Max-planck-gesellschaft Zur F&#xf6;rderung Der Wissenschaften E. V.

Eberhard-Karls-Universität Tübingen Universitätsklinikum

Eberhard-karls-universitat Tubingen

Bernhard Schölkopf

Florian Steinke

Bernd J Pichler

Stefan Harmeling

Michael Hirsch

Suvrit Sra

Christian J Schuler

Matthias Hofmann

Bernd Pichler

A computer-implemented method for recovering a digital image (x) from a sequence of observed digital images (y, . . . , y), includes: obtaining an observed digital image (y); estimating a point spread function (f) based on the observed image (y); estimating the recovered digital image (x), based on the estimated point spread function (f) and the observed image (y); and repeating the above steps. In order to correct optical aberrations of a lens, a point spread function of the lens may be used.

Method and device for recovering a digital image from a sequence of observed digital images

It is disclosed a system and method () for determining a property map () of an object, particularly a human being, based on at least a first image (), particularly an magnetic resonance (MR) image, of the object. In the method (), a structure of reference pairs is defined in a first step (), wherein each reference pair (-) comprises at least two entries (). The first entry represents a property value, particularly an attenuation value. The second entry () preferably represents a group of image points () belonging together, which is extracted particularly from MR images () and comprises an interesting image point corresponding to the property value. In another step () of the method () a plurality of training pairs (-) is provided. A structure of the training pairs (-) corresponds to the structure of reference pairs, and the entries of respective training pairs (-) are known. In another step () of the method (), an assignment between the first entries and the other entries (-) of the training pairs (-) is determined by machine learning, thus allowing prediction of a property value () corresponding to an arbitrary point () of the first image ().

Method for determining a property map of an object, particularly of a living being, based on at least a first image, particularly a magnetic resonance image

Growing community of inventors

Tübingen, Germany

Bernhard Schölkopf