Meeting Banner
Abstract #2690

Support Vector Machines Detect Huntington's Gene Effects in Mouse Brain Images with >98% Accuracy

Stephen J. Sawiak1, 2, A Jennifer Morton3, T. Adrian Carpenter1

1Wolfson Brain Imaging Centre, University of Cambridge, Cambridge, England, United Kingdom; 2Behavioural and Cognitive Neuroscience Institute, University of Cambridge, Cambridge, England, United Kingdom; 3Department of Pharmacology, University of Cambridge, Cambridge, England, United Kingdom

Support vector machines are used to detect whether high-resolution brain images are from healthy or transgenic Huntington's disease mice. We found that with leave-one-out cross validation the classifier has >98% accuracy at detecting the sick animals and we applied the same trained classifier to older healthy brains, revealing that the changes seen are not confused with healthy aging.

Abstract PDF

Keywords

according accordingly accuracy achieved acquisitions addition aged aging alternative analysts animal applying archive assessed audience axes best binary brain brains carpenter cell classification classified classifier clinicians coding cognitive common conspicuous coronal cortical cure currently derived detect detection differential disease disorder display distinct easy england error evidence excellent expansion exploring fatal finds frontal gene generally handle horizontal hyperplane identified illustrative implementation implicated important in vivo inherited initial institute interventions investigate involved kingdom known lancet learning leave like machine machines masked medicine mice model models mouse multidimensional neurological offering older original pathology performance pharmacology pools populations portions potential projections prominent public relatively remapped repeats scores segmented separation slow space strains suggests summed support target text thalamus therapeutic third thresholded toolbox trained translational typical unstable users validation vector views walker weeks