{"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/nonparametric-density-flows-for-mri-intensity","title":"Nonparametric Density Flows for MRI Intensity Normalisation","arxiv_id":"1806.02613","date":"2018-06-07","proceeding":null,"authors":["Daniel C. Castro","Ben Glocker"],"abstract":"With the adoption of powerful machine learning methods in medical image\nanalysis, it is becoming increasingly desirable to aggregate data that is\nacquired across multiple sites. However, the underlying assumption of many\nanalysis techniques that corresponding tissues have consistent intensities in\nall images is often violated in multi-centre databases. We introduce a novel\nintensity normalisation scheme based on density matching, wherein the\nhistograms are modelled as Dirichlet process Gaussian mixtures. The source\nmixture model is transformed to minimise its $L^2$ divergence towards a target\nmodel, then the voxel intensities are transported through a mass-conserving\nflow to maintain agreement with the moving density. In a multi-centre study\nwith brain MRI data, we show that the proposed technique produces excellent\ncorrespondence between the matched densities and histograms. We further\ndemonstrate that our method makes tissue intensity statistics substantially\nmore compatible between images than a baseline affine transformation and is\ncomparable to state-of-the-art while providing considerably smoother\ntransformations. Finally, we validate that nonlinear intensity normalisation is\na step toward effective imaging data harmonisation.","url_abs":"http://arxiv.org/abs/1806.02613v1","url_pdf":"http://arxiv.org/pdf/1806.02613v1.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":"nonparametric-density-flows-for-mri-intensity","repo_url":"https://github.com/dccastro/NDFlow","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}