Automated MR Image Prescription of the Liver Using Deep Learning: Development, Evaluation, and Prospective Implementation

Background There is an unmet need for fully automated image prescription of the liver to enable efficient, reproducible MRI. Purpose To develop and evaluate artificial intelligence (AI)‐based liver image prescription. Study Type Prospective. Population A total of 570 female/469 male patients (age: 5...

Full description

Saved in:
Bibliographic Details
Published in:Journal of magnetic resonance imaging 2023-08, Vol.58 (2), p.429-441
Main Authors: Geng, Ruiqi, Buelo, Collin J., Sundaresan, Mahalakshmi, Starekova, Jitka, Panagiotopoulos, Nikolaos, Oechtering, Thekla H., Lawrence, Edward M., Ignaciuk, Marcin, Reeder, Scott B., Hernando, Diego
Format: Article
Language:English
Subjects:
Annotations
Artificial intelligence
Artificial neural networks
automated scan prescription
Automation
Boxes
Datasets
Deep learning
Females
Field strength
image prescription
Liver
Machine learning
Magnetic resonance imaging
Males
Mathematical analysis
Medical imaging
Neural networks
Performance evaluation
Population studies
Reproducibility
Statistical analysis
Statistical tests
Torso
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background There is an unmet need for fully automated image prescription of the liver to enable efficient, reproducible MRI. Purpose To develop and evaluate artificial intelligence (AI)‐based liver image prescription. Study Type Prospective. Population A total of 570 female/469 male patients (age: 56 ± 17 years) with 72%/8%/20% assigned randomly for training/validation/testing; two female/four male healthy volunteers (age: 31 ± 6 years). Field Strength/Sequence 1.5 T, 3.0 T; spin echo, gradient echo, bSSFP. Assessment A total of 1039 three‐plane localizer acquisitions (26,929 slices) from consecutive clinical liver MRI examinations were retrieved retrospectively and annotated by six radiologists. The localizer images and manual annotations were used to train an object‐detection convolutional neural network (YOLOv3) to detect multiple object classes (liver, torso, and arms) across localizer image orientations and to output corresponding 2D bounding boxes. Whole‐liver image prescription in standard orientations was obtained based on these bounding boxes. 2D detection performance was evaluated on test datasets by calculating intersection over union (IoU) between manual and automated labeling. 3D prescription accuracy was calculated by measuring the boundary mismatch in each dimension and percentage of manual volume covered by AI prescription. The automated prescription was implemented on a 3 T MR system and evaluated prospectively on healthy volunteers. Statistical Tests Paired t‐tests (threshold = 0.05) were conducted to evaluate significance of performance difference between trained networks. Results In 208 testing datasets, the proposed method with full network had excellent agreement with manual annotations, with median IoU > 0.91 (interquartile range 
ISSN:1053-1807
1522-2586
1522-2586
DOI:10.1002/jmri.28564