Deep convolutional neural networks for tumor segmentation with positron emission tomography

US12115015B2 · kind B2 · utility

Assignee

• Genentech, Inc. · US

Inventors

• Nils Gustav Thomas Bengtsson · South San Francisco, US
• Richard Alan Duray CARANO · San Ramon, US
• Alexander James Stephen Champion De Crespigny · Redwood City, US
• Jill Fredrickson · Sunnyvale, US
• Mohamed Skander JEMAA · South San Francisco, US

Key dates

• Filing date: Sep 13, 2021
• Grant date: Oct 15, 2024
• Expiry date: Sep 6, 2042

Classification

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

Abstract

The present disclosure relates to techniques for segmenting tumors with positron emission tomography (PET) using deep convolutional neural networks for image and lesion metabolism analysis. Particularly, aspects of the present disclosure are directed to obtaining a PET scans and computerized tomography (CT) or magnetic resonance imaging (MRI) scans for a subject, preprocessing the PET scans and the CT or MRI scans to generate standardized images, generating two-dimensional segmentation masks, using two-dimensional segmentation models implemented as part of a convolutional neural network architecture that takes as input the standardized images, generating three-dimensional segmentation masks, using three-dimensional segmentation models implemented as part of the convolutional neural network architecture that takes as input patches of image data associated with segments from the two-dimensional segmentation mask, and generating a final imaged mask by combining information from the two-dimensional segmentation masks and the three-dimensional segmentation masks.