Meeting Banner
Abstract #2412

Combination of Sparse & Wrapper Feature Selection from Multi-Source Data for Accurate Brain Tumor Typing

Vangelis Metsis1, Ovidiu C. Andronesi2,3, Heng Huang1, Michael N. Mindrinos4, Laurence G. Rahme5, Fillia Makedon1, Aria A. Tzika2,3

1Computer Science & Engineering, University of Texas at Arlington, Arlington, TX, United States; 2NMR Surgical Laboratory, Dept. of Surgery, Harvard Medical School & Massachusetts General Hospital, Boston, MA, United States; 3Athinoula A. Martinos Center of Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Boston, MA, United States; 4Dept. of Biochemistry, Stanford University School of Medicine, Stanford, CA, United States; 5Molecular Surgery Laboratory, Dept. of Surgery, Massachusetts General Hospital & Shriners Burn Institute, Harvard Medical School, Boston, MA, United States


In this work we verify the advantage of combining features from Gene Expression and MRS data for brain tumor typing and we introduce a new feature selection method based on Joint ℓ2,1-Norms Minimization which improves classification accuracy in the multiclass problem.

Keywords