KOCHEN Sara Silvia
Machine learning for filtering out false positive grey matter atrophies in single subject voxel based morphometry: A simulation based study
KÜLSGAARD, HERNÁN C.; ORLANDO, JOSÉ I.; BENDERSKY, MARIANA; PRINCICH, JUAN P.; MANZANERA, LUIS S.R.; VARGAS, ALBERTO; KOCHEN, SILVIA; LARRABIDE, IGNACIO
JOURNAL OF THE NEUROLOGICAL SCIENCES
ELSEVIER SCIENCE BV
Single subject VBM (SS-VBM), has been used as an alternative tool to standard VBM for single case studies.However, it has the disadvantage of producing an excessively large number of false positive detections. In thisstudy we propose a machine learning technique widely used for automated data classification, namely SupportVector Machine (SVM), to refine the findings produced by SS-VBM. A controlled set of experiments was conductedto evaluate the proposed approach using three-dimensional T1 MRI scans from control subjects collectedfrom the publicly available IXI dataset. The scans were artificially atrophied at different locations and withdifferent sizes to mimic the behavior of neurological disorders. Results empirically demonstrated that the proposedmethod is able to significantly reduce the amount of false positive clusters (p < 0.05), with no statisticaldifferences in the true positive findings (p > 0.05). This evidence was observed to be consistent for differentatrophied areas and sizes of atrophies. This approach could be potentially be applied to alleviate the intensivemanual analysis that radiologists and clinicians have to perform to filter out miss-detections of SS-VBM,increasing its usability for image reading.