Imperial College London
Portrait Picture

DrJamesHoward

Faculty of Medicine, National Heart & Lung Institute

Clinical Senior Lecturer in Cardiology (Cardiac MR and AI)
 
 
 
//

Contact

 

james.howard1 Website CV

 
 
//

Location

 

Block B Hammersmith HospitalHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Howard:2022:10.1148/ryai.220050,
author = {Howard, J and Chow, K and Chacko, L and Fontana, M and Cole, G and Kellman, P and Xue, H},
doi = {10.1148/ryai.220050},
journal = {Radiology: Artificial Intelligence},
pages = {1--1},
title = {Automated inline myocardial segmentation of joint T1 and T2 mapping using deep learning},
url = {http://dx.doi.org/10.1148/ryai.220050},
volume = {1},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Purpose:To develop an artificial intelligence (AI) solution for automated segmentation and analysis of joint cardiac MRI T1 and T2 short-axis mapping.Materials and Methods:In this retrospective study, a joint T1 and T2 mapping sequence was used to acquire 4240 maps from 807 patients across 2 hospitals (March-November 2020). 509 maps from 94 consecutive patients were assigned to a holdout testing set. A convolutional neural network was trained to segment the endocardial and epicardial contours using an edge probability estimation approach. Training labels were segmented by an expert cardiologist. Predicted contours were processed to yield mapping values for each of the 16 AHA segments. Network segmentation performance and segment-wise measurements on the testing set were compared with two experts on the holdout testing set. The AI model was fully integrated using Gadgetron inline AI to run on MRI scanners.Results:A total of 3899 maps (92%) were deemed artifact-free and suitable for human segmentation. AI segmentation closely matched that of each expert (mean Dice coefficient 0.82 ± [SD] 0.07, 0.86 ± 0.06), comparing favorably with interexpert agreement (0.84 ± 0.06). AI-derived segment-wise values for native T1, postcontrast T1 and T2 mapping correlated with experts (R2 0.96, 0.98, 0.87, respectively versus expert 1; 0.97, 0.99, 0.97 versus expert 2) and fell within the range of interexpert reproducibility (R2 = 0.97, 0.99, 0.90). The AI has since been deployed at two hospitals, enabling automated inline analysis.Conclusion:Automated inline analysis of joint T1 and T2 mapping allows accurate segment-wise tissue characterization, with performance equivalent to human experts.
AU  - Howard,J
AU  - Chow,K
AU  - Chacko,L
AU  - Fontana,M
AU  - Cole,G
AU  - Kellman,P
AU  - Xue,H
DO  - 10.1148/ryai.220050
EP  - 1
PY  - 2022///
SN  - 2638-6100
SP  - 1
TI  - Automated inline myocardial segmentation of joint T1 and T2 mapping using deep learning
T2  - Radiology: Artificial Intelligence
UR  - http://dx.doi.org/10.1148/ryai.220050
UR  - https://pubs.rsna.org/doi/10.1148/ryai.220050
UR  - http://hdl.handle.net/10044/1/101045
VL  - 1
ER  -
Download