Medical instrument arrangement for minimally invasive examination and / or treatment of a subject, method for operating a medical instrument arrangement, computer program and electronically readable data carrier

Abstract

Medical instrument arrangement (1) for minimally invasive examination and / or treatment of a subject (20), comprising - a robot (8) for moving and manipulating a medical instrument (2) which can be inserted into the subject (20) and has a proximal control section (3) for moving and manipulating, at the control section (3), - an operator acquisition device (6) for acquiring operator movement patterns of the operating section (3) of the medical instrument (2), generated manually, in particular directly at the operating section (3), and - a control device (7), wherein the control device (7) comprises: - a control unit (9) for controlling the robot (8) according to control commands to generate control movements of the operating section (3), - a situation detection unit (12) for determining an intervention situation to be assigned to the operator movement patterns to be detected, - a storage unit (11) for storing, in particular operator-related, recorded operator movement patterns with the associated intervention situation in a storage means (29) of the control device (7), and - a situation unit (17) for automatically selecting and / or generating a control movement pattern from stored operator movement patterns depending on an intervention situation determined by the situation detection unit (12) and for providing the control movement pattern as control commands for controlling the robot (8) by means of the control unit (9).

Description

[0001] The invention relates to a medical instrument arrangement for minimally invasive examination and / or treatment of a subject, comprising - a medical instrument that can be inserted into the subject and has a proximal operating section for moving the instrument, and - a robot for the moving manipulation of the medical instrument at the operating section.

[0002] In addition, the invention relates to a method for operating such an instrument arrangement, a computer program and an electronically readable data carrier.

[0003] In minimally invasive examination and / or treatment of a subject, particularly a patient, which will be referred to below as minimally invasive procedure or simply procedure, a medical instrument, such as a catheter, guide wire, or the like, is inserted into the subject, for example, into a blood vessel system. The medical instrument may, for example, include at least one sensor for examination and / or at least one treatment device.

[0004] An example of such minimally invasive procedures are treatments and / or examinations of a patient's vascular system using a catheter as a medical instrument, for example, to dissolve complete vascular occlusions (CTO), to insert stents, and the like. The catheter, or more generally the medical instrument, such as a guidewire, is typically inserted via the patient's groin and guided from there to the actual intervention site, i.e., the examination and / or treatment site. This is currently mostly done manually by rotating, translating (advancing / retracting), or bending the medical instrument proximally outside the patient at a control unit.For navigation, in addition to pre-interventional image datasets and instrument positioning systems, fluoroscopy images or other intra-interventional images are usually acquired, which can then be superimposed on, for example, a pre-interventional three-dimensional image dataset. While navigating to the intervention site can already prove difficult, certain maneuvers that aid navigation, examination, and / or treatment depend particularly on the experience of the operator, i.e., the person performing the procedure. This results in complex movement patterns.

[0005] Examples of cases where complex movement patterns may occur to operate the medical instrument include, for example, navigation into small vessel branches far from the point of entry of the medical instrument into the subject, such as in neuroradiological procedures in the brain, and intricate navigation when opening total occlusions.

[0006] To simplify minimally invasive procedures, prior art has proposed using robots that, instead of a human operator, handle the medical instrument at the operating station and manipulate it. The robot, in turn, is controlled by the operator via appropriate controls, such as a joystick, to generate rotational and / or translational movements or bending of the medical instrument. While any medical instrument can be rotated and translated, only specially trained medical instruments can be bent. Such controls make it difficult to continue applying movement patterns for the medical instrument that have been learned and / or practiced over a long period.Although automated movement patterns for robots to move medical instruments have already been proposed, these only refer to a few simple movement patterns such as predefined translations or rotations of a small scale.

[0007] From US patent 2023 / 0117954A1, an endoscopic system is known which includes a steerable, elongated instrument configured to be robotically positioned and navigated within a patient's target anatomy via an actuator. A controller receives an image of the target anatomy. A trained machine learning (ML) model recognizes the target anatomy and estimates one or more cannulation or navigation parameters for maneuvering the instrument. The controller provides a control signal to the actuator to enable robotically assisted operation of the instrument within the target anatomy according to the estimated parameters.

[0008] From publication DE 10 2022 111 495 A1, a robotic telemanipulation system with an adaptable degree of autonomy is known, comprising a control unit for a user, at least one manipulation unit, and a bidirectional data transmission unit. The control unit converts user inputs into control signals for controlling the manipulation unit and transmits the control signals to the manipulation unit via the data transmission unit. The control unit receives initial information from a database. Depending on this initial information, the control unit selects a degree of autonomy for converting the user inputs into the control signals of the manipulation unit.

[0009] German patent application DE 10 2010 043 584 A1 discloses a medical workstation for treating a living being using a medical instrument. The workstation comprises a robot arm with several jointed segments, drives for moving the segments, and a clamping device. A control device coupled to the drives generates signals to control the drives, causing the clamping device to perform movements corresponding to the signals.

[0010] In summary, it can be said that medical instruments, such as catheters, can now be controlled either directly manually or indirectly via robots, although in the latter case only a few standard movements can be used.

[0011] The invention is therefore based on the objective of providing an improved, more extensive and in particular individualizable use of robots in minimally invasive procedures with medical instruments.

[0012] This problem is solved by a medical instrument arrangement with the features of claim 1, a method with the features of claim 13, a computer program with the features of claim 14 and an electronically readable data carrier with the features of claim 15. Advantageous further developments are set forth in the dependent claims.

[0013] According to the invention, a medical instrument arrangement for minimally invasive examination and / or treatment of a subject comprises: - a robot for the moving manipulation of a medical instrument which can be inserted into the subject and has a proximal control section for moving manipulation, at the control section, - an operator acquisition device for capturing operator movement patterns of the operating section of the medical instrument, generated manually, in particular directly at the operating section, and - a control device, wherein the control device has: - a control unit for controlling the robot according to control commands to generate control movements of the operating section, - a situation detection unit for determining an intervention situation to be assigned to the recorded operator movement patterns, - a storage unit for storing, in particular operator-related, recorded operator movement patterns with the associated intervention situation in a storage medium of the control device, and - a situation unit for automatically selecting and / or generating a control movement pattern from stored operator movement patterns depending on an intervention situation determined by the situation detection unit, and for providing the control movement pattern as control commands for controlling the robot by means of the control unit.

[0014] The subject can be a human and / or animal patient, but also a phantom, in particular a training phantom. In particular, a different subject can be used at different times, for example, a training phantom in a first application phase of the medical instrument arrangement according to the invention, namely a training phase. In particular, it can therefore be provided that the instrument arrangement also includes a phantom as a subject, on which at least some of the operator movement patterns are recorded.

[0015] The medical instrument may in particular be a catheter and / or a guide wire, although of course other medical instruments are also conceivable in order to carry out a minimally invasive procedure, i.e. an examination and / or treatment with the medical instrument.

[0016] The operator acquisition device, which can be considered a recorder, is used in the aforementioned first application phase, namely the training phase, to capture the operator's manual movements, particularly those performed directly at the operating section. It should be noted here that the operating section of the medical instrument need not be a fixed, immobile portion of the instrument, but can change depending on the insertion distance into the patient, for example, if the instrument can be gripped directly or by means of a movable gripping sleeve or similar device. In particular, the operating section is therefore a portion of the medical instrument that is fundamentally present in minimally invasive procedures and protrudes from the patient at the entry point, i.e., proximally.

[0017] The operator acquisition device provides acquisition data that describes the operator movement patterns performed by the operator. Since rotations and translations (advance / retraction) and / or curvatures of the medical instrument can typically be performed at the operating section, particularly by the operator's fingers, a convenient embodiment of the present invention provides that the acquisition data includes a rotation, translation, and / or curvature profile brought about by the operator's actions. Accordingly, it can be provided that the control commands include a rotation, translation, and / or curvature profile for the instrument, particularly its operating section, to be implemented by the control unit.

[0018] The invention ultimately proposes, in general terms, to transfer the movement patterns of at least one operator during the manual guidance of the medical instrument at the operating section to the robot's control system in such a way that these patterns can be automatically provided depending on the situation. In other words, the robot's movements are adapted to the movement patterns of the treating personnel for a specific intervention situation. The medical instrument arrangement according to the invention allows for the self-learning integration of specific movement patterns of an operator into a robotic minimally invasive intervention, thereby expanding the robot's movement repertoire. Specific movements of the at least one operator are learned along with the intervention situation and can be automatically retrieved by the robot, or more precisely, the control unit, in a corresponding intervention situation.

[0019] During a training phase, when the medical instrument is operated manually by an operator, particularly at the operating section itself, operator movement patterns are learned by recording them using the operator capture device and saving them in the control unit's memory. This process not only learns the operator movement patterns, such as a sequence of translations, rotations, and / or bends, but also captures and stores the intervention situation in which the operator movement pattern is used, assigning it to the corresponding movement pattern. The training phase is best conducted without any use of the robot, but with the use of the operator capture device (recorder unit), which can be positioned, for example, at the instrument access point to the patient.

[0020] The operator detection device can be designed in various ways. For example, it can have drivers, such as rollers, that are moved by friction or other interaction with the operating section of the medical instrument, and whose movement is measured. In a preferred embodiment, markers are provided on the operating section of the instrument, which can be detected by a corresponding sensor, for example, optical, in the operator detection device.

[0021] In a second phase of the medical instrument setup, which can be called the recall phase, the presence of a specific intervention situation is automatically detected. A corresponding control movement pattern, which may be an operator movement pattern or derived from one, is retrieved and executed, particularly after confirmation by an operator.

[0022] The medical instrument arrangement can operate in a particularly operator-specific manner, for which purpose the operator, along with their movement patterns and the associated intervention situation, is conveniently stored. Specifically, the situation unit can be configured to select and / or generate the control movement pattern based solely on the stored operator movement patterns associated with the current operator. In this way, the individual movement patterns of specific operators are learned, patterns to which the operator is particularly familiar due to their own authorship and ultimately recognizes themselves in the robot's operation. The operator's specific experience and approach are then reflected in the robot's automatic operation according to the control movement pattern.

[0023] Learning and recording specific operator movement patterns can be accomplished in various ways. Particularly when using a phantom, explicit, targeted training can be achieved via the medical instrument setup. For this purpose, the operator can manually initiate movement recording, for example, by activating the operator capture device in a special training mode via the control unit and consciously performing the corresponding movements of the operator movement pattern to be recorded, especially on the phantom as the subject. In this context, the intervention situation can also be provided by the operator, for example, via a user interaction unit of the control unit.

[0024] In preferred embodiments, however, particularly during training exercises on a phantom and / or actual minimally invasive procedures on a patient, the operator's minimally invasive interventions are captured by the medical instrument arrangement. Various approaches are conceivable in this context as well.

[0025] In a first concrete approach to learning by observation, the operator recording device could be designed to continuously capture the operator's actions during an intervention on the subject, while the situation capture unit would be designed to later assign the data to a specific situation and select appropriate operator movement patterns from the operator's actions. This means that the operator's movements can be continuously recorded, stored in memory, and subsequently, at least partially assigned to a specific intervention situation in an analysis. In this analysis, the operator could, for example, "review" the intervention and its execution. Furthermore, especially with the simultaneous storage of additional information, an automated analysis of such recordings of operator actions during a minimally invasive procedure is also possible.

[0026] In a second, preferred approach to observational learning, the control unit may include an activation unit for activating the operator recording device and / or for activating the recording of operator movement patterns when an activation condition is met. This activation condition evaluates a current intervention situation detected by the situation detection unit and / or a current operator movement pattern and / or instrument movement pattern. This means that recording can be automatically started by the medical instrument setup when a corresponding activation condition exists, for example, when it has been determined that a specific intervention situation, for which at least one operator movement pattern is to be recorded, has occurred.Additionally or alternatively, it is also conceivable to specifically detect and store "unusual" behaviors, particularly those deviating from the normal approach to the intervention site, especially operating or movement patterns. In this context, the operating and / or instrument movement pattern refers specifically to an operating period that ends at the current time.

[0027] Particularly when only the (final) saving is to be controlled, i.e., the operator data acquisition device is basically active during the minimally invasive procedure, it can be useful to use a ring buffer in which the most recently recorded data from the operator data acquisition device can always be stored, in order to be evaluated, for example, by the activation condition and at least partially incorporated into the total data set to be finally stored in the storage medium (which contains at least the operator movement pattern and the procedure situation).

[0028] However, variants are also conceivable in which the operator monitoring device does not need to be continuously operated, particularly if alternative methods of recording operator behavior are available and / or at least the current intervention situation is continuously monitored. For example, unusual movements can also be detected by imaging and similar means, especially if the minimally invasive procedure is being monitored using imaging techniques such as fluoroscopy. Furthermore, it is also conceivable to use additional sensors, such as cameras, to monitor the minimally invasive procedure. As mentioned, the analysis of the operator and / or instrument movement patterns serves, in particular, to detect unusual behaviors that deviate from the operator and / or movement patterns for the usual advancement and, if applicable, retraction.With regard to the intervention situation, the activation condition can, for example, monitor whether an intervention situation exists from a predefined list of intervention situations that lead to activation, in particular its initial state.

[0029] In a suitable embodiment, the activation unit can be configured to compare the current operating and / or instrument movement pattern with at least one predefined standard pattern, which in particular describes normal feed operation of the instrument, in order to evaluate the activation condition. If a deviation exceeds a threshold value for each standard pattern, the activation condition is met. For example, correlation values ​​of the current operating and / or instrument movement pattern with the standard patterns can be determined, and if a threshold value for the correlation value is not exceeded for any standard pattern, the activation condition is met. It is also conceivable to use a pattern classification function, particularly a trained one, which classifies an operating and / or instrument movement pattern as "normal" or "unusual."Generally, it can be intended that the normal patterns are derived from training data. In other words, the operator's "normal" movements can be learned based on training data, and a recording can be started when the current movements deviate from these.

[0030] It should also be noted at this point that, with regard to the intervention situation, a classifier, especially a trained one, can be used by the situation detection unit, which will be discussed in more detail below.

[0031] Preferably, the instrument arrangement can further comprise at least one sensor for acquiring sensor data to determine the current operating and / or instrument movement pattern by the activation unit and / or to determine the current intervention situation by the situation detection unit. For example, a camera pointed at the operator's hands can be used as the sensor. However, other comparable sensor data can also be used. For example, the instrument movement pattern can also refer to the tip of the medical instrument, as visible in image data.

[0032] Finally, it should be noted that in some cases, the situation detection unit may be configured, at least partially, to use operator input to determine the intervention situation. This can be particularly useful when introducing new intervention situations and / or when determining the intervention situation is otherwise impossible. For example, a user can define a new intervention situation or even a class of intervention situations and essentially start recording for it manually. This can be especially useful during the aforementioned "dry run" on a phantom or similar device.

[0033] Several approaches are conceivable for assigning intervention situations to operator movement patterns. As already mentioned, one option is explicit training by the operator, whereby the operator explicitly assigns the operator movement pattern to an intervention situation.

[0034] Furthermore, it is possible to observe operator procedures, whereby, for example, when activated via the activation unit, information describing the intervention situation is already assigned to the operator movement pattern to be recorded. This includes, for example, the position of the instrument and / or anatomical information, in particular the relative position of the instrument, especially the instrument tip, to the surrounding anatomy. Other anatomical assignments are also possible, for example, by determining—possibly even retrospectively, with the additional information recorded alongside the operator movement pattern—the anatomical background against which the medical instrument is located and / or whether a specific landmark, for example in an overlay, is reached.

[0035] A specific, preferred further development in this context could, for example, provide that the situation detection unit is designed to capture the intervention situation in relation to an operator movement pattern, to define a situation data set that describes at least the instrument position relative to the surrounding anatomy, in particular with respect to at least one landmark, and to determine the current intervention situation by comparison with stored situation data sets. Overall, it is advantageous if the situation detection unit is designed to use such situation data sets that define the intervention situation and describe at least the instrument position relative to the surrounding anatomy, in particular the position of the instrument tip relative to the surrounding anatomy.In particular, new intervention situations can arise if the intervention situation is not yet known, and therefore no (sufficient) match is found during comparison. Such intervention situations can include, for example, the instrument tip of the medical instrument being located in front of an anatomical feature that requires more complex movement patterns, such as a bifurcation, a vessel branch, or a complete occlusion.

[0036] Accordingly, general intervention situations and associated movement patterns can also include, for example, the opening of a total occlusion (CTO), navigation into a vessel branch, in particular probing a bifurcation and / or branch depicted only two-dimensionally, and navigating small vessels (“fingertip technique”).

[0037] Regarding the situation data set, appropriate further training stipulates that the situation acquisition unit is designed to save the situation data set with the associated operator movement pattern and / or that the situation data set includes image data showing the instrument in its anatomical position and / or position data from a position acquisition device for the medical instrument. In the case of landmark references, the landmark may be highlighted in the image data. Saving the situation data set, particularly in conjunction with the image data and / or position data, is especially useful when the intervention situation is to be automatically determined in the second application phase (recall phase) in order to select and / or generate a corresponding control movement pattern.For example, it may be possible to recognize the medical instrument and / or the anatomical region and / or the reaching of the landmark in current image data, in order to infer the corresponding intervention situation by comparing it with stored intervention scenarios or, more specifically, the situation data sets. The control movement pattern can then be selected and, in particular, suggested.

[0038] It should be noted at this point that the position data of the medical instrument may preferably refer to the instrument tip with regard to the intervention situation, but it is also conceivable that position data of the medical instrument may additionally or alternatively include system positions, for example a current advance into the subject.

[0039] In addition to or as an alternative to using situational data sets and / or image analysis to determine an intervention situation, or implementing these variants, an advantageous embodiment may also provide for the situation detection unit to be configured to use at least one, in particular trained, classification function for recognizing the intervention situation. The input data of such a trained classification function may include acquisition data from the operator control unit (for example, acquisition data stored in a ring buffer). However, it is expediently suitable to include at least one additional piece of information, in particular position data from a position detection unit for the medical instrument and / or the robot and / or image data from an imaging device and / or setting data of components of the instrument assembly.In particular, the above situation dataset can also be used to classify a current intervention situation. Accordingly, the input data of such a classification function generally includes classification into an intervention situation class. In this context, as is generally the case, it can also be useful for at least one intervention situation and / or intervention situation class to be defined by an instrument position relative to the surrounding anatomy.

[0040] In general, a trained function replicates cognitive functions that people associate with other human brains. Through training based on training data (machine learning), the trained function is able to adapt to new circumstances and detect and extrapolate patterns.

[0041] Generally speaking, the parameters of a trained function can be adjusted through training. Specifically, supervised learning, semi-supervised learning, unsupervised learning, reinforcement learning, and / or active learning can be used. Furthermore, representational learning (also known as feature learning) can be employed. The parameters of the trained function can be adjusted iteratively through multiple training steps.

[0042] A trained function can, for example, comprise a neural network, a support vector machine (SVM), a decision tree, and / or a Bayesian network, and / or the trained function can be based on k-means clustering, Q-learning, genetic algorithms, and / or assignment rules. Specifically, a neural network can be a deep neural network, a convolutional neural network (CNN), or a deep CNN. Furthermore, the neural network can be an adversarial network, a deep adversarial network, and / or a generative adversarial network (GAN).

[0043] In general terms, it is therefore also possible that in the second application phase (recall phase), an intervention situation can be recognized based on current movement patterns, such as those initiated by the operator using the robot. Thus, the control unit, in particular the situation detection unit, can, for example, recognize whether the operator is attempting to execute one of their specific movement patterns, such as a "special sequence," with the robot. From this, the current intervention situation can be deduced in order to then suggest the appropriate control movement pattern.

[0044] To implement suitable automation upon detection of an intervention situation for which a control movement pattern can be selected and / or generated and optionally suggested, a further expedient embodiment of the present invention provides that the control device also includes a trigger unit which, upon fulfillment of a trigger condition evaluating the current intervention situation of the situation detection unit, triggers the selection and / or generation of the situation unit. In particular, the trigger condition can check whether operator movement patterns and / or evaluation movement patterns are already stored in the storage medium for the current intervention situation, to which a corresponding intervention situation is assigned.In summary, the system automatically monitors whether an intervention situation occurs for which a control movement pattern can be provided, and this provision is automatically achieved due to the trigger unit.

[0045] Advantageously, the control unit can include a user interaction unit for suggesting the control movement pattern to the operator, particularly upon triggering, and / or for receiving operator input, especially for use in selection. A suggestion function that automatically opens up further, particularly individualized, operating options for the robot based on the current intervention situation is especially advantageous and also elicits confirmation from the operator.

[0046] In a particularly preferred embodiment of the present invention, the control unit may include an evaluation unit for the statistical evaluation of several operator movement patterns present in the storage medium for the same intervention situation in order to determine a selectable evaluation movement pattern for this intervention situation. Thus, if several operator movement patterns, especially those of the same operator, are present for an intervention situation, a statistical evaluation can be performed to derive the essence of the multiple recordings, in particular the actually desired movement characteristics, and especially to derive an optimal evaluation movement pattern that can then be selected by the situation unit for the intervention situation (and optionally the operator) or used generally.In particular, online generation is also conceivable, for example, directly before selection and / or generation in the situation unit. This allows, in particular, the identification of improved and also updatable control movement patterns after learning from several processes involving the same intervention situation.

[0047] The statistical analysis can include, for example, averaging similar segments of the movement pattern with regard to the duration and / or amplitude and / or course of the movement, particularly for translation and rotation and / or curvature. It is also possible, however, to statistically determine typical partial movement patterns for the intervention situation and to base the evaluation movement pattern on these.

[0048] In this context, it is particularly advantageous if the storage unit is further configured to store, especially with a time delay, success information describing the success of the respective operator movement pattern, particularly as a continuous efficiency metric, for each operator movement pattern, wherein the evaluation unit is configured to determine the evaluation movement pattern as the optimal movement pattern using the success information. In this configuration, efficiency and / or treatment success, described by the success information, are taken into account, whereby a preferred evaluation movement pattern optimized for the respective intervention situation is generated based on the success information.Success information allows statistical analysis to identify the most efficient components of operator movement patterns, such as particularly successful or pronounced partial movement patterns, and to incorporate these into the analysis of the movement pattern. Averaging processes within the statistical analysis can also include weighting based on the success information. Furthermore, operator movement patterns that result in insufficient success can be excluded. The success information is preferably continuous or at least graded, such as the highest efficiency, and therefore not binary. For example, a percentage efficiency or other score can be determined and used as success information, particularly as an efficiency measure.

[0049] In this context, a suitable further development of the medical instrument arrangement envisages that the evaluation unit be additionally equipped to evaluate image data of the instrument and the surrounding anatomy, acquired during and / or after the execution of the operator movement pattern, for at least partially automated determination of success information. In other words, it is conceivable to automatically derive success information from observational results for the procedure in which the operator movement pattern was used, through analysis. Image-based evaluation is particularly suitable here. For example, if a procedure in a patient's vascular system is the preferred application, image data can be used to assess, for instance, whether a vessel was punctured and / or to what extent a complete occlusion was removed.However, it is also conceivable, in principle, to independently incorporate user input and / or other information into such a postoperative evaluation.

[0050] It is advantageous to include previously identified analysis patterns and their associated success information in the evaluation. This is particularly useful for updates. Success information for analysis patterns, especially those used as control patterns, also allows for an assessment of the effectiveness of the statistical analysis and enables improvements as needed.

[0051] Preferably, the control unit can further include an adaptation unit that adjusts the operator movement patterns and / or evaluation movement patterns to be stored with respect to at least one restriction of movement related to the robot and / or the protection of the subject. In this way, it is possible to also incorporate requirements for the protection of the subject and / or specifications of the robot into the learning process, so that the learned operator movement patterns and / or evaluation movement patterns can actually be executed by the robot. The control unit can thus be "intelligent" and take into account restrictions relating to the robot and / or the subject.For example, if it is known that the robot must not exceed a limit for the number of revolutions per second during rotation, any operator movement pattern and / or evaluation movement pattern exceeding this limit can be reduced to the limit. The same applies to the feed / retraction.

[0052] In addition to the medical instrument arrangement, a method, particularly a computer-implemented method, for operating a medical instrument arrangement for minimally invasive examination and / or treatment of a subject, comprising a medical instrument that can be inserted into the subject and has a proximal operating section for moving the instrument, is also proposed, the method comprising the following steps: - Recording of operator movement patterns generated manually, especially directly at the operating section, of the operating section of the medical instrument, - Assigning an intervention situation to each captured operator movement pattern, - in particular operator-related, saving the recorded operator movement patterns with the associated intervention situation, and, - during a further intervention with the medical instrument and a robot for the manipulation of the medical instrument at the operating section, automatic selection and / or generation of a control movement pattern from stored operator movement patterns depending on the existing intervention situation, and - Automatic conversion of the control movement pattern into control commands for the robot.

[0053] All statements regarding the medical instrument arrangement according to the invention can be applied analogously to the method and vice versa, so that the advantages already mentioned can also be obtained here.

[0054] A computer program according to the invention can be directly loaded into a storage medium of a control unit of a medical instrument arrangement and comprises program means such that, when the computer program is executed in the control unit, the latter is caused to perform the steps of a method described herein. The computer program can be stored on an electronically readable data carrier according to the invention, which thus comprises control information stored thereon, which includes a computer program according to the invention and is configured such that, when the data carrier is used in a control unit of an instrument arrangement, the latter is configured to perform a method described herein. The data carrier is, in particular, a non-transient data carrier, for example, a CD-ROM.

[0055] Further advantages and details of the present invention will become apparent from the exemplary embodiments described below and from the drawings. These show: Fig. 1 a schematic diagram of a medical instrument arrangement according to the invention, Fig. 2 the functional structure of a control unit of the instrument arrangement of the Fig. 1, Fig. 3 a flowchart of an exemplary implementation of an operating procedure according to this disclosure, Fig. 4 an illustration of an intervention situation, Fig. 5 an exemplary operator movement pattern, and Fig. 6 schematically shows the implementation of the operator movement pattern as a control movement pattern for a robot.

[0056] Fig. Figure 1 shows a schematic diagram of a medical instrument arrangement 1 according to the invention for performing minimally invasive procedures with a medical instrument 2, for example, a catheter or a guidewire. The medical instrument 2 has a proximal operating section 3, in particular the section of the instrument 2 located just outside a subject. At an entry point, the instrument 2 can be inserted into a subject, for example, a patient or a phantom 5, for example, via an instrument sheath 4.

[0057] The medical instrument 2 can be operated directly by an operator at the operating section 3, for example, for advancement / retraction (translation) and with regard to the rotation and / or curvature of the medical instrument 2. In order to be able to detect such operator movement patterns initiated by an operator, the medical instrument arrangement 1 also has an operator detection device 6 which has corresponding measuring means, for example, to detect markers on the instrument 2 or otherwise to track the movement at the operating section 3. When the instrument 2 is manually guided at the operating section 3 by an operator, detection data describing the operator movement pattern can be recorded and transmitted to a control unit 7.To specifically record operator movement patterns, the Phantom 5 can be used, for example; it is of course also possible to record operator movement patterns during minimally invasive procedures on other subjects.

[0058] The medical instrument arrangement 1 also includes a robot 8, in this case by way of example a so-called vascular robot, which can be coupled to the control section 3 in order to effect movements of the medical instrument 2 according to control commands, which may be based on operator input at a control device or on another source, in this case rotations and translations and / or bends.

[0059] Fig. Figure 2 shows the functional structure of the control unit 7 in more detail. In this figure, the following are shown: Fig. 2. First, the various functional units of the control device 7 were presented, before their interconnected operation was demonstrated using the method of... Fig. 3 will be explained in more detail.

[0060] The control device 7 initially has a control unit 9, which is designed to control the robot 8 according to control commands to generate corresponding movements, here translations and rotations and / or curvatures.

[0061] In the present embodiment, the control unit 7 further comprises an activation unit 10, which controls the activity of various other functional units, in particular the operator input unit 6 and a storage unit 11 of the control unit 7, especially depending on an activation condition. The activation unit 10 has access to various other functional units, for example, a situation detection unit 12, an interface 13 for receiving additional information, in particular image data from an imaging device for monitoring a minimally invasive procedure and / or position data from a positioning system for the medical instrument 2, and a user interaction unit 14.

[0062] The aforementioned situation detection unit 12 is designed to detect intervention situations on various occasions, which, as will be explained in more detail later, can be based on different data or information. In particular, it is capable of assigning intervention situations to detected operator movement patterns.

[0063] The storage unit 11 is designed to store various, related pieces of information in a storage medium 29 of the control unit 7, in particular to store a recorded operator movement pattern together with the associated intervention situation, especially as a situation data record, and operator information describing the operator who performed the operator movement pattern. Such complete data records consisting of operator movement pattern (i.e., the corresponding recording data), intervention situation (i.e., the situation data record), and operator (i.e., operator information) can also be subsequently assigned success information by the storage unit 11, describing the treatment success and / or the efficiency of the minimally invasive procedure during which the respective operator movement pattern was recorded.

[0064] Such success information can be provided, for example, by an evaluation unit 15, which can evaluate image data and / or other material (received via interface 13) relating to the minimally invasive procedure to determine the success information. Other sources for at least partially determining the success information are the user interaction unit 14 or directly via interface 13.

[0065] The evaluation unit 15 is further designed to statistically evaluate operator movement patterns assigned to the same intervention situation and the same operator, taking into account the success information, in order to determine evaluation movement patterns which are also stored in the storage medium 29, in particular by the storage unit 11.

[0066] The control unit 7 further comprises a trigger unit 16, which is active when the robot 8 is in use. This trigger unit evaluates the intervention situations recorded by the situation detection unit 12 to determine whether a trigger condition is met. The trigger condition ultimately indicates that an intervention situation, in particular the beginning of an intervention situation, exists in which a recorded operator movement pattern or an evaluation movement pattern could be appropriately implemented by the robot 8 as a control movement pattern via control commands from the control unit 9. The selection of this control movement pattern is carried out by a situation unit 17, which then transmits it accordingly to the control unit 9.

[0067] The interaction of the functional units is now being examined with regard to the procedure of Fig. 3 explained in more detail. Accordingly, the use of the medical instrument arrangement 1 can be divided into two application phases 18, 19, namely a first application phase 18 (training phase) and a second application phase 19 (recall phase).

[0068] In the first application phase 18, during step S0 of a minimally invasive procedure on a subject, such as the Phantom 5 or another subject, the activation unit 10 monitors whether the activation condition is met. Several possible conditions exist for this. For example, an operator may manually start motion recording via the user interaction unit 14, for instance, when working with the Phantom 5, making analysis otherwise difficult.

[0069] Preferably, the activation unit 10 monitors the minimally invasive procedure. In a simple example, the activation unit 10 can check, for instance, whether a current procedure situation determined by the situation detection unit 12 is included in a list of procedure situations for which operator movement patterns are to be recorded. Furthermore, it is possible, particularly if the operator detection unit 6 provides data throughout the entire minimally invasive procedure, which can, for example, be stored in a ring buffer.It may then be possible to compare a current operating and / or instrument movement pattern with normal patterns that describe a normal feed operation of the instrument, for example by determining correlation values ​​for the normal patterns and by ensuring that the activation condition is met when a threshold value is undershot for all normal patterns.

[0070] However, current operating and / or instrument movement patterns can also be recorded alternatively or additionally in other ways, particularly with special sensors, such as a camera pointed at the operator's hands. Image data relating to the movement of the instrument tip, as well as position data of the medical instrument, can also be analyzed to detect unusual operating and / or instrument movement patterns that deviate from normal patterns.

[0071] It should be noted that, in addition to the embodiment described here, it is also conceivable in principle to continuously record the data and later assign it to intervention situations and extract the operator movement patterns for corresponding time intervals. However, this is less preferred.

[0072] After the activation condition is met in step S0, the data for the corresponding operator movement pattern is recorded in step S1. In step S2, an intervention situation is then assigned to the operator movement pattern using the situation detection unit 12. It should be noted that the order of steps S1 and S2 can be reversed, as, for example, the intervention situation or its description may already be known during activation.

[0073] While it is generally conceivable to determine an intervention situation based on operator input, particularly using the user interaction unit 14, this is primarily practical, as already described, for use with the phantom 5. Preferably, the intervention situation is recorded automatically. In this context, it is particularly advantageous to compile a situation data set that describes the position of the medical instrument 2, especially its tip, relative to the surrounding anatomy. This can, for example, explicitly include image data, such as that used for monitoring the minimally invasive procedure. It is therefore conceivable, for instance, to store image data and position data of the medical instrument 2 in the situation data set when the activation condition is met and to assign this data set to the operator movement pattern to be recorded.It is also conceivable to explicitly define the anatomical background against which medical instrument 2 is located, or whether a specific landmark, which can also be displayed in an overlay, is reached by the instrument. Such a landmark could be, for example, a complete vascular occlusion, a bifurcation, or a vessel origin.

[0074] It should also be noted that various methods for specifically determining the current intervention situation are conceivable, particularly when used concurrently. For example, a trained classification function can be employed and / or a comparison can be made using situational datasets.

[0075] In step S3, the storage unit 11 stores the operator movement pattern, in particular the corresponding acquisition data, the intervention situation, in particular the situation data set, and operator information describing the operator, since operator-specific work is carried out here, as a complete data set in the storage medium 29.

[0076] Steps S1 to S3 are schematically illustrated by the Fig. 4 and Fig. 5. Fig. Figure 4 shows the medical instrument 2 inserted into a subject 20 during an intervention, which in this case is being navigated within a blood vessel system 21. Operating section 3 shows the operator's hand 22, which initiates movements of operating section 3 and thus of the medical instrument 2, specifically translations (see arrow 23) and rotations (see arrow 24). Fig. Figure 5 shows, as an example, the curves 25, 26 of rotation (R(t)) and translation (T(t)) for an operator movement pattern.

[0077] Returning to Fig. In step S4, particularly after completion of the minimally invasive procedure, the evaluation unit 15 determines the success information, for example, by automatically evaluating image data and / or other additional information describing the state after execution of the operator movement pattern. The success information for the operator movement pattern describes its efficiency and / or treatment success, preferably continuously, for example, as a percentage / efficiency metric. For example, the success information can indicate the extent to which a CTO was resolved and / or how quickly normal navigation could resume and / or whether or to what extent unwanted effects, such as punctures, occurred. In step S5, the storage unit saves the success information in the complete data set of the operator movement pattern.

[0078] As indicated by the dashed arrow 27, further operator movement patterns can now be recorded, especially for the same intervention situation and the same operator.

[0079] In step S6, evaluation unit 15 is used to determine evaluation movement patterns for all intervention situations and operators for whom multiple operator movement patterns exist. For this purpose, the multiple operator movement patterns are statistically evaluated, taking into account the success information. In particular, an optimal movement pattern for the intervention situation and the operator is determined, which, statistically speaking, should yield the best treatment outcome and / or the best efficiency. The evaluation can include weighted averaging and / or the identification of efficient and / or characteristic partial movement patterns. Especially when updating the evaluation movement patterns after their use, these patterns, along with their corresponding success information, can also be included in the updated evaluation.

[0080] In step S7, the evaluation movement patterns with the associated intervention situations and operators are also stored in the storage medium 29 using the storage unit 11.

[0081] In the second application phase 19, the so-called “recall phase”, in step S8, during an intervention with the robot 8, the situation detection unit 12 constantly monitors the current intervention situation based on various information, but especially image data and position data of the medical instrument 2.

[0082] In step S9, the trigger unit 16 uses this to check, within the trigger condition, whether usable operator movement patterns or evaluation movement patterns for the current intervention situation are stored in the memory medium 29, in particular those for the current operator. If this is the case, i.e., if the trigger condition is met, the situation unit 17 selects the evaluation movement pattern appropriate to the intervention situation and the operator in step S10, or, if no evaluation movement pattern is available, the operator movement pattern as the control movement pattern.

[0083] In step S11, the control movement pattern is suggested to the operator for execution using the user interaction unit 14. If the operator wishes to execute the movement pattern, the control unit 9 carries it out in step S12 using control commands. Repetitions can, of course, also occur in application method 19, particularly within a single minimally invasive procedure.

[0084] This second application phase is in Fig. Figure 6 schematically illustrates where, instead of the hand 22, the robot 8 now performs the translations (arrow 23) and the rotations (arrow 24), for example based on the trajectories 25, 26.

[0085] Finally, it should be noted that the control unit 7, compare Fig.2, optionally also having an adaptation unit 28 that adapts operator movement patterns and / or evaluation movement patterns to restrictions relating to the robot 8 and to protect the subject 20.

[0086] Although the invention has been illustrated and described in detail by the preferred embodiment, the invention is not limited by the disclosed examples and other variations can be derived by the person skilled in the art without leaving the scope of protection of the invention.

[0087] Regardless of the grammatical gender of a particular term, persons with male, female or other gender identities are included.

Claims

[1] Medical instrument arrangement (1) for minimally invasive examination and / or treatment of a subject (20), comprising - a robot (8) for moving and manipulating a medical instrument (2) which can be inserted into the subject (20) and has a proximal control section (3) for moving and manipulating, at the control section (3), - an operator acquisition device (6) for acquiring operator movement patterns of the operating section (3) of the medical instrument (2), generated manually, in particular directly at the operating section (3), and - a control device (7), wherein the control device (7) comprises: - a control unit (9) for controlling the robot (8) according to control commands to generate control movements of the operating section (3), - a situation detection unit (12) for determining an intervention situation to be assigned to the operator movement patterns to be detected, - a storage unit (11) for storing, in particular operator-related, recorded operator movement patterns with the associated intervention situation in a storage means (29) of the control device (7), and - a situation unit (17) for automatically selecting and / or generating a control movement pattern from stored operator movement patterns depending on an intervention situation determined by the situation detection unit (12) and for providing the control movement pattern as control commands for controlling the robot (8) by means of the control unit (9). [2] Medical instrument arrangement according to claim 1, characterized by , that the control commands include a rotation profile (25) and translation profile (26) and / or curvature profile for the medical instrument (2), in particular its operating section (3), to be implemented by the control unit (9). [3] Medical instrument arrangement according to claim 1 or 2, characterized by , that the situation unit (17) is designed for operator-related selection and / or generation of the control movement pattern based only on the stored operator movement patterns related to the current operator. [4] Medical instrument arrangement according to any of the preceding claims, characterized by , that the control unit (7) further comprises an activation unit (10) for activating the operator detection unit (6) and / or for activating the storage of operator movement patterns when an activation condition is met, which evaluates a current intervention situation detected by the situation detection unit (12) and / or a current operating pattern and / or instrument movement pattern of the instrument (2). [5] Medical instrument arrangement according to claim 4, characterized by, that the activation unit (10) is designed to compare the current operating and / or instrument movement pattern with at least one predefined normal pattern, which in particular describes a normal feed operation of the instrument (2), in order to evaluate the activation condition, wherein the activation condition is fulfilled for each normal pattern if there is a deviation exceeding a threshold value. [6] Medical instrument arrangement according to any of the preceding claims, characterized by , that the situation detection unit (12) is designed to detect the intervention situation in relation to an operator movement pattern, to define a situation data set which describes at least the instrument position relative to the surrounding anatomy, in particular with respect to at least one landmark, and to determine the current intervention situation by comparison with stored situation data sets. [7] Medical instrument arrangement according to any of the preceding claims, characterized by , that the situation detection unit (12) is designed to use at least one, in particular trained, classification function to detect the intervention situation. [8] Medical instrument arrangement according to any of the preceding claims, characterized by , that the control device (7) further comprises a trigger unit (16) which, upon fulfillment of a trigger condition evaluating the current intervention situation of the situation detection unit (12), triggers the selection and / or generation of the situation unit (17). [9] Medical instrument arrangement according to any of the preceding claims, characterized by, that the control device (7) has an evaluation unit (15) for the statistical evaluation of several operator movement patterns present in the storage medium (29) for the same intervention situation in order to determine a selectable evaluation movement pattern for this intervention situation. [10] Medical instrument arrangement according to claim 9, characterized by , that the storage unit (11) is further configured to store, in particular at a time delay, success information describing the success of the respective operator movement pattern, in particular as a continuous efficiency variable, for each operator movement pattern, wherein the evaluation unit (15) is configured to determine the evaluation movement pattern as the optimal movement pattern using the success information. [11] Medical instrument arrangement according to claim 10, characterized by, that the evaluation unit (15) is also designed to evaluate image data of the instrument (2) and the surrounding anatomy recorded during and / or after the execution of the operator movement pattern for at least partially automatic determination of the success information. [12] Medical instrument arrangement according to any of the preceding claims, characterized by , that the control device (7) further comprises an adaptation unit (28) which adapts operator movement patterns to be stored with respect to at least one restriction of movement relating to the robot (8) and / or the protection of the subject (20). [13] Method for operating a medical instrument arrangement (1) for minimally invasive examination and / or treatment of a subject (20), comprising a medical instrument (2) that can be inserted into the subject (20) and having a proximal operating section (3) for moving the instrument (2), the method comprising the following steps: - Recording of operator movement patterns of the operating section (3) of the medical instrument (2), generated manually, in particular directly at the operating section (3), - Assigning an intervention situation to each captured operator movement pattern, - in particular operator-related, saving the recorded operator movement patterns with the associated intervention situation, and, - during a further intervention with the medical instrument (2) and a robot (8) for the moving manipulation of the medical instrument (2) at the operating section (3), automatic selection and / or generation of a control movement pattern from stored operator movement patterns depending on a determined intervention situation and - Provision of the control movement pattern as control commands for the robot (8). [14] Computer program which, when executed on a control device (7) of an instrument arrangement (1), causes the latter to perform the steps of a method according to claim 13. [15] Electronically readable data carrier on which a computer program according to claim 14 is stored.

Images