Metasystems Hard & Software Gmbh

Andreas Plesch

Thomas Lörch

Thomas Loerch

Ilse Chudoba

Oskar A Haas

Jorma Isola

Thomas L&ouml;rch

Methods are provided for efficient training of convoluted neural networks using computer-assisted microscope image acquisition and pre-classification of training images for biological objects of interest. The methods combine use of an automated scanning platform, on-the-fly image analysis parallel to the scanning process, and a user interface for review of the pre-classification performed by the software.

System and method for detection and classification of objects of interest in microscope images by supervised machine learning

The current invention relates to a method of identifying changes in biopolymers, especially in chromosomal DNA, using two or more different sets of labelled detector molecules, as well as to a diagnostic kit for detecting these changes.

Method of identifying changes in biopolymers

The present invention is relative to a method for the purposeful application of at least one reagent onto immobilized biological material as well as to a diagnostic kit containing small-area, local covers on which at least one reagent is fixed for contact hybridization.

Method for the targeted application of reagents onto immobilized biological material

A method is provided for comparing the relative copy number of nucleic sequences of two or more nucleic acid sequence collectives which includes hybridizing differentially labeled i) nucleic acid sequence collectives; ii) a reference nucleic acid sequence collective; and iii) a calibration nucleic acid sequence collective. The method includes determining quotient values for the reference nucleic acid sequence and the calibration nucleic acid sequence and using correction curve calculations to determine a final relative copy number of the nucleic acid sequences of the nucleic acid sequence collective.

Growing community of inventors

Schwetzingen, Germany

Andreas Plesch