Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V.

Technische Unversität Berlin

Technische Universitaet Beriin

Alexander Binder

Klaus-Robert Mueller

Wojciech Samek

Motoaki Kawanabe

Klaus-Robert Müller

Sebastian Lapuschkin

Frederick Klauschen

Grégoire Montavon

The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function.

Relevance score assignment for artificial neural networks

Method for the automatic analysis of an image of a biological sample with respect to a pathological relevance, wherein a)local features of the image are aggregated to a global feature of the image using a bag of visual word approach, b) step a) is repeated at least two times using different methods resulting in at least two bag of word feature datasets, c) computation of at least two similarity measures using the bag of word features obtained from a training image dataset and bag of word features from the image, d) the image training dataset comprising a set of visual words, classifier parameters, including kernel weights and bag of word features from the training images, e) the computation of the at least two similarity measures is subject to an adaptive computation of kernel normalization parameters and/or kernel width parameters, f) for each image one score is computed depending on the classifier parameters and kernel weights and the at least two similarity measures, the at least one score being a measure of the certainty of one pathological category compared to the image training dataset, g) for each pixel of the image a pixel-wise score is computed using the classifier parameters, the kernel weights, the at least two similarity measures, the bag of word features of the image, all the local features used in the computation of the bag of word features of the image and the pixels used in the computations of the local features, h) the pixel-wise score is stored as a heatmap dataset linking the pixels of the image to the pixel-wise scores.

Method and system for the automatic analysis of an image of a biological sample

Growing community of inventors

Berlin, Germany

Alexander Binder