System, apparatus and method for creating planning datasets for treating the tissue of a patient's retina

Abstract

The invention relates to a system for creating planning datasets (34, 35, 36, 37) for treating the tissue of the retina (16) of a patient's eye (4) by means of a laser (2), having: a camera (6, 7), which is designed to capture images of the retina continuously; an image-processing device (19), which is designed to generate and make available current structured image data of the retina from images captured by the camera; a personal data collection device (21, 22), which is designed to collect and / or make available a patient's personal data; and a processing device (20), which is designed to assign planning datasets for the tissue treatment 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 image data and patients' personal data are stored in the processing device.

Description

[0001] System, device and method for creating planning data sets for tissue treatment of a patient's retina

[0002] The invention lies in the field of medical technology and can be used particularly advantageously in the field of ophthalmology and in conjunction with certain ophthalmoscopes.

[0003] Laser treatment devices are often used to treat a patient's retina, allowing tissue treatment using a laser beam. The combined use of an ophthalmoscope and a laser treatment device is particularly advantageous, allowing simultaneous and coordinated visualization of the retina, even during treatment.

[0004] The basic function of an ophthalmoscope is to provide an examining person with an image of an eye or parts of an eye. In particular, an ophthalmoscope that provides an image of the retina of an eye can be combined with a device for laser treatment of the retina if, for example, the same optical imaging device is used at least partially to guide the laser beam as for visualizing the retina. In this case, the beam paths for imaging and laser treatment can be branched, for example by beam splitters, over part of their length and run together through the same optical elements over another part. This enables observation of the retina at the same time as the laser treatment, which would be significantly more difficult with separate imaging devices for observation and treatment, if only for space reasons.

[0005] European patent application EP 1 875 857 A1 discloses an ophthalmoscope with imaging optics, an illumination device, and an optical sensor for capturing images of the retina of an eye. Such an ophthalmoscope can also be used by a surgeon to plan laser treatment.

[0006] Against the background of the prior art, the present invention is based on the object of facilitating the creation of treatment plans for the tissue treatment of a retina using a laser device and of systematically standardizing and improving the planning data.

[0007] The object is achieved according to the invention by a system having the features of patent claim 1. The subclaims present advantageous implementations of such a system. Furthermore, the invention relates to a device and a method for creating planning data sets, which, together with advantageous embodiments, are set out in further patent claims. Accordingly, the invention relates to a system for creating planning data sets for the tissue treatment of the retina of a patient's eye using a laser,

[0008] - with a camera designed to continuously capture images of the retina,

[0009] - with an image processing device which is designed to generate and provide current structured image data of the retina from images captured by the camera,

[0010] - with an inventory data acquisition device which is designed to acquire and / or provide inventory data of a patient, and with a processing device which is designed to assign planning data sets for tissue treatment to the current structured image data of the retina and the inventory data of the patient, wherein specifications, in particular patterns and rules, for the assignment of planning data to image data and inventory data of patients are stored in the processing device.

[0011] Furthermore, it can advantageously be provided that the system has a change facility, which can also be referred to as a correction facility, which enables the manual modification of a planning data set. Such manual changes can be made during or, especially, after the creation of a planning data set by an expert based on their experience or additional knowledge.

[0012] The system according to the invention is designed to assist in the creation of a treatment plan, which is created in the form of a planning file or planning data, before the start of treatment of a patient's retina. A prerequisite for this is that the system has a camera or, more generally, an imaging system that is designed to continuously capture images of the retina. Such a camera can be designed as an optical color, infrared, or black-and-white camera, or as a scanning system, or can also have various filter options, and enables the capture of current images of the retina before and / or during planning data generation. This can be important, for example, in order to be able to compare other captured or currently determined retinal data with the currently captured state and positioning of the retina in the system.In the context of the present invention, structured graphic or image data refers to all processing of pure pixel data and the data derived from these or from the pixel data, in particular so-called vector-oriented image data. For example, the position and size of blood vessels, the position of the optic nerve, and the position, size, and type of drusen, namely soft drusen, hard drusen, and reticular pseudodrusen (RPD), can be provided as structured image data and taken into account when creating planning data sets.

[0013] If, for example, existing patient data is used, this may be in the form of a diagnosis or indication, or from images of the patient's retina previously taken by the system itself or by another imaging device. These images should then be able to be compared with a current image in the system. Existing data can also be data from a previous treatment performed on the patient or data on a treatment status. In principle, existing data can be all patient data already available in written or electronic, particularly digital, form before the start of treatment or before the start of creation of the planning data record. This data can be transmitted to the system via electronic interfaces or entered manually.The inventory data may, for example, be present in electronic form in a more comprehensive system, of which the system according to the invention for creating planning data sets represents a subsystem or subsystem.

[0014] One advantage of a camera that captures current images of the retina arises when the system for creating planning data is also combined with a treatment device that has a treatment laser that is adjusted or synchronized relative to the camera in order to carry out the treatment using the planning data. The structuring of the planning data is explained in detail below. Furthermore, an image processing device is provided that generates structured image data of the retina from the currently captured image data from the camera and makes this available for planning. Structured image data includes, for example, data that contains or represents certain objects recognized in the images by image processing, or properties of the image or the retina, or properties of image areas or parts of the retina.For example, the structured image data can describe brightness or color distributions, intensity distributions on an infrared image, the position, shape, and / or progression of objects or object boundaries. The representation of such structures in the form of data can be diverse and can include, for example, pure image data, but also vector representations, vectors, matrices, or other types of abstracted representations. For example, the structured data should describe the shape, position, and possibly other parameters of blood vessels, nerve nodes, and general anomalies on the retina in a clear format, for example, vector-oriented or with metadata related to geometric shapes.

[0015] The position of objects currently detected on the retina, such as blood vessels, the optic nerve or drusen, can and should be taken into account when preparing a treatment plan and generating corresponding planning data.

[0016] The extent to which such currently acquired structured image data is taken into account may depend, among other things, on the patient's existing data. As explained above, existing data refers to data relating to the patient that is already present and available when the system is applied to the patient.

[0017] The system may be designed so that certain elements of the system are present locally at the patient treatment site, while other elements are located elsewhere or are difficult to locate. For example, the image processing device or the processing device for generating planning data, or parts of this device, such as storage devices, may be located elsewhere than the treatment laser. Data processing devices may, for example, be located in larger computers or data processing systems than are available at the laser treatment site. If the processing devices need access to a large amount of stored data, both the processing devices and storage devices can be distributed across multiple computers or located in a larger, central computer system.For example, it may be useful to store treatment data from many patients in the form of a database centrally or in a distributed computer system in order to have as much data as possible available that is accessible to the system when interpreting individual data from a single patient or for training a learning device of the system.

[0018] Individual parts or modules of the system, such as the inventory data acquisition device, a measurement data acquisition device, a modification device for manually correcting planning data, or even a device for entering data describing treatment success, can also be installed as an application on a mobile device, for example. The data formats for transmitting input data to the mobile device and output from the mobile device to a stationary part of the system, which also contains the camera and / or the processing device, are then handled via interfaces where both the data formats and the data transmission paths, such as hardware connections, data bus, or radio interface, are clearly defined to create an integrated system.

[0019] An embodiment of such a system can, for example, provide that a patient is assigned one of several predefined patient categories on the basis of inventory data and / or currently recorded data and that specifications of the processing device (20), in particular patterns and rules, for the assignment of planning data to currently recorded data and inventory data are determined or influenced by the respectively assigned patient category.

[0020] The patient category assigned to each patient can, for example, depend on stored inventory data such as age, certain physiological parameters of the patient such as weight, type and intensity of skin pigmentation, hair color, iris pigmentation, medical history and the type, intensity and success of previous treatments and / or on currently measured or recorded data such as structured image data of the retina or currently recorded physiological data and / or parameters of the patient which can either be measured in or on the eye or can be independent of parameters of the eye such as, for example, the patient’s age, eye color, hair color, skin color, intensity of skin pigmentation, body type and current state of health.

[0021] In one embodiment, for example, only two patient categories may be provided, each determined by a single recorded parameter, for example, patients younger than 50 years or older, or light-skinned and dark-skinned patients. However, more than two, for example, three, more than three, more than five, or even more than ten categories may be provided, the respective assignment of which to a patient also depends on more than one parameter, for example, at least two or at least three parameters.

[0022] Depending on the patient category assigned to the individual patient, pre-defined planning data sets can be assigned in some cases. In other cases, the planning data sets can still be created individually using stored specifications, particularly templates and rules, but the patterns and rules used can depend on the assigned patient category. This allows the specifications to be designed less complex.

[0023] It is also conceivable to limit certain categories of planning data, such as laser parameters or target values ​​for measurement data (e.g., the target data representing the currently maximum permissible retinal temperature at the treatment site during treatment), depending on the patient category assigned to each patient, so that only a subset of possible parameters is available for the planning data sets. This simplifies and accelerates the creation of a planning data set in many cases after assigning a specific patient category to an individual patient.

[0024] However, it is also conceivable to create specific patient categories for patients identified as problem categories that require special planning, such as particularly careful or detailed planning, or that preclude or make impossible the automatic or semi-automatic creation of a planning dataset. In this case, an assigned patient category could also refer to fully expert-based treatment planning.

[0025] For example, a patient category that includes patients with highly pigmented skin and / or highly pigmented retina and / or a dark iris color could be linked to the rule that certain laser power densities must not be exceeded.

[0026] For example, certain patient categories related to pre-existing conditions can be linked to the condition that certain retinal temperatures, monitored by recording specific measurement data during treatment, must not be exceeded. Alternatively, the target data corresponding to the desired retinal temperature at the treatment site during treatment could be selected depending on the patient category, which is determined by pre-existing conditions or previous treatments. Likewise, the selection of location data for laser treatment and the selection of location data for areas excluded from laser treatment can also depend on the patient category.

[0027] A further advantageous embodiment of such a system can provide that the inventory data acquisition device is configured to acquire and provide diagnostic data and / or indication data and / or data from a previous treatment performed and / or previously known physiological data of the patient and / or already existing images of the patient's retina stored outside the system. Such inventory data can, for example, be in the form of an electronic file, can be manually entered or read in, for example a diagnosis in text or image form or an indication that already provides information on a recommended treatment. Such information can already contain data that differentiates certain locations or areas of the retina and is location-dependent on the respective location on the retina, such as the precise location of areas or areas to be treated.Such information can also be location-independent and describe the patient's general condition, their eyes, or other characteristics, such as the patient's physiological data. Such data can be in the form of various types of older retinal images, such as color images, black-and-white images, infrared images, fluorescence images, or tomography images, or can consist of information about the patient's age, skin color, or gender, the patient's identity, or information about previous treatments that may have taken place with or without the integration of the system according to the invention.

[0028] Furthermore, in one embodiment, such a system can be designed such that a measurement data acquisition device is provided which has one or more sensor devices for acquiring and providing physiological data of the patient, in particular data which depend on the respective location on the retina and / or data which does not depend on a location on the retina, and that the processing device is configured to take the acquired physiological data of the patient into account when assigning planning data.

[0029] Such measurement data acquisition devices can, in principle, be any type of device that enables the current acquisition of additional information about the patient and their physiological data. These include sensor devices such as cameras that record different properties than the camera mentioned above, for example, using different imaging techniques or similar or the same imaging technique as the camera mentioned above for recording the retina. Images of the retina captured with such cameras then provide data that depends on the respective location of the retina. For example, a sensor device can measure the temperature or temperature distribution on the retina. Using retinal images, for example, and using algorithms, a retinal disease can also be detected, which can be taken into account for the creation of planning data.A device for creating an OCT image or a device for reflectometry can also be provided. Using a camera, particularly the same camera configured to continuously capture images of the retina, retinal reactions to titration shots, i.e., trial applications of the treatment laser, can also be recorded in order to plan and control the laser parameters based on these reactions, or at least to take these reactions into account when generating planning data. Sensor devices that measure other physiological characteristics of the patient are also conceivable, such as skin color and / or brightness, skin thickness, hair color, color and / or color distribution of the iris, blood pressure, various blood values, or the like. These sensor devices can also comprise, for example, a camera or optical sensors.

[0030] A special implementation of the system can, for example, also provide that the above-mentioned measurement data acquisition devices continue to be operated to acquire data even after an initial generation of planning data for a laser treatment and, if necessary, even after a manual correction of planning data, even during the actual laser treatment. For example, the temperature of the retina or temperature distribution on the retina can be continuously recorded by such a measuring device even during the treatment or during treatment breaks. The measurement data obtained in this way may require or make advantageous a change to the planning data. Therefore, it can be provided that, based on the measurement data determined after the initial creation of a planning data set, the system generates a further, corrected planning file and uses this as the basis for further treatment.

[0031] The system can also be further developed, for example, by a display module or a display device that graphically displays a planning data set within a retinal image currently captured by the camera. In this way, the planning data can be visualized together with a graphical representation of a retinal image, allowing, for example, immediate assessment of the consideration of the structured image data by revealing whether, for example, certain sensitive areas of the retina, such as blood vessels or nerve nodes, are excluded from treatment or whether certain areas already visible in the current image and classified as requiring treatment are adequately considered in the treatment plan.

[0032] In addition, if a treatment device is integrated into the system and if the current camera image is compared with the guidance device for a treatment laser, the planning data set can also be compared directly with the guidance device.

[0033] The system can also be further developed with a tracking device that adjusts the display of the planning data set in the event of a movement, in particular a shift or rotation of the image currently captured by the camera. Such a shift in the image can occur, for example, when the patient moves relative to the camera or when the eye moves, and in such a case, the tracking device ensures that the display of the planning data continues to match the current camera image displayed. If a treatment device is integrated into the system, such tracking can also ensure that the steering device for a treatment laser remains aligned as planned.

[0034] In addition, in a system of the type mentioned, it can be provided that the processing device has a storage device which is set up to store inventory data of patients and planning data sets associated with them, and in particular additionally to store physiological data associated with the aforementioned data and recorded by a measurement data recording device and / or to store manual changes made to the planning data sets.

[0035] This enables the system to compare the assignment of a current planning data set to a patient's existing data with previous assignments for similar or different existing data. This allows, for example, a plausibility analysis to be performed. If planning changes were made manually in previous cases, these can also be taken into account and, for example, anticipated during the planning process. Furthermore, if recorded physiological data is also stored, this can also be considered when comparing and, if necessary, reconciling the planning file to be created with previous plans. Accordingly, the system according to the invention can be designed as an expert system or as a learning system.

[0036] Furthermore, in such a system, it can be provided that the processing device has a storage device which is set up to store patient inventory data as well as structured image data generated with the system and / or recordings of the patient's retina and planning data sets associated with these, in particular, among other things, target values ​​for measurement data, and in particular additionally to store physiological data associated with the aforementioned data and recorded by a measurement data recording device and / or to store manual changes made to the planning data sets.

[0037] This embodiment of the system makes it possible to compare the assignment of a current planning data set to a patient's existing data and the structured image data with previous assignments for similar or different existing data, as well as similarly stored structured image data. A plausibility analysis can also be performed with this data. If planning changes were made manually in previous cases, these can also be taken into account and, for example, anticipated during planning. Furthermore, if recorded physiological data is also stored in the expert system created in this way, these can also be considered when comparing and, if necessary, reconciling the planning file to be created with previous plans.

[0038] A further development of the system can be provided, for example, by a verification device, also called a monitoring device, which records and provides data on the effects of the treatment after a retinal treatment has been carried out.

[0039] The treatment of the retina can include laser treatment, but can also include additional treatment steps with or without the use of a laser. The review can be carried out immediately during the treatment or after completion of the treatment, in particular a certain minimum time after the treatment. The review device can comprise a device for performing an imaging procedure, for example, using the camera mentioned above to capture current images of the retina. The review device can also comprise an input device for manually entering data. Provision can be made for only binary information such as "treatment successful" or "treatment unsuccessful" to be recorded, or for a patient assessment, such as "I have pain, yes / no," or for a more detailed assessment, for example, which treatment parameters, such asThe laser parameters, selected geometric treatment patterns, and areas intended for or excluded from treatment were suboptimal in the opinion of an assessor. Certain assessment categories may be predefined for this purpose, such as an evaluation scheme. Such an evaluation can also be incorporated into the expert systems described above, saved together with the stored planning data sets, and taken into account when comparing current planning data with stored planning data.

[0040] The planning data sets generated by the system can, in one implementation of the system, contain planning data from one, two, three, four, or five of the following categories: laser parameters, location data for the laser treatment, treatment patterns, location data for areas excluded from laser treatment, and target values ​​for measured values ​​recorded during a subsequent treatment by the measured value recording device or otherwise. Such target values ​​can, for example, be an average or location-dependent target temperature on the retina, which is continuously recorded during the laser treatment and which, for example, should be reached, maintained, or not exceeded. The remaining treatment parameters can then be dynamically adjusted during the treatment so that the specified target values ​​are reached or not exceeded.For example, parameters for a control system are specified in the planning data sets. Furthermore, as a further category of planning data, report templates can also be generated for the treatment, such as forms and the selection and presentation of the data and parameters to be reported.

[0041] The invention can be further advantageously implemented in that the processing device is designed as a self-learning device in which the assignment function, which assigns planning data to the inventory data and in particular to the structured image data and in particular to measured physiological data of a patient, is trained in that, for each patient, on the one hand, at least data from at least one of the following categories: inventory data, structured image data, measured physiological data, and on the other hand, assigned planning data, in particular, inter alia, target values ​​for measurement data, as well as manual changes to planning data and in particular data on an effect of the treatment recorded after the planned treatment has been carried out, are specified as training data.

[0042] The planning data sets generated by the system can contain planning data from one, two, three, four, or five of the following categories: laser parameters, location data for laser treatment, treatment pattern, location data for areas excluded from laser treatment, and target values ​​for measurement data. The laser parameters can include, for example, the laser power, wavelength, pulse duration, pulse repetition rate, the total number of laser pulses, and the size of the laser spot on the retina, as well as any one of these parameters or any conceivable subcombinations. These laser parameters can each depend on the location or area on the retina. The location data for the laser treatment can include one or more geometric areas on the retina. The areas of the retina excluded from treatment can also include one or more geometric areas of the retina.The treatment patterns can comprise geometric patterns such as circles, ellipses, rectangles, triangles, or any other free-form shapes in which the laser treatment is to take place, for example, with constant laser parameters or in which one of the laser parameters remains the same. These treatment patterns can also be areas that are independently processed, i.e. irradiated, by the treatment laser after a start pulse from the surgeon. The treatment patterns can also simply comprise geometric regions that the laser processes in one go, for example, point by point following a point pattern, without the surgeon having to control each individual point. Only a starting point can be controlled manually or automatically, and the rest of a treatment pattern can then be carried out automatically under the control of the laser control system.The density of the target points can also be one of the parameters in the "treatment patterns" category. Planning data can also include target values ​​for measurement data collected during treatment, such as a temperature on the retina that must be reached or not exceeded during treatment. This temperature can be specified as an overall average or location-dependent and is continuously recorded / measured during treatment. The treatment system is then controlled to ensure that the target values ​​are maintained.

[0043] Continuously detectable optical quantities, such as a change in reflection, discoloration / spectral change or brightness change of the treated areas recorded by a camera or a hyperspectral sensor, can also be specified as target values.

[0044] Each of these planning data categories, or more precisely, the data of each of the aforementioned categories, can be manually modified by a person, particularly by the respective surgeon, possibly subject to the restrictions outlined above. The surgeon can compare the planning data generated by the system in the initial attempt with the image data currently captured by the camera or the structured data, as well as with his or her empirical values, and modify them according to his or her assessment.

[0045] The areas to be excluded from treatment can play a special role in this. Although in many cases they can be conceptually derived as a complement to the location data for the laser treatment, in many cases it is less error-prone to specify the areas of the retina to be excluded from treatment than the location data for the treatment, particularly if the retina is to be treated uniformly except for a few excluded areas. In addition, the excluded areas can be very safety-relevant, as they also include areas in which laser treatment could cause health damage. It can therefore also be planned, for example, to specify the areas to be excluded from treatment according to the planning data generated by the system in such a way that they cannot be changed manually, or that certain obstacles must be overcome or authorization must be proven to change them.

[0046] The system can be designed as a self-learning system that continuously improves the allocation algorithm that generates planning data based on the data provided to it. The system can comprise a trained neural network, an analytical, statistical, or parametric learning algorithm, or be static, guided learning, or self-learning. The allocation algorithm can also comprise analytical elements that cannot be changed by the learning process and are specified with expert knowledge, such as certain conditions that the laser parameters must meet, such as power limitations or regulations that must be followed for the exclusion of treatment sites.

[0047] For the learning process based on the available treatment data, which can be carried out regularly as the available treatment data expands and increases, the elements of the learning process can be ordered and weighted, for example. For example, the data based on the treatment successes determined with the monitoring device after laser treatment can be given a higher weighting than the manual corrections to planning data made by the treating staff. Conditions can also be introduced that must be met for treatment data to be made available to the learning system or learning algorithm.For example, such a condition may be that certain manual parameter changes, such as the laser parameters, must have been made within a specified range in a certain minimum number of cases or by a minimum number of treating persons or at a minimum number of treatment locations in order for these changes to be provided to the learning system as training data.

[0048] In addition to a system of the type described above, the invention also relates to a device for creating planning data sets for the tissue treatment of the retina of an eye by means of a laser beam,

[0049] - with a camera designed to continuously capture images of the retina,

[0050] - with an image processing device that generates and provides current structured image data of the retina from images captured by the camera,

[0051] - with an inventory data acquisition device configured to acquire and / or provide inventory data of a patient, and with a processing device configured to assign planning data sets to the current structured image data of the retina and the patient's inventory data, wherein specifications, in particular patterns and rules, for assigning planning data to structured image data and patient inventory data are stored in the processing device. The device can advantageously additionally have a modification device that enables the manual modification of a planning data set.

[0052] In addition to a system and a device, the invention also relates to a method for creating planning data sets for the tissue treatment of the retina of a patient’s eye by means of a laser beam,

[0053] - in which at least one image of the retina is captured by a camera, - in which current structured image data of the retina are generated and provided from images captured by the camera using an image processing device,

[0054] - in which patient data is recorded and / or provided within the framework of a patient data recording facility,

[0055] - and in which a processing device assigns planning data sets to the current structured image data of the retina and the previously known patient data on the basis of specifications, in particular patterns and rules, which are stored in the processing device.

[0056] The method can, for example, be advantageously designed in that assigned planning data records are manually changed after the assignment.

[0057] Furthermore, the method can be advantageously implemented by recording and providing the patient's physiological data, particularly with a measurement data acquisition device, and taking this data into account when assigning planning data sets by the processing device. The physiological data can also be recorded and entered by a person, especially if it concerns easily recognizable characteristics of the patient, such as hair or iris color.

[0058] The method can also be advantageously implemented in that the processing device is designed as a self-learning device and the assignment function, which assigns planning data to the inventory data and the structured image data and in particular to the physiological data of a patient measured by a measurement data acquisition device, is trained in that the inventory data, structured image data, assigned planning data, data of the manual planning data changes and in particular measured or recorded physiological data and / or data on the effect of the treatment recorded after implementation of the respective planned treatment are specified to it for a plurality of patients.In a first step, it can be provided that a patient is assigned to one of several predefined patient categories on the basis of inventory data and / or currently recorded data and that specifications of the processing device, in particular patterns and rules, for the assignment of planning data to currently recorded data and inventory data are determined or influenced by the respective assigned patient category.

[0059] The method can be designed, as in the system described above, in such a way that planning data from one, two, three, four or five of the following categories are generated as planning data sets: laser parameters, location data for laser treatment, treatment patterns, location data for areas excluded from laser treatment, target values ​​for measurement data.

[0060] The different types, appearances and forms of presentation of the individual types of planning data have already been described in detail above.

[0061] The invention may also relate to a method for operating a system and / or a device of the type described above, in which a planning data set is created and then a treatment according to the planning data set is carried out in a separate treatment device or a treatment device integrated into the system or device by means of a treatment laser.

[0062] Afterwards, for example, the success of the treatment can be assessed using a monitoring device and data representing the success can be fed into the system in digital form to enable the system to learn.

[0063] The invention is shown and explained below using exemplary embodiments in figures.

[0064] Fig. 1 essential parts of the device according to the invention and the system with a camera integrated into an ophthalmoscope and combined with a treatment laser, an image processing device, a processing device for generating planning data and some further data acquisition and input devices,

[0065] Fig. 2 schematically shows a system for creating planning data sets,

[0066] Fig. 3 schematically shows a system for creating planning data sets with a learning algorithm, as well as

[0067] Fig. 4 shows an exemplary flow diagram for the method according to the invention.

[0068] Figure 1 shows at least partially a device and a system according to the invention with a schematic ophthalmoscope 1 which can be used in the system for carrying out the method according to the invention and which combines the functions of an ophthalmoscope with a camera with functions of laser treatment of the retina.

[0069] The device comprises an illumination device 5 with a radiation source 5', which is configured to direct an illumination beam 14 onto the eye 4 and the retina 16 of a patient. This allows the retina 16 to be suitably illuminated for capturing a recording or a camera image. The illumination can be equipped, for example, with a light-emitting diode or an infrared diode as the light source, or with a light source of another type that provides a desired wavelength spectrum. The light source can also be a UV light source, for example.

[0070] The ophthalmoscope also has a camera 6, in which an image sensor is designated by 7. The sensor can, for example, be a CCD sensor. Instead of the camera 6, any other type of device can be provided, which, for example, is suitable as a scanning device for detecting radiation that reaches a sensor from the retina and generating an image of the retina. The goal when operating the illumination device 5 and the camera 6 or an equivalent device is to obtain the most accurate, spatially resolved measurement data possible from the retina 16 by capturing an image of reflected radiation and thus to capture the properties of the entire retina or of target areas to be treated or to be able to determine them from captured data.

[0071] The illumination beam 14 and the reflected radiation 15 are collimated and focused in a conventional manner by a suitable optical system 13 comprising mirrors and lenses. The optical system 13 also includes a beam splitter 12, which allows a laser beam 11 from the treatment laser 2 to be directed onto the retina 16. Instead of a beam splitter, different beams from the treatment laser and the illumination and / or image capture can also be guided parallel to each other at a certain distance.

[0072] To control the laser 2, a control unit 8 can be provided, which on the one hand controls the illumination device 5, for example triggers it, and on the other hand directly controls the laser 2 based on a camera image from the camera 6. The control unit 8 can also control deflecting mirrors 3, which direct the beam path of the treatment beam 11 and thus enable the targeted treatment of individual target areas on the retina 16. The system according to the invention also provides an image processing device 19, which allows digital processing of recordings / camera images from the camera 6 and determines structured data from the image data, which is present, for example, in the form of pixel data. This structured data can be provided, for example, in the form of a vector graphic or in another structured form. The image data and / or structured image data can also be made available to the control unit 8.The image processing device 19 also provides the data for the display device 17, which has a screen 18 on which, for example, an image of the retina is displayed. In addition to the image data from the camera 6 and / or structured image data from the image processing device 19, planning data can also be processed in the display device 17 and displayed together with the image data in numerical or graphical form. Thus, for example, treatment areas can be marked and / or treatment patterns or laser parameters can be displayed in the current image data, i.e., in a live view of the retina. A tracking device is also provided in the display device or connected thereto, which, in the event of movement of the camera image, i.e., movement of structures displayed in the camera image, shifts the elements of the planning data associated with the image data.

[0073] Figure 1 also shows, as part of the device and system, the processing device 20, which generates planning files or planning data for the laser treatment and, for this purpose, uses at least inventory data from an inventory data memory 21 or inventory data of the patient to be treated entered via a first input device 22, as well as structured camera images. In addition, the processing device can use measurement data from a measurement data acquisition device 23, as well as correction data or change data that can be entered by a surgeon via the second input device 24 after the initial planning data creation. The measurement data device 23 can, for example, comprise sensors 23b such as color sensors, a camera 23a for objectively detecting the patient's skin or hair color, or a camera directed at the iris of the eye to be treated for detecting the iris color, or can be connected to such sensors.The measurement data acquisition device can also use camera 6 for measurements, for example, by directing it at the iris or by using this camera to record data other than the image data of the retina. This data acquisition can, for example, be controlled directly by the measurement data acquisition device 23 or mediated by the image processing device 19.

[0074] The processing device can send planning data via the image processing device 19 or directly to the display device / display module 17, where the planning data can be displayed together with current images of the retina on a screen 18. The planning data can be displayed partially numerically, but at least partially they can also be directly represented graphically in an image of the retina. After the laser treatment, the success of the treatment can be assessed and reported to the processing device 20 using a success control device / monitoring device 25, which can receive, among other things, current images of the retina 16 from the camera 6. The processing device 20 has a learning algorithm or a self-learning device that improves the assignment algorithm for assigning planning data to initial data using training data.

[0075] According to the state of the art, the type and intensity of laser treatment—that is, the strength and / or duration, as well as the temporal and spatial distribution of the laser pulses—was previously determined by the surgeon based on his or her own judgment after evaluating a retinal image. Often, titration pulses were first directed at the retina and their effect assessed to scale the laser strength.

[0076] The largely independent, automated assignment of planning data to inventory data and image data and, if necessary, further data according to the invention makes it possible to assign planning data to each target area on the retina in an objective, transparent and comprehensible manner, if necessary even without titration shots, whereby the planning data can include various categories of data, such as laser parameters, treatment locations or areas, locations or areas excluded from treatment and treatment patterns.

[0077] Figure 2 shows a system according to the invention with an image capture 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 can contain, for example, detected objects such as nerve nodes, blood vessels, and detected diseased tissue areas, as well as data on the color and color intensity of the retina and other graphically recognizable properties, such as contrast, brightness and color distributions, and other comparable data. Using color intensity and brightness values, for example, the pigmentation intensity of the retina can be determined, which can be decisive for the absorption of laser light of certain wavelengths and thus decisive for the necessary laser intensity for a treatment.In the context of the present invention, structured graphic data is understood to mean all processing of pure pixel data and data derived from these.

[0078] In the figure, 29 denotes inventory data of the respective patient, which is provided to the processing device 20. This can be done by electronic transmission of data or by manual input. Potentially, measurement data from a sensor or measurement data acquisition device can also be supplied to the processing device 20, which is denoted by 30 in Figure 2. This data can be retinal-location-dependent data, such as a currently measured temperature distribution on the retina, or data obtained from OCT (optical coherence tomography), which can indicate, for example, edema, or color and / or brightness measurements of the retina. However, they can also be other measured or estimated variables that are independent of a retinal location, such as the patient's skin, hair, or iris color, which can each be measured or estimated and entered manually.

[0079] The processing device 20 contains an element 33 in the form of an assignment device which contains patterns and rules for the assignment of planning data to input data (current image data or structured image data, inventory data, sensor-captured data).

[0080] In the example shown, the allocation device outputs planning data of the categories laser parameters 34, location data 35 for the treatment, treatment patterns 36 for the treatment and data of the locations excluded from the treatment 37.

[0081] After the planning data has been output and, if necessary, graphically displayed, a surgeon can manually change the planning data for one, some, or all categories using an input device via element 31. The changed planning data then typically forms the basis for the laser treatment. The changed planning data then definitively forms the planning data 38 for the laser treatment, which can also be displayed in the graphic display 39, for example, together with current images of the retina. The system illustrated in Figure 2 can thus function statically if the patterns and rules of the allocation device 33 stored in the processing device 20 are sufficiently good and valid. Such patterns and rules can, for example, be made available within the framework of an expert system and can also be updated regularly.

[0082] Figure 3 shows a system in which the patterns and rules according to which the allocation device 33 carries out the allocation or generation of planning data are continuously corrected and / or improved in the processing device 20 within the framework of a learning algorithm.

[0083] For this purpose, for example, the treatment planning data resulting from manual corrections 31 to the planning data originally planned by the system are fed back to a learning device 44 within the framework of a feedback loop 42. This learning device analyzes the changes to the original planning data and can also determine whether these or similar correction entries occur more frequently, only once, or rarely. Taking into account certain learning specifications, such as the weighting of certain corrections according to certain criteria (frequency, sources for certain corrections, diversity of correction sources for similar corrections, etc.), the learning device changes the stored patterns and rules, at least in terms of tendency, if necessary repeatedly, until no more manual corrections occur in a given scenario or, for example, corrections statistically point in different directions with equal frequency.

[0084] According to the corrected planning data 38 and their graphic representation 39, a tissue treatment 40 of the retina is carried out on the patient.

[0085] After the treatment 40, a success check is performed as part of a monitoring 41, for example, by or with the aid of a monitoring device. This success check can include a new image of the retina, for example in the form of newly acquired image data, but in principle can include any type of data collection by the surgeon and / or the patient. For example, the surgeon and / or the patient can answer standard questions, and the answers can be entered in the form of data and forwarded to the processing device as an implementation of the feedback loop 43.

[0086] The data obtained by monitoring enables a final success check for each individual case and can also be used to improve the assignment algorithm or the patterns and rules of the assignment device 33 within the framework of a learning process controlled by the learning device 44.

[0087] The processing device 20 can be located locally at the laser treatment site or configured as a central device located remotely from the other elements shown in Figures 2 and 3. It performs data processing and determines planning data sets for a plurality of treatment stations with treatment lasers. When collaborating with a large number of treatment stations, the processing device, if configured as a learning device, receives a large amount of training data, allowing the allocation algorithm for the planning data to be rapidly improved.

[0088] The entry or transmission of inventory data can generally take place at the laser treatment site or remotely, for example, at a central location or in a distributed computer system. Likewise, correction inputs from a surgeon or other expert, as well as monitoring (if performed without directly collecting retinal measurement data), can be performed on-site at the treatment facility in the immediate vicinity of the patient, or remotely at a central location or via a distributed computer system.

[0089] Figure 4 shows an exemplary flowchart for a method according to the invention for creating a planning file for a laser treatment of the retina of an eye. TI

[0090] In a first step 45, all previously known data, i.e., the patient's existing data, such as a diagnosis, a treatment indication, and, if applicable, a treatment status if previous treatments have already taken place, and other known physiological data are retrieved and imported into the system. This can be done, among other things, by data transport in electronic form or by manual entry. In a second step 46, a current image of the patient's retina is created using a camera or other imaging device, i.e., a data representation of location-dependent retinal data. This data is processed in a third step 42 such that structures and / or objects are recognized, and the data is converted into structured data.In the next, fourth step 48, a planning data set for a retinal treatment is created, taking into account the existing data and the structured image data, using existing, stored templates in the form of patterns and rules. The planning data may also already contain a template for a report on the specifications and implementation and, if applicable, the success of the treatment. The planning data is then corrected by a surgeon in a subsequent step 49, if necessary. In one embodiment of the method, the corrected planning data can be sent to a training process 54 in a step 50, which influences the process 48 for generating planning data according to the existing patterns and rules and, for this purpose, collects, evaluates, and, if applicable, releases and weights empirical data within the training management 53 as training data.

[0091] Following a treatment of the retina (not shown in Figure 4 itself) according to the applicable planning data, monitoring 51 is performed in the form of a success assessment or success recording, which can be automated or manual based on measurement data and / or a person's assessment. In a further step 52, the success assessment can be incorporated into the training process 54 in order to improve the planning data generation process 48. The process according to the invention allows the method for generating planning files / planning data for laser retinal treatment to be continuously improved. By using an automated system improved in this way, the various known treatments can be planned in a reliable, comprehensible and objective manner with little effort.

Claims

Patent claims System for creating planning data sets (34, 35, 36, 37) for tissue treatment of the retina (16) of the eye (4) of a patient by means of a laser (2), - with a camera (6,7) designed to continuously capture images of the retina, - with an image processing device (19) which is configured to generate and provide current structured image data of the retina from images captured by the camera, - with an inventory data acquisition device (21, 22) that is set up to acquire and / or provide inventory data of a patient, and - with a processing unit (20) configured to assign planning data sets for tissue treatment to the current structured image data of the retina and the patient's inventory data, wherein specifications, in particular patterns and rules, for the assignment of planning data to image data and patient inventory data are stored in the processing unit. System according to claim 1, characterized in that a patient is assigned one of several predefined patient categories based on inventory data and / or currently acquired data, and that specifications of the processing unit (20), in particular patterns and rules, for the assignment of planning data to currently acquired data and inventory data are determined or influenced by the respective assigned patient category. System according to claim 1 or 2, characterized in that the inventory data acquisition device (21, 22) is configured to acquire and provide diagnostic data and / or indication data and / or data of a previously performed pretreatment and / or previously known physiological data of the patient and / or existing images of the patient's retina (16) stored outside the system.A system according to claim 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 depend on the respective location on the retina, and / or data that do not depend on a location on the retina, and that the processing device is configured to take the acquired physiological data of the patient into account when assigning planning data, and / or that the system has a modification device (24) that enables the manual modification of a planning data set. A system according to one of claims 1, 2, 3, or 4, characterized by a display module (17, 18) that provides a graphical representation of a planning data set within an image of the retina (16) currently acquired by the camera (6, 7).System according to claim 5, characterized by a tracking device which, upon displacement of the image currently captured by the camera (6, 7), causes the representation of the planning data set to be updated. System according to any one of claims 1 to 6, characterized in that the processing device (20) comprises a storage device (33) which is configured for storing patient inventory data and the planning data sets assigned to them, and. In particular, in addition to storing physiological data related to the aforementioned data, acquired by means of a measurement data acquisition device (23), and / or storing any manual changes made to the planning data sets. System according to one of claims 1 to 6, characterized in that the processing device (20) has a storage device (33) which is configured to store patient inventory data as well as structured image data and / or images of the patient's retina (16) generated by the system and the planning data sets (34, 35, 36, 37) associated with them, and in particular, in addition to storing physiological data related to the aforementioned data, acquired by means of a measurement data acquisition device (23), and / or storing any manual changes made to the planning data sets.System according to any one of claims 1 to 8, characterized by a monitoring device (25) which, after treatment of the retina (16) has been performed, records and provides data on the effects of the treatment. System according to any one of claims 1 to 8, characterized in that the processing device (20) is designed as a self-learning device in which the assignment function, which assigns planning data (34, 35, 36, 37), in particular target values ​​to measurement data, to the inventory data and in particular to the structured image data and in particular measured physiological data of a patient, is trained by providing it with at least data from at least one of the following categories for each patient: Inventory data Structured image data, measured physiological data, and, on the other hand, associated planning data, in particular target values ​​for measurement data, as well as manual planning data changes and, in particular, data on an effect of the treatment recorded after the planned treatment has been carried out, are specified as training data. System according to one of claims 1 to 10, characterized in that the planning data sets (34, 35, 36, 37) contain planning data from one, two, three, four, or five of the following categories: laser parameters (34), location data for the laser treatment (35), treatment pattern (36), location data for areas excluded from the laser treatment (37), target values ​​for measurement data. Device for creating planning data sets (34, 35, 36, 37) for the tissue treatment of the retina (16) of an eye (4) by means of a laser beam (11). - with a camera (6, 7) designed to continuously capture images of the retina (16), - with an image processing device (19) which generates and provides current structured image data of the retina from images captured by the camera (6, 7), - with an inventory data acquisition device (21, 22) that is set up to acquire and / or provide inventory data of a patient, - and with a processing unit (20) configured to assign planning data sets (34, 35, 36, 37) to the current structured image data of the retina and the patient's inventory data, wherein specifications, in particular, special patterns and rules are stored for the assignment of planning data to structured image data and patient inventory data. - and with a change device (22) that enables manual modification of a planning data record.

13. Device according to claim 12 characterized by a modification device (22) which enables the manual modification of a planning data set.

14. Method for creating planning data sets (34, 35, 36, 37) for tissue treatment of the retina (16) of an eye (4) of a patient using a laser beam (11), - in which at least one image of the retina is captured with a camera (6, 7), - in which current structured image data of the retina are generated and provided from images captured by the camera using an image processing device (19), - where, within the framework of an inventory data collection facility (21, 22), inventory data of a patient is collected and / or made available, - and in which planning data sets are assigned to the current structured image data of the retina and the patient's prior known inventory data by a processing unit (20) based on specifications, in particular patterns and rules, which are stored in the processing unit (20).

15. Method according to claim 14, characterized in that assigned planning data sets (34, 35, 36, 37) are manually changed after assignment. Method according to claim 14 or 15, characterized in that physiological data of the patient are recorded and provided in particular with a measurement data acquisition device (23) and are taken into account by the processing device (20) when assigning planning data sets (34, 35, 36, 37).Method according to one of claims 14 to 16, characterized in that the processing device (20) is designed as a self-learning device and the assignment function, which assigns planning data to the inventory data and the structured image data and in particular measured physiological data of a patient, is trained by providing it with the inventory data, structured image data, assigned planning data (34, 35, 36, 37), data of manual planning data changes and in particular measured or recorded physiological data and / or data on the effect of the treatment recorded after the respective planned treatment has been carried out, for a plurality of patients.A method according to any one of claims 14 to 17, characterized in that planning data sets (34, 35, 36, 37) are determined from one, two, three, four, or five of the following categories: laser parameters (34), location data for the laser treatment (35), treatment patterns (35), location data for areas excluded from the laser treatment (36), and target values ​​for measurement data. A method for operating a system according to any one of claims 1 to 11 and / or a device according to claim 12 or 13, characterized in that a planning data set is created and then a treatment is performed in a separate treatment unit or a treatment unit integrated into the system or device using a treatment laser in accordance with the planning data set.

Images