SYSTEM, APPARATUS AND METHOD FOR GENERATING PLANNING DATASET FOR TISSUE TREATMENT OF A PATIENT'S RETINA - Patent application

Abstract

The invention relates to a system for creating a planning dataset (34, 35, 36, 37) for tissue treatment of a retina (16) of a patient's eye (4) by means of a laser, the system comprising a camera (6, 7) configured to continuously capture images of the retina, an image processing device (19) configured to generate and provide current structured image data of the retina from the images captured by the camera, a personal data acquisition device (21, 22) configured to acquire and / or provide personal data of the patient, and a processing device (20) designed to assign a planning dataset for the tissue treatment to the current structured image data of the retina and to the personal data of the patient, wherein specifications (in particular patterns or rules) for assigning the planning data to the image data and the personal data of the patient are stored in the processing device.

Description

[Technical field]

[0001] The invention is in the field of medical technology and can be used with particular advantage in the field of ophthalmology and in combination with specific ophthalmoscopes. [Background technology]

[0002] In many cases, a laser therapy device is used to treat a patient's retina, which allows for tissue treatment using a laser beam. It is particularly advantageous to use an ophthalmoscope in combination with a laser therapy device to allow for simultaneous and coordinated visualization of the retina during treatment.

[0003] The basic function of an ophthalmoscope is to provide the examiner with an image of the eye or a part of the eye. In particular, it is possible to combine an ophthalmoscope, which provides an image of the retina of the eye, with a device for laser treatment of the retina, for example, if the same optical imaging device is used at least to some extent for guiding the laser beam and for visualizing the retina. In this case, the beam paths for imaging and for laser treatment may, for example, be branched by a beam splitter device in one part of their length and may pass together through the same optical element in another part. This makes it possible to observe the retina at the same time as the laser treatment, which would be much more difficult if separate imaging devices were used for observation and treatment, simply for reasons of space.

[0004] The ophthalmoscope disclosed in European Patent Application No. 1875857A1 has imaging optics and an illumination device, and an optical sensor capable of capturing an image of the retina of the eye. Such an ophthalmoscope may also be used by physicians to plan laser treatments. Summary of the Invention [Problem to be solved by the invention]

[0005] SUMMARY OF THE DISCLOSURE Against the background of the prior art, the present invention is founded on the problem of facilitating the creation of treatment plans for retinal tissue treatment with a laser device and of systematically standardizing and improving the planning data. [Means for solving the problem]

[0006] According to the invention, this object is solved by a system having the features of claim 1. The dependent claims present advantageous implementations of such a system. For the solution of the problem, the invention also relates to an apparatus and a method for creating a planning data set, which are described together with advantageous embodiments in the further patent claims.

[0007] Thus, the present invention relates to a system for generating a planning data set for a laser tissue treatment of a retina of an eye of a patient, the system comprising: a camera configured to continuously capture images of the retina; an image processing device configured to generate and provide retinal current structured image data from an image captured by the camera; a personal data capture device configured to capture and / or provide personal data of a patient; - a processing device configured to assign a planning data set for tissue treatment to current structured image data of the retina and to personal patient data, wherein specifications (e.g. patterns and rules) for assigning the planning data to the image data and to the personal patient data are stored in the processing device; has.

[0008] Furthermore, it may be advantageous for the system to have a correction device, sometimes called a correction device, that allows manual correction of the planning data set, which may be performed by a person skilled in the art during or especially after the creation of the planning data set, based on his experience or additional information.

[0009] The system according to the invention is configured to support the creation of a treatment plan, which is created in the form of a plan file or plan data before the start of the treatment of the patient's retina. A prerequisite for this is that the system has a camera or (generally) an imaging system configured to continuously capture images of the retina. Such a camera may be designed as an optical color camera, an infrared camera or a black and white camera or as a scanning system or may have various filter options, allowing the acquisition of a current image of the retina before and / or during the generation of the planning data. This may be important, for example, to be able to compare the currently acquired status and positioning of the retina in the system with other acquired or currently determined retinal data. In the context of the present invention, structured graphical data or structured image data is to be understood as pure pixel data and any preparation of data derived from these or from pixel data (in particular so-called vector oriented image data). For example, the location and size of blood vessels, the location of the optic nerve, and the location, size and type of drusen (so-called soft drusen, hard drusen, and reticular pseudodrusen (RPD)) may be provided as structured image data and taken into account when creating the planning dataset.

[0010] For example, if personal data of the patient are used, this may be in the form of a diagnosis or an indication, or in the form of images of the patient's retina already acquired by the system itself or by another imaging device, and these may be compared with the currently recorded images in the system. Personal data may also be data from previous treatments performed on the patient, or data relating to the treatment status. In principle, personal data may be all patient data that are already available in written or electronically (particularly digitally) stored form before the start of the treatment or before the start of the creation of the planning data set. These may be transmitted to the system via an electronic interface or may be entered manually. Personal data may for example be available in electronic form in a more comprehensive system, in which the system for creating the planning data set according to the invention is a subsystem or subsystems.

[0011] The advantages of a camera for capturing real images of the retina emerge when the system for generating the planning data is also combined with a treatment device having a treatment laser that is adjusted relative to or aligned with the camera to perform treatment using the planning data. Structuring the planning data will be described in more detail below.

[0012] Further, an image processing device may be provided, which generates retinal structured image data from the currently captured image data of the camera and makes it available for planning. The structured image data is data that includes or represents, for example, specific objects recognized in the image by image processing, or even properties of the image of the retina, or properties of image regions or image parts of the retina. For example, the structured image data may represent the brightness or color distribution, the intensity distribution on the infrared image, the position, shape, and / or gradient of objects or object boundaries. The representation of such structures in the form of data may be diverse and may include, for example, pure image data, but also vector representations, vectors, matrices, or other types of abstract representations. For example, the structured data must represent the shape, position, and possibly other parameters of retinal vessels, ganglia, and common anomalies in an unambiguous form (e.g. vector-oriented or with metadata regarding geometric shapes).

[0013] The location of currently recognized objects on the retina (e.g., blood vessels, optic nerves, or drusen) can and should be taken into account when creating a treatment plan and generating the corresponding planning data.

[0014] To what extent such currently acquired structured image data is taken into account may depend, inter alia, on the patient's personal data, where as mentioned above, personal data means data relating to the patient that already exists and is available when applying the system to the patient.

[0015] The system may have some elements of the system available locally when a patient is being treated, while other elements may be located elsewhere or may be difficult to localize. For example, the imaging or processing device that generates the planning data, or parts of this device (e.g. storage device), may be located at a different location than the treatment laser. The data processing device may be located, for example, in a computer or data processing system that is larger than the device available at the laser treatment site. If the processing device needs to access a large amount of stored data, both the processing device and the storage device may be distributed across several computers or may be located in a large central computer system. In order to make as much data as possible available and accessible to the system, for example when interpreting the individual data of a single patient or when training a learning system, it may be useful to store the treatment data of many patients in the form of a database, either centrally or in a distributed computer system.

[0016] The individual elements or modules of the system, such as the personal data acquisition device, the measurement data acquisition device, or the correction device for manual correction of the planning data, or the device for inputting data representative of the success of the treatment, may be installed, for example, as an application on a mobile device, and in order to realize the integration of the system, the transmission of the input data to the mobile device and the data format of the output from the mobile device to the fixed part of the system (which also includes the camera and / or the processing device) are performed via an interface where both the data format and the data transmission path (for example a hardware connection, a data bus, or a wireless interface) are clearly defined.

[0017] One embodiment of such a system enables, for example, one of a number of predefined patient categories to be assigned to a patient based on the personal data and / or currently acquired data, and the specifications (e.g., patterns and rules) of the processing device (20) for assigning planning data to the currently acquired data and personal data to be determined or influenced by the respectively assigned patient category.

[0018] The patient category assigned to each patient may, for example, depend on stored personal data (e.g., age, some of the patient's physiological parameters (e.g., weight), type and intensity of skin pigmentation, hair color, iris pigmentation, medical history, and type, intensity, and success of previous treatments performed) and / or on currently measured or acquired data (e.g., retinal structured image data, or the patient's currently acquired physiological data and / or parameters (which may be measured in or on the eye, or may be independent of ocular parameters (e.g., the patient's age, eye color, hair color, skin color, intensity of skin pigmentation, body size, and current health condition)).

[0019] In one embodiment, for example, only two patient categories may be provided, determined by one acquired parameter, for example whether the patient is under 50 or over 50, or whether the patient is light-skinned or dark-skinned. However, more than two, for example three, more than three, more than five or even more than ten categories may be provided, each of which assignment to a patient also depends on more than one parameter, for example at least two or at least three parameters.

[0020] In some cases, a predefined planning data set may be assigned to an individual patient depending on the patient category assigned to that patient. In other cases, the planning data set may also be individually created using the stored specifications (e.g., patterns and rules), but the patterns and rules used may depend on the assigned patient category. This can reduce the complexity of the specifications.

[0021] Also, depending on the patient category assigned to the patient, it is conceivable that some categories of planning data (e.g., laser parameters, or target values ​​of measurement data, e.g., target data representing the current maximum allowable temperature of the retina at the treatment site during treatment) may be restricted such that only a subset of possible parameters are available in the planning data set, which often simplifies and speeds up the creation of the planning data set after a particular patient category has been assigned to an individual patient.

[0022] On the one hand, it is conceivable to create some patient categories for patients who are identified as problematic and thus require special planning (e.g. particularly careful or small planning) or to exclude or disable the automatic or semi-automatic creation of planning data sets, in which case the assigned patient category may imply a completely expert-based treatment plan.

[0023] For example, a patient category into which patients with highly pigmented skin and / or highly pigmented retinas and / or dark iris color are classified may be linked to a rule that a certain laser power density must not be exceeded.

[0024] Some patient categories related to existing conditions may be linked to a condition that a certain retinal temperature must not be exceeded, which is monitored, for example, by obtaining certain measurement data during the treatment. Alternatively, the target data corresponding to the desired temperature of the retina at the treatment site during the treatment may be selected depending on the patient category, which is determined by a pre-existing condition or previous treatment. Similarly, the selection of the position data for the laser treatment and the selection of the position data of the ranges excluded from the laser treatment may also be performed depending on the patient category.

[0025] A further advantageous embodiment of such a system may realise that the personal data acquisition device is configured to acquire and provide diagnostic data, and / or adaptation data, and / or data of previous treatments performed, and / or known physiological data of the patient, and / or existing images of the patient's retina stored external to the system.

[0026] Such personal data may, for example, be in the form of an electronic file or may be entered manually or may be loaded in the form of an indication already providing information on the diagnosis results, for example in text or image format, or on a recommended treatment. Such information may already contain data differentiating several locations or areas of the retina and may vary depending on the respective location on the retina (for example the exact location of the site or area to be treated). However, such information may be location independent and may be indicative of the patient's general condition, his / her eye or other characteristics (for example physiological data). Such data may be in the form of old images of the retina of various types (for example color, black and white, infrared, fluorescent or tomographic images) or may be in the form of age information, the patient's skin color or sex, the patient's identity or information on previous treatments that may have been performed with or without the involvement of the system according to the invention.

[0027] Furthermore, in one embodiment, such a system may be designed such that a measurement data acquisition device is provided, comprising one or more sensor devices for acquiring and providing physiological data of the patient (in particular data that varies depending on the respective location on the retina and / or data that is independent of the location on the retina), and such that the processing device is configured to take into account the acquired physiological data of the patient when allocating the planning data.

[0028] Such a measurement data acquisition device can basically be any type of device that allows the current acquisition of additional information about the patient and his / her physiological data. It includes a sensor device, such as a camera, that records other characteristics than the camera mentioned at the beginning (for example using a different imaging process) or records the retina using a similar or identical imaging process as the camera mentioned at the beginning. The images of the retina captured by such a camera then provide different data depending on the respective location of the retina. For example, the sensor device can be used to measure the temperature or the temperature distribution on the retina. The images of the retina can also be used to use algorithms that detect, for example, retinal diseases, which can be taken into account when creating the planning data. A device for creating OCT images or a reflectance measurement device can be provided. A camera (specifically the same camera, also arranged to continuously capture images of the retina) can also capture the reactions of the retina to titration shots (i.e. experimental applications of the therapeutic laser) in order to be able to plan and control the laser parameters based on these reactions, or at least to be taken into account when generating the planning data. Sensor devices that measure other physiological characteristics of the patient are also contemplated (e.g., skin color and / or brightness, skin thickness, hair color, iris color and / or color distribution, blood pressure, various blood values, etc.) These sensor devices may include, for example, cameras or optical sensors.

[0029] A particular implementation of the system may, for example, allow the above-mentioned measurement data acquisition device to continue to operate to acquire data even after the planning data for the laser treatment has been initially generated, and possibly even after the planning data has been manually corrected during the actual laser treatment. For example, such a measurement device may continuously acquire the temperature of the retina or the temperature distribution on the retina, even during the treatment or between treatments. The measurement data thus acquired may make it necessary or advantageous to modify the planning data. Thus, the system may be required to generate a further corrected planning file based on the measurement data determined after the planning data set was initially created, and to use this as the basis for further treatments.

[0030] The system may also be further formed by a display module or device that effects a graphical representation of the planning data set in, for example, the image of the retina currently captured by the camera. In this way, the planning data may be visualized together with the graphical representation of the image of the retina, thereby making it possible to immediately assess, for example, structured image data considerations, for example by visualizing whether a particular sensitive area of ​​the retina (e.g., blood vessels or ganglia) is excluded from treatment, or whether a particular area already visualized in the current image and classified as requiring treatment has been properly taken into account in the treatment plan.

[0031] Furthermore, if a treatment device is integrated into the system and if the current camera image is synchronized with the steering of the treatment laser, the planning data set may also be directly synchronized with the steering.

[0032] The system may also be further enhanced by a tracking device that allows the display of the planning data set to track when the image currently captured by the camera moves (e.g., shifts or rotates). Such image shifts may occur, for example, when the patient moves relative to the camera or when the eye moves, and the tracking device ensures that the display of the planning data continues to correspond to the currently displayed camera image. If a treatment device is incorporated into the system, such tracking may also allow the steering device of the treatment laser to remain aligned as planned.

[0033] Furthermore, in a system of the aforementioned type, the processing device may have a memory device, which may be configured to store the patient's personal data and the planning data set assigned thereto, and in particular additionally to store physiological data acquired by the measurement data acquisition device in association with said data, and / or to store manual corrections made to the planning data set.

[0034] This allows the system to compare the assignment of the current planning data set to the patient's personal data with previous assignments to similar or different personal data. This can be used, for example, to perform a plausibility analysis. If in previous cases planning changes have been made manually at a later date, these can also be taken into account, for example, during planning. Furthermore, if the acquired physiological data are also stored, this can also be taken into account when adjusting the created planning file in comparison with the previous plan. The system according to the invention can therefore be designed as an expert system or as a learning system.

[0035] Furthermore, in such a system, the processing device may have a memory device, which may be configured to store the patient's personal data, as well as the structured image data and / or images of the patient's retina generated by the system and the planning datasets assigned thereto (specifically, in particular, the target values ​​of the measurement data), and in particular additionally to store physiological data acquired by the measurement data acquisition device in association with the aforementioned data, and / or to store manual corrections made to the planning dataset.

[0036] This embodiment of the system allows the assignment of the current planning data set to the patient's personal data and structured image data to be compared with previous assignments to similar or different personal data and structured image data that are also stored. A plausibility analysis with this data may also be performed. If in previous cases planning changes have been made manually at a later date, these can also be taken into account, for example, during planning. Furthermore, if already acquired physiological data are also stored in the expert system created in this way, this can also be taken into account when adjusting the created planning file compared to previous plans.

[0037] A further development of the system is, for example, realised by an examination device that acquires and provides data on the effectiveness of treatment after retinal treatment.

[0038] The treatment of the retina may include a laser treatment, but may also include additional treatment steps with or without a laser. This check may be performed during the treatment or immediately after the completion of the treatment, in particular also after a minimum certain time from the treatment. The examination device may include a device for performing an imaging process (for example, also using a camera, as mentioned at the beginning, that captures a current image of the retina). The examination device may also include an input device for manual input of data. It may be intended that only binary information such as "treatment successful" or "treatment unsuccessful" is obtained, or an assessment by the patient may be intended, such as "painful? yes / no", or further assessments may be intended, such as for example which of the parameters of the treatment (for example laser parameters, selected geometric treatment pattern, areas intended for treatment or areas excluded from treatment) were suboptimal in the opinion of the assessor. For this purpose, a specific category of assessment (for example evaluation formula) may be specified. Such assessments may also be included in the expert system described above, may be stored together with the stored planning data set, and may be taken into account when comparing the current planning data with the stored planning data.

[0039] The planning data set generated by the system may include one, two, three, four or five of the following categories of planning data in the implementation of the system: laser parameters, position data for laser treatment, treatment pattern, position data of areas excluded from laser treatment, and target values ​​of measurements acquired by a measurement acquisition device or other means during the subsequent treatment. Such target values ​​may be, for example, average target temperatures or target temperatures that vary with location on the retina, which are continuously acquired during the laser treatment, and which, for example, should reach or maintain these target temperatures or should not exceed these target temperatures. And other treatment parameters may be dynamically adjusted during the treatment to reach or not exceed the specified target values. For example, parameters of rules are so specified in the planning data set. Furthermore, a treatment reporting template may also be generated as a further category of planning data, i.e., a form for the selection and presentation of data and parameters to be reported may be generated.

[0040] The invention can furthermore advantageously be realized in that the processing device is designed as a self-learning device, in which an assignment function which assigns planning data to personal data, and in particular to structured image data and in particular to the measured physiological data of the patient, is trained in that, as planning data and as training data for each patient, at least data from at least one of the following categories, namely personal data, structured image data, measured physiological data, on the one hand, and, on the other hand, the assigned planning data (in particular target values ​​of the measurement data) and manual changes to the planning data, and in particular data regarding the effect of the treatment, obtained after the planned treatment data has been implemented, are specified.

[0041] The planning data set generated by the system may include planning data in one, two, three, four, or five of the following categories: laser parameters, position data for laser treatment, treatment pattern, position data of areas excluded from laser treatment, and target values ​​of measurement data. The laser parameters may include, for example, laser power, wavelength, pulse duration, pulse repetition rate, and total number of laser pulses, as well as the size of the light spot of the laser on the retina, and even each or all possible subcombinations of these parameters. These laser parameters may depend on the location or area on the retina. The position data of the laser treatment may include one or more geometric areas on the retina. The areas of the retina excluded from treatment may also include one or more geometric areas of the retina. The treatment patterns may include geometric patterns (e.g., circles, ellipses, rectangles, triangles, or any free shape) within which the laser treatment is performed with constant laser parameters (i.e., for example, any laser parameters remain the same). These treatment patterns may be areas that are individually treated (i.e., irradiated) by the treatment laser after an initiation impulse from the physician. A treatment pattern may also simply include a geometric area that the laser will process at once (e.g., point by point according to a point pattern), without requiring the doctor to control each individual point. Only one starting point can be controlled manually or automatically, and the rest of the treatment pattern thereafter can be automatically controlled by the laser control system. The density of the points to be addressed can also be one of the parameters in the "treatment pattern" category. The planning data may be a target value of the measurement data acquired during treatment (e.g., a temperature to be reached or not exceeded on the retina during treatment), which may be specified as an overall average value or may vary depending on the location, and is continuously acquired / measured during treatment. The treatment system is then controlled to reach the target value.

[0042] Continuously detectable optical variables (eg, changes in reflectance, color / spectral changes, or changes in luminance of each treatment area detected by a camera or hyperspectral sensor) may also be specified as target values.

[0043] Each of the above-mentioned categories of planning data (more precisely, the data in each of the above-mentioned categories) may be manually modified by a human (specifically, an individual operator) if required by the above-mentioned limitations, who may compare the planning data generated by the system in a first attempt with the image data currently captured by the camera, or the structured data, and with the operator's experience, and modify it according to the operator's assessment.

[0044] Areas excluded from treatment can play a special role here. In many cases they can be considered complementary to the position data for the laser treatment, but in many cases it is less error-prone to specify areas of the retina excluded from treatment than to specify the position data for the treatment. This is especially true, for example, when only a few areas are excluded and the rest of the retina is treated uniformly. Furthermore, excluded areas can be very relevant for safety, since they also include areas where the laser treatment can be harmful to health. It can therefore be possible to define areas excluded from treatment according to planning data generated by the system, for example, so that they cannot be changed manually or that some obstacle must be overcome or authorization must be proved in order to change them.

[0045] The system may be designed as a self-learning system, which uses the above-mentioned data provided to it to continually improve the allocation algorithm that generates the planning data. The system may have a neural network that is trained, or it may have analytical, statistical, or parametric learning algorithms for static guided learning or self-learning. The allocation algorithm may also have analytical elements that cannot be changed by the learning process and are defined by expert knowledge (e.g., certain conditions that the laser parameters must meet (e.g., power limits) or regulations to be followed regarding treatment site exclusions).

[0046] With the expansion and increase of available treatment data, a learning process based on the available treatment data can be periodically performed, for example, by ordering and weighting the elements of the learning process. For example, data based on the success of the treatment determined by the monitoring device after the laser treatment can be given a higher weight than manual corrections of the planning data made by the therapist. It is also possible, for example, to impose conditions to be met before the treatment data is made available to the learning system or learning algorithm. For example, one such condition can be that manual changes of certain parameters (e.g. laser parameters) must be made in a certain minimum number of cases, within a specified range, by a minimum number of therapists, or at a minimum number of treatment locations, in order for these changes to be provided to the learning system as training data.

[0047] In addition to a system of the above type, the invention also relates to an apparatus for generating a planning data set for the treatment of tissue of the retina of an eye by means of a laser beam, said apparatus comprising: a camera configured to continuously capture images of the retina; an image processor for generating and providing current structured image data of the retina from an image captured by the camera; a personal data capture device configured to capture and / or provide personal data of a patient; a processing device configured to assign a planning data set to the current structured image data of the retina and the patient's personal data for tissue treatment, wherein specifications (e.g. patterns and rules) for assigning the planning data to the structured image data and the patient's personal data are stored in the processing device; The device may also advantageously comprise a correction device allowing manual correction of the planning data set.

[0048] In addition to the system and device, the device also relates to a method for generating a planning data set for tissue treatment of a retina of an eye of a patient with a laser beam, the method comprising: capturing at least one image of the retina with a camera; generating and providing current structured image data of the retina from an image captured by the camera using an image processor; acquiring and / or providing, as part of a personal data acquisition device, personal data of a patient; - by the processing device, allocating the planning data set to the current structured image data of the retina and to the known individual data of the patient based on specifications (e.g. patterns and rules) stored in the processing device; Includes.

[0049] The method may, for example, be advantageously designed such that the assigned planning data set may be manually changed after assignment.

[0050] Furthermore, the method may be advantageously implemented in that physiological data of the patient is acquired and provided (in particular by a measurement data acquisition device) and taken into account in the allocation of the planning data set by the processing device. The physiological data may be acquired and entered by a human being, in particular physiological data relating to easily recognizable characteristics of the patient (e.g. hair or iris color).

[0051] The method may be advantageously realized in that the processing device is designed as a self-learning device and the assignment function which assigns planning data to personal data and structured image data, and in particular to the patient's physiological data measured by the measurement data acquisition device, is trained in that personal data, structured image data, assigned planning data, data of manual changes to the planning data, and in particular the patient's measured physiological data are assigned to it with respect to a number of patients or acquired physiological data and / or data regarding the effect of the treatment acquired after the planned treatment has been implemented.

[0052] As a first step, one of a number of predefined patient categories may be assigned to the patient based on the personal data and / or currently acquired data, and the specifications (specifically patterns and rules) of the processing device for assigning planned data to the currently acquired data and personal data may be determined or influenced by the respectively assigned patient category.

[0053] Similar to the above-described system, the method may be designed to generate planning data in one, two, three, four, or five of the following categories as a planning data set: laser parameters, position data for laser treatment, treatment pattern, position data of areas excluded from laser treatment, and target value categories of measurement data.

[0054] Thus far, various types, appearances and forms of representation of individual types of planning data have been described in detail.

[0055] The present invention may further relate to a method of operating a system and / or device of the above-mentioned type, in which a planning data set is created and then a treatment is performed by a treatment laser in a separate treatment device or in a treatment device integrated into the system or device in accordance with the planning data set.

[0056] The success of the treatment may then be assessed (e.g., using a monitoring device) and data representative of that success may be fed into the system in digital form, thereby enabling the system to learn.

[0057] The invention is illustrated and explained below by means of exemplary embodiments in the drawings, in which: [Brief description of the drawings]

[0058] [Figure 1]1 shows the basic elements of the device according to the invention as well as a system comprising a camera integrated in the ophthalmoscope and combined with a treatment laser, an image processing device, a processing device generating planning data, and some further data acquisition and input devices. [Diagram 2] 1 shows an overview of a system for creating a planning data set. [Diagram 3] 1 shows an overview of a system for creating a planning data set using a learning algorithm. [Figure 4] 2 shows an exemplary flow chart of a method according to the present invention; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0059] FIG. 1 shows at least part of an apparatus and system according to the invention by means of a schematic ophthalmoscope 1 which may be used in this system for implementing the method according to the invention and which combines the functions of a camera ophthalmoscope and of a retinal laser treatment.

[0060] The apparatus comprises an illumination device 5 with a radiation source 5', which is arranged to direct an illumination beam 14 towards the patient's eye 4 and retina 16, whereby the retina 16 can be suitably illuminated so that an image or camera image can be captured. The illumination device may comprise, for example, a light emitting diode or an infrared diode as a light source, or may comprise different types of light sources providing the desired wavelength spectrum. The light source may be, for example, a UV light source.

[0061] The ophthalmoscope also comprises a camera 6 with an image sensor 7. This sensor may be, for example, a CCD sensor. Instead of the camera 6, any other type of device (for example a scanning device) suitable for detecting radiation reaching the sensor from the retina and generating an image of the retina may be provided. The purpose of operating the illumination device 5 and the camera 6 (or equivalent device) is to obtain the most accurate possible spatially resolved measurement data from the retina 16 by capturing images of the reflected radiation, thereby allowing to obtain or identify characteristics of the entire retina or of the target area to be treated from the data obtained.

[0062] The illumination beam 14 and the reflected radiation 15 are suitably collimated or focused, in a manner known per se, by a suitable optical system 13 with mirrors and lenses. The optical system 13 also comprises a beam splitter 12, which makes it possible to direct the laser beam 11 from the treatment laser 2 onto the retina 16. Instead of using a beam splitter, separate beams of the treatment laser and the illumination and / or image acquisition may also be guided parallel to each other at a certain distance.

[0063] A control unit 8 may be provided for controlling the laser 2, which on the one hand controls (e.g. triggers) the illumination device 5 and on the other hand directly controls the laser 2 based on the camera image from the camera 6. The control unit 8 may also control the deflection mirror 3, which directs the beam path of the treatment beam 11 in such a way that individual target sites on the retina 16 can be treated. In the system according to the invention, an image processing device 19 is also provided, which allows digital processing of the images / camera images from the camera 6 and calculates structured data from the image data. The image data may be present, for example, in pixel data format and the structured data may be provided, for example, in vector graphic format or another structured format. The image data and / or the structured image data may also be made available to the control unit 8. The image processing device 19 also provides data to a display device 17, which has a screen 18, on which, for example, an image of the retina is displayed. In the display device 17, in addition to the image data of the camera 6 and / or the structured image data of the image processing device 19, the planning data may also be processed and displayed together with the image data in numerical or graphical format. For example, treatment sites may be marked and / or treatment patterns or laser parameters may be displayed on the current image data (i.e. a live view of the retina). A tracking device is also provided in the display device or connected to the display device, which moves the elements of the planning data assigned to the image data together when the camera image moves, i.e. when the structures displayed in the camera image move.

[0064] FIG. 1 also shows a processing device 20 as part of the device and system, which generates a planning file or planning data for the laser treatment, using at least the personal data in the personal data memory 21 or the personal data of the patient to be treated entered via the first input device 22, and the structured camera images. Furthermore, the processing device may use measurement data from the measurement data acquisition device 23, as well as correction or modification data that the operator may enter via the second input device 24 after the first planning data has been generated. The measurement data acquisition device 23 may for example include or be connected to a sensor 23b (such as a color sensor), a camera 23a for objectively detecting the color of the patient's skin or hair, or a camera directed at the iris of the eye to be treated to detect the iris color. The measurement data acquisition device may also use a camera 6 for measurements, which may be directed at the iris (for example), or which may be used to record data other than retinal image data. This data acquisition may for example be directly controlled by the measurement data acquisition device 23 or mediated by the image processing device 19.

[0065] The processing device may transmit the planning data by means of an image processing device 19 or directly to a display device / display module 17, where the planning data may be displayed together with the current image of the retina on a screen 18. Some of the planning data may be displayed numerically, but at least some of it may also be displayed graphically directly within the image of the retina.

[0066] After the laser treatment, the success of the treatment may be assessed and reported to the processing device 20 by a success controller / monitor 25, which may, among other things, receive a current image of the retina 16 from the camera 6. The processing device 20 has a learning algorithm or self-learning device, which uses the training data to improve the allocation algorithm that maps the planning data to the output data.

[0067] According to the state of the art, the type and intensity of the laser treatment, i.e. the intensity and / or duration of the laser pulse, as well as its temporal and local distribution, have been determined up until now by the physician following his own assessment after evaluating the retinal images, often by first directing titrating pulses to the retina, assessing their effect and then adjusting the laser intensity.

[0068] The largely autonomous and automated allocation of planning data to personal and image data, and possibly other data, according to the present invention enables planning data to be assigned to each target site on the retina in an objectified, transparent, and understandable manner without the use of titration shots, and the planning data may include various categories of data, such as laser parameters, locations or areas to be treated, locations or areas to be excluded from treatment, and treatment patterns.

[0069] 2 shows a system according to the invention, comprising an image acquisition device 26 of the retina and an image processing device 27, which supplies structured image data 28 to the processing device 20. The structured data may for example comprise data on the recognized objects (e.g. ganglia, blood vessels and recognized pathological tissue sites) as well as on the color and color intensity of the retina and other graphically recognizable properties (e.g. contrast, brightness and color distribution) and other comparable data. The color intensity and brightness values ​​may for example be used to identify the pigmentation intensity of the retina, which may be decisive for absorbing laser light of a certain wavelength and therefore for the laser intensity required for treatment. In the context of the present invention, structured graphical data is to be understood to mean pure pixel data and any preparation of data derived from these.

[0070] In Fig. 2, 29 indicates the patient's personal data provided to the processing device 20. This may be provided by electronic transfer of data or by manual input. Potentially, the processing device 20 may be supplied with measurement data from a sensor system or a measurement data acquisition device, indicated in Fig. 2 by 30. This data may be data that varies depending on the location on the retina (for example the latest measured temperature distribution on the retina) or data obtained from OCT (Optical Coherence Tomography) that may indicate (for example) retinal edema, or measurements of retinal color and / or brightness. However, they may also be other measured or estimated variables that do not depend on the location on the retina (for example the color of the patient's skin, hair or iris), which may be measured or estimated manually and input.

[0071] The processing device 20 includes an element 33 in the form of an allocation device, which contains patterns and rules for the allocation of planning data to input data (current or structured image data, personal data, sensor detection data). In the illustrated example, the allocation device outputs planning data in the following categories: laser parameters 34, position data for the treatment 35, treatment pattern for the treatment 36 and data of positions excluded for the treatment 37.

[0072] Once the planning data has been output and, if necessary, graphically displayed, the operator can manually modify one, some or all categories of planning data using elements 31 from the input device. The modified planning data is then typically used as the basis for the laser treatment, which then finally forms planning data 38 for the laser treatment, which may also be displayed in a graphical representation 39 (e.g. together with a current image of the retina). The system shown in Fig. 2 thus works statically, provided that the patterns and rules of the allocation device 33, stored in the processing device 20, are sufficiently good and valid. Such patterns and rules may, for example, be made available as part of an expert system and may be periodically updated.

[0073] In the system shown in FIG. 3, the patterns and rules according to which the allocation unit 33 allocates or generates planning data are continually corrected and / or refined in the processing unit 20 as part of a learning algorithm.

[0074] For example, the planning data for a treatment, which is the result of manual corrections 31 to the planning data originally planned by the system, is fed back to a learning device 44 as part of a feedback loop 42, which may analyze the changes to the initial planning data and determine whether these or similar corrective inputs are made more frequently, only once or infrequently. The learning device modifies the stored patterns and rules, taking into account some learning specifications, for example weighting of some corrections based on some criteria (frequency, causes of some corrections, diversity of correction causes for similar corrections, etc.), at least trendwise (repeatedly if necessary) until no further manual corrections are made under a given situation, or until for example the frequency of corrections in different directions is statistically equal.

[0075] In accordance with the corrected planning data 38 and its graphical representation 39, a retinal tissue treatment 40 is performed on the patient.

[0076] After the treatment 40, monitoring 41 of the success of the treatment is performed, for example, by or with the assistance of a monitoring device. This success control may include new images of the retina (for example in the form of newly acquired image data), but in principle may include any type of data collection by the doctor and / or the patient. For example, the doctor and / or the patient may answer standard questions, and these answers may be entered in the form of data and passed to the processing device as an implementation of the feedback loop 43.

[0077] The data determined by monitoring allows for ultimate success control on a case-by-case basis and may also be used to improve the allocation algorithms or patterns and rules of the allocation device 33 as part of a learning process controlled by the learning device 44.

[0078] The processing device 20 may be located locally at the laser treatment site or may be designed as a central device, located away from the other elements shown in Figures 2 and 3, and performing data processing and determination of planning data sets for multiple treatment situations with the treatment laser. If the processing device is set up as a learning device, it receives a large amount of training data in the course of working with multiple treatment sites, so that the planning data allocation algorithm can be rapidly improved.

[0079] Input or transfer of personal data may generally occur at the laser treatment site or may occur non-locally (e.g., at a central office or in a distributed computer system). Similarly, corrective input (as well as monitoring) from a physician or other specialist may occur on-site in close proximity to the patient at the treatment facility, or may occur remotely at a control center or via a distributed computer system, if done without direct collection of retinal measurement data.

[0080] FIG. 4 illustrates an exemplary flow chart of a method for creating a planning file for laser treatment of the retina of an eye according to the present invention.

[0081] In a first step 45, all known data, i.e. the patient's personal data (e.g. the diagnosis, the treatment indications and (if necessary) the treatment status (if a previous treatment has already been performed)) as well as other known physiological data, are retrieved and imported into the system. This can be done by transferring the data in electronic form or by manual input. In a second step 46, a camera or other imaging device creates a current image of the patient's retina, i.e. a data representation of the data that varies depending on the location on the retina. This data is processed in a third step 42 so that structures and / or objects are recognized and the data is converted into structured data. In a next fourth step 48, a planning data set for the retinal treatment is created, taking into account the personal data and the structured image data, using existing stored templates in the form of patterns and rules. The planning data may also already contain templates for reporting on the specifications, implementation and (if necessary) the success of the treatment. The planning data is then corrected by the doctor in a next step 49, if necessary. In one embodiment of the method, the corrected planning data may be sent in step 50 to a training process 54, which influences process 48 to generate planning data according to existing patterns and rules, and for this purpose collects and evaluates experience data within training management 53 and, if necessary, releases it as training data and further weights it.

[0082] Treatment of the retina according to the applicable planning data, not shown in Figure 4 itself, is followed by monitoring 51 in the form of evaluation or acquisition of success, which may be performed automatically or manually based on measurement data and / or human assessment. In a further step 52, the performance evaluation may be introduced into a training process 54 in order to improve the planning data generation process 48.

[0083] By using the process according to the invention it is possible to continuously improve the method of generating planning files / planning data for retinal laser treatment.

[0084] Using such an improved automated system, it is possible to plan a variety of known treatments in a reliable, straightforward, objective manner and with little effort.

Claims

1. 1. A system for generating a planning dataset (34, 35, 36, 37) for tissue treatment of a retina (16) of an eye (4) of a patient with a laser (2), comprising: a camera (6, 7) configured to continuously acquire images of the retina; an image processor (19) configured to generate and provide current structured image data of the retina from images captured by the camera; a personal data acquisition device (21, 22) configured to acquire and / or provide personal data of a patient; - a processing device (20) configured to assign a planning data set for the tissue treatment to the current structured image data of the retina and to the personal data of the patient, wherein specifications (e.g. patterns and rules) for the assignment of planning data to the image data and the personal data of the patient are stored in the processing device; A system including:

2. 2. The system of claim 1, characterized in that one of a plurality of predefined patient categories is assigned to a patient based on personal data and / or currently acquired data, and the specifications (particularly patterns and rules) of the processing device (20) for assigning planning data to currently acquired data and personal data are determined or influenced by the respectively assigned patient category.

3. 3. The method according to claim 1, wherein the personal data acquisition device (21, 22) is adapted to acquire and provide diagnostic data and / or adaptation data and / or data of previous treatments performed and / or known physiological data of the patient and / or existing images of the patient's retina (16) stored outside the system. The system described in

4. The system according to any one of claims 1, 2 or 3, characterized in that a measurement data acquisition device (23) is provided, which has one or more sensor devices for acquiring and providing physiological data of the patient (in particular data that varies depending on the respective location on the retina and / or data that is independent of the location on the retina), the processing device is configured to take into account the acquired physiological data of the patient when assigning planning data, and / or the system has a correction device (24) for enabling manual correction of the planning data set.

5. The system according to claim 1, 2, 3 or 4, characterized by a display module (17, 18) which brings about a graphical representation of a planning dataset in the image of the retina (16) currently captured by the cameras (6, 7).

6. 6. The system according to claim 5, characterized by a tracking device for causing the display of the planning data set to follow the image currently captured by the camera (6, 7) when it is moved.

7. 7. The system according to claim 1, wherein the processing device (20) comprises a storage device (33) adapted to store personal data of the patient and a planning data set assigned thereto, and in particular to additionally store physiological data acquired by the measurement data acquisition device (23) in association with said data, and / or to store manual corrections made to the planning data set.

8. 7. The system according to claim 1, wherein the processing device (20) comprises a storage device (33) adapted to store personal data of a patient as well as structured image data and / or images of the patient's retina (16) generated by the system and a planning data set (34, 35, 36, 37) assigned thereto, and in particular additionally to store physiological data acquired by a measurement data acquisition device (23) in each case associated with said data and / or to store manual corrections made to the planning data set.

9. The system according to any one of claims 1 to 8, characterized by an examination device (25) for obtaining and providing data on the effectiveness of a treatment on the retina (16) after the treatment has been administered.

10. The processing device (20) is characterized in that it is configured as a self-learning device in which the assignment function, which assigns planning data (34, 35, 36, 37) (in particular target values ​​of measurement data in particular) to the personal data and in particular to the structured image data and in particular to the measured physiological data of a patient, in each case of a patient, at least on the one hand, to the following categories: Personal Data Structured Image Data Physiological data measured The system according to any one of claims 1 to 8, wherein the system is trained by designating as training data data from one of the above categories, on the other hand, assigned planning data (in particular target values ​​of measurement data in particular) and manual changes to the planning data, and in particular data relating to the effect of the treatment, obtained after the planned treatment data has been implemented.

11. The system according to any one of claims 1 to 10, characterized in that the planning data set (34, 35, 36, 37) comprises planning data of one, two, three, four or five of the following categories: laser parameters (34), position data for the laser treatment (35), treatment pattern (36), position data of areas excluded from the laser treatment (37) and categories of target values ​​of measurement data.

12. 1. An apparatus for generating a planning data set (34, 35, 36, 37) for tissue treatment of a retina (16) of an eye (4) by a laser beam (11), comprising: a camera (6, 7) configured to continuously acquire images of the retina (16); an image processor (19) for generating and providing current structured image data of the retina from the images captured by the cameras (6, 7); a personal data acquisition device (21, 22) configured to acquire and / or provide personal data of a patient; a processing device (20) configured to assign a planning data set (34, 35, 36, 37) to the current structured image data of the retina and to the patient's personal data, wherein specifications (in particular patterns and rules) for the assignment of planning data to the structured image data and to the patient's personal data are stored in the processing device; a correction device (22) allowing manual correction of the planning data set; An apparatus comprising:

13. 13. Apparatus according to claim 12, characterized by a correction device (22) allowing manual correction of the planning data set.

14. 1. A method for generating a planning data set (34, 35, 36, 37) for tissue treatment of a retina (16) of an eye (4) of a patient by a laser beam (11), comprising: capturing at least one image of said retina with a camera (6, 7); generating and providing current structured image data of the retina from images captured by the camera using an image processor (19); - acquiring and / or providing personal data of a patient as part of a personal data acquisition device (21, 22); - allocating, by a processing device (20), a planning data set to the current structured image data of the retina and to the known individual data of the patient based on specifications (e.g. patterns and rules) stored in the processing device (20); The method includes:

15. 15. The method according to claim 14, characterized in that after said allocation, the allocated planning data sets (34, 35, 36, 37) are manually changed.

16. 16. The method according to claim 14 or 15, characterized in that physiological data of the patient are provided, in particular acquired by a measurement data acquisition device (23), and are taken into account in the allocation of planning data sets (34, 35, 36, 37) by the processing device (20).

17. 17. The method according to claim 14, wherein the processing device (20) is designed as a self-learning device and the assignment function, which assigns planning data to the personal data and to the structured image data, and in particular to the measured physiological data of patients, has been trained therefor by specifying the personal data, the structured image data, the assigned planning data (34, 35, 36, 37), data relating to the manual corrections to the planning data and, in particular, measured or acquired physiological data and / or data relating to the effect of the treatment, acquired after the respective planned treatment data has been implemented for each of a plurality of patients.

18. 18. The method according to claim 14, characterized in that planning data of one, two, three, four or five of the following categories are determined as the planning data set (34, 35, 36, 37): laser parameters (34), position data for the laser treatment (35), treatment pattern (35), position data for areas excluded from the laser treatment (36) and target values ​​of the measurement data.

19. A method of operating a system according to any one of claims 1 to 11 and / or an apparatus according to claim 12 or 13, characterized in that a planning data set is created and a treatment according to said planning data set is carried out using a treatment laser in a separate treatment device or in a treatment device integrated in said system or said apparatus.

Images