Literature DB >> 31547689

A Multicenter, Scan-Rescan, Human and Machine Learning CMR Study to Test Generalizability and Precision in Imaging Biomarker Analysis.

Anish Bhuva1,2, Wenjia Bai1, Clement Lau1, Rhodri Davies1,2, Yang Ye1,2, Heeraj Bulluck1,2, Elisa McAlindon1,2, Veronica Culotta1, Peter Swoboda1,2, Gabriella Captur1,2, Thomas Treibel2,3, Joao Augusto2, Kristopher Knott2,4, Andreas Seraphim2, Graham Cole2,3, Steffen Petersen5, Nicola Edwards6, John Greenwood7,8, Chiara Bucciarelli-Ducci7, Alun Hughes9, Daniel Rueckert9, James Moon10, Charlotte Manisty11.   

Abstract

BACKGROUND: Automated analysis of cardiac structure and function using machine learning (ML) has great potential, but is currently hindered by poor generalizability. Comparison is traditionally against clinicians as a reference, ignoring inherent human inter- and intraobserver error, and ensuring that ML cannot demonstrate superiority. Measuring precision (scan:rescan reproducibility) addresses this. We compared precision of ML and humans using a multicenter, multi-disease, scan:rescan cardiovascular magnetic resonance data set.
METHODS: One hundred ten patients (5 disease categories, 5 institutions, 2 scanner manufacturers, and 2 field strengths) underwent scan:rescan cardiovascular magnetic resonance (96% within one week). After identification of the most precise human technique, left ventricular chamber volumes, mass, and ejection fraction were measured by an expert, a trained junior clinician, and a fully automated convolutional neural network trained on 599 independent multicenter disease cases. Scan:rescan coefficient of variation and 1000 bootstrapped 95% CIs were calculated and compared using mixed linear effects models.
RESULTS: Clinicians can be confident in detecting a 9% change in left ventricular ejection fraction, with greater than half of coefficient of variation attributable to intraobserver variation. Expert, trained junior, and automated scan:rescan precision were similar (for left ventricular ejection fraction, coefficient of variation 6.1 [5.2%-7.1%], P=0.2581; 8.3 [5.6%-10.3%], P=0.3653; 8.8 [6.1%-11.1%], P=0.8620). Automated analysis was 186× faster than humans (0.07 versus 13 minutes).
CONCLUSIONS: Automated ML analysis is faster with similar precision to the most precise human techniques, even when challenged with real-world scan:rescan data. Assessment of multicenter, multi-vendor, multi-field strength scan:rescan data (available at www.thevolumesresource.com) permits a generalizable assessment of ML precision and may facilitate direct translation of ML to clinical practice.

Entities:  

Keywords:  artificial intelligence; image processing; left ventricular remodeling; magnetic resonance imaging, cine; ventricular function

Mesh:

Substances:

Year:  2019        PMID: 31547689     DOI: 10.1161/CIRCIMAGING.119.009214

Source DB:  PubMed          Journal:  Circ Cardiovasc Imaging        ISSN: 1941-9651            Impact factor:   7.792


  26 in total

Review 1.  Reference ranges ("normal values") for cardiovascular magnetic resonance (CMR) in adults and children: 2020 update.

Authors:  Nadine Kawel-Boehm; Scott J Hetzel; Bharath Ambale-Venkatesh; Gabriella Captur; Christopher J Francois; Michael Jerosch-Herold; Michael Salerno; Shawn D Teague; Emanuela Valsangiacomo-Buechel; Rob J van der Geest; David A Bluemke
Journal:  J Cardiovasc Magn Reson       Date:  2020-12-14       Impact factor: 5.364

2.  Interinstitutional Portability of a Deep Learning Brain MRI Lesion Segmentation Algorithm.

Authors:  Andreas M Rauschecker; Tyler J Gleason; Pierre Nedelec; Michael Tran Duong; David A Weiss; Evan Calabrese; John B Colby; Leo P Sugrue; Jeffrey D Rudie; Christopher P Hess
Journal:  Radiol Artif Intell       Date:  2021-11-10

3.  AI Based CMR Assessment of Biventricular Function: Clinical Significance of Intervendor Variability and Measurement Errors.

Authors:  Shuo Wang; Hena Patel; Tamari Miller; Keith Ameyaw; Akhil Narang; Daksh Chauhan; Simran Anand; Emeka Anyanwu; Stephanie A Besser; Keigo Kawaji; Xing-Peng Liu; Roberto M Lang; Victor Mor-Avi; Amit R Patel
Journal:  JACC Cardiovasc Imaging       Date:  2021-10-13

4.  Computational analysis of cardiac structure and function in congenital heart disease: Translating discoveries to clinical strategies.

Authors:  Nickolas Forsch; Sachin Govil; James C Perry; Sanjeet Hegde; Alistair A Young; Jeffrey H Omens; Andrew D McCulloch
Journal:  J Comput Sci       Date:  2020-09-19

5.  Effects of Spironolactone and Chlorthalidone on Cardiovascular Structure and Function in Chronic Kidney Disease: A Randomized, Open-Label Trial.

Authors:  Nicola C Edwards; Anna M Price; Samir Mehta; Thomas F Hiemstra; Amreen Kaur; Peter J Greasley; David J Webb; Neeraj Dhaun; Iain M MacIntyre; Tariq Farrah; Vanessa Melville; Anna S Herrey; Gemma Slinn; Rebekah Wale; Natalie Ives; David C Wheeler; Ian Wilkinson; Richard P Steeds; Charles J Ferro; Jonathan N Townend
Journal:  Clin J Am Soc Nephrol       Date:  2021-08-30       Impact factor: 10.614

Review 6.  Clinical Manifestations, Monitoring, and Prognosis: A Review of Cardiotoxicity After Antitumor Strategy.

Authors:  Wei Huang; Rong Xu; Bin Zhou; Chao Lin; Yingkun Guo; Huayan Xu; Xia Guo
Journal:  Front Cardiovasc Med       Date:  2022-06-10

Review 7.  Cardiac MRI-Update 2020.

Authors:  Anke Busse; Rengarajan Rajagopal; Seyrani Yücel; Ebba Beller; Alper Öner; Felix Streckenbach; Daniel Cantré; Hüseyin Ince; Marc-André Weber; Felix G Meinel
Journal:  Radiologe       Date:  2020-11       Impact factor: 0.635

Review 8.  Applications of artificial intelligence in cardiovascular imaging.

Authors:  Maxime Sermesant; Hervé Delingette; Hubert Cochet; Pierre Jaïs; Nicholas Ayache
Journal:  Nat Rev Cardiol       Date:  2021-03-12       Impact factor: 32.419

9.  MRI Manufacturer Shift and Adaptation: Increasing the Generalizability of Deep Learning Segmentation for MR Images Acquired with Different Scanners.

Authors:  Wenjun Yan; Lu Huang; Liming Xia; Shengjia Gu; Fuhua Yan; Yuanyuan Wang; Qian Tao
Journal:  Radiol Artif Intell       Date:  2020-07-01

10.  A population-based phenome-wide association study of cardiac and aortic structure and function.

Authors:  Wenjia Bai; Hideaki Suzuki; Jian Huang; Catherine Francis; Shuo Wang; Giacomo Tarroni; Florian Guitton; Nay Aung; Kenneth Fung; Steffen E Petersen; Stefan K Piechnik; Stefan Neubauer; Evangelos Evangelou; Abbas Dehghan; Declan P O'Regan; Martin R Wilkins; Yike Guo; Paul M Matthews; Daniel Rueckert
Journal:  Nat Med       Date:  2020-08-24       Impact factor: 87.241

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.