Oslo Universitetssykehus

Oslo Universitetssykehus, Institute for Cancer Genetics and Informatics

Tarjei Sveinsgjerd Hveem

John Robert Maddison

Havard Emil Greger Danielsen

Knut Liestol

Ole Johan Skrede

Knut Liestøl

Håvard Emil Greger Danielsen

Rolf Anders Syvertsen

Sepp De Raedt

Andreas Kleppe

Ole-Johan Skrede

A computer implemented system for determining an overall-classifier for one or more source-histological-images. The system comprising: a first tile generator () configured to generate a plurality of first-tiles () from the one or more source-histological-image (); and a second tile generator () configured to generate a plurality of second-tiles () from the one or more source-histological-images (). The first-area of the first-tiles () is larger than the second-area of the second-tiles (); and the second-resolution of the second-tiles () is higher than the first-resolution of the first-tiles (). The system also includes a machine-learning network () configured to process the plurality of first-tiles () in order to determine a first-classifier (); a machine-learning network () configured to process the plurality of second-tiles () in order to determine a second-classifier (); and a classifier combiner configured to combine the first-classifier () and the second-classifier () to determine the overall-classifier ().

Histological image analysis

A machine learning algorithm is trained on a number of microscopic images and a measure of outcome of each image. Each image is divided into tiles. The measure of outcome is assigned to each tile of the image. The tiles are then used to train the machine learning algorithm. The trained algorithm may then be used to evaluate images.

A method of image classification is used for classifying images of stained cell nuclei. For each nucleus, the total integrated optical density is calculated and a histogram calculated. The image is then classified by automatically identifying peaks, identifying the lowest peak as a 2C peak and classifying the image as at least one of diploid, tetraploid, aneuploid or polyploid based on the number of peaks and the count at an integrated optical densities above the 2C peak.

Automatic calculation for ploidy classification

Growing community of inventors

Oslo, Norway

Tarjei Sveinsgjerd Hveem