{"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/mr-acquisition-invariant-representation","title":"MR Acquisition-Invariant Representation Learning","arxiv_id":"1709.07944","date":"2017-09-22","proceeding":null,"authors":["Wouter M. Kouw","Marco Loog","Lambertus W. Bartels","Adriënne M. Mendrik"],"abstract":"Voxelwise classification approaches are popular and effective methods for\ntissue quantification in brain magnetic resonance imaging (MRI) scans. However,\ngeneralization of these approaches is hampered by large differences between\nsets of MRI scans such as differences in field strength, vendor or acquisition\nprotocols. Due to this acquisition related variation, classifiers trained on\ndata from a specific scanner fail or under-perform when applied to data that\nwas acquired differently. In order to address this lack of generalization, we\npropose a Siamese neural network (MRAI-net) to learn a representation that\nminimizes the between-scanner variation, while maintaining the contrast between\nbrain tissues necessary for brain tissue quantification. The proposed MRAI-net\nwas evaluated on both simulated and real MRI data. After learning the MR\nacquisition invariant representation, any supervised classification model that\nuses feature vectors can be applied. In this paper, we provide a proof of\nprinciple, which shows that a linear classifier applied on the MRAI\nrepresentation is able to outperform supervised convolutional neural network\nclassifiers for tissue classification when little target training data is\navailable.","url_abs":"http://arxiv.org/abs/1709.07944v2","url_pdf":"http://arxiv.org/pdf/1709.07944v2.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":"mr-acquisition-invariant-representation","repo_url":"https://github.com/wmkouw/mrai-net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}