3D deformable registration of longitudinal abdominopelvic CT images using unsupervised deep learning

Maureen van Eijnatten (Corresponding author), Leonardo Rundo, K. Joost Batenburg, Felix Lucka, Emma Beddowes, Carlos Caldas, Ferdia A. Gallagher, Evis Sala, Carola Bibiane Schönlieb, Ramona Woitek

Research output: Contribution to journalArticleAcademicpeer-review

8 Citations (Scopus)
214 Downloads (Pure)


Background and Objectives: Deep learning is being increasingly used for deformable image registration and unsupervised approaches, in particular, have shown great potential. However, the registration of abdominopelvic Computed Tomography (CT) images remains challenging due to the larger displacements compared to those in brain or prostate Magnetic Resonance Imaging datasets that are typically considered as benchmarks. In this study, we investigate the use of the commonly used unsupervised deep learning framework VoxelMorph for the registration of a longitudinal abdominopelvic CT dataset acquired in patients with bone metastases from breast cancer. Methods: As a pre-processing step, the abdominopelvic CT images were refined by automatically removing the CT table and all other extra-corporeal components. To improve the learning capabilities of the VoxelMorph framework when only a limited amount of training data is available, a novel incremental training strategy is proposed based on simulated deformations of consecutive CT images in the longitudinal dataset. This devised training strategy was compared against training on simulated deformations of a single CT volume. A widely used software toolbox for deformable image registration called NiftyReg was used as a benchmark. The evaluations were performed by calculating the Dice Similarity Coefficient (DSC) between manual vertebrae segmentations and the Structural Similarity Index (SSIM). Results: The CT table removal procedure allowed both VoxelMorph and NiftyReg to achieve significantly better registration performance. In a 4-fold cross-validation scheme, the incremental training strategy resulted in better registration performance compared to training on a single volume, with a mean DSC of 0.929±0.037 and 0.883±0.033, and a mean SSIM of 0.984±0.009 and 0.969±0.007, respectively. Although our deformable image registration method did not outperform NiftyReg in terms of DSC (0.988±0.003) or SSIM (0.995±0.002), the registrations were approximately 300 times faster. Conclusions: This study showed the feasibility of deep learning based deformable registration of longitudinal abdominopelvic CT images via a novel incremental training strategy based on simulated deformations.

Original languageEnglish
Article number106261
Number of pages14
JournalComputer Methods and Programs in Biomedicine
Publication statusPublished - Sept 2021

Bibliographical note

Publisher Copyright:
© 2021 The Author(s)


FundersFunder number
CRUK National Cancer Imaging Translational Accelerator
Cancer Research UKC9685/A25177
Cantab Capital Institute for the Mathematics of Information
Microsoft InnerEye
Royal Dutch Academy of Sciences
Wellcome TrustRG98755
Alan Turing Institute
Mark Foundation For Cancer Research
Engineering and Physical Sciences Research CouncilEP/M00483X/1, EP/N014588/1, EP/T017961/1
National Institute for Health Research
Leverhulme TrustEP/S026045/1
Koninklijke Nederlandse Akademie van Wetenschappen
Nederlandse Organisatie voor Wetenschappelijk Onderzoek639.073.506
UCLH Biomedical Research CentreBRC-1215-20014


    • Abdominopelvic imaging
    • Computed tomography
    • Convolutional neural networks
    • Deformable registration
    • Displacement vector fields
    • Incremental training


    Dive into the research topics of '3D deformable registration of longitudinal abdominopelvic CT images using unsupervised deep learning'. Together they form a unique fingerprint.

    Cite this