Quality control of cardiac magnetic resonance imaging segmentation, feature tracking, aortic flow, and native T1 analysis using automated batch processing in the UK Biobank study

Sucharitha Chadalavada^{1

2}, Elisa Rauseo^{1

2

3}, Ahmed Salih^{1

4}, Hafiz Naderi^{1

2}, Mohammed Khanji^{1

2}, Jose D Vargas⁵, Aaron M Lee¹, Alborz Amir-Kalili⁶, Lisette Lockhart⁶, Ben Graham⁶, Mihaela Chirvasa⁶, Kenneth Fung^{1

2}, Jose Paiva¹, Mihir M Sanghvi^{1

2}, Gregory G Slabaugh^{3

7

8}, Magnus T Jensen^{1

9}, Nay Aung^{1

2

3}, Steffen E Petersen^{1

2

6

8

10

11}

Affiliations

¹ William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, Charterhouse Square, London, UK.
² Barts Heart Centre, St Bartholomew's Hospital, Barts Health NHS Trust, West Smithfield, London, UK.
³ Digital Environment Research Institute, Queen Mary University of London, London, UK.
⁴ Department of Computer Science, University of Zakho, Zakho, Kurdistan of Iraq, Iraq.
⁵ Department of Cardiology, US Department of Veterans Affair Medical Center, Washington, D.C., USA.
⁶ Circle Cardiovascular Imaging Inc., Calgary, Canada.
⁷ School of Electronic Eng. & Computer Science, Queen Mary University of London, UK.
⁸ Alan Turing Institute, The British Library, John Dodson House, London, UK.
⁹ Steno Diabetes Center Copenhagen, Cardiometabolic Disease Department, Borgmester Ib Juuls Vej 83, 2730 Herlev, Denmark.
¹⁰ Health Data Research UK, London, UK.
¹¹ National Institute for Health and Care Research, UK.

PMID: 39385845
PMCID: PMC11462446
DOI: 10.1093/ehjimp/qyae094

Quality control of cardiac magnetic resonance imaging segmentation, feature tracking, aortic flow, and native T1 analysis using automated batch processing in the UK Biobank study

Sucharitha Chadalavada et al. Eur Heart J Imaging Methods Pract. 2024.

. 2024 Sep 16;2(3):qyae094.

doi: 10.1093/ehjimp/qyae094. eCollection 2024 Jul.

Authors

Affiliations

¹ William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, Charterhouse Square, London, UK.
² Barts Heart Centre, St Bartholomew's Hospital, Barts Health NHS Trust, West Smithfield, London, UK.
³ Digital Environment Research Institute, Queen Mary University of London, London, UK.
⁴ Department of Computer Science, University of Zakho, Zakho, Kurdistan of Iraq, Iraq.
⁵ Department of Cardiology, US Department of Veterans Affair Medical Center, Washington, D.C., USA.
⁶ Circle Cardiovascular Imaging Inc., Calgary, Canada.
⁷ School of Electronic Eng. & Computer Science, Queen Mary University of London, UK.
⁸ Alan Turing Institute, The British Library, John Dodson House, London, UK.
⁹ Steno Diabetes Center Copenhagen, Cardiometabolic Disease Department, Borgmester Ib Juuls Vej 83, 2730 Herlev, Denmark.
¹⁰ Health Data Research UK, London, UK.
¹¹ National Institute for Health and Care Research, UK.

PMID: 39385845
PMCID: PMC11462446
DOI: 10.1093/ehjimp/qyae094

Abstract

Aims: Automated algorithms are regularly used to analyse cardiac magnetic resonance (CMR) images. Validating data output reliability from this method is crucial for enabling widespread adoption. We outline a visual quality control (VQC) process for image analysis using automated batch processing. We assess the performance of automated analysis and the reliability of replacing visual checks with statistical outlier (SO) removal approach in UK Biobank CMR scans.

Methods and results: We included 1987 CMR scans from the UK Biobank COVID-19 imaging study. We used batch processing software (Circle Cardiovascular Imaging Inc.-CVI42) to automatically extract chamber volumetric data, strain, native T1, and aortic flow data. The automated analysis outputs (∼62 000 videos and 2000 images) were visually checked by six experienced clinicians using a standardized approach and a custom-built R Shiny app. Inter-observer variability was assessed. Data from scans passing VQC were compared with a SO removal QC method in a subset of healthy individuals (n = 1069). Automated segmentation was highly rated, with over 95% of scans passing VQC. Overall inter-observer agreement was very good (Gwet's AC2 0.91; 95% confidence interval 0.84, 0.94). No difference in overall data derived from VQC or SO removal in healthy individuals was observed.

Conclusion: Automated image analysis using CVI42 prototypes for UK Biobank CMR scans demonstrated high quality. Larger UK Biobank data sets analysed using these automated algorithms do not require in-depth VQC. SO removal is sufficient as a QC measure, with operator discretion for visual checks based on population or research objectives.

Keywords: Shiny app; automated image analysis; cardiac magnetic resonance imaging; machine learning; quality control.

PubMed Disclaimer

Conflict of interest statement

Conflict of interest: S.E.P. provides consultancy to Circle Cardiovascular Imaging, Inc., Calgary, Alberta, Canada. The remaining authors have nothing to disclose.

Figures

**Graphical Abstract**
Created using Biorendr.com.

**Figure 1**
Flow chart detailing timeline of CMR image analysis and quality control process. Created using Biorendr.com.

**Figure 2**
Custom-built shiny app user-friendly interface and layout. Created using Biorendr.com.

**Figure 3**
Coefficient (Gwet AC2) by image sequence of scans visually checked by six different operators. The P value for all the results shown was <0.05, and the detailed results are shown in Supplementary data online, *Table S3*. Created using Biorendr.com. LV, Left ventricle; SAX, short axis; LAX, long axis; RV, right ventricle; LA, left atrium.

See this image and copyright information in PMC

References

1. Arnold JR, McCann GP. Cardiovascular magnetic resonance: applications and practical considerations for the general cardiologist. Heart 2020;106:174–81. - PubMed
1. Baritussio A, Scatteia A, Bucciarelli-Ducci C. Role of cardiovascular magnetic resonance in acute and chronic ischemic heart disease. Int J Cardiovasc Imaging 2018;34:67–80. - PMC - PubMed
1. Bailly A, Lipiecki J, Chabrot P, Alwdja A, Garcier JM, Ughetto S et al. Assessment of left ventricular volumes and function by cine-MR imaging depending on the investigator’s experience. Surg Radiol Anat 2009;31:113–20. - PubMed
1. Bernard O, Lalande A, Zotti C, Cervenansky F, Yang X, Heng PA et al. Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans Med Imaging 2018;37:2514–25. - PubMed
1. Leiner T, Rueckert D, Suinesiaputra A, Baeßler B, Nezafat R, Išgum I et al. Machine learning in cardiovascular magnetic resonance: basic concepts and applications. J Cardiovasc Magn Reson 2019;21:1–14. - PMC - PubMed

LinkOut - more resources

Full Text Sources
- PubMed Central

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Quality control of cardiac magnetic resonance imaging segmentation, feature tracking, aortic flow, and native T1 analysis using automated batch processing in the UK Biobank study

Affiliations

Quality control of cardiac magnetic resonance imaging segmentation, feature tracking, aortic flow, and native T1 analysis using automated batch processing in the UK Biobank study

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

LinkOut - more resources

Full Text Sources