{"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/train-smarter-not-harder-learning-deep","title":"Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation","arxiv_id":"2211.15717","date":"2022-11-28","proceeding":null,"authors":["Javier Pérez de Frutos","André Pedersen","Egidijus Pelanis","David Bouget","Shanmugapriya Survarachakan","Thomas Langø","Ole-Jakob Elle","Frank Lindseth"],"abstract":"Purpose: This study aims to explore training strategies to improve convolutional neural network-based image-to-image deformable registration for abdominal imaging. Methods: Different training strategies, loss functions, and transfer learning schemes were considered. Furthermore, an augmentation layer which generates artificial training image pairs on-the-fly was proposed, in addition to a loss layer that enables dynamic loss weighting. Results: Guiding registration using segmentations in the training step proved beneficial for deep-learning-based image registration. Finetuning the pretrained model from the brain MRI dataset to the abdominal CT dataset further improved performance on the latter application, removing the need for a large dataset to yield satisfactory performance. Dynamic loss weighting also marginally improved performance, all without impacting inference runtime. Conclusion: Using simple concepts, we improved the performance of a commonly used deep image registration architecture, VoxelMorph. In future work, our framework, DDMR, should be validated on different datasets to further assess its value.","url_abs":"https://arxiv.org/abs/2211.15717v3","url_pdf":"https://arxiv.org/pdf/2211.15717v3.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":"train-smarter-not-harder-learning-deep","repo_url":"https://github.com/jpdefrutos/ddmr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-registration","task_name":"Image Registration"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.15717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15717"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jpdefrutos/ddmr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"13f627c303636bba","entry":"build_affine_trf","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/data_generator.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/data_generator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13f627c303636bba"}},{"code_sha256_prefix":"4a32c32258fe8b41","entry":"cubic_interpolate","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/layers/upsampling.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/layers/upsampling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a32c32258fe8b41"}},{"code_sha256_prefix":"ffc81695c50856c4","entry":"distance_map","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/layers.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ffc81695c50856c4"}},{"code_sha256_prefix":"81e5a852219a31d2","entry":"interpolate_spline","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/layers/b_splines.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/layers/b_splines.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81e5a852219a31d2"}},{"code_sha256_prefix":"5b111c938d606f63","entry":"linear_interpolate","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/layers/upsampling.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/layers/upsampling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b111c938d606f63"}},{"code_sha256_prefix":"3b0d56210b285ce2","entry":"pchip_interpolate","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/layers/upsampling.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/layers/upsampling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b0d56210b285ce2"}},{"code_sha256_prefix":"1799f1455cc6d4a8","entry":"target_registration_error","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/losses.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/losses.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1799f1455cc6d4a8"}},{"code_sha256_prefix":"4c4ddf1fb4e7bf79","entry":"volume_to_ov_and_dm","repo":"jpdefrutos/ddmr","repo_kind":"official","path":"ddmr/layers.py","file_url":"https://github.com/jpdefrutos/ddmr/blob/HEAD/ddmr/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c4ddf1fb4e7bf79"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}