EP1425679A2 - Systeme comprenant des neurones artificiels, destine a decrire un comportement de transmission d'une cellule nerveuse d'excitation et procede pour determiner un comportement de transmission d'une cellule nerveuse d'excitation par utilisation de neurones artificiels - Google Patents

Systeme comprenant des neurones artificiels, destine a decrire un comportement de transmission d'une cellule nerveuse d'excitation et procede pour determiner un comportement de transmission d'une cellule nerveuse d'excitation par utilisation de neurones artificiels

Info

Publication number
EP1425679A2
EP1425679A2 EP02774330A EP02774330A EP1425679A2 EP 1425679 A2 EP1425679 A2 EP 1425679A2 EP 02774330 A EP02774330 A EP 02774330A EP 02774330 A EP02774330 A EP 02774330A EP 1425679 A2 EP1425679 A2 EP 1425679A2
Authority
EP
European Patent Office
Prior art keywords
artificial neuron
nerve cell
signal
input
activity
Prior art date
Legal status (The legal status 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 status listed.)
Withdrawn
Application number
EP02774330A
Other languages
German (de)
English (en)
Inventor
Bernd SCHÜRMANN
Martin Stetter
Gustavo Deco
Jan Storck
Silvia Corchs
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens AG
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 Siemens AG filed Critical Siemens AG
Publication of EP1425679A2 publication Critical patent/EP1425679A2/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders

Definitions

  • the invention relates to the determination and description of a transmission behavior of an exciting nerve cell using artificial neurons.
  • nerve cells nerve cells
  • their biological functionality i.e. to reproduce their biological behavior using artificial neurons.
  • FIG. 2 schematically shows the structure of such a nerve cell 200 that can be simulated by an artificial neuron.
  • This nerve cell 200 a basic building block of the brain, has D so-called dendrites 210, i.e. thin, tubular and mostly heavily branched extensions, with which the nerve cell receives 200 input signals. These input signals, a so-called synaptic activity, are processed 3 in the nerve cell 200, in particular there in a cell body 220, and passed on as electrical nerve impulses or electrical potentials, also referred to as action potential or “spiking activity”.
  • the electrical nerve impulses are forwarded via a nerve fiber 230, the so-called axon, which branches 231 at its end.
  • a synapse 240 is thus a contact point between two nerve cells or the contact point between an end of an axon 230 of a neuron and a dendrite 210 of another neuron.
  • Inhibitory synapses 252 lower electrical potentials to be transmitted or to be transmitted, exciting synapses 251 increase electrical potentials to be transmitted.
  • an artificial nerve cell (artificial neuron) is known from [1], which simulates a (biological) nerve cell.
  • an artificial neuron is a mathematical representation which, in accordance with the transmission behavior of the biological nerve cell, maps an input variable of the artificial neuron to an output variable of the artificial neuron.
  • an artificial neuron consists of three components: the cell body, the dendrimers) th, sum which input signals to the artificial neuron, the axon, which forwards the output of the artificial neuron outward branches and with the dendrites subsequent artificial neurons come into contact via synapses.
  • a strength of a synapse or the type of synapse is usually represented by a numerical value or its sign. This value is called the connection weight.
  • the previously known magnetic resonance tomography (also magnetic resonance imaging, abbreviated: MR) is an imaging method that generates sectional images of the human body without the use of stressful X-rays. Instead, it takes advantage of the behavior of body tissue in a strong magnetic field. Pathological changes in the body tissue, for example in the brain or spinal cord, can be identified.
  • BOLD signal Bit Oxygenation Level Dependent
  • fMRI measurements shows the course of the activity of the individual areas over a certain period of time, for example during cognitive processes as a result of certain perceptual processes or motor tasks. Functional disorders in the brain are therefore implicit in the measured fMRI signals.
  • the fMRI-5 measurements are analyzed using mathematical methods and thus direct conclusions can be drawn about functional disorders in a brain and their causes.
  • the currently known and used analysis methods usually have the disadvantage that they are insufficiently accurate .5 and thus possibly lead to incorrect conclusions in a diagnosis and / or are inefficient, i.e. are too slow and too complex to use the respective analysis method.
  • [6] discloses a software tool for an fMRI analysis method, an “fmri.pro”.
  • a device for carrying out the fMRI technique is known from [7].
  • the object of the invention is to provide an arrangement and an associated method with which the functionality, in particular the transmission behavior, of a nerve cell is better, i.e. with greater accuracy and consistency
  • the arrangement with artificial neurons to describe a transmission behavior of an exciting nerve cell, through which transmission behavior an external and an internal synaptic activity is converted into an action potential activity shows: .0 -. a first artificial neuron, which describes the excitatory nerve cell, with a first input for supplying a first input signal which corresponds to the external synaptic activity, with a second input for supplying a second input signal which corresponds to .5 the internal synaptic activity, and with a Output for the discharge of an output signal which corresponds to the action potential activity,
  • an inhibitory nerve cell describes which second artificial neuron generates the second input signal of the first artificial neuron.
  • ! 5 becomes a second input signal, which corresponds to the internal synaptic activity and which is used by a second input with the first artificial neuron.
  • bound second artificial neuron which describes an inhibitory nerve cell, is produced, - at an output of the first artificial neuron, an output signal which corresponds to the action potential activity is dissipated using the first and the second input signal and the output signal the transmission behavior determined.
  • an artificial neuron is to be understood as a computing element which maps an input variable supplied to the computing element using a predefinable mapping to an output variable which can be dissipated by the computing element.
  • the mapping can be a linear as well as a non-linear mapping and describes a function or a transmission behavior of an inhibitory or an exciting nerve cell.
  • the exciting and the inhibiting nerve cell or the first and the second artificial neuron can also be considered as a unit.
  • Such a unit can be referred to as “Voxel X.
  • the invention has the particular advantage that it enables the description of complex nerve cell structures as they occur in the brain and their complex activity patterns in a particularly simple and precise manner.
  • the invention thus enables reliable conclusions to be drawn about functional disorders of nerve cells or nerve cell structures.
  • Computer program is stored, which carries out the invention or the training.
  • the first input signal is generated by a further artificial neuron which describes a further excitatory nerve cell and which is connected to the first artificial neuron via the first input.
  • the first artificial neuron has a self-feedback for self-excitation by a self-excitation signal, through which self-feedback a further output of the first artificial neuron is connected to a third input of the first artificial neuron.
  • the exciting nerve cell 5 described by the first artificial neuron represents a large number of exciting nerve cells, in particular a large number of exciting nerve cells in the brain or in one Area of the brain.
  • the inhibitory nerve cell described by the second artificial neuron is a
  • the large number of excitatory nerve cells and the large number of inhibitory nerve cells are assigned to the same predetermined brain area or belong to the same brain area.
  • nerve cells summarized in a representative and described by a representative are referred to as a population.
  • an inhibitory population results if 5 a large number of inhibitory nerve cells are combined, or an exciting population if a large number of exciting nerve cells are combined.
  • a unit composed of an exciting and an inhibiting population can also be drawn as a voxel. 0
  • a mean field model when combining nerve cells into a population. As a result, individual interaction effects between individual nerve cells are no longer taken into account, but 5 these individual interactions are approximated by means of an averaged interaction.
  • Such a mean field model can also be used when describing a single nerve cell or when describing a single voxel.
  • the output signal of the first artificial neuron of the first voxel is the first input signal to the first artificial neuron of the second voxel and as another input signal to the second artificial neuron of the second voxel
  • the excitatory nerve cell of the first voxel is clearly connected to both the excitatory nerve cell and the inhibitory nerve cell of the second voxel! 0.
  • mapping a differential approach i.e. a time-variant approach to provide, for example:
  • ⁇ is a time constant d / dt is derived from a time variable ta
  • b is an index for a nerve cell or for a population
  • m is a “spiking” activity
  • h is a synaptic activity
  • g (. ' ) is a mapping rule.
  • Such weights which can be determined using a physiological and / or neuroanatomical knowledge, can be used to emulate a nerve conduction, in particular a synaptic transmission, in the biological model, for example the transmission of a nerve signal from an axon of a nerve cell via a synapse a dendrite of a subsequent nerve cell.
  • all weights are set as the same and / or time-invariant as part of an idealization in the reproduction of the biological model.
  • the output signal which corresponds to an action potential or a “spiking” activity in the biological model, is further processed in such a way that a number and / or statistics of action potentials are determined from the output signal.
  • the invention is used in functional magnetic resonance imaging (fMRI).
  • fMRI functional magnetic resonance imaging
  • BOLD signal Blood Oxygenation Level Dependent Signal
  • ! 0 signal is determined as the first input signal using the invention, the output signal representing brain activity.
  • FIG. 1 shows a schematic representation of nerve conduction in a voxel according to an exemplary embodiment
  • FIG. 2 shows a schematic representation of a structure of a nerve cell
  • FIG. 4 shows a schematic representation of nerve conduction in an artificial voxel according to an exemplary embodiment
  • FIG. 5 Schematic representation of steps in nerve conduction in a voxel according to an exemplary embodiment
  • FIG. 6 shows a schematic representation of a nerve conduction in LO two interlinked voxels according to an exemplary embodiment
  • Figure 7 Schematic representation of a transmission behavior of a voxel according to an embodiment L5 using an input signal and an output signal, which describe the transmission behavior of the voxel.
  • Exemplary embodiment functional magnetic resonance imaging
  • FIG. 3 shows a device 300 for performing a functional magnetic resonance tomography or magnetic resonance tomography (abbreviated to fMRI), a functional magnetic resonance tomograph or magnetic resonance tomograph 300.
  • fMRI functional magnetic resonance tomography or magnetic resonance tomography
  • the magnetic resonance tomograph 300 has a closed tube 310, which is embedded in a magnet 320 in such a way that it generates a strong magnetic field in the tube 310.
  • the MRI scanner 300 has a patient table 330 which can be moved into the tube 310 5 and on which a patient is supported during an examination.
  • the magnetic resonance tomograph 300 has a control device 331, which enables the patient table 330 to be checked and controlled during the examination, for example a controlled entry of the patient table 330 into the tube 320.
  • the MRI scanner 300 has a measuring device 340 for measuring a BOLD signal (Blood Oxygenation r Level Dependent), an associated evaluation device.
  • BOLD signal Bit Oxygenation r Level Dependent
  • LO device 341 for evaluating the measured BOLD signal, in this case a high-performance computer, as well as an operating or interaction device 342 for operating personnel and a display device 343 for displaying an examination result.
  • the components of the magnetic resonance tomograph 300 are functionally connected to one another, for example via signal or data lines via which data and signals can be transmitted.
  • the neuronal activity in areas of the brain of a patient can be measured on the basis of the fMRI technique.
  • the BOLD signal (Blood Oxygenation Level Dependent) is measured in individual areas of the patient's brain by means of the measuring device 340, which is related to the neuronal activity in the respective areas.
  • fMRI measurements shows the course of the activity of the individual areas over a certain period of time, for example during cognitive processes as a result of certain perceptual processes or motor tasks which are to be carried out by the patient during an examination 5.
  • Functional disorders in the patient's brain are therefore implicit in the measured fMRI signals.
  • the evaluation device 341 which provides or carries out a corresponding analysis method, the fMRI measurements, ie the BOLD signals measured in individual areas of the brain, are analyzed, thereby the brain activity in the form of corresponding activation patterns in the examined areas in the Brain is determined and from this direct conclusions can be drawn about functional disorders in the brain and their causes.
  • the analysis method provided by the evaluation device 340 is based on a model of the brain, the neuron structures in the brain and their (transmission) behavior, on the basis of which the measured BOLD signal is analyzed and evaluated.
  • the results or the conclusions of an examination are shown on the display device 343 and can be processed further by means of the operating and interaction device 342 in connection with the evaluation device 341.
  • a direction of flow of a signal in a signal line for example a direction of flow of a nerve signal in a nerve line, is identified by an arrow direction.
  • FIG. 1 shows a basic structure 100 of a complex nerve cell structure in the brain, comprising a large number of individually linked nerve cells.
  • this basic structure 100 a voxel, an excitatory nerve cell 101 is connected to an inhibitory nerve cell 102 via a first 103 and a second nerve line 104 in such a way that nerve signals of the inhibitory nerve cell 102 can be transmitted into the excitatory 5 nerve cell 101 and nerve signals of the excitatory nerve cell 101 into that inhibitory nerve cell 101 are transferable.
  • the excitatory nerve cell 101 has a third nerve conduction 105 (dendrite), by means of which nerve signals from another nerve cell of another voxel can be transmitted to the excitatory nerve cell 101 (post-synaptic activity h).
  • a third nerve conduction 105 dendrite
  • the exciting nerve cell 101 also has a fourth nerve line 106 (axon), by means of which nerve signals can be transmitted from the exciting nerve cell 101 into a second further nerve cell of a second further voxel (spiking activity M).
  • the exciting nerve cell 101 and the inhibitory nerve cell 102 each have a self-exciting nerve conduction 107 and 108.
  • Each nerve line 103 to 108 is assigned a weight w (wl to w6; 111 to 116), which represents a synaptic transmission of the respective nerve signal.
  • FIG. 4 shows the corresponding voxel model 400 of the voxel 100 shown in FIG. 10.
  • a first artificial neuron 101 with a second artificial neuron 102 is over a first 103 and the second signal line 104 are connected in such a way that signals from the second artificial neuron 102 can be transmitted to the first artificial neuron 101 and signals from the first artificial neuron 101 can be transmitted to the second artificial neuron 101.
  • the first artificial neuron 101 has a third signal line 105, by means of which signals from a further artificial neuron of a further voxel can be transmitted into the first artificial neuron 101 (post-synaptic activity h).
  • the first artificial neuron 101 also has a fourth signal line 106, by means of which signals from the first L5 artificial neuron 101 can be transmitted to a second further artificial neuron of a second further voxel (spiking activity M).
  • Each signal line 103 to 106 is assigned a weight w (wl to 20 w4; 111 to 114), which represents a synaptic transmission of the nerve signal on which the respective signal is based.
  • FIG. 5 shows a list 500 of steps 501 to 504, 25 which take place or are carried out in the biological basic structure 100 and in the voxel model 400.
  • a neuron which describes the excitatory nerve cell, is supplied at a first input with a first input signal, which corresponds to the external synaptic activity.
  • a second input signal which corresponds to the internal synaptic activity and which is connected to the first neuron via the second input, is connected to a second input 35 of the first neuron. which second neurons, which describes an inhibitory nerve cell, is produced.
  • an output signal which corresponds to the action potential activity is carried off at an output of the first 5 neurons.
  • a .0 transmission behavior of the basic biological structure 100 or voxels or the model 400 is determined using the first and the second input signal and the output signal.
  • FIG. 6 shows a link between two voxel or voxel models 120 and 121 according to voxel 100 or voxel .5 model 400.
  • the two voxels or voxel models 120 and 121 are linked to one another in such a way that the excitatory nerve cell 101 of the first voxel 120 is connected both to the excitatory nerve cell 122 5 of the second voxel 121 and to the inhibitory nerve cell 123 of the second voxel 121 via lines 106 and 110 is connected.
  • Weights of lines that transmit output signals from exciting neurons are positive. Weights of lines that transmit output signals from inhibitory neurons are negative.
  • M a g ( ⁇ w from M b ) b effective synaptic activity: ⁇
  • Mi2 g (wM e 2 + wM e i) w 2 - n 2 + 2wM e ! + wM e 2 + Mi2
  • the BOLD signal measured for this area is applied to the model described above as synaptic activity (He2 + Hi2).
  • the corresponding spiking activity Me2 is determined from this as an immediate variable for the neuronal activity in the selected brain area.
  • FIG. 7 shows, by way of example, a first and a second time profile 701 and 702 of such a BOLD signal for a first and a second brain area together with the first and the second associated time profile 711 and 712 of the first and second spiking activity determined therefrom or the corresponding one first and second neuronal activity pattern.
  • Functional disturbances in this area can be recognized from the signal course of the spiking activity Me2 or from the activity pattern generated by the signal course in a brain area.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Epidemiology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Pathology (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Primary Health Care (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Investigating Or Analysing Biological Materials (AREA)
  • Feedback Control In General (AREA)

Abstract

La présente invention concerne la détermination et la description d'un comportement de transmission d'une cellule nerveuse d'excitation par utilisation de neurones artificiels. Un premier neurone artificiel qui décrit la cellule nerveuse d'excitation, présente une première entrée destinée à l'apport d'un premier signal d'entrée qui correspond à l'activité synaptique externe, une seconde entrée destinée à l'apport d'un second signal d'entrée qui correspond à l'activité synaptique interne et qui est produit par un second neurone artificiel, ainsi qu'une sortie destinée à la production d'un signal de sortie qui correspond à l'activité de potentiel d'action.
EP02774330A 2001-09-12 2002-09-11 Systeme comprenant des neurones artificiels, destine a decrire un comportement de transmission d'une cellule nerveuse d'excitation et procede pour determiner un comportement de transmission d'une cellule nerveuse d'excitation par utilisation de neurones artificiels Withdrawn EP1425679A2 (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
DE10144920 2001-09-12
DE10144920 2001-09-12
PCT/DE2002/003381 WO2003023642A2 (fr) 2001-09-12 2002-09-11 Systeme comprenant des neurones artificiels, destine a decrire un comportement de transmission d'une cellule nerveuse d'excitation et procede pour determiner un comportement de transmission d'une cellule nerveuse d'excitation par utilisation de neurones artificiels

Publications (1)

Publication Number Publication Date
EP1425679A2 true EP1425679A2 (fr) 2004-06-09

Family

ID=7698770

Family Applications (1)

Application Number Title Priority Date Filing Date
EP02774330A Withdrawn EP1425679A2 (fr) 2001-09-12 2002-09-11 Systeme comprenant des neurones artificiels, destine a decrire un comportement de transmission d'une cellule nerveuse d'excitation et procede pour determiner un comportement de transmission d'une cellule nerveuse d'excitation par utilisation de neurones artificiels

Country Status (4)

Country Link
US (1) US20040234508A1 (fr)
EP (1) EP1425679A2 (fr)
JP (1) JP2005502147A (fr)
WO (1) WO2003023642A2 (fr)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE10342274B4 (de) * 2003-09-12 2007-11-15 Siemens Ag Identifizieren pharmazeutischer Targets
DE10344345B3 (de) 2003-09-24 2005-05-12 Siemens Ag Verfahren zur Kommunikation in einem Adhoc-Funkkommunikationssystem
EP2718864A4 (fr) * 2011-06-09 2016-06-29 Univ Wake Forest Health Sciences Modèle de cerveau à base d'agents et procédés associés
JP6516321B2 (ja) * 2015-02-09 2019-05-22 学校法人日本大学 形状特徴抽出方法、形状特徴抽出処理装置、形状記述方法及び形状分類方法
CN108711351A (zh) * 2018-06-27 2018-10-26 兰州交通大学 基于fpga的电子突触实验平台

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4906940A (en) * 1987-08-24 1990-03-06 Science Applications International Corporation Process and apparatus for the automatic detection and extraction of features in images and displays

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO03023642A2 *

Also Published As

Publication number Publication date
WO2003023642A2 (fr) 2003-03-20
JP2005502147A (ja) 2005-01-20
WO2003023642A3 (fr) 2003-08-14
US20040234508A1 (en) 2004-11-25

Similar Documents

Publication Publication Date Title
DE112018002822T5 (de) Klassifizieren neuronaler netze
WO2004021243A2 (fr) Procede et programme informatique a moyens de code programme et produit programme informatique pour l'analyse d'une activite d'une preparation pharmaceutique
EP1456798A2 (fr) Evaluation d'images du cerveau obtenues par tomographie par resonance magnetique fonctionnelle
DE112013000671T5 (de) Gerät zum Planen einer Neuromodulationsbehandlung
DE112020003050T5 (de) Fehlerkompensation in analogen neuronalen netzen
DE4039648A1 (de) Messwertverarbeitungssystem fuer ein biologisches objekt
EP1425679A2 (fr) Systeme comprenant des neurones artificiels, destine a decrire un comportement de transmission d'une cellule nerveuse d'excitation et procede pour determiner un comportement de transmission d'une cellule nerveuse d'excitation par utilisation de neurones artificiels
DE10121802A1 (de) Verfahren zur Bilderzeugung bei einem Kernspintomographie-Gerät und Kernspintomographie-Gerät
DE112006003729T5 (de) Testzeitberechnungseinrichtung
EP1175865B1 (fr) Appareil cardiologique implantable équipé avec un procédé d'évaluation pour la détermination de la stationarité temporelle de signaux cardiologique mesuré
DE19913547C2 (de) Verfahren zur Nachbildung der von Gradientenspulen eines Kernspinresonanzgeräts erzeugten elektrischen Stimulationen in einem Untersuchungsobjekt und Vorrichtung zur Durchführung des Verfahrens
DE4121453C2 (de) Näherungsschlußfolgerungsvorrichtung
DE102019204118A1 (de) Verfahren zum Übertragen eines Merkmals eines ersten Bilds an ein zweites Bild
DE212005000005U1 (de) Vorrichtung zur adaptiven Datenanalyse
EP1527354A1 (fr) Procede, dispositif et programme informatique comprenant un systeme de code de programmation pour analyser des activites neuronales dans des zones neuronales
EP0978052B1 (fr) Selection assistee par ordinateur de donnees d'entrainement pour reseau neuronal
EP1527406A2 (fr) Procede, dispositif, programme informatique comprenant un systeme de code de programmation et produit de programme informatique pour analyser des activites neuronales dans des zones neuronales
EP1359539A2 (fr) Modèle neurodynamique de traitement d'informations visuelles
DE102018203784A1 (de) Verfahren zur Ermittlung einer örtlichen Konzentrationsverteilung von magnetischen Partikeln, System zur visuellen Darstellung von MPI-Bilddaten
WO2004021244A2 (fr) Procede, dispositif et programme informatique avec codes de programme et produit de programme pour analyser des activites neuronales dans des zones neuronales
EP1114398B1 (fr) Procede pour entrainer un reseau neuronal, procede de classification d'une sequence de grandeurs d'entree au moyen d'un reseau neuronal, reseau neuronal et dispositif pour l'entrainement d'un reseau neuronal
EP1071985B1 (fr) Composante logicielle pour un systeme de diagnostic avec projection assistee
WO2004021246A2 (fr) Procede, dispositif, programme informatique comprenant un systeme de code de programmation et produit de programme informatique pour determiner une irregularite dans une structure neuronale
DE102020106857A1 (de) Mikroskopiesystem und verfahren zum verarbeiten von mikroskopbildern
DE102022206850A1 (de) Vorrichtung und Verfahren zur Modellierung eines Magnetresonanztomografiesystems

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20040213

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR IE IT LI LU MC NL PT SE SK TR

17Q First examination report despatched

Effective date: 20041209

17Q First examination report despatched

Effective date: 20041209

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20070413