Utilization of Spatial Coherence in Functional Neuroimage-based Classification

摘要：

Functional Magnetic Resonance Imaging provides a non-invasive mechanism for monitoring brain activity of subjects during performance of a task. While this approach has been used extensively for human brain mapping activities, automated classification of subjects based on neural activation patterns is also of interest. However, due to the high dimensionality of the image data, classification accuracy is highly dependent upon the adequacy of the features used in the models. In this work1, we present a new feature refinement strategy that uses spatial coherence information to eliminate irrelevant features from consideration. For a neurobehavioral disinhibition dataset, we show that this new approach for feature selection using Spatially Coherent Voxels (SCV) outperforms conventional methods.

关键词： Functional Magnetic Resonance Imaging feature selection spatially coherent vozels classification

作者: Pinaki Mitra Vanathi Gopalakrishnan Rebecca L.McNamee

作者单位: Department of Biomedical Informatics University of Pittsburgh Pittsburgh,PA,USA Departments of Pharmaceutical Sciences and Bioengineering University of Pittsburgh Pittsburgh,PA,USA

会议类型: 国际会议

会议名称: The 3rd International Conference on Bioinformatics and Biomedical Engineering(iCBBE 2009)(第三届生物信息与生物医学工程国际会议)

会议地点: 北京

会议语种:英文

页码: 1-5

在线出版日期: 2009-06-11（万方平台首次上网日期，不代表论文的发表时间）