Abstract: There is described a method for computer-aided learning of a neural network, with a plurality of neurons in which the neurons of the neural network are divided into at least two layers, comprising a first layer and a second layer crosslinked with the first layer. In the first layer input information is respectively represented by one or more characteristic values from one or several characteristics, wherein every characteristic value comprises one or more neurons of the first layer. A plurality of categories is stored in the second layer, wherein every category comprises one or more neurons of the second layer. For one or several pieces of input information, respectively at least one category in the second layer is assigned to the characteristic values of the input information in the first layer.

Abstract: In a screening test method, and a device for implementing the screening test method, a diagnostic substance is provided that contains at least one biomarker connected with at least one ferromagnetic particle, the biomarker binding specifically to a target molecule that is formed by specific pathological prostrate tissue. The diagnostic substance is administered to the blood stream of a patient. A magnetometer is used to detect enrichment of the ferromagnetic particle in the prostrate, as an indicator of a level of the specific pathological prostrate tissue.

Abstract: In a method for treating a carcinoma in a patient, a medicine is administered via the blood stream of the patient that appears, to the patient's immune system, that tissue of the carcinoma is an inflammation source. The medicine employs two active components that are coupled to each other in a form allowing administration of the two active components to the carcinoma via the blood stream of the patient. A first of the active components is at least one coupling molecule that specifically tethers to a target molecule formed by cancer tissue of the carcinoma. A second of the active ingredients is at least one signal molecule typical to inflammation, or at least one originating molecule encoding such a signal molecule, that induces the immune system of the body to attack the cancer cells.

Abstract: In a screening test method, and a device for implementing the screening test method, a diagnostic substance is provided that contains at least one biomarker connected with at least one ferromagnetic particle, the biomarker binding specifically to a target molecule that is formed by specific pathological prostrate tissue. The diagnostic substance is administered to the blood stream of a patient. A magnetometer is used to detect enrichment of the ferromagnetic particle in the prostrate, as an indicator of a level of the specific pathological prostrate tissue.

Abstract: In order to determine the aggressiveness of a prostate tumor, a diagnostic substance is administered to a patient that includes a biomarker provided with a first label that is detectable with a detection device and that specifically binds to a VEGF molecule, and that contains a biomarker that binds specifically to a target molecule that occurs uniformly in the endothelium of blood vessels of healthy tissue and the blood vessels of a prostate tumor, and that is provided with a second label that is detectable with the detection device independently of the first label.

Abstract: A diagnostic substance for use in a method for diagnosing prostate diseases contains multiple different coupling molecules that respectively bind to signal molecules (target molecules) of a molecular surface structure of a pathological tissue that is associated with a prostate disease. A first of the coupling molecules specifically binds to signal molecules of cancer tissue, and a second of the coupling molecules specifically binds to signal molecules formed in inflamed tissue. First and second markers are respectively associated with the first and second coupling molecules, the first and second markers being detectable, and differentiated from each other, with a detection device.

Abstract: There is described a method for computer-aided learning of a neural network, with a plurality of neurons in which the neurons of the neural network are divided into at least two layers, comprising a first layer and a second layer crosslinked with the first layer. In the first layer input information is respectively represented by one or more characteristic values from one or several characteristics, wherein every characteristic value comprises one or more neurons of the first layer. A plurality of categories is stored in the second layer, wherein every category comprises one or more neurons of the second layer. For one or several pieces of input information, respectively at least one category in the second layer is assigned to the characteristic values of the input information in the first layer.

Abstract: In a method to determine at least one parameter pertaining to a prostate of a patient, an integrated diagnostic support system implements the following steps. A first risk value for prostate illness is determined using a screening method. In the event that this first characteristic risk value exceeds a first limit value, at least one second characteristic risk value for prostate illness and its location are determined using a method supplying a medical image of the patient. An integrated report system outputs at least one of the characteristic risk values and/or the location. A corresponding device has a mini-laboratory analysis unit for the screening test, an intelligent decision support system for the first characteristic risk value, a first interface with an imaging system, an evaluation system for the medical image for the second characteristic risk value, and a report system with a user interface.

Abstract: The invention concerns a medicine for treatment of prostate cancer and a corresponding treatment method. The medicine can be supplied to a prostate tumor through the bloodstream, contains an active component and a binding component as well as ultrasound microbubbles. The binding component includes coupling molecules that specifically bind to a determined target molecule formed in the endothelium of tumor-associated blood vessels and that is typical of the tumor or the tumor stage. The active component contains at least one chemotherapeutic substance. The coupling molecules are bound to the outside of the microbubbles and active substance molecules are likewise bound to the outside of the microbubbles or are enclosed by the microbubbles.

Abstract: A diagnosis substance for application in a method for diagnosis of pathological tissue, contains at least one virus population with virus particles specifically binding to target molecules typical of a specific pathological tissue, with a label that is detectable with the use of a detection device being bound to the virus particles. In a method for production of such a diagnosis substance, the principle of directed biological evolution is applied.

Abstract: A medicine for treatment of a carcinoma which can be supplied to the carcinoma via the circulatory system, contains two active components coupled to one another. The first active component is formed of at least one coupling molecule that specifically tethers to a target molecule formed by the cancer tissue. The second active component is formed of at least one signal molecule typical to inflammation, or of at least originating molecule encoding such a signal molecule.

Abstract: In a method for diagnosis and treatment of a patient with a tumor relating to prostate cancer, the following steps are implemented. A differential diagnosis of prostate cancer versus prostatitis and/or BPH is conducted on a patient using a cost-effective diagnosis method. If prostate cancer is diagnosed in the patient using a cost-effective measurement method, a characteristic value for the tumor aggressiveness of the prostate cancer is determined. A watchful waiting treatment is implemented with the patient given a characteristic value below a predeterminable first limit value. The size and position of the tumor is determined using a cost-effective method given a characteristic value above the first limit value. A cost-effective ultrasonic theranosis or a conventional therapy is conducted for a size below a second predeterminable limit value. The presence of metastases in the patient is checked, with a cost-intensive method generating image information, for a size above the second limit value.

Abstract: In a method for diagnosis and treatment of a patient with regard to prostatitis, a differential diagnosis of prostatitis versus prostate cancer and/or BPH is conducted on a patient using a cost-effective diagnosis method. Given diagnosed prostatitis, a cost-effective decision test is implemented on the patient to determine whether the patient exhibits complaints locally in the region of the prostate or in the rest of the body. A molecular inflammation marker is administered to the patient, wherein a cost-effective imaging method is implemented in the region of the prostate of the patient given local complaints or a cost-intensive imaging method is implemented on the entire patient given complaints in the rest of the body. An inflammation-inhibiting treatment is implemented in the body region of the patient that is detected as inflamed via the respective imaging method.

Abstract: In a method for imaging a prostate tumor in which a contrast agent that can be distributed via the circulatory system is administered to the patient, the contrast agent contains at least one type of biomarkers which are bound to a ferromagnetic particle and specifically bind to a target molecule typical of the tumor and formed within the tumor or in a tissue adjacent to the tumor. The imaging ensues with the use of magnetic resonance tomography.

Abstract: The invention provides a method for semantic relation extraction, wherein on the basis of an annotated training corpus having tokens with associated relational labels each indicating a relation between the respective token and a selectable key entity semantic relation between said key entity and other entities are directly extracted from unstructured text using a probabilistic extraction model.

Abstract: There is described a method for computer-assisted processing of measured values detected in a sensor network, with the sensor network comprising a plurality of sensor nodes, which each feature one or more sensors for detection of the measured values, with the measured values of a number of adjacent sensor nodes being known in a sensor node. A multi-area neural network will be mapped onto a corresponding sensor network by the inventive method, which creates the opportunity, with the aid of the information from adjacent sensors, even with incorrect or failed measurements of a sensor node, of guaranteeing detection of a global situation at the location of the sensor node. A sensor network operated with such a method is in such cases more robust against the failure of a few sensors, since a corresponding measured value can be estimated in a suitable way, so that the measurement not available can be replaced by the estimated measured value.

Abstract: At least one genotype-phenotype relationship is extracted based on genotype data of a group of genes for different organisms of a group of organisms. A first database stores genotype data of each organism of the group of organisms. For each organism a genotype vector is stored having a vector component for each gene of the group of genes. A second database stores phenotype data of each organism of the group of organisms. For each organism a phenotype vector is stored having a vector component for each phenotype feature of a group of phenotype features of the organism. A calculation unit uses a machine learning process to classify organisms with different phenotypes depending on the genotype vectors stored in the first database and the phenotype vectors stored in the second database to extract the genotype-phenotype relationship.

Abstract: A method for evaluating an image (fMRI-image) of the brain that has been obtained by functional magnetic resonance tomography is provided. According to the method, a neuronal network is used to simulate the activities of the brain. Supposed disorders of the brain are simulated in the neuronal network (as a disturbed neuronal network). The activities determined in the brain can be artificially simulated in the model and its effect on the complex synergy of the areas of the brain can be quantified. The comparison with the fMRI image or fMRI activity pattern relating to the patient enables the cause of the disorders to be localized, thus leading to a successful diagnosis.

Abstract: An equivalence relationship is created between a) the functional network of the genome and proteome and b) a neuronal network. Both networks represent highly cross-linked feedback systems. The equivalence relationship makes it possible to model the functional network of proteins of and genes by an equivalent artificial neuronal network. The dynamic interaction of genes and regulatory proteins is modeled by a dynamic neuronal network. The method uses information obtained in a temporal sequence of gene expression patterns for identification of causal regulatory correlations, thereby enabling target proteins to be identified on a systematic basis.

Abstract: A regulator genetic network of a cell is analyzed using a causal network after predefining a gene expression rate for a selected gene of the regulatory genetic network. The causal network is used to generate a resultant gene expression pattern relating to the genetic network for the predefined gene expression rate. The generated resultant gene expression pattern is subsequently compared with a predefined gene expression pattern of the regulatory genetic network.