![\"\"](\"https:\/\/cdn.vanderbilt.edu\/vu-URL\/wp-content\/uploads\/sites\/193\/2021\/07\/19203513\/Headshot_NNewlin-150x150.jpg\")
<\/p>\n
<\/p>\n
<\/p>\n
<\/p>\n
Tianyuan Yao<\/strong> (CS), PhD Candidate <\/p>\n <\/p>\n <\/p>\n RiP Speaker #1:<\/strong> RiP Speaker #2:<\/strong> VISE Summer Seminar to be led by Nancy Newlin (CS), PhD Candidate and Tianyuan Yao (CS), PhD Candidate Date: Thursday, June 22, 2023 Time: 11:45 am for lunch, noon start Location: Stevenson Center 532 RiP Speaker #1: Nancy Newlin, PhD Candidate, Computer Science Department RiP Title #1: MidRISH: Unbiased…<\/p>\n","protected":false},"author":670,"featured_media":10370,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"spay_email":"","jetpack_publicize_message":"","jetpack_is_tweetstorm":false,"jetpack_publicize_feature_enabled":true,"_links_to":"","_links_to_target":""},"categories":[12],"tags":[41,282,368,825,32,64,72,31,824,30],"acf":[],"jetpack_featured_media_url":"https:\/\/cdn.vanderbilt.edu\/vu-URL\/wp-content\/uploads\/sites\/193\/2023\/06\/16082128\/VISE_06-22-2023-scaled.jpg","jetpack_publicize_connections":[],"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p98pzF-2H6","_links":{"self":[{"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/posts\/10360"}],"collection":[{"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/users\/670"}],"replies":[{"embeddable":true,"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/comments?post=10360"}],"version-history":[{"count":6,"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/posts\/10360\/revisions"}],"predecessor-version":[{"id":10369,"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/posts\/10360\/revisions\/10369"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/media\/10370"}],"wp:attachment":[{"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/media?parent=10360"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/categories?post=10360"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.vanderbilt.edu\/vise\/wp-json\/wp\/v2\/tags?post=10360"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\nand<\/strong><\/p>\n
\n![\"\"](\"https:\/\/cdn.vanderbilt.edu\/vu-URL\/wp-content\/uploads\/sites\/193\/2023\/06\/16072603\/Tianyuan-Yao-150x150.jpg\")
<\/p>\n
\nDate<\/strong>: Thursday, June 22, 2023
\n<\/span>Time:<\/strong> 11:45 am for lunch, noon start
\n<\/span>Location:<\/strong> Stevenson Center 532<\/p>\n
\nNancy Newlin, PhD Candidate, Computer Science Department
\nRiP Title #1:<\/strong>
\nMidRISH: Unbiased harmonization of rotationally invariant harmonics of the diffusion signal
\nAbstract #1:<\/strong>
\nObjective<\/span>: Data harmonization is necessary for removing confounding effects in multi-site diffusion image analysis. One such harmonization method, LinearRISH, scales rotationally invariant spherical harmonic (RISH) features from one site (\u201ctarget\u201d) to the second (\u201creference\u201d) to reduce confounding scanner effects. However, reference and target site designations are not arbitrary and resultant diffusion metrics (fractional anisotropy, mean diffusivity) are biased by this choice. In this work we propose MidRISH: rather than scaling reference RISH features to target RISH features, we project both sites to a mid-space.<\/span>\u00a0<\/span>Methods:<\/span>\u00a0We validate MidRISH with the following experiments: harmonizing scanner differences from 37 matched healthy patients, and harmonizing acquisition and study difference on 117 matched healthy patients. <\/span>Conclusion:<\/span>\u00a0MidRISH reduces bias of reference selection while preserving harmonization efficacy of LinearRISH<\/span>\u00a0Significance:<\/span>\u00a0Users should be cautious when performing LinearRISH harmonization. To select a reference site is to choose effect-size. Our proposed method eliminates the bias inducing site selection step.<\/span><\/p>\n
\nTianyun Yao, PhD Candidate, Computer Science Department
\nRiP Title #2:<\/strong>
\nDiffusion MRI fiber\u00a0 orientation distribution function estimation using deep learning networks
\nAbstract #2:<\/strong>
\nDiffusion-weighted Magnetic Resonance Imaging (DW-MRI), is a pivotal imaging technique that allows for the analysis and modeling of brain tissue microarchitecture at both microscopic and millimeter scales. This technique is particularly effective for examining the structure of white matter in the brain. An essential component of dMRI is the fiber orientation distribution function (fODF), which represents the orientation and volume fraction of axon bundles within each voxel. The fODF serves as the fundamental first step for the downstream processes of tractography and connectivity analyses, providing crucial insights into the brain’s intricate network of fiber pathways.\u00a0However, measurement variabilities (e.g., inter- and intra-site variability, hardware performance, and sequence design) are inevitable during the acquisition of DW-MRI. Most existing model-based methods (e.g., constrained spherical deconvolution (CSD)) and learning-based methods (e.g., deep learning (DL)) do not explicitly consider such variabilities in fODF modeling, which consequently leads to inferior performance on multi-site and\/or longitudinal diffusion studies. In this talk, I will present our work that utilizes deep learning\u00a0methods to explicitly reduce the scan-rescan variabilities, so as to model a more reproducible and robust brain microstructure.<\/p>\n","protected":false},"excerpt":{"rendered":"