Deep learning method for predicting patient response to a therapy

US11348231B2 · kind B2 · utility

Assignee

• AstraZeneca Computational Pathology GmbH · DE

Inventors

• Guenter Schmidt · Leun, DE
• Nicolas Brieu · Munich, DE
• Ansh Kapil · Munich, DE
• Jan Martin Lesniak · Munich, DE

Key dates

• Filing date: Dec 6, 2019
• Grant date: May 31, 2022
• Expiry date: Sep 21, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/30242
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

A method for indicating how a cancer patient will respond to a predetermined therapy relies on spatial statistical analysis of classes of cell centers in a digital image of tissue of the cancer patient. The cell centers are detected in the image of stained tissue of the cancer patient. For each cell center, an image patch that includes the cell center is extracted from the image. A feature vector is generated based on each image patch using a convolutional neural network. A class is assigned to each cell center based on the feature vector associated with each cell center. A score is computed for the image of tissue by performing spatial statistical analysis based on classes of the cell centers. The score indicates how the cancer patient will respond to the predetermined therapy. The predetermined therapy is recommended to the patient if the score is larger than a predetermined threshold.