Deep Learning Reconstruction of Accelerated MRI: False-Positive Cartilage Delamination Inserted in MRI Arthrography Under Traction.
Options
BORIS DOI
Publisher DOI
PubMed ID
39016321
Description
OBJECTIVES
The radiological imaging industry is developing and starting to offer a range of novel artificial intelligence software solutions for clinical radiology. Deep learning reconstruction of magnetic resonance imaging data seems to allow for the acceleration and undersampling of imaging data. Resulting reduced acquisition times would lead to greater machine utility and to greater cost-efficiency of machine operations.
MATERIALS AND METHODS
Our case shows images from magnetic resonance arthrography under traction of the right hip joint from a 30-year-old, otherwise healthy, male patient.
RESULTS
The undersampled image data when reconstructed by a deep learning tool can contain false-positive cartilage delamination and false-positive diffuse cartilage defects.
CONCLUSIONS
In the future, precision of this novel technology will have to be put to thorough testing. Bias of systems, in particular created by the choice of training data, will have to be part of those assessments.
The radiological imaging industry is developing and starting to offer a range of novel artificial intelligence software solutions for clinical radiology. Deep learning reconstruction of magnetic resonance imaging data seems to allow for the acceleration and undersampling of imaging data. Resulting reduced acquisition times would lead to greater machine utility and to greater cost-efficiency of machine operations.
MATERIALS AND METHODS
Our case shows images from magnetic resonance arthrography under traction of the right hip joint from a 30-year-old, otherwise healthy, male patient.
RESULTS
The undersampled image data when reconstructed by a deep learning tool can contain false-positive cartilage delamination and false-positive diffuse cartilage defects.
CONCLUSIONS
In the future, precision of this novel technology will have to be put to thorough testing. Bias of systems, in particular created by the choice of training data, will have to be part of those assessments.
Date of Publication
2024-08-01
Publication Type
Article
Subject(s)
Language(s)
en
Contributor(s)
Montazeri, Elham | |
Series
Topics in magnetic resonance imaging
ISSN
1536-1004
Access(Rights)
open.access