Leica Biosystems Imaging, Inc.

Genetix Corporation

Mark Gregson

Allen Olson

Kiran Saligrama

Walter Georgescu

Bharat Annaldas

Kevin Shields

Darragh Lawler

A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

Processing of histology images with a convolutional neural network to identify tumors

The present invention provides methods and systems for automatic detection of the location of cell colonies on a specimen slide, in particular under the coverslip of a specimen slide. Slide scanning can be performed using an automated microscope with motorized axes. The location of the colonies can be determined by image analysis, which is followed by automatically finding metaphase cells and associating them with each colony. The invention also provides an automated, Hough-transform-based method for identifying the location of the slide coverslip and, if desired, analyzing only the image area contained within the coverslip.

Automated detection of cell colonies and coverslip detection using hough transforms

Growing community of inventors

Newcastle, United Kingdom

Mark Gregson