Maureen van Eijnatten1, Leonardo Rundo2, K Joost Batenburg3, Felix Lucka4, Emma Beddowes5, Carlos Caldas5, Ferdia A Gallagher2, Evis Sala2, Carola-Bibiane Schönlieb6, Ramona Woitek7. 1. Centrum Wiskunde & Informatica, 1098 XG Amsterdam, the Netherlands; Medical Image Analysis Group, Department of Biomedical Engineering, Eindhoven University of Technology, 5600 MB Eindhoven, the Netherlands. Electronic address: m.a.j.m.v.eijnatten@tue.nl. 2. Department of Radiology, University of Cambridge, CB2 0QQ Cambridge, United Kingdom; Cancer Research UK Cambridge Centre, University of Cambridge, CB2 0RE Cambridge, United Kingdom. 3. Centrum Wiskunde & Informatica, 1098 XG Amsterdam, the Netherlands; Mathematical Institute, Leiden University, 2300 RA Leiden, the Netherlands. 4. Centrum Wiskunde & Informatica, 1098 XG Amsterdam, the Netherlands; Centre for Medical Image Computing, University College London, WC1E 6BT London, United Kingdom. 5. Cancer Research UK Cambridge Centre, University of Cambridge, CB2 0RE Cambridge, United Kingdom; Cancer Research UK Cambridge Institute, University of Cambridge, CB2 0RE Cambridge, United Kingdom; Department of Oncology, Addenbrooke's Hospital, Cambridge University Hospitals National Health Service (NHS) Foundation Trust, CB2 0QQ Cambridge, United Kingdom. 6. Department of Applied Mathematics and Theoretical Physics, University of Cambridge, CB3 0WA Cambridge, United Kingdom. 7. Department of Radiology, University of Cambridge, CB2 0QQ Cambridge, United Kingdom; Cancer Research UK Cambridge Centre, University of Cambridge, CB2 0RE Cambridge, United Kingdom; Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, 1090 Vienna, Austria.
Abstract
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.
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.