General Electric Company

Yunxia Sui

Michael John Gerdes

Alberto Santamaria-Pang

Fiona Ginty

Qing Li

Christopher James Sevinsky

Anup Sood

Dmitry Vladimirovich Dylov

Michael Ernest Marino

Zhengyu Pang

Daniel Eugene Meyer

Srabani Bhaumik

Keyur Hemantkumar Desai

The subject matter of the present disclosure generally relates to techniques for image analysis. In certain embodiments, various morphological or intensity-based features as well as different thresholding approaches may be used to segment the subpopulation of interest and classify object in the images.

Systems and methods for automatic generation of training sets for machine interpretation of images

The present disclosure relates to characterization of biological samples. By way of example, a biological sample may be contacted with a plurality of probes specific for targets in the sample, such as probes for immune markers and segmenting probes. Acquired image data of the sample may be used to segment the images into epithelial and stromal regions to characterize individual cells in the sample based on the binding of the probes. Further, the biological sample may be characterized by a distribution, location, and type of a plurality of the characterized cells.

Quantitative in situ characterization of biological samples

A computer implemented method of analyzing tissue features based on multiplexed biometric images includes storing a data set including cell profile data and an assessment associated with a field of view or a patient. The cell profile data includes biomarker expression intensity data for at least one cell feature. The method includes normalizing the biomarker expression intensity data for each field of view. The method includes determining a plurality of positive cell percentages for a first cell feature for each field of view or for each patient based on a plurality of normalized expression cutoffs for all fields of view. The method further includes correlating positive cell percentages with assessments for each field of view or each patient. The method also includes identifying a combination of a cell feature for expression of a biomarker and a normalized expression cutoff that most closely correlate the positive cell percentage with the assessment.

Generate percentage of positive cells for biomarkers by normalizing and autothresholding the image intensity produced by immunohistochemistry technique

Growing community of inventors

Clifton Park, NY, United States of America

Yunxia Sui