公开(公告)号：US12051200B2

公开(公告)日：2024-07-30

申请号：US17606400

申请日：2020-04-24

Applicant: NANJING TURING MICROBIAL TECHNOLOGIES CO. LTD

Inventor： Zhongxiao Wang ,  Wei Wu

IPC: G06T7/00 ,  G06V10/26 ,  G06V10/70 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V10/94 ,  G06V20/69 ,  G16H50/20

CPC classification number: G06T7/0012 ,  G06V10/26 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V10/87 ,  G06V10/95 ,  G06V10/955 ,  G06V20/695 ,  G06V20/698 ,  G16H50/20 ,  G06T2207/10056 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06V2201/03

Abstract: An artificial intelligence (AI)-based medical image automatic diagnosis system and method. The method comprises: acquiring a medical microscope image and corresponding diagnostic data; annotating the medical microscope images to obtain annotation data corresponding to the medical microscope images; building a training set and a test set on the basis of the diagnostic data and annotation data corresponding to the medical microscope images; and performing training on the basis of a deep learning model to obtain the optimal AI classification model and the optimal AI semantic segmentation model to implement the automatic diagnosis of the medical microscope image of a test sample. The system and method can effectively save human resources, shorten the diagnosis time, and improve diagnosis accuracy.