{"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/a-multi-contrast-mri-approach-to-thalamus","title":"A multi-contrast MRI approach to thalamus segmentation","arxiv_id":"1807.10757","date":"2018-07-27","proceeding":null,"authors":["Veronica Corona","Jan Lellmann","Peter Nestor","Carola-Bibiane Schoenlieb","Julio Acosta-Cabronero"],"abstract":"Thalamic alterations are relevant to many neurological disorders including\nAlzheimer's disease, Parkinson's disease and multiple sclerosis. Routine\ninterventions to improve symptom severity in movement disorders, for example,\noften consist of surgery or deep brain stimulation to diencephalic nuclei.\nTherefore, accurate delineation of grey matter thalamic subregions is of the\nupmost clinical importance. MRI is highly appropriate for structural\nsegmentation as it provides different views of the anatomy from a single\nscanning session. Though with several contrasts potentially available, it is\nalso of increasing importance to develop new image segmentation techniques that\ncan operate multi-spectrally. We hereby propose a new segmentation method for\nuse with multi-modality data, which we evaluated for automated segmentation of\nmajor thalamic subnuclear groups using T1-, T2*-weighted and quantitative\nsusceptibility mapping (QSM) information. The proposed method consists of four\nsteps: highly iterative image co-registration, manual segmentation on the\naverage training-data template, supervised learning for pattern recognition,\nand a final convex optimisation step imposing further spatial constraints to\nrefine the solution. This led to solutions in greater agreement with manual\nsegmentation than the standard Morel atlas based approach. Furthermore, we show\nthat the multi-contrast approach boosts segmentation performances. We then\ninvestigated whether prior knowledge using the training-template contours could\nfurther improve convex segmentation accuracy and robustness, which led to\nhighly precise multi-contrast segmentations in single subjects. This approach\ncan be extended to most 3D imaging data types and any region of interest\ndiscernible in single scans or multi-subject templates.","url_abs":"http://arxiv.org/abs/1807.10757v1","url_pdf":"http://arxiv.org/pdf/1807.10757v1.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":"a-multi-contrast-mri-approach-to-thalamus","repo_url":"https://github.com/veronicacorona/multicontrastSegmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"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}