FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384563115> ?p ?o ?g. }

• W4384563115 endingPage "102893" @default.
• W4384563115 startingPage "102893" @default.
• W4384563115 abstract "A tractogram is a virtual representation of the brain white matter. It is composed of millions of virtual fibers, encoded as 3D polylines, which approximate the white matter axonal pathways. To date, tractograms are the most accurate white matter representation and thus are used for tasks like presurgical planning and investigations of neuroplasticity, brain disorders, or brain networks. However, it is a well-known issue that a large portion of tractogram fibers is not anatomically plausible and can be considered artifacts of the tracking procedure. With Verifyber, we tackle the problem of filtering out such non-plausible fibers using a novel fully-supervised learning approach. Differently from other approaches based on signal reconstruction and/or brain topology regularization, we guide our method with the existing anatomical knowledge of the white matter. Using tractograms annotated according to anatomical principles, we train our model, Verifyber, to classify fibers as either anatomically plausible or non-plausible. The proposed Verifyber model is an original Geometric Deep Learning method that can deal with variable size fibers, while being invariant to fiber orientation. Our model considers each fiber as a graph of points, and by learning features of the edges between consecutive points via the proposed sequence Edge Convolution, it can capture the underlying anatomical properties. The output filtering results highly accurate and robust across an extensive set of experiments, and fast; with a 12GB GPU, filtering a tractogram of 1M fibers requires less than a minute." @default.
• W4384563115 created "2023-07-18" @default.
• W4384563115 creator A5047652078 @default.
• W4384563115 creator A5049825997 @default.
• W4384563115 creator A5060974774 @default.
• W4384563115 creator A5064052365 @default.
• W4384563115 creator A5064432821 @default.
• W4384563115 creator A5080101869 @default.
• W4384563115 creator A5081429343 @default.
• W4384563115 creator A5087701523 @default.
• W4384563115 date "2023-12-01" @default.
• W4384563115 modified "2023-10-10" @default.
• W4384563115 title "Supervised tractogram filtering using Geometric Deep Learning" @default.
• W4384563115 cites W1967159562 @default.
• W4384563115 cites W1969637629 @default.
• W4384563115 cites W1979757232 @default.
• W4384563115 cites W1983208069 @default.
• W4384563115 cites W1995138343 @default.
• W4384563115 cites W2001611992 @default.
• W4384563115 cites W2010125850 @default.
• W4384563115 cites W2013160622 @default.
• W4384563115 cites W2020745232 @default.
• W4384563115 cites W2024729467 @default.
• W4384563115 cites W2027094605 @default.
• W4384563115 cites W2033088751 @default.
• W4384563115 cites W2058085357 @default.
• W4384563115 cites W2062791478 @default.
• W4384563115 cites W2064675550 @default.
• W4384563115 cites W2071666283 @default.
• W4384563115 cites W2077095532 @default.
• W4384563115 cites W2079735306 @default.
• W4384563115 cites W2091910928 @default.
• W4384563115 cites W2094435366 @default.
• W4384563115 cites W2107051185 @default.
• W4384563115 cites W2110431535 @default.
• W4384563115 cites W2111508341 @default.
• W4384563115 cites W2114856020 @default.
• W4384563115 cites W2142900310 @default.
• W4384563115 cites W2145132952 @default.
• W4384563115 cites W2194775991 @default.
• W4384563115 cites W2222869326 @default.
• W4384563115 cites W2400850456 @default.
• W4384563115 cites W2467410077 @default.
• W4384563115 cites W2502730944 @default.
• W4384563115 cites W2523274259 @default.
• W4384563115 cites W2558748708 @default.
• W4384563115 cites W2625448573 @default.
• W4384563115 cites W2735700022 @default.
• W4384563115 cites W2753817523 @default.
• W4384563115 cites W2766639217 @default.
• W4384563115 cites W2775461784 @default.
• W4384563115 cites W2803890652 @default.
• W4384563115 cites W2808875895 @default.
• W4384563115 cites W2809877631 @default.
• W4384563115 cites W2887072805 @default.
• W4384563115 cites W2887558295 @default.
• W4384563115 cites W2891995230 @default.
• W4384563115 cites W2901502594 @default.
• W4384563115 cites W2912944597 @default.
• W4384563115 cites W2920773390 @default.
• W4384563115 cites W2946239819 @default.
• W4384563115 cites W2950279821 @default.
• W4384563115 cites W2951972782 @default.
• W4384563115 cites W2970898057 @default.
• W4384563115 cites W2977883299 @default.
• W4384563115 cites W2979750740 @default.
• W4384563115 cites W2999007024 @default.
• W4384563115 cites W3000134386 @default.
• W4384563115 cites W3004082770 @default.
• W4384563115 cites W3010369603 @default.
• W4384563115 cites W3036595745 @default.
• W4384563115 cites W3042104279 @default.
• W4384563115 cites W3045895067 @default.
• W4384563115 cites W3080288479 @default.
• W4384563115 cites W3088698194 @default.
• W4384563115 cites W3093146773 @default.
• W4384563115 cites W3124084750 @default.
• W4384563115 cites W3135550350 @default.
• W4384563115 cites W3172893236 @default.
• W4384563115 cites W3173443563 @default.
• W4384563115 cites W4205798776 @default.
• W4384563115 cites W4241074797 @default.
• W4384563115 cites W4294975481 @default.
• W4384563115 cites W795339718 @default.
• W4384563115 doi "https://doi.org/10.1016/j.media.2023.102893" @default.
• W4384563115 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37741032" @default.
• W4384563115 hasPublicationYear "2023" @default.
• W4384563115 type Work @default.
• W4384563115 citedByCount "0" @default.
• W4384563115 crossrefType "journal-article" @default.
• W4384563115 hasAuthorship W4384563115A5047652078 @default.
• W4384563115 hasAuthorship W4384563115A5049825997 @default.
• W4384563115 hasAuthorship W4384563115A5060974774 @default.
• W4384563115 hasAuthorship W4384563115A5064052365 @default.
• W4384563115 hasAuthorship W4384563115A5064432821 @default.
• W4384563115 hasAuthorship W4384563115A5080101869 @default.
• W4384563115 hasAuthorship W4384563115A5081429343 @default.
• W4384563115 hasAuthorship W4384563115A5087701523 @default.

• next