International Business Machines Corporation

Aditya Kashyap

Govind V Kaigala

Emmanuel Delamarche

Maria Gabrani

Xander Frank Van Kooten

Anna Fomitcheva Khartchenko

Julien Autebert

Pushpak Pati

Gustavo Alejandro Stolovitzky

Nuri Murat Arar

Navneet Dogra

Robert Vogel

Lena Voith Von Voithenberg

Embodiments of the invention relate to a computer-implemented method for quantifying a biomarker in a tissue sample of an organism. An image analysis system receives images of a stained tissue sample. Each received digital image depicts the tissue sample region at the end of an exposure interval. The system analyzes the intensity values and exposure intervals of the received digital images for determining the time when the intensity values corresponding to the plurality of exposure intervals ordered according to ascending exposure interval lengths reach a plateau (saturation residence time&#x2014;SRT). The system determines the amount of a biomarker in the tissue sample and/or predicts a tumor stage and/or a treatment recommendation as a function of the SRT.

Biomarker quantification in a tissue sample

Techniques regarding measuring a position and transcriptome of one or more cells from a biological sample are provided. For example, one or more embodiments described herein can comprise a method, which can comprise covalently bonding a probe to a molecular structure located on a cell to label the cell according to a position of the cell with regards to a biological sample comprising the cell. The probe comprises an oligonucleotide sequence that can be indicative of the position.

Determining position and transcriptomes of biological cells

The invention relates to the automated determination of the staining quality of an IHC stained biological sample. A plurality of features is extracted from a digital IHC stained tissue image. The features are input into a first classifier configured to identify the extended tissue type of the depicted tissue as a function of the extracted features. An extended tissue type is a tissue type with a defined expression level of the tumor marker. In addition, the extracted features are input into a second classifier configured to identify a contrast level of the depicted tissue as a function of at least some second ones of the extracted features. The contrast level indicates the intensity contrast of pixels of the stained tissue. Then, a staining quality score of the image is computed as a function of the identified extended tissue type and the identified contrast level.

Tissue staining quality determination

A microfluidic probe head for providing a sequence of separate liquid volumes separated by spacers, the separate liquid volumes including a respective target substance associated with a respective target area, the microfluidic probe head including an inlet and an outlet; a first fluid channel fluidly connected to the inlet, the first fluid channel configured for delivering an injection liquid from the inlet to a respective target area; a second fluid channel fluidly connected to the outlet, the second fluid channel configured for delivering liquid volumes from the respective target area to the outlet; and a spacer insertion unit fluidly connected to the second fluid channel, the spacer insertion unit configured for inserting spacers into the second fluid channel between the liquid volumes to provide the sequence of separate liquid volumes separated by spacers.

Microfluidic probe head for providing a sequence of separate liquid volumes separated by spacers

Growing community of inventors

Zurich, Switzerland

Aditya Kashyap