Medical system, medical imaging instrument and method for imaging by means of a medical system for the airway management of a patient

Abstract

Medical system (10) comprising: a medical imaging instrument (12) configured to image an anatomical object region (14) and generate image data of the object region (14); a display device (16) configured to receive the image data and generate a representation (18) of the object area (14) for a user; an image recognition unit (20) configured to recognize anatomical landmarks (22) of the object area (14) based on the image data; and a navigation unit (24) configured to generate a navigation aid (26) to assist the user in locating a target structure (28), wherein the navigation aid (26) comprises a visual enhancement of a first image area (30) compared to a second image area (32) in the representation (18), wherein the first image area (30) comprises an anatomical landmark (22), and wherein the second image area (32) does not comprise the anatomical landmark (22), characterized in that the image recognition unit (20) is configured to recognize a part of a medical device (58); and that the navigation unit (24) is configured to at least partially hide the recognized part of the medical device (58) in the display (18).

Description

[0001] The present application relates to a medical system, a medical imaging instrument and a method for imaging.

[0002] The term "airway management" encompasses a series of measures and procedures designed to maintain and secure a patient's patent airway, for example, to enable external ventilation. In general, airway management can ensure that the patient's lungs are supplied with sufficient oxygen and that gas exchange can occur. Airway management is particularly crucial when intubating a patient in an emergency situation or prior to surgical intervention.

[0003] Intubation is the process of inserting an endotracheal tube through the mouth or nose of a patient to be intubated into the trachea. This allows the patient's airway to be opened and / or maintained open for external ventilation. Typically, medical personnel such as physicians and emergency medical technicians (EMTs) perform intubation based on anatomical landmarks, advancing the tube along and / or relative to these landmarks. However, difficulties can arise during intubation. One of the greatest intubation challenges that emergency medical technicians face on a daily basis is a limited view of the airway and anatomical landmarks.Poor visibility can occur, especially in emergency situations where establishing a patent airway as quickly as possible is crucial to the patient's survival, due to blood, mucus, vomit, or swelling in the patient's mouth and throat. Furthermore, anatomical features such as a large tongue or unusual anatomy in the patient's throat can also complicate intubation.

[0004] To overcome these difficulties and facilitate intubation, medical personnel use certain medical instruments such as laryngoscopes. A special type of laryngoscope, a video laryngoscope, can image a patient's larynx and show it on a display to facilitate intubation for medical personnel. A laryngoscope typically comprises a handle and a blade. The blade allows the laryngoscope user to compress soft tissues in the floor of the patient's mouth, depress the lower jaw, and push the tongue aside. This gives the user a direct view into the larynx and allows them to see, for example, the vocal cords. A video laryngoscope also includes a light source and a camera on the blade.

[0005] Although the use of video laryngoscopes already provides assistance for intubation, this may not be sufficient, especially in emergency situations. For example, if the patient is bleeding heavily or has an anatomical abnormality, medical staff may still have difficulty identifying important anatomical landmarks, thus losing valuable time. In principle, it may also be desirable to further relieve medical staff of the burden of performing intubation, allowing them to focus more on other relevant tasks, such as monitoring the patient's vital signs.

[0006] WO 2023 / 102 891 A1, US 2022 / 0354 380 A1, US 2019 / 0 350 659 A1 and US 2018 / 0 221 610 A1 are known from the prior art, each of which discloses systems and methods for image-assisted navigation in the body using anatomical landmarks, wherein image regions containing the landmarks can be displayed with visual enhancement.

[0007] From DE 11 2021 004 183 T5 an image enhancement system is known in which a light pattern is projected onto an anatomical target so that contour information of the surface of the anatomical target can be determined.

[0008] Based on the prior art, the invention is based on the object of supporting a user in intracorporeal navigation.

[0009] This object is achieved according to the invention by a medical system, a medical imaging instrument and a method for imaging as described herein and defined in the claims.

[0010] The present invention provides a medical system. The medical system comprises a medical imaging instrument configured to image an anatomical object region and generate image data of the object region, a display device configured to receive the image data and generate a representation of the object region for a user, an image recognition unit configured to recognize anatomical landmarks of the object region based on the image data, and a navigation unit configured to generate a navigation aid to assist the user in locating a target structure, wherein the navigation aid comprises visually enhancing a first image region relative to a second image region in the representation, wherein the first image region includes an anatomical landmark, and wherein the second image region does not include the anatomical landmark.

[0011] Furthermore, the present invention provides a medical imaging instrument.The medical imaging instrument comprises an image acquisition unit configured to image an anatomical object region and generate image data of the object region, a display device configured to receive the image data and generate a representation of the object region for a user, an image recognition unit configured to recognize anatomical landmarks of the object region based on the image data, and a navigation unit configured to generate at least one navigation aid to assist the user in locating a target structure, wherein the navigation aid comprises visually enhancing a first image region compared to a second image region in the representation, wherein the first image region comprises an anatomical landmark, and wherein the second image region does not comprise the anatomical landmark.

[0012] These features ensure that the user is better supported during intracorporeal navigation, for example in connection with intubation or bronchoscopy. The user can, for example, perform intubation more efficiently, safely, and quickly. However, the features are not limited to intubation. For example, the insertion of an endoscope into the trachea is better supported and can be carried out more efficiently, safely, and quickly. In an emergency situation, the user can perform intubation more quickly and accurately and, for example, monitor the patient's vital parameters without significantly impairing the intubation process. This can generally improve the quality of treatment. The user is supported in locating anatomical landmarks and / or target structures more quickly and reliably.This is achieved by visually enhancing the user's attention, which is primarily directed to the first image area with the waymark. This allows the user to reliably find the waymarks or another target structure even under difficult conditions. As a result, they can guide a tube or other medical instrument more safely, quickly and precisely using the anatomical waymark. For example, the user can use the waymark to position the tube or other medical instrument relative to the target structure. It is also advantageously ensured that the user can also observe the second image area if necessary. This can be necessary, for example, when coordinating several parallel treatments. Since the first image area is only visually enhanced, the second image area can still be shown in great detail.Furthermore, it may be advantageous for the image recognition unit to be able to recognize anatomical landmarks that the user would not readily recognize. For example, image data quality may be poor due to soiling of the imaging instrument, or the landmark may be at least partially covered by mucus or blood. Despite these difficulties, the image recognition unit can recognize an anatomical landmark.

[0013] The medical system may be a medical imaging system, in particular a medical endoscopy system. This may mean that the medical system is configured for endoscopic imaging. The endoscopic imaging may be provided to support intubation. Furthermore, the endoscopic imaging may be configured, for example, to image at least a portion of the trachea and / or the lungs. This may mean that the medical system is configured to perform and / or support a diagnostic procedure. In further embodiments, the medical system may comprise an exoscopy system.

[0014] The medical imaging instrument may comprise an exoscope and / or an endoscope. The medical imaging instrument may be configured to be inserted into a body cavity of the patient. A body cavity may be any body cavity of the patient. For example, the body cavity may include the nasal cavity, the oral cavity, the trachea, the lungs, the stomach, the intestines, an abdominal cavity, a thoracic cavity, and / or a joint space.

[0015] In some embodiments, the imaging instrument, in particular the endoscope, can be a laryngoscope and / or a bronchoscope. The medical imaging instrument and / or the medical system can be configured, in particular, for airway management, in particular to support intubation. Using a bronchoscope, for example, a tube can be placed more precisely in the trachea. Using a laryngoscope, the tube can be placed more easily relative to the patient's glottis and / or inserted more easily into the trachea.

[0016] In some embodiments, the medical system can comprise a laryngoscope and a bronchoscope. The laryngoscope and the bronchoscope can cooperate to support intubation. The bronchoscope can in particular comprise a video stylet. The tube to be placed can be arranged on the bronchoscope, in particular the video stylet, and can be inserted into the trachea together with it. The tube can, for example, be pushed onto the bronchoscope, in particular the video stylet. The bronchoscope, in particular the video stylet, can be configured to impart greater flexural rigidity to the tube so that the tube can be more easily inserted into a body cavity of the patient. In this context, the laryngoscope can be used, for example, to locate the patient's glottis more quickly. The display device can be configured to first generate a representation of image data from the laryngoscope.After the bronchoscope, in particular the video stylet, has been pushed past the glottis, the display device can be configured together with the tube to generate a display of image data from the bronchoscope, in particular the video stylet. In general, the display device can be configured to selectively generate a display of image data from the laryngoscope and / or the bronchoscope, in particular the video stylet. The selection of which image data is used to generate the display can be made automatically and / or based on user input. For example, the image recognition unit can be configured to make the selection. The image recognition unit can, for example, be configured to detect the progress of an intubation and to make the selection based on the detected progress. Furthermore, the selection can be made by the user.For example, the user can switch from the laryngoscope to the bronchoscope, in particular the video stylet, by operating a user interface.

[0017] The anatomical object area can refer to a part of the patient's body. In particular, the anatomical object area can include anatomical structures and / or organs. In particular, the anatomical object area can include anatomical landmarks and / or the target structure.

[0018] The image data can comprise analog and / or digital signals and / or digital information that represent a representation, in particular of the anatomical object area. The image data can be divided into several sub-areas, in particular pixels, each of which contains, for example, color values, brightness values, and / or intensity values. The image data can be transmitted via cable and / or wirelessly. Furthermore, the image data can be formatted in previously known formats.

[0019] The display device can comprise a screen. The display device can be arranged on the medical imaging instrument, attachable to it, and / or integrated with it. The user can, for example, view and / or evaluate the object area on the display device based on the representation of the image data. To do so, the user does not have to look away from the imaging instrument and / or the patient. Furthermore, the display device can be formed separately from the imaging instrument and / or comprise at least one screen separate from the imaging instrument. The display device can, for example, be part of a treatment environment. This can mean that the display device comprises a screen of an ambulance and / or an operating room. Furthermore, multiple display devices can be provided. Each of the display devices can generate a representation of the object area.In particular, the display devices can be configured to selectively generate the representation. This can mean, in particular, that at least one display device can be selected from the plurality of display devices, in particular by the user, to generate the representation. According to some embodiments, the display device can comprise a user interface. For example, the display device can comprise a touchscreen.

[0020] The representation can depict information, in particular visual information, about the object area and make it available to the user. The representation can be based on the image data. The image data can be processed for representation purposes. For example, analog and / or digital image filters, in particular smoothing filters, color filters, and pass filters, can be applied to the image data. Furthermore, a color representation can be generated. The color representation can be based on the captured colors of the object area. Furthermore, the representation can be generated differently on a pixel-by-pixel and / or section-by-section basis. This can mean that at least partially different processing of the image data can be carried out on a pixel-by-pixel and / or section-by-section basis. The image recognition unit can be configured to determine the pixels and / or the at least one section that is to be subjected to different processing.The determination can, for example, be based on a recognized anatomical landmark.

[0021] An anatomical landmark refers, for example, to a specific structural and / or anatomical reference point and / or landmark in the body, in particular the human body, that can be used, for example, by a doctor, surgeon or other medical professional to identify and / or describe positions, directions and / or locations in the body.

[0022] The image recognition unit can be configured to analyze and / or process image data in order to obtain information from the image data. The information can, in particular, relate to anatomical landmarks and / or the target structure. In particular, the image recognition unit can comprise a pattern recognition unit and / or an object recognition unit. This can mean that the image recognition unit is configured to recognize patterns and / or objects in images and / or image data. Furthermore, the image recognition unit can be configured to classify and / or classify obtained information, recognized images, and / or recognized objects. This can mean that the image recognition unit is configured to assign a recognized anatomical landmark and / or a recognized target structure to a group of landmarks and / or target structures.In some embodiments, the image recognition unit is configured to assign a recognized landmark and / or a recognized target structure to a specific landmark and / or target structure, for example, a landmark and / or target structure preselected, in particular, by a user, or automatically determined, for example, depending on an application and / or operating mode. For example, the medical system can be configured to detect the progress of an intubation. Alternatively or additionally, the medical system can be configured, for example, to determine an anatomical landmark to be recognized based on the progress. The image recognition unit can then be configured to assign a recognized landmark to the landmark to be recognized. As a result, selecting a landmark and recognizing a landmark can be carried out at least partially automatically.This may mean that the user does not need to provide any user input to select a waypoint.

[0023] Image recognition can be based on a mathematical calculation rule and / or artificial intelligence. In general, patterns and / or objects can be recognized by weighting features of the image data. For example, the image recognition unit can recognize anatomical landmarks using a model with a neural network based, for example, on machine learning and / or deep learning. Furthermore, the image recognition unit can include a self-learning module. The self-learning module can have a model with a neural network based on machine learning and / or deep learning. In general, a neural network can be an open neural network, a closed neural network, a single-layer neural network, a multi-layer feedforward network with hidden layers, a feedback neural network, and / or a combination of these.

[0024] The image recognition unit, in particular the self-learning module, can be configured to learn and / or improve image recognition based on training data. The training data can be generated, for example, during use of the medical system. Furthermore, the training data can be stored and / or retrieved centrally. This can mean that the training data can be stored in a cloud, in particular in a reference database of the cloud, and / or retrieved from the cloud, in particular from the reference database of the cloud. Several healthcare facilities, for example hospitals and / or ambulances, can be networked and / or configured to communicate with the cloud. This allows training data sets to be continuously and / or discontinuously uploaded to the cloud, in particular to the reference database of the cloud.The image recognition unit can be configured to transmit information about a recognition of an anatomical landmark and / or information about an anatomical landmark to the navigation unit.

[0025] In principle, the navigation aid can be a support aid that supports the user by changing and / or adapting the display, for example by directing the user's attention to a part of the display. The navigation unit can be designed jointly with the display device. Alternatively or additionally, the navigation unit and the display device can jointly have a computing unit. The computing unit can be configured to receive and / or process the image data. The navigation unit, in particular the computing unit, can be configured to influence the generation of the display on the display device. This can mean that the navigation unit and the display device are configured to jointly generate the display, in particular by means of the computing unit.

[0026] The navigation aid can comprise part of the display and, in particular, can be generated together with the display. The navigation aid can, in particular, be different from a fade-in, overlay, and / or the like that can be subsequently added to the display. For example, the navigation aid can comprise a locally and / or sectionally different display of the object area.

[0027] Through visual enhancement, a section, in particular the first image region, can be highlighted in such a way that the user primarily perceives this section, in particular the first image region, visually. Visual enhancement can comprise an improvement and / or highlighting of certain visual properties in an image region so that the region and / or certain features are more clearly visible. “Visual enhancement” can also be understood as “emphasizing the representation” and / or “visually highlighting,” in particular with reference to human perception. In particular, visual enhancement can comprise highlighting a section of the representation without adding structural features, such as markings, to the representation. Visual enhancement can comprise a change in the representation of the object region such that the representation in the first image region is different from the representation in the second image region.If, for example, the user glances at the display device, the user's focus is directed directly and / or primarily to the first image area. In some embodiments, this occurs expressly without a marker superimposed on the representation. However, a marker can be added additionally. However, "visual enhancement" does not mean simply displaying a marker. The representation of the object area can depict all structural features of the anatomical object area that a conventional color representation would depict. This can mean that, in particular, no information is lost due to the visual enhancement, for example due to an overlay of another structure and / or details of the representation.

[0028] The target structure may comprise any anatomical structure. In particular, the target structure may comprise an anatomical landmark. In some embodiments, the target structure may comprise one of a mouth opening, a tongue, a nasal opening, a laryngeal cover (epiglottis), the vallecula epiglottica, an arytenoid cartilage (arytenoid cartilage), a glottis, a tracheal clasp, and / or a tracheal carina of a patient. The target structure may be an anatomical structure that the user uses to orient themselves when performing an action. For example, the user can place and / or guide a tube relative to the anatomical structure. The target structure does not necessarily have to be depicted in the first image area and / or the second image area.The target structure can, for example, be a structure within the trachea, in particular a cartilage brace of the trachea, especially while a video stylet has not yet been inserted into the patient's oral cavity. In this context, "support" can mean, for example, that anatomical landmarks along a path of a video stylet to the target structure, in particular the cartilage brace, are recognized and made more easily recognizable by visually enhancing the first image area. If the target structure "cartilage brace" is to be found, anatomical landmarks along the path can include the oral opening, the epiglottis, a cartilage brace and / or the glottis. The visual enhancement supports the user in such a way that the video stylet can be positioned more quickly and / or the target structure, in particular the cartilage brace, is easier to find later on.For example, the user is already assisted in locating the target structure "cartilage brace" if the anatomical landmark "mouth opening" is displayed in the first image area, but not the target structure "cartilage brace." Since the representation of the anatomical landmark "mouth opening" is visually enhanced, the user can locate the target structure "cartilage brace" in a subsequent procedure, for example, an intubation. According to other embodiments, "locating a target structure" can mean that the representation of the object area includes the target structure.

[0029] The first image region can in particular comprise a central image region of the representation. The medical system, in particular the display device, can be configured to generate the representation such that the first image region is arranged in a central region of the representation. This can mean that the first image region can be aligned and / or arranged. The representation can be generated such that the first image region is arranged in a central region. The alignment and / or arrangement can be carried out using a recognized anatomical landmark. For example, an image of the anatomical object region can be larger than the generated representation, or the entire captured anatomical object region is not displayed in the representation. Only a section of the image can be displayed.The section can be selected such that the first image region is located in a central area of ​​the display. The arrangement of the image region can be carried out such that the first image region can be determined based on a recognized anatomical landmark and / or the display can be generated based on the determined first image region. Alternatively or additionally, the user can guide and / or operate the imaging instrument such that the anatomical landmark to be recognized is usually present in a central area of ​​the imaged and / or to-be-imaged object region.

[0030] The first image area can have a rectangular, in particular square, and / or a rounded, in particular circular and / or oval, shape and / or a shape that at least substantially corresponds to a contour of an anatomical structure and / or an anatomical landmark, in particular a contour of the anatomical landmark contained in the first image area. The contour can be recognizable, for example, by means of the image recognition unit and / or the shape can be determined by the display device and / or the image recognition unit. The second image area can border the first image area. The second image area can mean the image area in the representation that at least substantially comprises the image area that does not correspond to the first image area.

[0031] The image acquisition unit can be a device configured to image an object region and / or generate image data. The image acquisition unit can comprise at least one input optic, in particular a converging lens, an image sensor, in particular a CMOS sensor and / or a CCD sensor, an illumination means for illuminating the object region, for example an LED, and / or an output optic for coupling out externally generated illumination light, a computing unit, for example for processing image data, and / or a data transmission unit for transmitting the image data. The image acquisition unit can be arranged in a distal section of the imaging instrument. The input optic can be configured to preferably collect light distal to the distal end of the imaging instrument.This may mean that the entrance optics are oriented in the distal direction and / or that its optical axis forms an angle with the distal direction and / or a longitudinal axis of the medical imaging instrument and / or its distal section that is less than 45°, for example less than 30°.

[0032] Furthermore, the visual enhancement can comprise applying a location-dependent image filter to an image of the object region. Visual enhancement can be achieved simply and / or efficiently. Furthermore, the computing power required for visual enhancement can be kept small and / or reduced. “Location-dependent” can mean that the image filter does not act uniformly across the entire image, but rather acts only in specific regions and / or is distributed inhomogeneously across the image. In some embodiments, the image filter can act only in specific regions. In other embodiments, the image filter can act differently in specific regions. The first image section and / or the second image section can be changed using the image filter. In particular, “location-dependent” can mean that the image filter acts in a region of the image of the object region corresponding to the first image region and / or the second image region.The spatial dependence may depend on the position of an anatomical landmark. The image filter may, in particular, act in an area of ​​an anatomical landmark and / or an area around an anatomical landmark. This may mean that the spatial dependence is adaptable, in particular based on the position of an anatomical landmark. The image filter may, in particular, comprise a digital image filter. The image filter may comprise mathematical operations applied to pixels and / or regions of an image. Using the image filter, visual effects can be generated, details, features, and / or regions can be highlighted, colors can be changed, a frequency can be changed, and / or images can be smoothed. The image filter may comprise a color filter, a blur filter, a black-and-white filter, a distortion filter, a contrast filter, a negative filter, a brightness filter, and / or the like.

[0033] Furthermore, the image recognition unit can be configured to define the image filter based on the recognition of the anatomical landmark. This achieves a high degree of flexibility. In particular, not only a central area of ​​the image is visually enhanced continuously. The spatial dependence of the image filter can be dynamically adapted. In particular, the spatial dependence of the image filter can be dynamically adapted to a position of the anatomical landmark. In this context, "based" can mean, for example, "related to the position." There can be a spatial relationship between the image filter and the landmark.

[0034] Furthermore, the visual enhancement can comprise a different color representation of the first image area and the second image area. A different color representation is a reliable method of directing the user's attention to the first image area. The user perceives a different color representation particularly quickly. Furthermore, at least substantially all features and / or details can be recognized in the first image area and in the second image area. Either the first image area or the second image area can have a changed color representation. Alternatively or additionally, both image areas can have a changed color representation. Changed can mean a difference to a "normal" color representation.

[0035] In addition, the second image area can have a lower color saturation than the first image area. This is a method in which very few details and / or little information from the second image area is lost. In particular, the second image area is displayed in “normal” colors. Information that can only be derived from the color representation is quickly and easily accessible. For example, blood can be displayed in red in both image areas. This allows intuitive use of the medical system. The lower color saturation can refer to a change in the intensity and / or vibrancy of the colors. “Color saturation” can describe the degree of purity and / or intensity of a color. A higher color saturation can make the colors appear stronger and / or more vibrant. A lower color saturation can make the colors appear paler and / or more muted.Color saturation can be changed, for example, by adjusting color balance and / or contrast and / or by specifically editing individual color channels. Alternatively or additionally, the first image area can have a higher color saturation than the second image area, whereby the second image area can have a "normal" color saturation. "Normal" can generally mean a representation that would be created without visual enhancement.

[0036] Alternatively or additionally, the second image area can be slightly blurred compared to the first image area. This allows details to be recognized, but the first image area is still highlighted and primarily perceived by the user. The slight blur can be created, for example, using a filter. The filter can include a Gaussian blur, a mean value filter, a motion blur filter, a radial blur filter, a depth of field filter, and / or a lens blur filter.

[0037] Additionally, the second image area can be displayed in grayscale. This draws the user's attention to the first image area particularly quickly and efficiently. Furthermore, grayscale display is an efficient and / or intuitive method of visual enhancement.

[0038] Furthermore, the visual enhancement can be based on a false-color representation. In particular, the second image region can have the false-color representation. Alternatively or additionally, the first image region can have the false-color representation. The false-color representation can comprise a representation of data, in particular image data, in colors that are not the actual colors of the object region. A false-color representation can be understood as a pseudo-color representation. By means of the false-color representation, image data can be represented in a visually understandable and / or interpretable manner. The false-color representation can refer in particular to a modified color representation of detected colors.

[0039] In principle, the different color representation can comprise a combination of the various methods described for different color representation of the first image area and the second image area. For example, the second image area can be displayed in grayscale, and the first image area can be displayed in false color and / or with higher color saturation.

[0040] Furthermore, the navigation unit can be configured to determine a distance of the imaging instrument from the target structure. The accuracy of an action can thereby be improved. Furthermore, the risk of injury can be reduced. The distance can, in particular, refer to a distance of a distal end of the imaging instrument. Determining the distance can comprise an estimation and / or an inclusion of geometric positional relationships of components of the imaging instrument. For example, the determination can include a distance of an image acquisition unit and / or a part of the image acquisition unit from the distal end of the imaging instrument. Furthermore, the distance can be determinable in relative terms. The distance does not have to be determinable on a metric length scale. For example, a relative approach of the imaging instrument to the target structure can be determinable.The relative approach can refer to a temporal sequence of distance determination steps. A relative change in the distance can be determined and / or compared in at least substantially consecutive distance determination steps. In particular, a movement of the imaging instrument relative to the target structure can be determined thereby.

[0041] In addition, the visual enhancement can be dependent on the distance. Information about the distance can be made available in a simple and intuitive manner. The user can quickly grasp information about the distance without distracting their attention from the first image region, in particular the target structure and / or anatomical landmark. In particular, the intensity of the visual enhancement can depend on the distance. For example, a large distance can result in a slight visual enhancement and a small distance can result in a strong visual enhancement. The dependence can be non-linear. This can mean that the visual enhancement begins and / or begins to change after a distance threshold is undercut.Furthermore, for example, the visual enhancement may depend quadratically on the distance, with the visual enhancement being stronger at a smaller distance or at a larger distance.

[0042] Furthermore, the visual enhancement can comprise increasing the brightness of the first image region and / or decreasing the brightness of the second image region depending on the distance. The brightness of a representation and / or an image region in a representation is a particularly quickly perceivable feature. The user can therefore quickly and intuitively estimate the distance and / or a change in the distance. A base brightness difference between the brightness of the first and second image regions can be provided. Based on the base brightness difference, the brightness can be increased and / or decreased. The base brightness difference can mean that the first image region generally has a slightly higher brightness than the second image region. “Slightly” can mean, for example, a brightness value difference of up to 10%, in particular up to 7%, preferably up to 5%.The difference in base brightness can occur particularly at a large distance.

[0043] In general, a large distance can be defined, for example, relative to the diameter of a tube and / or a video stylet. A large distance in this context can be at least 2, 3, 4, and / or 5 times the diameter.

[0044] In addition, the imaging instrument can be configured to generate stereo images, and the navigation unit can be configured to determine the distance of the imaging instrument from the target structure based on the stereo images. This makes it possible to provide a reliable and easy-to-implement method for determining the distance. In particular, the image acquisition unit of the imaging instrument can comprise a stereo image acquisition unit and / or be configured to generate stereo images. Stereo images can comprise at least two images of an object region that were acquired from an at least slightly different viewing angle. The imaging instrument, in particular the image acquisition unit, can comprise two image sensors and / or two input optics, which can be arranged spatially spaced from one another. The input optics can be configured to collect light from the same object region.The distance can be determined, for example, by triangulation and / or based on disparities in the stereo image. Alternatively or additionally, the distance can be determined using a mathematical calculation rule, in particular one involving artificial intelligence.

[0045] Furthermore, the navigation aid can include changing the display of the object area depending on the distance. Advantageously, information about the distance can be made available in the display. Changing the display can include displaying additional features. "Change" can explicitly refer to a different method for "visual enhancement."

[0046] In addition, an overlay of distance information based on the distance can be superimposed on the representation of the object area. The user can thereby capture particularly precise information about the distance. The overlay also allows intuitive capture of the distance. The overlay can comprise a numeric field and / or a symbolic distance display. A distance value and / or a numeric value based on the distance can be displayed in the numeric field. The symbolic distance display can, for example, comprise a bar whose length changes depending on the distance, a clock symbol whose hand changes depending on the distance, and / or a fill level indicator that changes depending on the distance. The overlay can be arranged in the second image area.

[0047] In addition, the imaging instrument can comprise sensors by means of which a movement of the imaging instrument can be determined. This makes it possible to determine a relative position and / or a distance traveled. Furthermore, a path traveled can be determined. The movement can comprise a longitudinal displacement and / or a rotation. The sensors can in particular be arranged in a distal section of the imaging instrument. Preferably, the sensors can be arranged in an area close to the image acquisition unit. The movement of the distal section of the imaging instrument can thereby be determined. This is particularly advantageous if the distance of the distal section and / or the distal end from the target structure is to be determined.The sensor system may comprise at least one image sensor, in particular an image-based depth sensor, a motion sensor, an electromagnetic sensor, a mouse sensor, a sensor for optical tracking, a gyroscope, an ultrasonic sensor, a magnetometer, an inertial sensor, a light sensor, an infrared sensor, a distance sensor, a ToF (Time of Flight) sensor, a RADAR sensor and / or an acceleration sensor.

[0048] Furthermore, motion blur, which may occur due to movement of the imaging instrument during image acquisition, and / or reduced exposure in an edge region of an image of the object region can be reduced by means of a long-term exposure of the object region. For example, an image can be reconstructed that corresponds to an image with at least substantially uniform exposure.

[0049] Furthermore, the navigation unit can be configured to determine the distance of the imaging instrument from the target structure based on the image data and the determined movement. The distance can be determined easily, in particular reliably. In particular, the distance determination can be carried out without a stereo camera and / or stereo imaging. Based on the determined movement, the position and / or orientation of the imaging instrument, in particular of a distal section of the imaging instrument, can be estimated. By moving the imaging instrument, the object region can be imaged from various relative positions and / or distances. This can result in a situation similar to that occurring during stereo image acquisition. This can mean that various relative positions and images of the object region associated with these positions are known.By means of triangulation and / or based on a disparity between at least two images of the object region, the distance can be determined from this data. Preferably, an acceleration sensor and / or an inertial sensor can be used to detect the movement. A determined acceleration value in one spatial direction can be integrated twice to determine a movement value. This makes it possible to determine the position of the imaging instrument, in particular the sensor system. The position can be known at the times at which the object region is imaged. A combination of position data and image data can be known at several times. Based on this data, a stereo imaging-like reconstruction of images can be carried out, based on which a distance can be determined.

[0050] Furthermore, in addition to the visual enhancement, the navigation aid can comprise at least one marker that can be superimposed on the representation. This can support the effect of visual enhancement. A focus-directing effect for the user can be enhanced. The user can perceive important features in the representation more quickly and reliably. The marker can comprise, for example, a frame, a circle, and / or the like that encloses the first image region, the target structure, and / or an anatomical landmark. Furthermore, the marker can comprise an arrow pointing to an important feature in the representation. A superimposed marker can obscure part of the representation. Furthermore, the marker can be added to a representation after its creation. The generated representation can already comprise a visually enhanced first image region. The marker can be at least partially transparent.This may mean that superimposed structures and / or features of the image of the object area are at least partially visible.

[0051] In addition, the target structure can be selected by the user from several possible target structures. This increases user-friendliness and flexibility. For example, the medical system can recognize preselected anatomical structures corresponding to the target structures. Furthermore, the medical system can be operated in an operating mode dependent on the selected target structure. For example, a target structure can be a cartilage ring of the trachea. The medical system can be operated in a corresponding tube placement operating mode. Alternatively or additionally, the target structure can be the glottis. The medical system can be operated in a corresponding intubation operating mode. Furthermore, the target structure can be a section of a lung. The medical system can be operated in a corresponding bronchoscopy operating mode. The user can select the target structure from a list selection.The list selection can be displayed on the display device as needed and / or selectively. The display device can include a user interface. The user can interact with the display device via the user interface and / or initiate a selection of a target structure.

[0052] In addition, the target structure can be selectable by the user from the representation of the object area. The user can select the target structure intuitively. Furthermore, the user can react quickly to the situation and, for example, select a new target structure. For example, the display device can comprise a touch-sensitive screen. In addition, the image recognition unit can recognize a selection of common and / or possible target structures in the representation of the object area. The user can select a target structure by touching an area of ​​the touch-sensitive screen, wherein one of the common and / or possible target structures is represented in the area. In general, the user can tap on a representation of the target structure to select it.

[0053] In some embodiments, the anatomical landmarks may include at least one of a patient's mouth opening, tongue, nasal opening, epiglottis, vallecula epiglottica, arytenoid cartilage, glottis, tracheal ridge, and / or carina trachea. Generally, the anatomical landmarks may include anatomical landmarks for intubation. Advantageously, intubation can thus be performed quickly, safely, and error-free.

[0054] Furthermore, the image recognition unit is configured to recognize a part of a medical device, and the navigation unit is configured to at least partially hide the recognized part of the medical device in the display. This can increase user-friendliness and operating safety. Furthermore, the system can be operated more intuitively. The medical device can, for example, comprise a tube and / or a surgical instrument, for example forceps, tweezers, a suturing tool, a needle, and / or the like. Partial hiding can mean a partially transparent display. In general, this can mean that the display does not completely contain the hidden part. The recognition can be carried out using an application of artificial intelligence, in particular machine learning.

[0055] In addition, the navigation unit can be configured to display a real and / or pseudo-real anatomy in the representation instead of the at least partially hidden part of the medical device. The object region can be displayed as if the medical device were not present. The user can view the entire object region and, in particular, estimate features hidden by the medical device. The anatomy can be displayed based on an anatomy previously recorded from the object region. This can mean that it is "real." For example, at least one reference image of the object region can be captured before the medical device is made available. The real anatomy can be displayed based on the reference image. Alternatively or additionally, at least one reference image can be retrieved from a centrally and / or decentrally stored data set.The dataset can be accessed, for example, via a data cloud. Using this retrieved reference image, the pseudo-real anatomy can be represented. The selection of the reference image can be based on pattern recognition and / or artificial intelligence, in particular machine learning. Furthermore, a reference image can be created from multiple training reference images. The training reference images can include real reference images that have been transmitted to a central and / or decentralized data storage. The data storage can be a cloud data storage.

[0056] Preferably, intubation can be performed using the medical system and the medical imaging instrument. The image recognition unit can recognize the anatomical landmarks important for intubation and / or identify the next anatomical landmark based on the progress of the intubation. For example, during intubation, the tube must be guided through the mouth opening, along the tongue, between the glottis. For this purpose, the imaging instrument can comprise a laryngoscope. Images of these anatomical features can be captured using the laryngoscope. The navigation unit guides the user through visual reinforcement during intubation. This can result in valuable time savings, particularly during difficult intubation. A laryngoscope and a video stylet can also be used together.If the tube is attached to the video stylet and the tube and video stylet are partially guided through the glottis, the image recognition unit can detect anatomical landmarks of the trachea. In particular, a specific tracheal stent can be identified, which is used to position the tube.

[0057] Furthermore, the invention provides a method for imaging, in particular by means of a medical system according to the invention. The method comprises the steps of imaging an anatomical object region comprising an anatomical landmark and generating image data of the object region using a medical imaging instrument, generating a representation of the object region for a user, recognizing the anatomical landmark of the object region based on the image data, and generating a navigation aid to assist the user in locating a target structure, wherein the navigation aid comprises visually enhancing a first image region compared to a second image region in the representation, wherein the first image region comprises the anatomical landmark, and wherein the second image region does not comprise the anatomical landmark.

[0058] The invention is explained below using exemplary figures. The drawings, the description, and the claims contain numerous features in combination. Those skilled in the art will expediently consider the features individually and use them in meaningful combination within the scope of the claims.

[0059] If there is more than one instance of a particular object, only one of them may be provided with a reference symbol in the figures and in the description. The description of this instance can be transferred accordingly to the other instances of the object. If objects are named using numerical terms, such as first, second, third object, etc., these serve to name and / or assign objects. Accordingly, for example, a first object and a third object, but not a second object, may be included. However, a number and / or sequence of objects could also be derived using numerical terms.

[0060] They show: Fig. 1 a schematic representation of a medical system; Fig. 2 a schematic representation of a laryngoscope inserted into a patient's oral cavity; Fig. 3 is a schematic representation of a display device which generates a representation of an anatomical object region; Fig. 4 shows a further embodiment of a medical system in a schematic representation; Fig. 5 shows a further schematic representation of a representation comprising a navigation aid, a marker and an overlay; Fig. 6 a further schematic representation of a representation comprising a navigation aid and an overlay; Fig. 7 a schematic representation of a bronchoscope comprising a stereo camera at a distance from the carina tracheae; Fig. 8 shows a schematic representation of steps of a method for determining distance; Fig. 9 is a schematic representation of a representation of an object area and a medical device; Fig. 10 a schematic representation of the representation of the object area and a section; and Fig. 11 a schematic representation of steps of an imaging method.

[0061] Fig. 1 shows a schematic representation of a medical system 10. The medical system 10 includes two medical imaging instruments 12, a laryngoscope 42 and a bronchoscope 44, a computing unit 70, which includes an image recognition unit 20 and a navigation unit 24, and a display device 16.

[0062] The laryngoscope 42 comprises a handle 45 and a blade 43. A user can hold the laryngoscope 42 by the handle 45 and guide the blade 43 through a mouth opening 46 of a patient, as is shown, for example, in the Fig. 2. Using the spatula 43, the user can compress soft structures of the patient's mouth floor, press down the lower jaw, and push the tongue 48 to the side. This allows a view of a glottis 54 to be exposed, as shown, for example, in the Fig. 3. The laryngoscope 42 is designed as a video laryngoscope. This means that it is designed to image an anatomical object area 14 (see, for example, Fig. 3) and to generate image data of the object area 14. To generate the image data, the laryngoscope 42 comprises an image acquisition unit 60 within the spatula 43. The image acquisition unit 60 is arranged such that it captures an area distal to the spatula 43. In order to provide illumination light for illuminating the object area 14, the image acquisition unit 60 comprises a light source (not shown). The image data are generated by means of an image sensor (not shown) of the image acquisition unit 60. Furthermore, the laryngoscope 42 comprises sensors 38, by means of which a movement of the laryngoscope 42 can be determined. As described in connection with the Fig. 7 and Fig. As explained in Figure 8, the specific movement can be used to determine a distance between the distal end of the laryngoscope 42 and a target structure 28. In the illustrated case, the sensor system 38 comprises an inertial sensor configured to detect acceleration in three different spatial directions and / or an angular position.

[0063] To intubate the patient, the user can insert the blade 43 of the laryngoscope 42 into the patient’s oral cavity (see Fig. 2) and push away soft tissue, whereby an object area 14 comprising the glottis 54 can be imaged (see Fig. 3). The image data of the object area 14 thus generated are transmitted to the display device 16. Based on the received image data, the display device 16 generates a representation 18 of the object area 14 for the user. The user can thus view the glottis 54 and the area around the glottis 54 on the display device 16 (see Fig. 3) when aligning the image acquisition unit 60 toward the glottis 54. Supported by the representation 18 of the glottis 54, the user can insert a tube 82 past the glottis 54 into the patient's trachea 78 and position it there. In this case, the glottis 54 is an anatomical landmark 22 for intubation and can also be viewed as a target structure 28. To perform intubation, the user must locate the target structure 28 and anatomical landmark 22 of the glottis 54 in the representation, which, as explained below, is supported by the present invention.

[0064] In the Fig. 1, the display device 16 is shown with a representation 18 of the mouth opening 46, another possible anatomical landmark 22, of the patient. Such a representation 18 can be generated, for example, before the spatula 43 is inserted into the oral cavity. Furthermore, it can be seen that the representation 18 is divided into two areas, the first image area 30 and the second image area 32. The anatomical landmark 22 of the mouth opening 46 is arranged in the first image area 30. The first image area 30 includes the other possible anatomical landmark 22 of the tongue 48.

[0065] For example, if the patient is bleeding heavily, the view of the glottis 54 and / or the mouth opening 46 may be restricted. To assist the user in locating a target structure 28, such as the trachea 78, glottis 54, and / or a tracheal stent, the image recognition unit 20 and the navigation unit 24 are provided in such a case. However, even without a complication such as heavy bleeding, the patient can be assisted in locating the target structure, for example, to improve intubation speed and / or to make intubation safer.

[0066] The image recognition unit 20 and the navigation unit 24 are implemented on the shared computing unit 70. Alternatively or additionally, the image recognition unit 20 and / or the navigation unit 24 can be implemented on the display device and / or at least one of the imaging instruments 12. The image recognition unit 20 is configured to recognize anatomical landmarks 22 of the object region 14 based on the image data. The image recognition unit 20 can recognize the anatomical landmarks 22, for example, using a model with a neural network based, for example, on machine learning and / or deep learning. Furthermore, the image recognition unit 20 can include a self-learning module (not shown). The self-learning module can have a model with a neural network based on machine learning and / or deep learning.In general, a neural network can be an open neural network, a closed neural network, a single-layer neural network, a multi-layer feedforward network with hidden layers, a feedback neural network and / or a combination of these.

[0067] The image recognition unit 20, in particular the self-learning module, can be configured to learn and / or improve image recognition based on training data. The training data can be generated, for example, during use of the medical system 10. Furthermore, the training data can be stored and / or retrieved centrally. This can mean that the training data can be stored in a cloud 80, in particular in a reference database of the cloud 80, and / or retrieved from the cloud 80, in particular from the reference database of the cloud 80. Several healthcare facilities, for example hospitals and / or ambulances, can be networked and / or configured to communicate with the cloud 80. As a result, training data sets can be continuously and / or discontinuously uploaded to the cloud 80, in particular to the reference database of the cloud 80.

[0068] The image recognition unit 20 is configured to transmit information about the recognition of an anatomical landmark 22 and / or information about an anatomical landmark 22 to the navigation unit 24. The navigation unit 24 is configured to generate a navigation aid 26 to assist the user in locating the target structure 28. A navigation aid 26 is described, for example, in the Fig. 3, Fig. 5 and Fig. 6 shown in more detail. However, also in the Fig. 1, the navigation aid 26 can be seen in the representation 18 of the object area 14 comprising the mouth opening 46. The navigation aid 26 comprises a visual enhancement of the first image area 30 compared to the second image area 32 in the representation 18, wherein the first image area 30 comprises the anatomical landmark 22, such as the mouth opening 46, and wherein the second image area 32 does not comprise the anatomical landmark 22. By way of example, the second image area 32 is shown hatched in order to visually delimit it from the first image area 30. Contrary to this schematic representation, however, details of the object area 14 can also be seen in the second image area 32 (see Fig. 6). For example, the visual enhancement may include a different color representation of the first image area 30 and the second image area 32. Alternatively or additionally, the second image area 32 may have a lower color saturation than the first image area 30 and / or the second image area 32 may be represented in grayscale. Furthermore, the visual enhancement may be based on a false color representation.

[0069] The medical system 10 includes a location-dependent image filter (not shown) for visual enhancement. The location-dependent image filter acts on a section of an image of the object region 14. The image recognition unit 20 is configured to define the image filter based on the detection of the anatomical landmark 22. After an anatomical landmark 22, such as the mouth opening 46, and its position in the image have been detected, this position is used to define the image filter. For this purpose, the first image region 30 and the second image region 32 are determined based on the position of the landmark 22, and the image filter is adjusted such that it only changes the representation 18 of the second image region 32. The image filter can effect different color saturation, different color representation, grayscale representation, and / or false color representation, particularly in the second image region 32.In other embodiments, the image filter may also be configured to change the representation in the first image area 30 in order to visually enhance it.

[0070] If the representation 18 includes the navigation aid 26, which can be generated as described above, the user can perform intubation and / or other endoscopic and / or exoscopic actions more easily and safely. In order for a target structure 28 to be known to the system 10, the user can select the target structure 28 from several possible target structures 28. A list selection of possible target structures 28, from which the user can choose, can be displayed on the display device 16, for example. The target structure 28 can be selected by the user alternatively or additionally from the representation 18 of the object region 14. If, for example, a representation of the mouth opening 46 is generated, the user can specify highlighted and / or visually enhanced structures and / or other structures as the target structure 28.For example, the display device 16 may have a touchscreen and the user may tap the desired target structure in the display 18 on the touchscreen.

[0071] The further imaging instrument 12 is a bronchoscope 44, which is designed as a video stylet. The bronchoscope 44 comprises an elongated, flexible shaft 72. A distal end section 74 of the shaft 72 comprises an image acquisition unit 60, which is designed as a stereoscopic image acquisition unit. This means that the image acquisition unit 60 of the bronchoscope 44 comprises two cameras 76, each having an image sensor (not shown). The cameras 76 together define a stereo camera 75. As a result, the object region 14 can be imaged from two slightly different viewing angles and / or stereo images can be generated. Based on a disparity between images from both cameras 76, the navigation unit 24 can determine a distance 34 (see, for example, Fig. 7) of the imaging instrument 12 to the target structure 28.

[0072] A medical device 58, more precisely the tube 82, is arranged on the shaft 72. The tube 82 is releasably fixed to the shaft 72. During intubation, the shaft 72 is inserted together with the tube 82 into the patient's trachea 78 (see, for example, Fig. 4) and positioned and fixed in the trachea 78 to enable ventilation of the patient. Positioning can be performed using the bronchoscope 44 by positioning the tube 82 relative to a tracheal collar (not shown) of the trachea. In this context, the tracheal collar can be a target structure 28. The user is assisted in locating the tracheal collar by the image recognition unit 20 and the navigation unit 24 by generating the visual enhancement of the first image area 30. Once the tube 82 is positioned, the tube 82 can be detached from the shaft 72 and the shaft removed from the trachea to prepare the tube 82 for ventilation.

[0073] To assist in positioning the tube 82, a distance 34 to the tracheal collar can be determined using the stereo camera 75 of the bronchoscope 44. To indicate the distance 34 to the user and / or inform them of a good positioning, the visual enhancement can be dependent on the distance 34. Alternatively or additionally, the visual enhancement can include increasing the brightness of the first image area 30 and / or decreasing the brightness of the second image area 32 depending on the distance 34. In such a case, the navigation aid 26 includes a change in the representation 18 of the object area 14 depending on the distance 34.

[0074] Alternatively or additionally, the representation 18 of the object area 14 can be overlaid with an overlay 36 of distance information based on the distance 34, as is the case, for example, in the Fig. 5 and Fig. 6 is shown.

[0075] The bronchoscope 44 and the laryngoscope 42 can be used together during intubation. Both imaging instruments 12 are connected to the computing unit 70 and the display device 16. First, the navigation aid 26 is generated based on image data from the laryngoscope 42. After a distal end of the shaft 72 has been pushed past the glottis 54, the navigation aid 26 is generated based on image data from the bronchoscope 44. Switching can occur automatically and / or upon user input.

[0076] The Fig. Figure 2 shows a schematic representation of the laryngoscope 42, whose blade 43 is partially inserted into the patient's oral cavity past the anatomical landmark 22, the mouth opening 46. Using the blade 43, the lower jaw is pressed down and soft tissue such as the tongue 48 is compressed and / or pushed aside. This allows the anatomical object area 14 to be imaged using the image acquisition unit 60 of the laryngoscope 42. A representation based on such an image is shown in the Fig. 3. The anatomical object area 14 includes the epiglottis 52, the glottis 54 (see Fig. 3) and an entrance to the trachea 78. In the Fig. 2, the tube 82 can be inserted into the trachea, whereby the user can view the anatomical landmark 22 glottis 54 on the display device 16.

[0077] The Fig. Figure 3 shows a schematic representation of the display device 16, which generates a representation 18 of the object area 14 based on image data which is acquired by means of the laryngoscope 42 in the Fig. 2. In the illustration 18, a first image area 30 is visually enhanced compared to a second image area 32 by means of a navigation aid 26. In the first image area 30, the anatomical landmarks 22, glottis 54 and epiglottis 52, are shown. The second image area 32 does not include these landmarks 22. Furthermore, one can see an access to the trachea 78, through which the user pushes the tube 82 for intubation. By way of example, the second image area 32 is shown hatched, similar to the second image area 32 in the Fig. 1. According to the Fig. 3, the second image area 32 is shown with a lower brightness than the first image area 30. Although it is not in the Fig. 3, the user can recognize details of the object area 14 in the second image area 32. However, if the user glances briefly at the display device 16, their focus is directed directly to the first image area 30, since this is visually enhanced by the navigation aid 26. The navigation aid 26 and / or the first image area 30 is arranged centrally in the display 18 and is at least substantially circular. The medical system 10 is configured to align the navigation aid 26 and / or the first image area 30 centrally in the display 18.

[0078] The Fig. Figure 4 shows a schematic representation of another embodiment of a medical system 10', which has some features in common with the medical system 10. Therefore, differences will be discussed primarily.

[0079] The medical system 10' comprises a bronchoscope 44', which is configured to be guided through a nasal opening 50, which is an anatomical landmark 22, to the trachea 78 of the patient. For this purpose, the bronchoscope 44' comprises a long, flexible shaft 72', at the distal end portion 74' of which a stereo camera 75' is arranged. By means of the stereo camera 75', an anatomical object region is imaged and image data is generated. Furthermore, a distance 34 to a target structure 28 can be determined. In the illustrated case, the target structure 28 is the carina tracheae 56 (see also Fig. 5, Fig. 6 and Fig. 7), which is also an anatomical landmark 22. For example, the bronchoscope 44' can be inserted into one of the left or right main bronchi 84, 86 using the anatomical landmark 22 Carina tracheae 56. Distance information can be displayed to the user (see Fig. 5 and Fig. 6), which will help him to insert the device more safely.

[0080] In the Fig. 7 schematically shows a state of the bronchoscope 44' within the trachea 78 of the patient, which at least substantially corresponds to the state of the bronchoscope 44' in the Fig. 4. The distal end section 74' is arranged at a distance 34 from the carina tracheae 56, which is the target structure 28. The distance to the target structure 28 is determined by means of the stereo camera 75'. Furthermore, the object area is imaged and image data is generated, based on which a representation 18', 18" is generated, which is shown by way of example in the Fig. 5 and Fig. 6. It can be seen that the left main bronchi 86 branches off to the left of the carina tracheae 56, and the right main bronchi 84 branches off to the right of the carina tracheae 56. The distal end section 74' can be directed to one of these bronchi 84, 86, with the user being assisted by the navigation aid 26', 26".

[0081] Referring again to the Fig. 4 shows that the bronchoscope 44' further comprises an image recognition unit 20', a navigation unit 24' and a display device 16'. These units can have at least substantially the same functions as those already described in connection with the Fig. 1. The bronchoscope 44' is configured to wirelessly transmit data, in particular image data and / or data based on image data. In the illustrated case, the bronchoscope 44' wirelessly transmits image data to a computing unit 70' connected to the cloud 80. This allows, for example, training data to be stored in the cloud 80, which can be used for training the self-learning module.

[0082] In the Fig. 5 and Fig. 6 shows schematic representations of exemplary representations 18', 18", as they are based on the image data of the bronchoscope 44' in the Fig. 4 and Fig. 7 state can be generated. The representations 18', 18" are very similar and therefore share some reference numerals, which will therefore not be discussed separately for each of the figures. The representations 18', 18" comprise a navigation aid 26', 26", which at least substantially corresponds to the navigation aid 26.

[0083] The representation 18' according to Fig. 5 includes, in addition to the navigation aid 26', a marker 40 and an overlay 36'. In the representation 18', the carina tracheae and the left and right main bronchi 84, 86 can be seen in the first image area 30', which is visually enhanced. The marker 40 includes an arrow that is superimposed over the representation 18', in particular the first and second image areas 30', 32', and points to the target structure 28. By means of the marker 40, the user is more specifically directed to the target structure 28, the carina tracheae 56. The overlay 36' is a text field in which a metric distance value can be displayed. The overlay 36' is superimposed over the second image area 32'.

[0084] The representation 18" according to Fig. 6 shows, in addition to the navigation aid 26", an overlay 36", which includes a bar whose length changes depending on the distance 34. The bar changes its length similar to a fill level indicator, with the bar reaching its greatest length when the distal end of an imaging instrument 12 touches and / or almost touches the target structure.

[0085] Furthermore, one can see in the Fig. 6, that the second image area 32" is displayed such that the user can recognize details of the anatomical object area in the second image area 32". All second image areas 32, 32', 32" shown here can be displayed in this way. In the present case, the second image area 32" is displayed with a lower color saturation and a lower brightness. The color saturation and / or the brightness can change depending on the distance 34 such that the color saturation becomes weaker with a smaller distance 34 and the second image area 32" is displayed brighter with a smaller distance 34.

[0086] The Fig. Figure 8 shows a schematic representation of steps of a method 120 for determining the distance of a medical imaging instrument 12 comprising sensors and a camera. For example, by means of the method 120, a distance of the laryngoscope 42 of the Fig. 1 to a target structure 28 can be determined. The method 120 can be divided into two sub-aspects, a calibration 116 and a distance determination 118. In a step 88, a reference image is recorded using the camera, and a reference image is generated, based on which a distortion can be determined. For example, an image of a checkerboard pattern can be generated. In a step 90, a correction determination is carried out based on the reference image, and, for example, correction parameters are generated. In a step 92, camera parameters are determined and / or provided. In a step 94, the sensor system 38, in particular the inertial sensor, is calibrated and / or initialized. In a step 96, the position of the image acquisition unit 60, in particular the camera, is calibrated and / or initialized. Using the system 10 calibrated in this way, a distance determination 118 can subsequently be carried out.For this purpose, in a step 98 the object area is mapped and image data of the object area 14 is generated.

[0087] During image data generation, an acceleration is determined by means of the sensor system 38 in a step 100 and an angle of the sensor system 38 is determined in a step 102. The position and angle of the sensor system 38 are determined by double integration in a step 104. With knowledge of a positional relationship between the sensor system 38 and the camera, the position and angle of the camera are determined in a step 106. If the imaging instrument 12 is moved, several images of the object area 14 are generated, with a position and angle of the camera being determined for each of the images. The images can be corrected in a correction step 108 using the correction parameters generated in step 90. For example, distortions detected using the checkerboard pattern can be removed.In a step 110, disparities between different corrected images are determined, and based on the disparities, the distance 34 to the target structure 28 is determined in a step 112. Based on the distance 34, an overlay 36 is generated in step 114, which can be superimposed on the representation 18.

[0088] The Fig. 9 and Fig. 10 show a section of illustration 18 of the Fig. 3. In particular, the first image area 30 is shown. Furthermore, one can see in the Fig. 9 a medical device 58, which in the illustrated case is the tube 82. Thus, the case is shown in which the user images the glottis 54 using the laryngoscope 42 and guides the tube 82 to the trachea 78. The tube 82 is thus arranged between the camera of the laryngoscope 42 and the object area 14. The image recognition unit 20 is configured to recognize a part of the medical device 58, in particular the tube 82. In particular, the image recognition unit 20 recognizes the Fig. 9 shown part of the tube 82.

[0089] In a section 122 of Figure 18, according to the Fig. 9, the tube is shown in such a way that it covers part of the anatomy, or rather the object area 14. The navigation unit 24 is configured to at least partially hide the detected part of the medical device 58, in particular the tube 82, in the representation 18. This is shown in the Fig. 10. In the representation 18, the navigation unit 24 displays a pseudoreal anatomy, which is generated based on reference images, instead of the at least partially hidden and / or recognized part of the medical device 58, in particular the tube 82. Therefore, the representation 18 includes a representation of the pseudoreal anatomy in the section 122, and the user can view the object area 14 via a display device 16 as if the tube 82 were not arranged between the camera and the object area 14.

[0090] The Fig.11 shows a schematic representation of steps of an imaging method, in particular by means of the medical system 10, 10'.The method comprises the step 62 of imaging the anatomical object region 14, which includes an anatomical landmark 22, and generating image data of the object region 14 by means of the medical imaging instrument 12, the step 64 of generating the representation 18, 18', 18" of the object region 14 for the user, the step 66 of recognizing the anatomical landmark 22 of the object region 14 based on the image data, and the step 68 of generating the navigation aid 26, 26', 26" to assist the user in locating a target structure 28, wherein the navigation aid 26, 26', 26" visually enhances the first image region 30, 30', 30" compared to the second image region 32, 32', 32" in the representation 18, 18', 18", wherein the first image area 30, 30', 30" includes the anatomical landmark 22, and wherein the second image area 32, 32', 32" does not include the anatomical landmark 22. List of reference symbols 10 medical system 12 medical imaging instrument 14 anatomical object area 16 Display device 18 Representation 20 Image recognition unit 22 anatomical milestones 24 Navigation unit 26 Navigation aid 28 Target structure 30 first image area 32 second image area 34 distance 36 Fade-in 38 Sensor technology 40 Marking 42 Laryngoscope 43 spatulas 44 Bronchoscope 45 Handle 46 Mouth opening 48 Tongue 50 Nostrils 52 epiglottis 54 glottis 56 Carina tracheae 58 medical device 60 image acquisition unit 62 steps 64 steps 66 steps 68 steps 70 computing unit 72 shaft 74 distal end section 75 stereo camera 76 Camera 78 Trachea 80 Cloud 82 tube 84 right main bronchi 86 left main bronchi 88 steps 90 steps 92 steps 94 steps 96 steps 98 steps 100 steps 102 steps 104 steps 106 steps 108 steps 110 steps 112 steps 114 steps 116 Calibration 118 Distance determination 120 procedures 122 Excerpt

Claims

[1] Medical system (10) comprising: a medical imaging instrument (12) configured to image an anatomical object region (14) and generate image data of the object region (14); a display device (16) configured to receive the image data and generate a representation (18) of the object area (14) for a user; an image recognition unit (20) configured to recognize anatomical landmarks (22) of the object area (14) based on the image data; and a navigation unit (24) configured to generate a navigation aid (26) to assist the user in locating a target structure (28), wherein the navigation aid (26) comprises a visual enhancement of a first image area (30) compared to a second image area (32) in the representation (18), wherein the first image area (30) comprises an anatomical landmark (22), and wherein the second image area (32) does not comprise the anatomical landmark (22), characterized by that the image recognition unit (20) is configured to recognize a part of a medical device (58); and that the navigation unit (24) is configured to at least partially hide the recognized part of the medical device (58) in the display (18). [2] The medical system (10) of claim 1, wherein the visual enhancement comprises applying a location-dependent image filter to an image of the object region (14). [3] Medical system (10) according to claim 2, wherein the image recognition unit (20) is configured to determine the image filter based on the recognition of the anatomical landmark (22). [4] The medical system (10) of any preceding claim, wherein the visual enhancement comprises a different color representation of the first image area (30) and the second image area (32). [5] The medical system (10) of claim 4, wherein the second image area (32) has a lower color saturation than the first image area (30). [6] The medical system (10) of claim 5, wherein the second image area (32) is displayed in grayscale. [7] Medical system (10) according to one of the preceding claims, wherein the visual enhancement is based on a false color representation. [8] Medical system (10) according to one of the preceding claims, wherein the navigation unit (24) is configured to determine a distance (34) of the imaging instrument (12) to the target structure (28). [9] The medical system (10) of claim 8, wherein the visual enhancement is dependent on the distance (34). [10] Medical system (10) according to claim 8 or 9, wherein the visual enhancement comprises an increase in the brightness of the first image area (30) and / or a decrease in the brightness of the second image area (32) depending on the distance (34). [11] Medical system (10) according to one of claims 8 to 10, wherein the imaging instrument (12) is adapted to generate stereo images, and wherein the navigation unit (24) is configured to determine the distance (34) of the imaging instrument (12) to the target structure (28) based on the stereo images. [12] Medical system (10) according to one of claims 8 to 11, wherein the navigation aid (26) comprises a change in the representation (18) of the object area (14) depending on the distance (34). [13] Medical system (10) according to one of claims 8 to 12, wherein an overlay (36) of distance information based on the distance (34) can be superimposed on the representation (18) of the object region (14). [14] Medical system (10) according to one of the preceding claims, wherein the imaging instrument (12) comprises sensors (38) by means of which a movement of the imaging instrument (12) can be determined. [15] Medical system (10) according to one of claims 8 to 13 and additionally according to claim 14, wherein the navigation unit (24) is configured to determine the distance (34) of the imaging instrument (12) to the target structure (28) based on the image data and the determined movement. [16] Medical system (10) according to one of the preceding claims, wherein the navigation aid (26) comprises, in addition to the visual enhancement, at least one marker (40) which can be superimposed on the representation (18). [17] Medical system (10) according to one of the preceding claims, wherein the target structure (28) can be selected by the user from a plurality of possible target structures. [18] Medical system (10) according to one of the preceding claims, wherein the target structure (28) can be selected by the user from the representation (18) of the object area (14). [19] The medical system (10) of any preceding claim, wherein the imaging instrument (12) is a laryngoscope (42) or a bronchoscope (44). [20] Medical system (10) according to one of the preceding claims, wherein the anatomical landmarks (22) comprise at least one of a mouth opening (46), a tongue (48), a nasal opening (50), an epiglottis (52), the vallecula epiglottica, an arytenoid cartilage (cartilagines arytenoideae), a glottis (54), a tracheal clasp and / or a carina tracheae (56) of a patient. [21] Medical system (10) according to one of the preceding claims, wherein the navigation unit (24) is configured to display a real and / or pseudo-real anatomy in the display (18) instead of the at least partially hidden part of the medical device (58). [22] Medical imaging instrument (12) comprising: an image acquisition unit (60) configured to image an anatomical object region (14) and to generate image data of the object region (14); a display device (16) configured to receive the image data and generate a representation of the object area (14) for a user; an image recognition unit (20) configured to recognize anatomical landmarks (22) of the object area (14) based on the image data; and a navigation unit (24) configured to generate at least one navigation aid (26) to assist the user in locating a target structure (28), wherein the navigation aid (26) comprises a visual enhancement of a first image area (30) compared to a second image area (32) in the representation (18), wherein the first image area (30) comprises an anatomical landmark (22), and wherein the second image area (32) does not comprise the anatomical landmark (22), characterized byin that the image recognition unit (20) is configured to recognize a part of a medical device (58); and wherein the navigation unit (24) is configured to at least partially hide the recognized part of the medical device (58) in the representation (18). [23] Method for imaging by means of a medical system (10) according to one of claims 1 to 21, comprising the steps: imaging an anatomical object region (14) comprising an anatomical landmark (22) and generating image data of the object region (14) by means of a medical imaging instrument (12); Generating a representation (18) of the object area (14) for a user; Detecting the anatomical landmark (22) of the object area (14) based on the image data; Generating a navigation aid (26) to assist the user in locating a target structure (28), wherein the navigation aid (26) comprises visually enhancing a first image region (30) compared to a second image region (32) in the representation (18), wherein the first image region (30) comprises the anatomical waymark (22), and wherein the second image region (32) does not comprise the anatomical waymark (22); detecting a part of the medical device (58); and at least partially hiding the detected part of the medical device (58) in the representation (18).

Images