FEDERATED LEARNING OF MEDICAL VALIDATION MODEL

Title:

FEDERATED LEARNING OF MEDICAL VALIDATION MODEL

Document Type and Number:

WIPO Patent Application WO/2022/247143

Kind Code:

A1

Abstract:

A computer-implemented method is provided that includes transmitting, by a master node to a plurality of computing nodes, definition information about an initial medical validation model (410); performing, by the master node, a federated learning process together with the plurality of computing nodes (420), to jointly train the initial medical validation model using respective processed local training datasets available at the plurality of computing nodes, the respective local training datasets being processed by the plurality of computing nodes based on the definition information; and determining, by the master node, a final medical validation model based on a result of the federated learning process (430). Through the solution, by means of federated learning, it addresses the data security and privacy concerns from local sites owning.

Inventors:

YAO YI (CN)
XING WEIBIN (CN)
TAO XIAOJUN (CN)
QIAN JING (CN)
ZHOU QI (CN)
ZHANG CHENXI (CN)
QIAN YIN (CN)

Application Number:

PCT/CN2021/127937

Publication Date:

December 01, 2022

Filing Date:

November 01, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

HOFFMANN LA ROCHE (CH)
ROCHE DIAGNOSTICS GMBH (DE)
ROCHE DIAGNOSTICS OPERATIONS INC (US)
YAO YI (CN)

International Classes:

G16H50/20

Foreign References:

CN112768056A	2021-05-07
US20210042628A1	2021-02-11
US20210150269A1	2021-05-20
US20210073678A1	2021-03-11
US20200285980A1	2020-09-10

Attorney, Agent or Firm:

KING & WOOD MALLESONS (CN)

Download PDF:

View/Download PDF PDF Help

Previous Patent: ORGANIC GADOLINIUM NANOPARTICLES, PREPARATION METHOD THEREFOR, AND USE THEREOF

Next Patent: TRANSVERSE WAVE-TYPE HIGH-FREQUENCY ATOMIZATION METHOD AND TRANSVERSE WAVE ATOMIZATION STRUCTURE