Skip to main content
SpringerLink
Log in

Quality Control

  • Chapter
  • First Online:
AI and Big Data in Cardiology

  • 413 Accesses

Abstract

Assessing and controlling the quality of medical data such as images, as well as AI-derived parameters from these data, is an important component of clinical imaging and retrospective population studies. This chapter deals with the issue of how AI can be used to automatically control the quality of its results. The clinical introduction discusses the role of current role and potential of quality control techniques. The technical review summarizes the state-of-the-art in AI-enabled quality control. The main focus is on cardiac MR imaging, but applications in echocardiography are also introduced. Methods to identify motion artefacts, poor planning, missing slices and failed segmentations are discussed. The practical tutorial involves implementing a simple motion artefact detection model. The closing clinical opinion piece discusses the future role of AI in ensuring that the quality of images and their derived measures is maximized.

Authors’ contribution:

\(\bullet \) Introduction, Opinion: AL.

\(\bullet \) Main chapter: IO, EPA.

\(\bullet \) Tutorial: IO.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 59.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Free shipping worldwide - see info
Hardcover Book
USD 84.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    The EchoNet Dynamic dataset contains \({>}10,000\) annotated apical 4-chamber videos: https://echonet.github.io/dynamic/.

  2. 2.

    Data augmentation is a technique commonly used in deep learning to boost the amount of training data. It involves supplementing the training set by including transformed versions of the existing training data. For example, common augmentations of imaging data can involve translations, rotations, flipping and elastic deformations. Data augmentation has been shown to improve generalization performance.

  3. 3.

    Atlas-based segmentation was a popular approach before the rise to prominence of deep learning-based segmentation models. The ‘atlas’ consists of an example image with associated ground truth segmentation. A new image is segmented by registering it to the atlas image, then transforming the atlas segmentation to the new image using the resulting displacement field. Multi-atlas segmentation is an extension of this approach to make use of multiple image/segmentation pairs in the atlas.

References

  1. Lalande A, Salvé N, Comte A, Jaulent M, Legrand L, Walker P, Cottin Y, Wolf J, Brunotte F. Left ventricular ejection fraction calculation from automatically selected and processed diastolic and systolic frames in short-axis cine-MRI. J Cardiovasc Magn Reson. 2004; 6:817–27.

    Google Scholar 

  2. Leclerc S, Smistad E, Pedrosa J, Østvik A, Cervenansky F, Espinosa F, Espeland T, Berg EAR, Jodoin PM, Grenier T, Lartizien C, D’hooge J, Lovstakken L, Bernard O. Deep learning for segmentation using an open large-scale dataset in 2D echocardiography. IEEE Trans Med Imaging. 2019; 38(9): 2198–210.

    Google Scholar 

  3. Ouyang D, He B, Ghorbani A, Yuan N, Ebinger J, Langlotz CP, Heidenreich PA, Harrington RA, Liang DH, Ashley EA, Zou JY. Video-based AI for beat-to-beat assessment of cardiac function. Nature. 2020; 580:252–6.

    Google Scholar 

  4. Abdi AH, Luong C, Tsang T, Allan G, Nouranian S, Jue J, Hawley D, Fleming S, Gin K, Swift J, Rohling R, Abolmaesumi P. Automatic quality assessment of echocardiograms using convolutional neural networks: feasibility on the apical four-chamber view. IEEE Trans Med Imaging. 2017; 36(6):1221–30.

    Google Scholar 

  5. Zhang J, Gajjala S, Agrawal P, Tison GH, Hallock LA, Beussink-Nelson L, Lassen MH, Fan E, Aras MA, Jordan C, Fleischmann KE, Melisko M, Qasim A, Shah SJ, Bajcsy R, Deo RC. Fully automated echocardiogram interpretation in clinical practice. Circulation. 2018; 138(16):1623–35.

    Google Scholar 

  6. Labs R, Vrettos A, Azarmehr N, Howard J, Shun-shin M, Cole G, Francis D, Zolgharni M. Automated assessment of image quality in 2D echocardiography using deep learning, Intelligent Medicine. 2022. In press.

    Google Scholar 

  7. Klinke V, Muzzarelli S, Lauriers N, Locca D, Vincenti G, Monney P, Lu C, Nothnagel D, Pilz G, Lombardi M, et al. Quality assessment of cardiovascular magnetic resonance in the setting of the European CMR registry: description and validation of standardized criteria. J Cardiovasc Magn Reson. 2013; 15(1):55.

    Google Scholar 

  8. Alfudhili K, Masci PG, Delacoste J, Ledoux J-B, Berchier G, Dunet V, Qanadli SD, Schwitter J, Beigelman-Aubry C. Current artefacts in cardiac and chest magnetic resonance imaging: tips and tricks. Br J Radiol. 2016; 89(1062):20150987.

    Google Scholar 

  9. Ferreira PF, Gatehouse PD, Mohiaddin RH, Firmin DN. Cardiovascular magnetic resonance artefacts. J Cardiovasc Magn Reson. 2013;15(1):41.

    Google Scholar 

  10. Lorch B, Vaillant G, Baumgartner C, Bai W, Rueckert D, Maier A. Automated detection of motion artefacts in MR imaging using decision forests. J Med Eng. 2017; 2017.

    Google Scholar 

  11. Oksuz I, Ruijsink B, Puyol-Antón E, Bustin A, Cruz G, Prieto C, Rueckert D, Schnabel JA, King AP. Deep learning using K-space based data augmentation for automated cardiac MR motion artefact detection. In: International conference on medical image computing and computer-assisted intervention. Springer; 2018. p. 250–58.

    Google Scholar 

  12. Oksuz I, Ruijsink B, Puyol-Antón E, Clough JR, Cruz G, Bustin A, Prieto C, Botnar R, Rueckert D, Schnabel JA, et al. Automatic CNN-based detection of cardiac MR motion artefacts using K-space data augmentation and curriculum learning. Med Image Anal. 2019; 55:136–47.

    Google Scholar 

  13. Oksuz I, Clough JR, Ruijsink B, Anton EP, Bustin A, Cruz G, Prieto C, King AP, Schnabel JA. Deep learning-based detection and correction of cardiac MR motion artefacts during reconstruction for high-quality segmentation. IEEE Trans Med Imaging. 2020; 39(12):4001–10.

    Google Scholar 

  14. Sundararajan R, Patel H, Shanbhag D, Vaidya V. An SVM based approach for cardiac view planning. 2014; arXiv:1407.3026.

  15. Lu X, Jolly M-P, Georgescu B, Hayes C, Speier P, Schmidt M, Bi X, Kroeker R, Comaniciu D, Kellman P, et al. Automatic view planning for cardiac MRI acquisition. In: International conference on medical image computing and computer-assisted intervention. Springer; 2011. p. 479–86.

    Google Scholar 

  16. Lê M, Lieman-Sifry J, Lau F, Sall S, Hsiao A, Golden D. Computationally efficient cardiac views projection using 3D convolutional neural networks. In: Cardoso MJ, Arbel T, Carneiro G, Syeda-Mahmood TF, Tavares JMRS, Moradi M, Bradley AP, Greenspan H, Papa JP, Madabhushi A, Nascimento JC, Cardoso JS, Belagiannis V, Lu Z, editors. Deep learning in medical image analysis and multimodal learning for clinical decision support - third international workshop, DLMIA 2017, and 7th international workshop, ML-CDS 2017, held in conjunction with MICCAI 2017, Québec City, QC, Canada, September 14, 2017, proceedings, series lecture notes in computer science, vol. 10553. Springer; 2017. p. 109–16.

    Google Scholar 

  17. Alansary A, Folgoc LL, Vaillant G, Oktay O, Li Y, Bai W, Passerat-Palmbach J, Guerrero R, Kamnitsas K, Hou B, McDonagh SG, Glocker B, Kainz B, Rueckert D. Automatic view planning with multi-scale deep reinforcement learning agents. In: Frangi AF, Schnabel JA, Davatzikos C, Alberola-López C, Fichtinger G, editors. Medical image computing and computer assisted intervention - MICCAI 2018 - 21st international conference, Granada, Spain, September 16-20, 2018, proceedings, part I, series lecture notes in computer science, vol. 11070. Springer; 2018. p. 277–85.

    Google Scholar 

  18. Oksuz I, Ruijsink B, Puyol-Antón E, Sinclair M, Rueckert D, Schnabel JA, King AP. Automatic left ventricular outflow tract classification for accurate cardiac MR planning. In: IEEE 15th international symposium on biomedical imaging (ISBI 2018). IEEE; 2018. p. 462–65.

    Google Scholar 

  19. Zhang L, Gooya A, Dong B, Hua R, Petersen SE, Medrano-Gracia P, Frangi AF. Automated quality assessment of cardiac MR images using convolutional neural networks. In: Tsaftaris SA, Gooya A, Frangi AF, Prince JL, editors.Simulation and synthesis in medical imaging - first international workshop, SASHIMI 2016, held in conjunction with MICCAI 2016, Athens, Greece, October 21, 2016, proceedings, series lecture notes in computer science, vol. 9968, 2016. p. 138–45.

    Google Scholar 

  20. Zhang L, Gooya, A, Frangi AF. Semi-supervised assessment of incomplete LV coverage in cardiac MRI using generative adversarial nets. In: Tsaftaris SA, Gooya A, Frangi AF, Prince JL, editors. Simulation and synthesis in medical imaging - second international workshop, SASHIMI 2017, held in conjunction with MICCAI 2017, Québec City, QC, Canada, September 10, 2017, proceedings, series lecture notes in computer science, vol. 10557. Springer; 2017. p. 61–8.

    Google Scholar 

  21. Tarroni G, Oktay O, Bai W, Schuh A, Suzuki H, Passerat-Palmbach J, de Marvao A, O’Regan DP, Cook S, Glocker B, Matthews PM, Rueckert D. Learning-based quality control for cardiac MR images. IEEE Trans Med Imaging. 2019; 38(5):1127–38.

    Google Scholar 

  22. Zhang L, Pereañez M, Piechnik SK, Neubauer S, Petersen SE, Frangi AF. Image quality assessment for population cardiac magnetic resonance imaging. In: Deep learning and convolutional neural networks for medical imaging and clinical informatics. Springer; 2019. p. 299–321.

    Google Scholar 

  23. Zhang L, Pereañez M, Bowles C, Piechnik S, Neubauer S, Petersen S, Frangi A. Missing slice imputation in population CMR imaging via conditional generative adversarial nets. In: International conference on medical image computing and computer-assisted intervention. Springer; 2019. p. 651–59.

    Google Scholar 

  24. Audelan B, Delingette H. Unsupervised quality control of image segmentation based on Bayesian learning. In: International conference on medical image computing and computer-assisted intervention. Springer; 2019. p. 21–9.

    Google Scholar 

  25. Fahmy A, El-Rewaidy H, Nezafat M, Nakamori S, Nezafat R. Automated analysis of cardiovascular magnetic resonance myocardial native T1 mapping images using fully convolutional neural networks. J Cardiovasc Magn Reson. 2019; 21(1):7.

    Google Scholar 

  26. Hann E, Biasiolli L, Zhang Q, Popescu IA, Werys K, Lukaschuk E, Carapella V, Paiva JM, Aung N, Rayner JJ, et al. Quality control-driven image segmentation towards reliable automatic image analysis in large-scale cardiovascular magnetic resonance aortic cine imaging. In: International conference on medical image computing and computer-assisted intervention. Springer; 2019. p. 750–58.

    Google Scholar 

  27. Kass M, Witkin A, Terzopoulos D. Snakes: active contour models. Int J Comput Vis. 1988; 1(4):321–31.

    Google Scholar 

  28. Kohlberger T, Singh V, Alvino C, Bahlmann C, Grady L. Evaluating segmentation error without ground truth. In: International conference on medical image computing and computer-assisted intervention. Springer; 2012. p. 528–36.

    Google Scholar 

  29. Roy AG, Conjeti S, Navab N, Wachinger C, Initiative ADN, et al. Bayesian QuickNAT: model uncertainty in deep whole-brain segmentation for structure-wise quality control. NeuroImage. 2019; 195:11–22.

    Google Scholar 

  30. Sander J, de Vos BD, Wolterink JM, Išgum I. Towards increased trustworthiness of deep learning segmentation methods on cardiac MRI. In: Medical imaging 2019: image processing, vol. 10949. International society for optics and photonics, 2019. p. 1094919.

    Google Scholar 

  31. Puyol-Antón E, Ruijsink B, Baumgartner CF, Sinclair M, Konukoglu E, Razavi R, King AP. Automated quantification of myocardial tissue characteristics from native T1 mapping using neural networks with Bayesian inference for uncertainty-based quality-control. J Cardiovasc Magn Reson. 2020;22:60.

    Google Scholar 

  32. Baumgartner CF, Tezcan KC, Chaitanya K, Hötker AM, Muehlematter UJ, Schawkat K, Becker AS, Donati O, Konukoglu E. PHiSeg: capturing uncertainty in medical image segmentation. In: Shen D, Liu T, Peters TM, Staib LH, Essert C, Zhou S, Yap P-T, Khan A, editors. Medical image computing and computer assisted intervention - MICCAI 2019. Cham: Springer International Publishing; 2019. p. 119–27.

    Google Scholar 

  33. Bouix S, Martin-Fernandez M, Ungar L, Nakamura M, Koo M-S, McCarley RW, Shenton ME. On evaluating brain tissue classifiers without a ground truth. Neuroimage. 2007; 36(4):1207–24.

    Google Scholar 

  34. Robinson R, Valindria VV, Bai W, Oktay O, Kainz B, Suzuki H, Sanghvi MM, Aung N, Paiva JM, Zemrak F, et al. Automated quality control in image segmentation: application to the UK Biobank cardiovascular magnetic resonance imaging study. J Cardiovasc Magn Reson. 2019; 21(1):18.

    Google Scholar 

  35. Dubost F, de Bruijne M, Nardin M, Dalca AV, Donahue KL, Giese A-K, Etherton MR, Wu O, de Groot M, Niessen W, et al. Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation. Medical image analysis, 2020. p. 101698.

    Google Scholar 

  36. Alfaro-Almagro F, Jenkinson M, Bangerter NK, Andersson JL, Griffanti L, Douaud G, Sotiropoulos SN, Jbabdi S, Hernandez-Fernandez M, Vallee E, et al. Image processing and quality control for the first 10,000 brain imaging datasets from UK Biobank. Neuroimage. 2018; 166:400–24.

    Google Scholar 

  37. Tarroni G, Bai W, Oktay O, Schuh A, Suzuki H, Glocker B, Matthews PM, Rueckert D. Large-scale quality control of cardiac imaging in population studies: application to UK Biobank. Sci Rep. 2020; 10(1):1–11.

    Google Scholar 

  38. N. Painchaud, Y. Skandarani, T. Judge, O. Bernard, A. Lalande, and P. Jodoin, Cardiac segmentation with strong anatomical guarantees, IEEE Transactions on Medical Imaging, pp. 1, 2020;39:3703–13.

    Google Scholar 

  39. Ruijsink B, Puyol-Antón E, Oksuz I, Sinclair M, Bai W, Schnabel JA, Razavi R, King AP. Fully automated, quality-controlled cardiac analysis from CMR: validation and large-scale application to characterize cardiac function. JACC: Cardiovasc Imaging. 2020; 13(3):684–95.

    Google Scholar 

  40. Machado I, Puyol-Anton E, Hammernik K, Cruz G, Ugurlu D, Ruijsink B, Castelo-Branco M, Young A, Prieto C, Schnabel JA, King AP. Quality-aware cine cardiac MRI reconstruction and analysis from undersampled K-space data. In: Proceedings of the workshop on statistical atlases and computational modelling of the heart (STACOM), 2021.

    Google Scholar 

  41. ACDC challenge website. https://www.creatis.insa-lyon.fr/Challenge/acdc/.

  42. Singh R, Weiwen W, Wang G. Artificial intelligence in image reconstruction: the change is here. Phys Med. 2020; 79:113–25.

    Google Scholar 

  43. Skandarani Y, Lalande A, Afilalo J, Jodoin P. Generative adversarial networks in cardiology. Can J Cardiol. 2022; 38:196–203.

    Google Scholar 

Download references

Acknowledgements

IO was supported by the 2232 International Fellowship for Outstanding Researchers Program of TUBITAK (Project No: 118C353). However, the entire responsibility of the work belongs to the authors.

EPA was supported by the EPSRC (EP/R005516/1) and by core funding from the Wellcome/EPSRC Centre for Medical Engineering (WT 203148/Z/16/Z).

Author information

Authors and Affiliations

  1. Computer Engineering Department, Istanbul Technical University, Istanbul, Turkey

    Ilkay Oksuz

  2. University of Burgundy, Dijon, France

    Alain Lalande

  3. Medical Imaging Department, University Hospital of Dijon, Dijon, France

    Alain Lalande

  4. School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom

    Esther Puyol-Antón

Authors
  1. Ilkay Oksuz
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alain Lalande
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Esther Puyol-Antón
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Esther Puyol-Antón .

Editor information

Editors and Affiliations

  1. CREATIS, Lyon 1 University, Villeurbanne Cedex, France

    Nicolas Duchateau

  2. School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK

    Andrew P. King

7.1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (zip 419551 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Oksuz, I., Lalande, A., Puyol-Antón, E. (2023). Quality Control. In: Duchateau, N., King, A.P. (eds) AI and Big Data in Cardiology. Springer, Cham. https://doi.org/10.1007/978-3-031-05071-8_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-05071-8_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-05070-1

  • Online ISBN: 978-3-031-05071-8

  • eBook Packages: Medicine

Publish with us

Policies and ethics

Search

Navigation