example, by the detection device 20 or the evaluation device 30. The output interface 40 can further be configured to output the first output signal H1 if the determined speed exceeds a second speed threshold F2.Sudden movements, even if they do not move the electrical device G outside the working area AB, may indicate uncontrollable or uncontrolled movements. For safety reasons, the system according to the invention can also trigger a power interruption to the electrical device G in these cases.

[0077] In some embodiments of the invention, it is provided that if the electrical device G (or the predefined part) is again within the operating range AB after a power interruption, a second output signal H2 is output from the output interface 40, which reactivates the power supply to the electrical device G and puts the electrical device G back into operation. For example, the output interface 40 can switch the device from standby mode to normal operating mode.

[0078] It can also be provided that the second output signal H2 is output as soon as the determined speed of the electrical device G, after exceeding the second speed threshold F2, falls below the second speed threshold F2 (or optionally a lower third speed threshold F3 to avoid constant switching on and off).

[0079] Typically, the first output signal H1 and the second output signal H2 are transmitted to an actuator (not shown in Fig. 1), which can enable and disable the power supply to the device. Depending on the type of actuator, the signal can be an acoustic signal, an optical signal, the command line of a computer program, etc. In Fig. 1, the system 100 also includes a user interface 50, which is connected at least to the detection device 20 and the output interface 40. The user interface 50 can visibly display the position of the electrical device G and the working area AB. The user interface 50 can also display the first output signal H1 and / or the second output signal H2 or graphically represent the reason for it (e.g.,The output signal H1 may include a visual highlight of an exceedance range) to explain and visualize to the operator of the electrical device G the reason for the power interruption of the electrical device G.

[0080] The user interface 50 can also display the captured image data BD0 in real time, overlaying the information generated by the recognition device 30 and the output interface 40. The user interface 50 also allows the operator to edit the displayed images (e.g., to enlarge specific image sections or select specific frames).

[0081] Fig. 2 shows a schematic flowchart to illustrate a computer-implemented method according to an embodiment of the second aspect of the present invention, i.e., a computer-implemented method for safeguarding an electrical device G. The method according to Fig. 2 is particularly feasible using the system 100 from Fig. 1 and can therefore be adapted according to all options or variants described with respect to the system 100 according to the invention, and vice versa.

[0082] In step S1, image data BD0 of at least one treatment area (ROI) is continuously acquired. As explained previously, this image data BD0 can comprise multiple images acquired directly in real time by an imaging device, particularly a time-based series of images (image sequence) of an endoscopic procedure. Alternatively or additionally, the image data BD0 can be retrieved from a database. This can be raw data or pre-processed data.

[0083] In step S2, the position of an electrical device G is determined based on an analysis of the acquired image data BDO. The position determination can be performed using one or more machine learning models, preferably supported by state-of-the-art image processing software.

[0084] In some preferred embodiments of the invention, a first velocity threshold F1 is specified. Movements of the electrical device G can be determined by one or more machine learning models, particularly when the movement speed is below the first velocity threshold F1. Faster movements, with speeds above the first velocity threshold F1, can advantageously be determined using faster image processing software (which typically requires fewer resources). With this solution according to the invention, fast and accurate position determination of the electrical device G can be ensured at all times, making the method according to the second aspect of the invention suitable for supporting medical procedures in real time.

[0085] In step S3, a work area AB is identified within the treatment area ROI, based on an analysis of the acquired image data BDO and preferably with the aid of surgical planning. This identification can also be performed using one or more machine learning models.

[0086] In step S4, based on the determined position of the electrical device G and the identified work area AB, it is determined whether the electrical device G is currently located inside or outside the work area AB. The electrical device G does not need to be completely inside or outside the work area AB. Advantageously, it is possible to focus on at least one predefined part (comprising or consisting of the functional part) of the electrical device G. Thus, step S4 can determine whether the predefined part of the electrical device G is located inside or outside the work area AB.

[0087] If at least the predefined part of the electrical device G is located outside the working area AB, a first output signal H1 is issued in a further step S5, which triggers an interruption of the current to the electrical device G. The predefined part usually comprises the functional part of the electrical device G. Parts of the electrical device G that do not perform the function of the electrical device G (e.g., the handle of the device) are typically harmless and can be located outside the working area AB in many applications without this having undesirable consequences.

[0088] If at least the predefined part of the electrical device G is within the operating range AB again after an interruption of the current, a second output signal H2 is output in an optional step S6, which releases the power supply to the electrical device G and puts the electrical device G back into operation.

[0089] Fig. 3 shows a schematic flowchart illustrating a computer-implemented method according to a further embodiment of the second aspect of the present invention. As explained above, the first output signal H1 can also be triggered if the speed of the electrical device G (or at least the speed of the parts of the electrical device G that perform the functionality of the device) exceeds a second speed threshold F2. Fig. 3 illustrates two criteria that can trigger the first output signal H1. The first criterion (comprising steps S1 to S6) has already been explained in connection with Fig. 2 and is therefore not repeated here.

[0090] The second criterion comprises steps S1, S2, S7, S8, S5, and S6. Steps S1 and S2 have already been explained above.

[0091] In step S7, the speed of the electrical device G is determined. In step S8, it is determined whether the speed of the electrical device G is currently above or below a second speed threshold F2.

[0092] If the measured speed exceeds the second speed threshold F2, the first output signal H1 is output in step S5. Accordingly, in Fig. 3, the output signal H1 is output in step S5 because either the electrical device G is outside the operating range AB or because the measured speed of the electrical device G exceeds the second speed threshold F2.

[0093] In the optional step S6, a second output signal H2 is output, which releases the power supply to the electrical device G and restarts the electrical device G, provided that the determined speed of the electrical device G is below the second speed threshold F2 (or below an even lower third speed threshold F3) after exceeding the second speed threshold F2 and / or that the electrical device G is at least partially (functionally) within the working area AB after exceeding the working area AB.

[0094] Fig. 4 shows a schematic block diagram illustrating a system according to an embodiment of the first aspect of the present invention, wherein the system 100 is partially integrated into the protected electrical device G. The electrical device G can preferably be an RF device (such as the column electrode of Fig. 4) or a shaver device. In the embodiment of Fig.

[0095] 4. Thus, at least part of the security measures can be implemented locally, with the image acquisition device 10 and the output interface 40 being integrated into the electrical device G, while the recognition device 20 and / or the evaluation device 30 can be implemented in a server or a cloud computing platform. The various devices and interfaces of the system are preferably wirelessly connected.

[0096] Fig. 5 shows a schematic block diagram of a computer program product 300 according to an embodiment of the third aspect of the present invention. The computer program product 300 comprises executable program code 350, which, when executed (e.g., by a computing device), is configured to perform the method according to an embodiment of the second aspect of the present invention, for example, according to Fig. 2.

[0097] Fig. 6 shows a schematic block diagram of a non-volatile, computer-readable data storage medium 400 according to an embodiment of the fourth aspect of the present invention. The data storage medium 400 comprises executable program code 450, which, when executed (e.g., by a computing device), is configured to perform the method according to an embodiment of the second aspect of the present invention, for example, according to Fig. 2.

[0098] The non-volatile, computer-readable data storage medium 400 can, for example, be configured as or comprise a semiconductor memory, e.g., an SSD. The data storage medium 400 can also comprise or comprise a CD, DVD, Blu-ray disc, or a magnetic storage device. The foregoing description of the disclosed embodiments contains only examples of possible implementations, which are described to enable a person skilled in the art to manufacture or use the present invention. Various variations and modifications of these embodiments are readily apparent to a person skilled in the art—after knowledge of the present invention—and the general principles defined herein can be applied to other embodiments without departing from the scope of this disclosure.Therefore, the present invention is not to be limited to the specific embodiments shown herein, but is to be granted the broadest scope that is consistent with the principles and features disclosed herein.

[0099] Reference symbol list

[0100] 10 Image capture device

[0101] 20 Recognition device

[0102] 30 Evaluation unit

[0103] 40 Output interface

[0104] 50 User interface

[0105] 100 System

[0106] 210 Artificial Intelligence Entity

[0107] 220 Image processing database

[0108] 300 computer program product

[0109] 350 program code

[0110] 400 data storage medium

[0111] 450 program code

[0112] AB work area

[0113] BD0 image data

[0114] G Electrical device

[0115] F1 First Speed ​​Threshold

[0116] F2 Second speed threshold

[0117] ROI treatment area

[0118] H1 First output signal

[0119] H2 Second output signal

[0120] S1..S8;

[0121] Procedural steps

Claims

Patent claims 1. System (100) for safeguarding an electrical device (G), comprising: an image acquisition device (10) configured to continuously acquire image data (BDO) of at least one treatment area (ROI); a detection device (20) configured to determine the position of the electrical device (G) and to identify a work area (AB) within the treatment area (ROI) by analyzing the acquired image data (BDO); ​​an evaluation device (30) configured to determine, based on the determined position of the electrical device (G) and the identified work area (AB), whether the electrical device (G) is located inside or outside the work area (AB);and an output interface (40) which is configured to output a first output signal (H1) when at least a predefined part of the electrical device (G) is located outside the working area (AB), which triggers an interruption of the current of the electrical device (G).

2. System (100) according to claim 1, wherein the image acquisition device (10) comprises a camera of an endoscopic medical device and the image data (BDO) comprises photographs and / or video recordings of a treatment area (ROI) of a patient (P).

3. System (100) according to one of claims 1 or 2, wherein the recognition device (20) comprises an artificial intelligence entity (210) which is trained and designed to perform object recognition, wherein the object recognition comprises identification of the electrical device (G).

4. System (100) according to any one of claims 1 to 3, wherein the detection device (20) comprises an artificial intelligence entity (210) that is trained and designed to determine the work area (AB) based on an operating plan.

5. System (100) according to any one of claims 1 to 4, wherein the recognition device (20) comprises an artificial intelligence entity (210) and an image processing database (220), wherein the artificial intelligence entity (210) is designed to perform the determination of the position of the electrical device (G) using the image processing database (220).

6. System (100) according to claim 5, wherein the artificial intelligence entity (210) is designed to detect movements of the electrical device (G) via a first speed threshold (F1) using the image processing database (220).

7. System (100) according to one of claims 5 or 6, wherein the artificial intelligence entity (210) is designed to transmit localization parameters of the electrical device (G) and localization parameters of the identified work area (AB) to the image processing database (220).

8. System (100) according to any one of claims 1 to 7, wherein interrupting the current comprises placing the electrical device (G) into a standby mode.

9. System (100) according to any one of claims 1 to 8, wherein the output interface (40) is further configured to output a second output signal (H2) which enables the power supply to the electrical device (G) to be restored if the electrical device (G) is located within the working area (AB) after an interruption of the current of the electrical device (G).

10. System (100) according to one of claims 1 to 9, wherein the evaluation device (30) is further designed to determine a speed of the electrical device, wherein the output interface (40) is further configured to output the first output signal (H1) when the determined speed is above a second speed threshold (F2).

11. System (100) according to any one of claims 1 to 10, wherein the detection device (20) is designed to visibly display the position of an electrical device (G) and a working area (AB) within the treatment area on a user interface (50).

12. System (100) according to any one of claims 1 to 11, wherein the system (100) is at least partially integrated into an RF device or into a shaver device.

13. Computer-implemented method for safeguarding an electrical device (G), comprising at least: continuous acquisition (S1 ) of image data (BD0) of at least one treatment area (ROI); Determine (S2), based on an analysis of the captured image data (BDO) the position of the electrical device (G); Identify (S3), based on an analysis of the captured image data (BDO), a work area (AB) within the treatment area (ROI); Determine (S4), based on the determined position of the electrical device (G) and the identified working area (AB), whether the electrical device (G) is inside or outside the working area (AB); and output (S5), if at least a predefined part of the electrical device (G) is outside the working area (AB), a first output signal (H1) which triggers an interruption of the current of the electrical device (G).

14. Computer program product (300), comprising executable program code (350) which, when executed by a computing device, is configured to perform the method according to claim 13.

15. Non-volatile, computer-readable data storage medium (400) comprising executable program code (450) which, when executed by a computing device, is configured to perform the method according to claim 13.

Images