Matches in SemOpenAlex for { <https://semopenalex.org/work/W2809233735> ?p ?o ?g. }
- W2809233735 endingPage "136" @default.
- W2809233735 startingPage "119" @default.
- W2809233735 abstract "Many algorithms have been proposed for automated segmentation of white matter hyperintensities (WMH) in brain MRI. Yet, broad uptake of any particular algorithm has not been observed. In this work, we argue that this may be due to variable and suboptimal validation data and frameworks, precluding direct comparison of methods on heterogeneous data. As a solution, we present Leave-One-Source-Out Cross Validation (LOSO-CV), which leverages all available data for performance estimation, and show that this gives more realistic (lower) estimates of segmentation algorithm performance on data from different scanners. We also develop a FLAIR-only WMH segmentation algorithm: Voxel-Wise Logistic Regression (VLR), inspired by the open-source Lesion Prediction Algorithm (LPA). Our variant facilitates more accurate parameter estimation, and permits intuitive interpretation of model parameters. We illustrate the performance of the VLR algorithm using the LOSO-CV framework with a dataset comprising freely available data from several recent competitions (96 images from 7 scanners). The performance of the VLR algorithm (median Similarity Index of 0.69) is compared to its LPA predecessor (0.58), and the results of the VLR algorithm in the 2017 WMH Segmentation Competition are also presented." @default.
- W2809233735 created "2018-06-29" @default.
- W2809233735 creator A5008508358 @default.
- W2809233735 creator A5025250666 @default.
- W2809233735 creator A5034466911 @default.
- W2809233735 date "2018-12-01" @default.
- W2809233735 modified "2023-10-18" @default.
- W2809233735 title "Voxel-Wise Logistic Regression and Leave-One-Source-Out Cross Validation for white matter hyperintensity segmentation" @default.
- W2809233735 cites W1523320996 @default.
- W2809233735 cites W1581181058 @default.
- W2809233735 cites W1901129140 @default.
- W2809233735 cites W1919821049 @default.
- W2809233735 cites W1922119240 @default.
- W2809233735 cites W1965976393 @default.
- W2809233735 cites W1970736935 @default.
- W2809233735 cites W1973078936 @default.
- W2809233735 cites W1973457617 @default.
- W2809233735 cites W1984505558 @default.
- W2809233735 cites W1992265439 @default.
- W2809233735 cites W1996745671 @default.
- W2809233735 cites W2000439270 @default.
- W2809233735 cites W2007146250 @default.
- W2809233735 cites W2010238590 @default.
- W2809233735 cites W2013234597 @default.
- W2809233735 cites W2014513166 @default.
- W2809233735 cites W2015052590 @default.
- W2809233735 cites W2018017287 @default.
- W2809233735 cites W2021204548 @default.
- W2809233735 cites W2022772618 @default.
- W2809233735 cites W2024050078 @default.
- W2809233735 cites W2024991751 @default.
- W2809233735 cites W2028094999 @default.
- W2809233735 cites W2030792741 @default.
- W2809233735 cites W2036564586 @default.
- W2809233735 cites W2037317633 @default.
- W2809233735 cites W2037972318 @default.
- W2809233735 cites W2043698677 @default.
- W2809233735 cites W2047062145 @default.
- W2809233735 cites W2047440597 @default.
- W2809233735 cites W2048074616 @default.
- W2809233735 cites W2049791419 @default.
- W2809233735 cites W2053189124 @default.
- W2809233735 cites W2057164916 @default.
- W2809233735 cites W2063948766 @default.
- W2809233735 cites W2065757781 @default.
- W2809233735 cites W2069577302 @default.
- W2809233735 cites W2074414901 @default.
- W2809233735 cites W2084392880 @default.
- W2809233735 cites W2085829822 @default.
- W2809233735 cites W2096609500 @default.
- W2809233735 cites W2102099319 @default.
- W2809233735 cites W2102290518 @default.
- W2809233735 cites W2102848905 @default.
- W2809233735 cites W2104901197 @default.
- W2809233735 cites W2105202736 @default.
- W2809233735 cites W2111405917 @default.
- W2809233735 cites W2113884510 @default.
- W2809233735 cites W2115017507 @default.
- W2809233735 cites W2117340355 @default.
- W2809233735 cites W2122477279 @default.
- W2809233735 cites W2122545833 @default.
- W2809233735 cites W2128480089 @default.
- W2809233735 cites W2133061701 @default.
- W2809233735 cites W2133750711 @default.
- W2809233735 cites W2136573752 @default.
- W2809233735 cites W2140696958 @default.
- W2809233735 cites W2143895814 @default.
- W2809233735 cites W2146712216 @default.
- W2809233735 cites W2149414429 @default.
- W2809233735 cites W2152973397 @default.
- W2809233735 cites W2156717321 @default.
- W2809233735 cites W2156768950 @default.
- W2809233735 cites W2158742097 @default.
- W2809233735 cites W2159037096 @default.
- W2809233735 cites W2161913873 @default.
- W2809233735 cites W2166219471 @default.
- W2809233735 cites W2166636660 @default.
- W2809233735 cites W2168399612 @default.
- W2809233735 cites W2256732691 @default.
- W2809233735 cites W2291395045 @default.
- W2809233735 cites W2312841784 @default.
- W2809233735 cites W2327037637 @default.
- W2809233735 cites W2342591535 @default.
- W2809233735 cites W2404211754 @default.
- W2809233735 cites W2471406153 @default.
- W2809233735 cites W2506018611 @default.
- W2809233735 cites W2514722235 @default.
- W2809233735 cites W2549949175 @default.
- W2809233735 cites W2604830170 @default.
- W2809233735 cites W266124145 @default.
- W2809233735 cites W341325887 @default.
- W2809233735 cites W375705258 @default.
- W2809233735 cites W4230920194 @default.
- W2809233735 cites W4252514887 @default.
- W2809233735 cites W989828740 @default.
- W2809233735 doi "https://doi.org/10.1016/j.mri.2018.06.009" @default.
- W2809233735 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29932970" @default.
- W2809233735 hasPublicationYear "2018" @default.