Back to results
US 12,694,302 B2Granted
Techniques for resolving discordant HER2 status in pathology images for diagnosing breast cancer
AssigneeTempus AI, Inc.
InventorsJoshua S.K. Bell, Catherine Igartua, Nike Tsiapera Beaubier
Life of this patent
Estimating the term…
Abstract
Techniques are provided for replacing image assays using real world data and real word evidence RNA-seq analysis for assessing biologic pathways for identifying molecular subtypes. Systems of a methods diagnose HER2 status for a patient, by identifying discordant HER2 status result between the HER2 status from immunohistochemistry (IHC) and the HER2 status from fluorescence in-situ hybridization (FISH) and diagnosing HER2 status based gene expression data.
Claims20
A computer-implemented pathway analysis method, the computer-implemented method comprising:
- obtaining, via an electronic network using a pre-processing application layer of a pathway analysis computing system, human epidermal growth factor receptor 2 (HER2) status for a specimen from a labeled immunohistochemistry (IHC) image corresponding to a sample of the subject;
- obtaining, via the electronic network using the pre-processing application layer, HER2 status for a specimen from a labeled fluorescence in-situ hybridization (FISH) image corresponding to the sample;
- identifying, via one or more processors using a pipeline application layer of the pathway analysis computing system, discordant HER2 status result between the HER2 status labeled in the IHC image and the HER2 status labeled in the FISH image;
- and
- in response to the identification of the discordant HER2 status:
- I) obtaining, via the electronic network using the pipeline application layer, gene expression data corresponding to the sample;
- II) processing, via the one or more processors using the pipeline application layer, the gene expression data using a molecular subtype model to generate a HER2 status for the specimen,
- wherein the molecular subtype model is accessible by the pipeline application layer and trained using bulk gene expression data from multiple patient specimens each associated with gene expression data and a positive or negative HER2 status;
- and
- III) generating, via the one or more processors using the pipeline application layer, a comprehensive HER2 status by classifying the processed gene expression data using the molecular subtype model;
- receiving, via a graphical user interface of a digital display using a molecular subtype processing and report generation application layer of the pathway analysis computing system, one or more user-settable preferences configuring a report template;
- and
- storing, via the one or more processors using the molecular subtype processing and report generation application layer, the user-settable preferences.
10 more elements
A pathway analysis computing system, comprising:
- a digital display;
- one or more processors;
- an electronic network;
- a pre-processing application layer including computer-executable instructions configured to be executed by the one or more processors;
- a pipeline application layer including computer-executable instructions configured to be executed by the one or more processors;
- a molecular subtype processing and report generation application layer including computer-executable instructions configured to be executed by the one or more processors;
- and
- a molecular subtype model,
- accessible by the pipeline application layer and trained using bulk gene expression data from multiple patient specimens each associated with gene expression data and a positive or negative HER2 status,
- wherein the molecular subtype model is configured to analyze gene expression data of a specimen and generate a corresponding HER2 status;
- wherein the computer-executable instructions of the pre-processing application layer are configured to, when executed by the one or more processors:
- obtain, via the electronic network, human epidermal growth factor receptor 2 (HER2) status for a specimen from a labeled immunohistochemistry (IHC) image corresponding to a sample of a subject;
- and
- obtain, via the electronic network, HER2 status for a specimen from a labeled fluorescence in-situ hybridization (FISH) image corresponding to the sample of the subject;
- wherein the computer-executable instructions of the pipeline application layer are configured to, when executed by the one or more processors:
- identify, via the one or more processors, discordant HER2 status result between the HER2 status labeled in the IHC image and the HER2 status labeled in the FISH image;
- and
- in response to the identification of discordant HER2 status,
- obtain, via the electronic network, gene expression data corresponding to the sample;
- process, via the one or more processors, the gene expression data using the molecular subtype model to generate a HER2 status for the specimen;
- and
- generate, via the one or more processors, a comprehensive HER2 status by classifying the processed gene expression data using the molecular subtype model;
- and
- wherein the molecular subtype processing and report generation application layer is configured to:
- receive, via a graphical user interface of the digital display, one or more user-settable preferences configuring a report template;
- and
- store, via the one or more processors, the user-settable preferences.
24 more elements
Dependencies are inferred from the claim text.