Skip to main content
SpringerLink
Log in

A 3D Sparse Autoencoder for Fully Automated Quality Control of Affine Registrations in Big Data Brain MRI Studies

  • Published:
Journal of Imaging Informatics in Medicine Aims and scope Submit manuscript

Abstract

This paper presents a fully automated pipeline using a sparse convolutional autoencoder for quality control (QC) of affine registrations in large-scale T1-weighted (T1w) and T2-weighted (T2w) magnetic resonance imaging (MRI) studies. Here, a customized 3D convolutional encoder-decoder (autoencoder) framework is proposed and the network is trained in a fully unsupervised manner. For cross-validating the proposed model, we used 1000 correctly aligned MRI images of the human connectome project young adult (HCP-YA) dataset. We proposed that the quality of the registration is proportional to the reconstruction error of the autoencoder. Further, to make this method applicable to unseen datasets, we have proposed dataset-specific optimal threshold calculation (using the reconstruction error) from ROC analysis that requires a subset of the correctly aligned and artificially generated misalignments specific to that dataset. The calculated optimum threshold is used for testing the quality of remaining affine registrations from the corresponding datasets. The proposed framework was tested on four unseen datasets from autism brain imaging data exchange (ABIDE I, 215 subjects), information eXtraction from images (IXI, 577 subjects), Open Access Series of Imaging Studies (OASIS4, 646 subjects), and “Food and Brain” study (77 subjects). The framework has achieved excellent performance for T1w and T2w affine registrations with an accuracy of 100% for HCP-YA. Further, we evaluated the generality of the model on four unseen datasets and obtained accuracies of 81.81% for ABIDE I (only T1w), 93.45% (T1w) and 81.75% (T2w) for OASIS4, and 92.59% for “Food and Brain” study (only T1w) and in the range 88–97% for IXI (for both T1w and T2w and stratified concerning scanner vendor and magnetic field strengths). Moreover, the real failures from “Food and Brain” and OASIS4 datasets were detected with sensitivities of 100% and 80% for T1w and T2w, respectively. In addition, AUCs of > 0.88 in all scenarios were obtained during threshold calculation on the four test sets.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data Availability

The datasets analyzed during the current study are available in the HCP-YA repository, https://www.humanconnectome.org/study/hcp-young-adult/overview; ABIDE I, https://fcon_1000.projects.nitrc.org/indi/abide/abide_I.html; OASIS4, https://www.oasis-brains.org/#data; Food and Brain; https://openneuro.org/datasets/ds004697/versions/1.0.1.

References

  1. Eliot L, Ahmed A, Khan H, Patel J (2021) Dump the “dimorphism”: Comprehensive synthesis of human brain studies reveals few male-female differences beyond size. Neurosci Biobehav Rev 125:667–697. https://doi.org/10.1016/j.neubiorev.2021.02.026

  2. Pomponio R, Erus G, Habes M, et al (2020) Harmonization of large MRI datasets for the analysis of brain imaging patterns throughout the lifespan. Neuroimage 208:116450. https://doi.org/10.1016/j.neuroimage.2019.116450

  3. Liew S-L, Zavaliangos-Petropulu A, Jahanshad N, et al (2022) The ENIGMA Stroke Recovery Working Group: Big data neuroimaging to study brain–behavior relationships after stroke. Hum Brain Mapp 43:129–148. https://doi.org/10.1002/hbm.25015

  4. Alfaro-Almagro F, Jenkinson M, Bangerter NK, et al (2018) Image processing and Quality Control for the first 10,000 brain imaging datasets from UK Biobank. Neuroimage 166:400–424. https://doi.org/10.1016/j.neuroimage.2017.10.034

  5. Poldrack RA, Gorgolewski KJ (2014) Making big data open: data sharing in neuroimaging. Nat Neurosci 17:1510–1517. https://doi.org/10.1038/nn.3818

    Article  CAS  PubMed  Google Scholar 

  6. Chen S, He Z, Han X, et al (2019) How Big Data and High-performance Computing Drive Brain Science. Genomics Proteomics Bioinformatics 17:381–392. https://doi.org/10.1016/j.gpb.2019.09.003

  7. Di Martino A, Yan C-G, Li Q, et al (2014) The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol Psychiatry 19:659–667. https://doi.org/10.1038/mp.2013.78

    Article  PubMed  Google Scholar 

  8. Marcus DS, Wang TH, Parker J, et al (2007) Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults. J Cogn Neurosci 19:1498–1507. https://doi.org/10.1162/jocn.2007.19.9.1498

    Article  PubMed  Google Scholar 

  9. Van Essen DC, Smith SM, Barch DM, et al (2013) The WU-Minn Human Connectome Project: An overview. Neuroimage 80:62–79. https://doi.org/10.1016/j.neuroimage.2013.05.041

  10. Weiner MW, Veitch DP, Aisen PS, et al (2012) The Alzheimer’s Disease Neuroimaging Initiative: a review of papers published since its inception. Alzheimers Dement 8. https://doi.org/10.1016/J.JALZ.2011.09.172

  11. Food and Brain Study - OpenNeuro. https://openneuro.org/datasets/ds004697/versions/1.0.1. Accessed 2 Oct 2023

  12. Helms G, Kallenberg K, Dechent P (2006) Contrast-driven approach to intracranial segmentation using a combination of T2- and T1-weighted 3D MRI data sets. Journal of Magnetic Resonance Imaging 24:790–795. https://doi.org/10.1002/JMRI.20692

    Article  PubMed  Google Scholar 

  13. Denis De Senneville B, Manjón J V., Coupé P (2020) RegQCNET: Deep quality control for image-to-template brain MRI affine registration. Phys Med Biol 65. https://doi.org/10.1088/1361-6560/ABB6BE

  14. Tummala S, Thadikemalla VSG, Kreilkamp BAK, et al (2021) Fully automated quality control of rigid and affine registrations of T1w and T2w MRI in big data using machine learning. Comput Biol Med 139:104997. https://doi.org/10.1016/j.compbiomed.2021.104997

  15. Bottani S, Burgos N, Maire A, et al (2022) Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse. Med Image Anal 75:102219. https://doi.org/10.1016/j.media.2021.102219

  16. Tang L, Hui Y, Yang H, et al (2022) Medical image fusion quality assessment based on conditional generative adversarial network. Front Neurosci 16. https://doi.org/10.3389/FNINS.2022.986153/FULL

  17. Hann E, Popescu IA, Zhang Q, et al (2021) Deep neural network ensemble for on-the-fly quality control-driven segmentation of cardiac MRI T1 mapping. Med Image Anal 71:102029. https://doi.org/10.1016/j.media.2021.102029

  18. Aprea F, Marrone S, Sansone C (2021) Neural Machine Registration for Motion Correction in Breast DCE-MRI. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp 4332–4339

  19. Samani ZR, Alappatt JA, Parker D, et al (2020) QC-Automator: Deep Learning-Based Automated Quality Control for Diffusion MR Images. Front Neurosci 13. https://doi.org/10.3389/fnins.2019.01456

  20. Kiser K, Meheissen MAM, Mohamed ASR, et al (2019) Prospective quantitative quality assurance and deformation estimation of MRI-CT image registration in simulation of head and neck radiotherapy patients. Clin Transl Radiat Oncol 18:120–127. https://doi.org/10.1016/j.ctro.2019.04.018

  21. Shoroshov G, Senyukova O, Semenov D, Sharova D (2022) MRI Quality Control Algorithm Based on Image Analysis Using Convolutional and Recurrent Neural Networks. Proc IEEE Symp Comput Based Med Syst 2022-July:412–415. https://doi.org/10.1109/CBMS55023.2022.00080

  22. Klapwijk ET, van de Kamp F, van der Meulen M, et al (2019) Qoala-T: A supervised-learning tool for quality control of FreeSurfer segmented MRI data. Neuroimage 189:116–129. https://doi.org/10.1016/j.neuroimage.2019.01.014

    Article  PubMed  Google Scholar 

  23. Islam KT, Wijewickrema S, O’Leary S (2021) A deep learning based framework for the registration of three dimensional multi-modal medical images of the head. Scientific Reports 2021 11:1 11:1–13. https://doi.org/10.1038/s41598-021-81044-7

  24. Sokooti H, de Vos B, Berendsen F, et al (2019) 3D Convolutional Neural Networks Image Registration Based on Efficient Supervised Learning from Artificial Deformations. https://doi.org/10.48550/arxiv.1908.10235

  25. Dubost F, de Bruijne M, Nardin M, et al (2020) Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation. Med Image Anal 63:101698. https://doi.org/10.1016/J.MEDIA.2020.101698

    Article  PubMed  PubMed Central  Google Scholar 

  26. Benhajali Y, Badhwar AP, Spiers H, et al (2020) A Standardized Protocol for Efficient and Reliable Quality Control of Brain Registration in Functional MRI Studies. Front Neuroinform 14. https://doi.org/10.3389/FNINF.2020.00007

  27. Fonov VS, Dadar M, ADNI TPARG, Collins DL (2022) DARQ: Deep learning of quality control for stereotaxic registration of human brain MRI to the T1w MNI-ICBM 152 template. Neuroimage 257:. https://doi.org/10.1016/J.NEUROIMAGE.2022.119266

  28. Ravi D, Barkhof F, Alexander DC, et al (2022) An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training

  29. Galib SM, Lee HK, Guy CL, et al (2020) A fast and scalable method for quality assurance of deformable image registration on lung CT scans using convolutional neural networks. Med Phys 47:99–109. https://doi.org/10.1002/mp.13890

    Article  PubMed  Google Scholar 

  30. Sokooti H, Yousefi S, Elmahdy MS, et al (2021) Hierarchical Prediction of Registration Misalignment Using a Convolutional LSTM: Application to Chest CT Scans. IEEE Access 9:62008–62020. https://doi.org/10.1109/ACCESS.2021.3074124

    Article  Google Scholar 

  31. Muenzing SEA, van Ginneken B, Murphy K, Pluim JPW (2012) Supervised quality assessment of medical image registration: Application to intra-patient CT lung registration. Med Image Anal 16:1521–1531. https://doi.org/10.1016/j.media.2012.06.010

    Article  PubMed  Google Scholar 

  32. Koenig LN, Day GS, Salter A, et al (2020) Select Atrophied Regions in Alzheimer disease (SARA): An improved volumetric model for identifying Alzheimer disease dementia. Neuroimage Clin 26:102248. https://doi.org/10.1016/J.NICL.2020.102248

    Article  PubMed  PubMed Central  Google Scholar 

  33. Gorgolewski K, Burns CD, Madison C, et al (2011) Nipype: A flexible, lightweight and extensible neuroimaging data processing framework in Python. Front Neuroinform 5:13. https://doi.org/10.3389/FNINF.2011.00013/ABSTRACT

    Article  PubMed  PubMed Central  Google Scholar 

  34. Smith SM, Jenkinson M, Woolrich MW, et al (2004) Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 23 Suppl 1: https://doi.org/10.1016/J.NEUROIMAGE.2004.07.051

  35. Tustison NJ, Avants BB, Cook PA, et al (2010) N4ITK: Improved N3 Bias Correction. IEEE Trans Med Imaging 29:1310–1320. https://doi.org/10.1109/TMI.2010.2046908

    Article  PubMed  PubMed Central  Google Scholar 

  36. Baur C, Denner S, Wiestler B, et al (2021) Autoencoders for unsupervised anomaly segmentation in brain MR images: A comparative study. Med Image Anal 69:101952. https://doi.org/10.1016/J.MEDIA.2020.101952

    Article  PubMed  Google Scholar 

  37. Chatterjee S, Sciarra A, Dünnwald M, et al (2022) StRegA: Unsupervised anomaly detection in brain MRIs using a compact context-encoding variational autoencoder. Comput Biol Med 149:106093. https://doi.org/10.1016/J.COMPBIOMED.2022.106093

    Article  PubMed  Google Scholar 

  38. Luo G, Xie W, Gao R, et al (2023) Unsupervised anomaly detection in brain MRI: Learning abstract distribution from massive healthy brains. Comput Biol Med 154:106610. https://doi.org/10.1016/J.COMPBIOMED.2023.106610

    Article  PubMed  Google Scholar 

  39. Kingma DP, Ba JL (2014) Adam: A Method for Stochastic Optimization. 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings. https://doi.org/10.48550/arxiv.1412.6980

  40. Le NQK, Ho QT, Nguyen VN, Chang JS (2022) BERT-Promoter: An improved sequence-based predictor of DNA promoter using BERT pre-trained model and SHAP feature selection. Comput Biol Chem 99:107732. https://doi.org/10.1016/J.COMPBIOLCHEM.2022.107732

    Article  CAS  PubMed  Google Scholar 

  41. Lam LHT, Do DT, Diep DTN, et al (2022) Molecular subtype classification of low-grade gliomas using magnetic resonance imaging-based radiomics and machine learning. NMR Biomed 35:e4792. https://doi.org/10.1002/NBM.4792

    Article  CAS  PubMed  Google Scholar 

  42. Gondara L (2016) Medical Image Denoising Using Convolutional Denoising Autoencoders. In: 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW). pp 241–246

  43. Pintelas E, Livieris IE, Pintelas PE (2021) A Convolutional Autoencoder Topology for Classification in High-Dimensional Noisy Image Datasets. Sensors 21. https://doi.org/10.3390/s21227731

Download references

Acknowledgements

We would like to thank HCP-YA, ABIDE I, IXI, OASIS4, and “Food and Brain” maintenance team for providing the datasets for this study.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada, Andhra Pradesh, India

    Venkata Sainath Gupta Thadikemalla

  2. Clinic for Neurology, University Medical Center, Göttingen, Germany

    Niels K. Focke

  3. Department of Electronics and Communication Engineering, School of Engineering and Sciences, SRM University-AP, Andhra Pradesh, India

    Sudhakar Tummala

Authors
  1. Venkata Sainath Gupta Thadikemalla
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Niels K. Focke
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sudhakar Tummala
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

VSGT contributed with conceptualisation, formal analysis, investigation, data curation, software, validation, and writing original draft. NKF contributed with conceptualization and supervision. ST contributed with conceptualization, methodology, editing, data curation, and supervision. All authors read and approved the final manuscript.

Corresponding authors

Correspondence to Venkata Sainath Gupta Thadikemalla or Sudhakar Tummala.

Ethics declarations

Ethical Approval and Consent to Participate

This research study was conducted retrospectively using human subject data made available in open access. Hence, written informed consent is not required.

Competing Interests

A patent was filed and published on this presented work (Indian Patent, application number: 202241065452, Published on 15/11/2022).

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Thadikemalla, V.S.G., Focke, N.K. & Tummala, S. A 3D Sparse Autoencoder for Fully Automated Quality Control of Affine Registrations in Big Data Brain MRI Studies. J Digit Imaging. Inform. med. 37, 412–427 (2024). https://doi.org/10.1007/s10278-023-00933-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-023-00933-7

Keywords

Search

Navigation