Image processing method and apparatus and neural network model training method

US11501431B2 · kind B2 · utility

Assignee

• TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED · CN

Inventors

• Fen Xiao · Tangxia, CN
• Jia Chang · Lo Wu, CN
• Xuan Zhou · Nanhu, CN
• Ke Yan · Nanhu, CN
• Cheng Jiang · Plano, US
• Kuan TIAN · Lo Wu, CN
• Jian Ping Zhu · Lo Wu, CN

Key dates

• Filing date: Jun 18, 2020
• Grant date: Nov 15, 2022
• Expiry date: Jun 18, 2041

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/30096
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

An image processing method performed by a terminal is provided. A molybdenum target image is obtained, and a plurality of candidate regions are extracted from the molybdenum target image. In the molybdenum target image, a target region is marked in the plurality of candidate regions by using a neural network model obtained by deep learning training, a probability that a lump comprised in the target region is a target lump being greater than a first threshold, a probability that the target lump is a malignant tumor being greater than a second threshold, and the neural network model being used for indicating a mapping relationship between a candidate region and a probability that a lump comprised in the candidate region is the target lump.