MULTI-PARAMETER BREAST MAGNETIC RESONANCE IMAGE SEGMENTATION METHOD BASED ON DYNAMIC ADAPTIVE NETWORK

WIPO Patent Application WO/2023/116585

A1

Provided in the embodiments of the present invention is a multi-parameter breast magnetic resonance image segmentation method based on a dynamic adaptive network, which method is applied to the technical field of medical images. The method comprises: acquiring a multi-parameter magnetic resonance sample image; inputting the multi-parameter magnetic resonance sample image into an image segmentation model to be trained, and training the image segmentation model to be trained, so as to obtain a trained image segmentation model; acquiring a single-parameter magnetic resonance sample image; inputting the single-parameter magnetic resonance sample image into the trained image segmentation model to test the trained image segmentation model, and when the test succeeds, obtaining a successfully trained image segmentation model; acquiring a magnetic resonance image to be subjected to recognition; and inputting said magnetic resonance image into the successfully trained image segmentation model, so as to obtain information of a breast lesion area in the said magnetic resonance image. Therefore, the requirement for a sample image during a training process of an image segmentation model is reduced.

WANG SHANSHAN (CN)
ZHENG HAIRONG (CN)
LI CHENG (CN)
XUE ZHENZHEN (CN)
LIU XIN (CN)
LIANG DONG (CN)

PCT/CN2022/139816

June 29, 2023

December 17, 2022

Click for automatic bibliography generation  

SHENZHEN INST OF ADV TECH CAS (CN)

G06T7/11; G06V10/774

CN114463345A	2022-05-10
CN113808143A	2021-12-17
CN111539930A	2020-08-14
CN112132808A	2020-12-25

BEIJING ZHONG XUN TONG DA INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)

View/Download PDF      PDF Help

Previous Patent: DEEP HIGH-RESOLUTION PHASE INFORMATION EXTRACTION METHOD

Next Patent: METHOD FOR SYNTHESIZING SI-FITC RATIOMETRIC FLUORESCENT NANOPROBE AND USE OF SI-FITC RATIOMETRIC FLU...