ARTIFICIAL INTELLIGENCE-BASED DUAL ENERGY X-RAY IMAGE MOTION CORRECTION TRAINING METHOD AND SYSTEM

A dual energy x-ray imaging system (100) and method of operation includes an artificial intelligence-based motion correction system (180) to minimize the effects of motion artifacts in images produced by the imaging system (100). The motion correction system (180) is trained to apply simulated motio...

Full description

Saved in:
Bibliographic Details
Main Authors HERCZEG, Zita, WANEK, Justin M, SONI, Ravi, CZIRIA, Balázs P, TAN, Tao, TEGZES, Pál, VERA GONZALEZ, German Guillermo, AVINASH, Gopal B, RAO, Gireesha Chinthamani
Format Patent
LanguageEnglish
French
German
Published 17.04.2024
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A dual energy x-ray imaging system (100) and method of operation includes an artificial intelligence-based motion correction system (180) to minimize the effects of motion artifacts in images produced by the imaging system (100). The motion correction system (180) is trained to apply simulated motion to various objects of interest within the LE and HE projections (1002,1004) in the training dataset to improve registration of the LE and HE projections (1002,1004). The motion correction system (180) is also trained to enhance the correction of small motion artifacts using noise attenuation and subtraction image-based edge detection on the training dataset images reduce noise from the LE projection (1004), consequently improving small motion artifact correction. The motion correction system (180) additionally employs separate motion corrections for soft and bone tissue in forming subtraction soft tissue (1016) and bone tissue images (1018), and includes a motion alarm to indicate when motion between LE and HE projections (1002,1004) requires a retake of the projections.
Bibliography:Application Number: EP20230200664