System and method for automatic assessment of cancer
OwnerKavya Venkata Kota Sai Kopparapuinventor
Life of this patent
Estimating the term…
Abstract
Cancer can be an aggressive disease. It is critical to determine the most effective patient-specific treatment quickly. Exemplary embodiments use a data-driven approach to extracting tumor information from data obtain from Whole Slide Image that is uploaded through an interface. Exemplary embodiments generate the following information about a tumor from a biopsy slide using neural networks: annotated areas of relevant tissues, molecular subtype, and expression status of an important gene and include three steps: the segmentation of tumor features; prediction of molecular subtype; and prediction of gene methylation status from a WSI.
Claims22
A computer-implemented method for the molecular and genetic characterization of a malignant tumor comprising:
- receiving, on at least one processor, data from a subject with a malignant tumor;
- evaluating, using the at least one processor, the data using a classifier which is an electronic representation of a classification system, each said classifier trained using an electronically stored set of training data vectors, each training data vector representing an individual human and data for the respective human, each training data vector further comprising a classification with respect to the characterization of the malignant tumor in the respective human;
- and
- outputting, using the at least one processor, a classification of the sample from the subject concerning the characterization of the malignant tumor in the subject based on the evaluating step.
A computer implemented method, comprising:
- receiving, by a computer, patient information comprising a scanned biopsy whole slide image (WSI), genetic testing results, and methylation information, for tissue of a subject with a malignant tumor extracted via biopsy and wherein the computer comprises a cloud-based server comprising one or more computer processors and wherein the patient information is received through a secure web-based application;
- preprocessing, by the computer, the patient information;
- processing, by the computer, the preprocessed patient information using one or more machine learning architectures;
- outputting, by the computer, through the use of the one or more machine learning architectures, an annotated image and tumor feature report, wherein the annotated image comprises a tumor feature segmentation and the tumor feature report comprises a subtype of the tumor and methylation status for implicated genes based on the tumor's classification;
- and
- giving a capability, through the annotated image, to determine a personalized treatment plan for the subject with the malignant tumor based on the tumor's subtype and implicated genes.
A system, comprising:
- a server comprising at least one processor and memory comprising computer-readable instructions which, when executed by the at least one processor, cause the at least one processor to perform the steps comprising:
- receiving patient information comprising a scanned biopsy whole slide image (WSI), genetic testing results, and methylation information, for tissue of a subject with a malignant tumor extracted via biopsy wherein the computer comprises a cloud-based server and wherein the patient information is received through a secure web-based application;
- preprocessing the patient information;
- processing the preprocessed patient information using one or more machine learning architectures;
- outputting through the use of the one or more machine learning architectures, an annotated image and tumor feature report, wherein the annotated image comprises a tumor feature segmentation and the tumor feature report comprises a subtype of the tumor and methylation status for implicated genes based on the tumor's classification;
- and
- giving a capability, through the annotated image, to determine a personalized treatment plan for the patient with a pre-diagnosed malignant tumor based on the tumor's subtype and implicated genes.
Dependencies are inferred from the claim text.