Ultrasonic diagnosis intelligent interaction system based on liver attribute analysis

The invention relates to the technical field of medical artificial intelligence, and discloses an ultrasonic diagnosis intelligent interaction system based on liver attribute analysis, which comprises an image alignment subsystem, an attribute analysis subsystem and a large language model dialogue subsystem. And the image alignment subsystem is used for performing feature recognition on the liver ultrasonic image, acquiring required image features according to a text described by a problem, and then aligning the image features to a text space so as to obtain image text alignment features which can be recognized by a large language model. And the attribute analysis subsystem is used for carrying out liver and liver placeholder region target detection on the liver ultrasonic image and carrying out classification and identification on the liver placeholder lesion attribute so as to obtain a liver attribute classification result. And the large language model dialogue subsystem is used for inputting the problem description, the image text alignment features and the liver attribute classification result and outputting a diagnosis result by using a large language model, and the diagnosis result generated by the system is more intelligent and accurate..

Medienart:

Patent

Erscheinungsjahr:

2024

Erschienen:

2024

Enthalten in:

Europäisches Patentamt - (2024) vom: 02. Jan. Zur Gesamtaufnahme - year:2024

Sprache:

Englisch

Beteiligte Personen:

CHENG DONGLIANG [VerfasserIn]
HUANG QI [VerfasserIn]
WANG CHEN [VerfasserIn]
LIU ZHEN [VerfasserIn]

Links:

Volltext [kostenfrei]

Themen:

Sonstige Themen:
615
G06N: Computer systems based on specific computational mo (...)
G06T: Image data processing or generation, in general (...)
G06V (...)
G16H: Healthcare informatics, i.e. information and commun (...)
inf

Anmerkungen:

Source: www.epo.org (no modifications made), First posted: 2024-01-02, Last update posted on www.tib.eu: 2024-03-18, Last updated: 2024-03-22

Patentnummer:

CN117333462

Förderinstitution / Projekttitel:

PPN (Katalog-ID):

EPA00124311X