{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/voxelmorph-going-beyond-the-cranial-vault-1","title":"Voxelmorph++ Going beyond the cranial vault with keypoint supervision and multi-channel instance optimisation","arxiv_id":"2203.00046","date":"2022-02-28","proceeding":null,"authors":["Mattias P. Heinrich","Lasse Hansen"],"abstract":"The majority of current research in deep learning based image registration addresses inter-patient brain registration with moderate deformation magnitudes. The recent Learn2Reg medical registration benchmark has demonstrated that single-scale U-Net architectures, such as VoxelMorph that directly employ a spatial transformer loss, often do not generalise well beyond the cranial vault and fall short of state-of-the-art performance for abdominal or intra-patient lung registration. Here, we propose two straightforward steps that greatly reduce this gap in accuracy. First, we employ keypoint self-supervision with a novel network head that predicts a discretised heatmap and robustly reduces large deformations for better robustness. Second, we replace multiple learned fine-tuning steps by a single instance optimisation with hand-crafted features and the Adam optimiser. Different to other related work, including FlowNet or PDD-Net, our approach does not require a fully discretised architecture with correlation layer. Our ablation study demonstrates the importance of keypoints in both self-supervised and unsupervised (using only a MIND metric) settings. On a multi-centric inspiration-exhale lung CT dataset, including very challenging COPD scans, our method outperforms VoxelMorph by improving nonlinear alignment by 77% compared to 19% - reaching target registration errors of 2 mm that outperform all but one learning methods published to date. Extending the method to semantic features sets new stat-of-the-art performance on inter-subject abdominal CT registration.","url_abs":"https://arxiv.org/abs/2203.00046v1","url_pdf":"https://arxiv.org/pdf/2203.00046v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"voxelmorph-going-beyond-the-cranial-vault-1","repo_url":"https://github.com/mattiaspaul/voxelmorphplusplus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"voxelmorph-going-beyond-the-cranial-vault-1","repo_url":"https://github.com/multimodallearning/Lung250M-4B","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-registration","task_name":"Image Registration"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"heatmap","method_name":"Heatmap"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}