Invention Application
- Patent Title: ADAPTIVE ULTRASOUND DEEP CONVOLUTION NEURAL NETWORK DENOISING USING NOISE CHARACTERISTIC INFORMATION
-
Application No.: US17730954Application Date: 2022-04-27
-
Publication No.: US20220367039A1Publication Date: 2022-11-17
- Inventor: Liang CAI , Jian ZHOU , Ting XIA , Zhou YU , Tomohisa IMAMURA , Ryosuke IWASAKI , Hiroki TAKAHASHI
- Applicant: CANON MEDICAL SYSTEMS CORPORATION
- Applicant Address: JP Tochigi
- Assignee: CANON MEDICAL SYSTEMS CORPORATION
- Current Assignee: CANON MEDICAL SYSTEMS CORPORATION
- Current Assignee Address: JP Tochigi
- Main IPC: G16H30/40
- IPC: G16H30/40 ; A61B8/08 ; G06T5/00 ; G06N3/08

Abstract:
A method and system enable to-be-processed medical image data and its corresponding noise characteristic information to be normalized to resemble noise characteristic information of training data used to train at least one neural network for at least one ultrasound data acquisition mode. After normalizing, this processed medical image data is input into the trained neural network for producing output data used for generating cleaner images. Noise characteristic information can be used directly in training a neural network, generating a trained neural network that can handle medical image data with various noise characteristics.
Information query