{"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/factorised-spatial-representation-learning","title":"Factorised spatial representation learning: application in semi-supervised myocardial segmentation","arxiv_id":"1803.07031","date":"2018-03-19","proceeding":null,"authors":["Agisilaos Chartsias","Thomas Joyce","Giorgos Papanastasiou","Scott Semple","Michelle Williams","David Newby","Rohan Dharmakumar","Sotirios A. Tsaftaris"],"abstract":"The success and generalisation of deep learning algorithms heavily depend on\nlearning good feature representations. In medical imaging this entails\nrepresenting anatomical information, as well as properties related to the\nspecific imaging setting. Anatomical information is required to perform further\nanalysis, whereas imaging information is key to disentangle scanner variability\nand potential artefacts. The ability to factorise these would allow for\ntraining algorithms only on the relevant information according to the task. To\ndate, such factorisation has not been attempted. In this paper, we propose a\nmethodology of latent space factorisation relying on the cycle-consistency\nprinciple. As an example application, we consider cardiac MR segmentation,\nwhere we separate information related to the myocardium from other features\nrelated to imaging and surrounding substructures. We demonstrate the proposed\nmethod's utility in a semi-supervised setting: we use very few labelled images\ntogether with many unlabelled images to train a myocardium segmentation neural\nnetwork. Specifically, we achieve comparable performance to fully supervised\nnetworks using a fraction of labelled images in experiments on ACDC and a\ndataset from Edinburgh Imaging Facility QMRI. Code will be made available at\nhttps://github.com/agis85/spatial_factorisation.","url_abs":"http://arxiv.org/abs/1803.07031v2","url_pdf":"http://arxiv.org/pdf/1803.07031v2.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":"factorised-spatial-representation-learning","repo_url":"https://github.com/agis85/spatial_factorisation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":null,"task_name":"Myocardium Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.07031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.07031"}},"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/agis85/spatial_factorisation","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"a9aaff12acd6c28d","entry":"get_net","repo":"agis85/spatial_factorisation","repo_kind":"official","path":"sdnet.py","file_url":"https://github.com/agis85/spatial_factorisation/blob/HEAD/sdnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9aaff12acd6c28d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}