Cross Atlas Remapping via Optimal Transport (CAROT): Creating connectomes for different atlases when raw data is not available
Dadashkarimi J, Karbasi A, Liang Q, Rosenblatt M, Noble S, Foster M, Rodriguez R, Adkinson B, Ye J, Sun H, Camp C, Farruggia M, Tejavibulya L, Dai W, Jiang R, Pollatou A, Scheinost D. Cross Atlas Remapping via Optimal Transport (CAROT): Creating connectomes for different atlases when raw data is not available. Medical Image Analysis 2023, 88: 102864. PMID: 37352650, PMCID: PMC10526726, DOI: 10.1016/j.media.2023.102864.Peer-Reviewed Original ResearchConceptsDifferent atlasesRaw data accessWeb applicationData accessOpen source dataSource codePatient privacyOptimal transportRaw dataStorage concernsLarge-scale data collection effortsOriginal counterpartsExtensive setData collection effortsProcessing effortPredictive modelNeuroimaging dataDownstream analysisPrivacyAtlasesCollection effortsComputationalTime seriesDatasetConnectomeConnectome-based machine learning models are vulnerable to subtle data manipulations
Rosenblatt M, Rodriguez R, Westwater M, Dai W, Horien C, Greene A, Constable R, Noble S, Scheinost D. Connectome-based machine learning models are vulnerable to subtle data manipulations. Patterns 2023, 4: 100756. PMID: 37521052, PMCID: PMC10382940, DOI: 10.1016/j.patter.2023.100756.Peer-Reviewed Original ResearchData manipulationNoise attacksPrediction performanceMachine learning modelsManipulated dataLearning modelHigh trustworthinessConnectome dataTrustworthinessAttacksModel performancePredictive modelDownstream analysisPerformanceAcademic researchMachineRobustnessModelConnectomeConnectome-based modelsFunctional connectomeManipulation