WO2019219450A1 - Système électro-chirurgical et procédé pour faire fonctionner un système électro-chirurgical - Google Patents

Système électro-chirurgical et procédé pour faire fonctionner un système électro-chirurgical Download PDF

Info

Publication number
WO2019219450A1
WO2019219450A1 PCT/EP2019/061648 EP2019061648W WO2019219450A1 WO 2019219450 A1 WO2019219450 A1 WO 2019219450A1 EP 2019061648 W EP2019061648 W EP 2019061648W WO 2019219450 A1 WO2019219450 A1 WO 2019219450A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
electrode
neural network
processing unit
data processing
Prior art date
Application number
PCT/EP2019/061648
Other languages
German (de)
English (en)
Inventor
Christian Stange
Original Assignee
Olympus Winter & Ibe Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Olympus Winter & Ibe Gmbh filed Critical Olympus Winter & Ibe Gmbh
Publication of WO2019219450A1 publication Critical patent/WO2019219450A1/fr

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/00002—Operational features of endoscopes
    • A61B1/00004—Operational features of endoscopes characterised by electronic signal processing
    • A61B1/00009—Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope
    • A61B1/000096—Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope using artificial intelligence
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
    • A61B18/04—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating
    • A61B18/12—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating by passing a current through the tissue to be heated, e.g. high-frequency current
    • A61B18/14—Probes or electrodes therefor
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
    • A61B90/36—Image-producing devices or illumination devices not otherwise provided for
    • A61B90/361—Image-producing devices, e.g. surgical cameras
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B90/00—Instruments, implements or accessories specially adapted for surgery or diagnosis and not covered by any of the groups A61B1/00 - A61B50/00, e.g. for luxation treatment or for protecting wound edges
    • A61B90/90—Identification means for patients or instruments, e.g. tags
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/04—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances
    • A61B1/05—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances characterised by the image sensor, e.g. camera, being in the distal end portion
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
    • A61B18/04—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating
    • A61B18/12—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating by passing a current through the tissue to be heated, e.g. high-frequency current
    • A61B18/14—Probes or electrodes therefor
    • A61B2018/1405—Electrodes having a specific shape
    • A61B2018/1407—Loop
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
    • A61B18/04—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating
    • A61B18/12—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating by passing a current through the tissue to be heated, e.g. high-frequency current
    • A61B18/14—Probes or electrodes therefor
    • A61B2018/1405—Electrodes having a specific shape
    • A61B2018/1417—Ball
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B18/00—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
    • A61B18/04—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating
    • A61B18/12—Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body by heating by passing a current through the tissue to be heated, e.g. high-frequency current
    • A61B18/14—Probes or electrodes therefor
    • A61B2018/1495—Electrodes being detachable from a support structure
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Definitions

  • the invention relates to an electrosurgical system and a method for operating an electrosurgical system.
  • high-frequency surgery also referred to as HF surgery
  • a high-frequency alternating current is passed through tissue that is to be treated surgically in order to specifically damage or cut it.
  • the essential advantage of this surgical technique compared to the use of a conventional scalpel is that, at the same time as the incision, bleeding is stopped by occlusion of the affected vessels.
  • an electrode is plugged onto a surgical instrument, for example a resectoscope.
  • a surgical instrument for example a resectoscope.
  • operating parameters include, for example, the electrode applied voltage.
  • different voltage values must be set.
  • an electrosurgical system and a method for operating the same is disclosed, with which an electrode is detected and the operating parameters of the electro -urgical system are adapted to the detected electrode.
  • an image of an identification feature present on the electrode for example a bar code or a color code, is detected by means of an image acquisition system already present on the surgical instrument.
  • This identifier is compared with identification features stored in a database so as to identify the electrode.
  • the operating parameters assigned to this electrode are transmitted to a controller of the electrosurgical system.
  • the bar code or the color coding is detected by the image acquisition system in such a way that the electrode can be uniquely identified on the basis of the acquired image of the bar code or the color coding. If, for example, the electrode is picked up under an unfavorable angle or if the illumination is too weak, erroneous identification may occur since the detected identification feature, as shown in the image, no longer exactly matches the identification feature stored in the database is deposited.
  • an electrosurgical system comprising a surgical instrument with an imaging system and a shaft, wherein an electrode holder is provided at a distal end of the shaft, and wherein the image acquisition system is arranged for detecting an operation field, which extending distally in front of the distal end of the shaft, the system further comprising an electrode connectable to the electrode holder for performing a surgical treatment and a data processing unit, wherein the imaging system is adapted to capture an image of the electrode and to the Data processing unit to transmit, wherein the data processing unit is adapted to
  • the electrosurgical system is further developed in that the data processing unit is adapted to identify the electrode type of the electrode by machine learning.
  • machine learning is to be understood as a technology in which a data processing unit is set up to perform tasks by learning from data instead of being programmed for the tasks.
  • Machine learning therefore always requires a learning phase during which the data processing unit is trained to perform later tasks. After the learning phase, the data processing unit can be placed in a classification phase to take over the required tasks.
  • One way to implement machine learning in a data processing unit is an artificial neural network.
  • the electrosurgical system is developed in that the mechanical learning is implemented in an artificial neural network.
  • the type of electrode is more reliably identified. Instead of a direct comparison of the detected identification feature with stored in a database identification features, the identification is carried out by means of the neural network.
  • the neural network is trained to detect the types of electrodes. For this purpose, for example, training images are supplied to the neural network. The electrode types of the electrodes depicted in these training images are known and given to the neural network during the training process. The trained neural network is able to recognize the types of electrodes depicted in the training images. If subsequently unknown images of electrodes are supplied to this neuronal network, the neural network reliably identifies the type of electrode of these electrodes, provided that it has previously been trained to recognize electrodes of this type of electrode.
  • the neural network must be trained with a corresponding number of images of each type of electrode to be identified.
  • the artificial neural network is trained with images of all types of electrodes associated with surgery. see instrument can be used.
  • the artificial neural network is trained with at least 100 images, in particular at least 500 images, in particular at least 750 images per electrode type. These images are preferably taken from different angles and in particular also under different lighting conditions.
  • all arithmetic operations to be performed in connection with the identification of the type of electrode by means of the artificial neural network are carried out by the data processing unit. This advantageously makes it unnecessary to provide and / or set up a further data processing unit, for example an external computer, for the identification of the electrode type.
  • the electrochurgical system comprises a control unit in which the controller and the data processing unit are arranged as separate units.
  • the control unit is a correspondingly populated rack.
  • the controller is part of an external computer system, such as a computer connected to the electrosurgical system.
  • the data processing unit comprises a data memory on which a plurality of electrode data records are stored.
  • Each of these electrode data records comprises, for example, an electrode type name and at least one operating parameter intended for operating this electrode type.
  • an electrode type data set is stored on the data memory. After identification of the electrode type by the artificial neural network, it becomes advantageous The electrode type data set is retrieved, whose electrode type name corresponds to the identified electrode type. Subsequently, the operating parameters stored in this electrode data record are transferred to the controller.
  • the data processing unit comprises a database on which parameter information of the artificial neural network is stored, the data processing unit being adapted to supply the identification features to an input layer of the artificial neural network, to parametrize a hidden layer of the artificial neural network by means of the parameter information and output the identified type of electrode in an output layer of the artificial neural network.
  • this structuring of the neural network achieves a short training duration of the artificial neural network as well as a simple and reliable identification of the electrode types by means of the at least one identification feature.
  • both the parameter information of the artificial neural network and the electrode type data sets are stored on the same database.
  • the parameter information includes, for example, information about the number and weights of the neurons of the artificial neural network.
  • some parameter information, such as the number of neurons, may be given by a user.
  • the activation function of the artificial neural network is a radial basis function.
  • the artificial neural network is thus preferably a so-called Radial Base Function Network (RBFN).
  • RBFN Radial Base Function Network
  • An RBFN has an input Layer, a single buried layer, and an output layer.
  • a RBFN has a simple architecture.
  • the time required to train the RBFN is shorter than other, more complex artificial neural networks.
  • the data processing unit is set up to carry out the following processing steps before extracting the at least one identification feature:
  • the transferred image is processed with these processing steps in such a way that the post-processed image contains only insignificant image disturbances or artifacts.
  • the post-processed image is segmented, that is, electrode segments are defined in that image.
  • the electrode segments essentially correspond to the image area of the transmitted image, which shows the detected electrode.
  • the remaining image areas essentially comprise the Background of the transferring image.
  • the electrode segments thus give exactly the shape of the electrode. Since the identification features of the electrode are extracted from these electrode segments or by means of these electrode segments, the identification features allow reliable characterization of the electrode.
  • the segmentation of the post-processed image is in particular a pixel-based segmentation.
  • the conversion of an image into a greyscale image or a binary image as well as the application of mean value filters, dilation operations and erosion operations are known processing steps of image processing, which require no further explanation.
  • all pixels which have a certain gray scale value, in particular white are defined as the electrode segment.
  • All other pixels, for example below this gray scale value, ie in particular all black pixels, are set as the background.
  • two processing steps are carried out in which a mean value filter is applied.
  • the first average filter is preferably a strong average filter, so that the edges of the electrode in the gray scale image are blurred.
  • the data processing unit is preferably a one-chip system which comprises a programmable logic gate arrangement, in particular an FPGA, and a processor arranged on the one-chip system.
  • a single-chip system better known by the English term "system-on-a-chip” (SoC) integrates many functions of a data processing unit on a single chip.
  • SoC system-on-a-chip
  • a so-called “stand-alone system” is achieved, which makes it possible to identify the electrode type independently of other components of the electrosurgical system and external components.
  • an external computer is often provided for displaying and evaluating the images acquired by the image acquisition system during a surgical treatment. If the identification were made by means of this external computer, the functionality of the identification would depend on the structure and the device of this external computer.
  • the one-chip system comprises, in particular, an FPGA, that is to say a so-called field programmable gate array, as well as a processor.
  • FPGA field programmable gate array
  • the use of an FPGA and a processor advantageously reduces the time required to identify the electrode type. This is because certain computational operations with an FPGA and other computations with a processor are performed faster.
  • the algorithms that run on the FPGA are implemented in particular with VHDL.
  • the algorithms that are executed on the processor for example, in the programming language C pro- programmed.
  • the identification features extracted from the image are invariant moments and / or an eccentricity and / or chromaticity coordinates of at least one electrode segment.
  • the invariant moments and the eccentricity of the at least one electrode segment are determined by a number of partial calculations performed one after the other. With the partial calculations, a variable describing the electrode segment is calculated in each case. For example, the object centroid is calculated with a first partial calculation, the object mass with a second partial calculation, with a third partial calculation the central moments, with a fourth partial calculation the normal central moments and with a fifth partial calculation the invariant moments.
  • the eccentricity is calculated from the central moments.
  • the post-processed image is superimposed with a color image of the electrode, in particular the transmitted image.
  • the pixels of the color image lying on an electrode segment are plotted in a flistogram. This histogram is used to determine the color value fraction of the electrode segment. Due to the additional consideration of this color value component, different colors of the electrodes are taken into account in the identification of the electrode type. This is useful, for example, if the electrodes are provided by the manufacturer with differently colored electrical supply lines, so that the electrodes can be identified by the colors of this supply line.
  • the one-chip system is adapted to perform at least a partial calculation, in particular a calculation of central moments of the electrode segment, on the programmable logic gate arrangement and at least one of the remaining partial calculations on the processor ,
  • the computing time required for this partial calculation is substantially reduced.
  • the object is also achieved by a method for operating an electrosurgical system, comprising a surgical instrument with an imaging system and a shaft, wherein at an distal end of the shaft, an electrode receptacle is present, which is suitable for receiving from an electrode to Performing a surgical treatment is formed, comprising the following steps:
  • the method for operating the electrosurgical system has the same or similar advantages as already mentioned with regard to the electrosurgical system itself, so that repetition should be dispensed with at this point.
  • the machine learning takes place in an artificial neural network, so that the electrode type of the electrode is identified by means of the artificial neural network.
  • the method steps of extracting the at least one identification feature, identifying the type of electrode and transmitting the at least one operating parameter are performed by the data processing unit.
  • the identification features are supplied to an input layer of the artificial neural network, a hidden layer of the artificial neural network is parametrized by means of parameter information stored on a database of the data processing unit, and the identified type of electrode is output from the output layer artificial neural network.
  • the activation function of the artificial neural network is a radial basis function.
  • the image is processed by means of the following processing steps:
  • Segment the postprocessed image by defining at least one electrode segment.
  • the data processing unit is preferably a one-chip system which comprises a programmable logic gate arrangement, in particular an FPGA, and a processor arranged on the one-chip system.
  • the identification features extracted from the image are preferably invariant moments and / or an eccentricity and / or chromaticity coordinates of at least one electrode segment.
  • FIG. 1 shows an electrosurgical system in schematically simplified representation
  • FIG. 2 shows a schematically simplified illustration of images showing electrodes of different electrode types
  • FIG. 3 shows a flow diagram of a method for operating an electrosurgical system
  • FIG. 4 shows a schematically simplified representation of an artificial neural network by means of which an electrode type is identified.
  • Fig. 1 shows, in a schematically simplified illustration, an electrochemical system 2, comprising a surgical instrument 4 with an imaging system, not shown in FIG. 1, and a shaft 6. At the distal end 8 of the shaft 6, there is an electrode holder. This serves to receive an electrode 10 for performing a surgical treatment.
  • a resectoscope is shown as a surgical instrument 4 in FIG. 1. Accordingly, the electrode 10 is a resection electrode, ie a loop.
  • the surgical instrument 4 is connected via a supply line 12 to a control unit 14.
  • the supply line 12 serves for the electrical supply of the surgical instrument 4 and also for the data transmission between the control unit 14 and the surgical instrument 4.
  • the control unit 14 in FIG. 1 is an example of a mobile component carrier or a rack and, in addition to further, generally known units, comprises a controller 16 and a data processing unit 20.
  • the controller 16 is used to control the surgical instrument 4 and, for example, specifies the voltage value of the voltage applied to the electrode 10.
  • the data processing unit 20 is, for example, a one-chip system (SoC), which comprises a database 22, a programmable logic gate arrangement 24, that is to say an FPGA, and a processor 26.
  • SoC one-chip system
  • the processor 26 is arranged as part of the SoC on a common board with the FPGA.
  • the control unit 14 in the exemplary arrangement shown in FIG. 1 is connected to an external computer system 18.
  • the external computer system 18 for example, images taken by the image acquisition system can be viewed and control commands transmitted to the surgical instrument 4 and / or the controller 16.
  • the controller 16 is part of the external computer system 18.
  • the image acquisition system of the surgical instrument 4 is set up to capture an image of the electrode 10 and to transmit it to the data processing unit 20.
  • the data transmission takes place for example via the supply line 12. It can also be done in other ways, such as wireless.
  • the data processing unit 20 is configured to extract at least one identification feature of the electrode 10 from the image, to identify an electrode type of the electrode 10 by evaluating the at least one identification feature and at least one operating parameter associated with the identified electrode type. For example, a voltage value to be transmitted to the controller 16.
  • the transmitted image is advantageously post-processed, for example to remove sources of interference from the image and to define electrode segments in the image.
  • the identification of the electrode type of the electrode 10 takes place by means of an artificial neural network, for example a Radial Basis Function Network.
  • This artificial neural network is previously trained with a sufficient number of training images so that it reliably detects the type of electrode.
  • the first image 50 shows an electrode 32 in the form of a loop
  • the second image 50 shows an electrode 34 in FIG The shape of a serrated rolling element
  • the third image 50 a button electrode 36.
  • the number of different electrode types is significantly larger.
  • the electrosurgical system 2 can be used with twelve different types of electrodes.
  • some types of electrodes are so similar that they are pure can not be distinguished reliably by a visual inspection by the medical staff.
  • three electrodes 32, 34, 36 were chosen, which are visually easy to distinguish.
  • the images 50 in FIG. 2 are square, for example 256 x 256 pixels.
  • the actual field of view of a typical image acquisition system of a surgical instrument 4 is often circular, as indicated in FIG. 2, so that an edge arises between the square frame and the circular field of view. This border is typically set to black for easier post-processing of the images 50.
  • FIG. 3 shows a schematically simplified flowchart of an exemplary method for operating an electrosurgical system 2 with the method steps 71 to 76.
  • the image acquisition system 9 present in the shaft 6 of the surgical instrument 4, which in FIG for illustrative purposes as a camera, an image 50 of the electrode 32 is detected. Subsequently, this image 50 is transferred to the data processing unit 20 in method step 72.
  • step 73 the image 50 in the data processing unit 20 is reworked.
  • the processing steps performed in step 73 include, for example, transforming the transmitting image into a grayscale image, applying various averaging filters, dilation operations and erosion operations, converting the image to a binary image, and similar processing steps.
  • the image 50 is segmented, with one or more Rere electrode segments 52 are set. In this case, for example, all white areas of a binary image are defined as the electrode segment 52 and all black areas as the background.
  • the identification features 54 are extracted from the electrode segment 52 in method step 74. This method step is also carried out in the data processing unit 20.
  • the identification features 54 of the electrode segment 52 are, for example, the invariant moments and / or the eccentricity and / or chromaticity coordinates of the electrode segment 52.
  • the calculation is used to determine the invariant - Moments necessary central moments on the programmable logic gate arrangement 24 performed.
  • the Programmable Logic Gate Array 24 (FPGA) is specially programmed for this task. Therefore, the calculation of the invariant moments is very efficient, ie in a very short time. The remaining partial calculations for determining the invariant moments are performed on the processor 26.
  • the identification features 54 are supplied to an artificial neural network 40.
  • an artificial neural network 40 As an example of machine learning.
  • the artificial neural network 40 has previously been trained on the detection of various types of electrodes and identifies the electrode type of the electrode 32 based on the identification features 54.
  • an electrode type data record 60 is subtracted. which contains by way of example an electrode type name 61 which corresponds to the identified electrode type.
  • the electrode data record 60 contains at least one operating parameter 68, that is, for example, a current and voltage range permissible in operation for the electrode type 62, 64, 66.
  • the method step 75 is also executed by the data processing unit 20.
  • the operating parameters 68 of the electrode type data record 60 are transmitted to the controller 16 so that the controller 16 can set or set, for example, the voltage value required for the electrode 32.
  • FIG. 4 shows schematically the artificial neural network 40.
  • the exemplary representation shown in FIG. 4 is a so-called Radial Basis Function Network which has three layers, namely an input layer 42, a hidden layer 44 and an output layer 46.
  • the input layer 42 has a plurality of input neurons 43, to each of which identification features 54 are supplied. For example, the invariant moments are fed to a first input neuron 43, the eccentricity to a second input neuron 43, and the chromaticity coordinates of the electrode segment 52 to a third input neuron 43.
  • the hidden layer 44 comprises a plurality of hidden neurons or centers 45, which perform the arithmetic operations necessary for the identification of the electrode type 62, 64, 66.
  • Each of the identification features 54 is supplied to each of the centers 45.
  • the parameterization of the hidden layer 44 that is, for example, the number and weighting of the centers 45, is determined during the training of the neural network 40. This training takes place for example on the basis of training images in which electrodes can be seen with known types of electrodes. For example, the number of centers 45 is twelve to forty depending on constraints such as the camera used by the imaging system 9.
  • the result of the identification is output from the output neuron 47 of the output layer 46.
  • a known probability is assigned to each known electrode type 62, 64, 66, which expresses how likely the electrode 32 is to be the respective electrode type 62, 64, 66. If this probability exceeds a threshold value, for example 50%, 90% or 99%, the corresponding electrode type 62, 64, 66 is output as a result of the identification. In Fig. 4 this is indicated by the fact that the electrode type 62 is marked with a hook, while the electrode types 64 and 66 are marked with an X.
  • the neural network 40 has thus successfully identified the electrode type 62 of the electrode 32. Through the use of an artificial neural network 40, accuracy in the identification of electrode types 62, 64, 66 of 99% and more can be achieved.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Surgery (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Signal Processing (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Optics & Photonics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Plasma & Fusion (AREA)
  • Otolaryngology (AREA)
  • Surgical Instruments (AREA)
  • Image Processing (AREA)

Abstract

L'invention concerne un système électro-chirurgical (2) et un procédé pour faire fonctionner un système électro-chirurgical (2). Le système électro-chirurgical (2) comprend un instrument chirurgical (4) comprenant système d'imagerie (9) et un manche (6), à l'extrémité distale (8) duquel se trouve un logement d'électrode. Le système d'imagerie (9) est configuré pour capter une image (50) de l'électrode (10, 32, 34, 36) et la transmettre à l'unité de traitement de données (20). L'unité de traitement de données (20) est configurée pour extraire de l'image (50) au moins une caractéristique d'identification (54) de l'électrode (10, 32, 34, 36), identifier un type d'électrode (62, 64, 66) de l'électrode (10, 32, 34, 36) par l'analyse de l'au moins une caractéristique d'identification (54), et transmettre à une commande (16) de l'instrument chirurgical (4) au moins un paramètre de fonctionnement (68) appartenant au type d'électrode (62, 64, 66) identifié. Le système électro-chirurgical (2) et le procédé sont conçus pour que l'unité de traitement de données (20) soit configurée pour identifier le type d'électrode (62, 64, 66) de l'électrode (10, 32, 34, 36) par un apprentissage machine.
PCT/EP2019/061648 2018-05-15 2019-05-07 Système électro-chirurgical et procédé pour faire fonctionner un système électro-chirurgical WO2019219450A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102018111659.4A DE102018111659A1 (de) 2018-05-15 2018-05-15 Elektrochirurgisches System und Verfahren zum Betreiben eines elektrochirurgischen Systems
DE102018111659.4 2018-05-15

Publications (1)

Publication Number Publication Date
WO2019219450A1 true WO2019219450A1 (fr) 2019-11-21

Family

ID=66448558

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2019/061648 WO2019219450A1 (fr) 2018-05-15 2019-05-07 Système électro-chirurgical et procédé pour faire fonctionner un système électro-chirurgical

Country Status (2)

Country Link
DE (1) DE102018111659A1 (fr)
WO (1) WO2019219450A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102013002832A1 (de) * 2013-03-25 2014-09-25 Rg Mechatronics Gmbh Roboter für die HF-Chirurgie
DE102014217095A1 (de) 2014-08-27 2016-03-03 Olympus Winter & Ibe Gmbh Elektrochirurgisches System und Verfahren zum Betreiben desselben
WO2017169098A1 (fr) * 2016-03-31 2017-10-05 ソニー株式会社 Dispositif et procédé de commande

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150164605A1 (en) * 2013-12-13 2015-06-18 General Electric Company Methods and systems for interventional imaging
DE102016218201A1 (de) * 2016-09-22 2018-03-22 Siemens Healthcare Gmbh Verfahren zu einer automatischen Auswahl zumindest eines Messprogramms für eine Magnetresonanzuntersuchung mit einer Magnetresonanzvorrichtung an einem Patienten

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102013002832A1 (de) * 2013-03-25 2014-09-25 Rg Mechatronics Gmbh Roboter für die HF-Chirurgie
DE102014217095A1 (de) 2014-08-27 2016-03-03 Olympus Winter & Ibe Gmbh Elektrochirurgisches System und Verfahren zum Betreiben desselben
WO2017169098A1 (fr) * 2016-03-31 2017-10-05 ソニー株式会社 Dispositif et procédé de commande

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"CARS 2017-Computer Assisted Radiology and Surgery Proceedings of the 31st International Congress and Exhibition Barcelona, Spain, June 20-24, 2017 ED - Barratt D; Jannin P; Fichtinger G; Cotin S", INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, SPRINGER, DE, vol. 12, no. 1, 19 May 2017 (2017-05-19), pages 1 - 286, XP036248842, ISSN: 1861-6410, [retrieved on 20170519], DOI: 10.1007/S11548-017-1588-3 *

Also Published As

Publication number Publication date
DE102018111659A1 (de) 2019-11-21

Similar Documents

Publication Publication Date Title
DE102018105334B4 (de) Bildverarbeitungsvorrichtung und Bildverarbeitungsverfahren zur Berechnung der Bildwahrscheinlichkeit eines aus einem Eingangsbild erfassten Zielobjekts
DE102005039685B4 (de) Verfahren zur Identifizierung eines kontrastierten Blutgefäßes in digitalen Bilddaten
DE102008040804B4 (de) Verfahren, Operationsmikroskop und Analysesystem zur quantitativen Darstellung des Blutflusses
EP3332730B1 (fr) Procédé et système de suivi permettant le suivi d'un objet médical
EP3540632B1 (fr) Procédé pour la classification des échantillons tissulaires
DE112019005696T5 (de) Verfahren und Vorrichtung zur Berechnung eines Koronararterien-Kalzium-Scores
DE102018210973A1 (de) Verfahren zu einem Überwachen eines Patienten während einer medizinischen Bildgebungsuntersuchung, insbesondere einer Magnetresonanzuntersuchung
WO2009080791A1 (fr) Procédé de détection et/ou de suivi de la position de composants caractéristiques de l'oeil
WO2012013186A2 (fr) Procédé et dispositif de détermination de la torsion d'un oeil
EP1180258A1 (fr) Reconnaissance de formes par examen de caracteristiques complementaires apres traitement partiel
EP1143373A1 (fr) Méthode pour acquérir des images sans erreur avec un capteur électronique
DE102016105962A1 (de) Positionsermittlungsanordnung für Intraokularlinse
EP3185799B1 (fr) Système électrochirurgical et procédé pour faire fonctionner celui-ci
DE102004003381B4 (de) Verfahren zur Bestimmung der Lage einer Schicht in einem Untersuchungsgebiet, in welcher Schicht eine Schichtbildaufnahme erfolgen soll
WO2019219450A1 (fr) Système électro-chirurgical et procédé pour faire fonctionner un système électro-chirurgical
EP3155588B1 (fr) Système d'acquisition et de traitement d'une image d'un corps complet et procédé pour faire fonctionner celui-ci
DE102018211477A1 (de) Verfahren zum automatischen Bestimmen einer Gewichtung für ein Roadmap-Verfahren, Computerprogramm, Datenspeicher und entsprechendes bildgebendes Gerät
DE112019005655T5 (de) Myokardbildanalyseverfahren und -vorrichtung
EP3582140B1 (fr) Système de détection automatique des objets de travail de laboratoire ainsi que procédé de fonctionnement d'un système de détection automatique des objets de travail de laboratoire
DE102007055921A1 (de) Verfahren zur Ermittlung von Eigenschaften bzw. Ermittlung und/oder Verfolgung der Position des Zentrums charakteristischer Augenbestandteile
DE102018124114B4 (de) Verfahren zum Auffinden von funktionstragendem Gehirngewebe mittels elektrischer Stimulation
DE102009038248A1 (de) Verfahren zum Entfernen modularer Software
EP3581935A1 (fr) Système de détection automatique des objets de travail de laboratoire ainsi que procédé de fonctionnement d'un système de détection automatique des objets de travail de laboratoire
WO2009124679A1 (fr) Procédé pour détecter et segmenter automatiquement la papille lors de fonds d’œil
DE102010054168B4 (de) Verfahren, Vorrichtung und Programm zur Bestimmung der torsionalen Komponente der Augenposition

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19722874

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19722874

Country of ref document: EP

Kind code of ref document: A1