Meeting Banner
Abstract #3728

Computer Aided Diagnosis of Parkinsons Disease from T1-Weighted MRI

Mohit Saxena1, Namita Aggarwal2, Bharti Rana2, S. Senthil Kumaran3, Ramesh Kumar Agrawal2, Madhuri Behari1

1Department of Neurology, All India Institute of Medical Sciences, New Delhi, Delhi, India; 2School of Computer & Systems Sciences, Jawaharlal Nehru University, New Delhi, Delhi, India; 3Department of NMR, All India Institute of Medical Sciences, New Delhi, Delhi, India

Support vector machine (SVM) is used to distinguish PD from controls in terms of white matter changes in substantia nigra, thalamus and/ or combination of both areas from the T1-weighted MR images. We extracted voxels from white tissue probability maps of substantia nigra and thalamus region. The performance of the decision system was evaluated in terms of sensitivity, specificity and accuracy. Experimental results demonstrate the importance of white matter change in thalamus and effectiveness of SVM to automatically distinguish PD from controls.

Keywords

able accuracy acquisition activity affects aided automatically balance bandwidth best brain central choice classification classified classifier combination comparatively comprised computer considered constructed containing control controls correctly cross decision default deficits defined degeneration denoted diagnosis dimensional dimensions disease disorder disorders dist distinguish documented effectiveness evaluate experimental extracted extraction false feature features fluid fold good gradient gray importance independently individual institute known learning linear loss machine magnetically maps marker material measured measures medical model modulated movement much muscle negatives nervous neurological neurology neurons normalized patient pattern percentage performance perturb plot positives potential precisely predict prepared preprocessed preprocessing probability progressive rapid recognition rectangular relevant reported resolution respectively routine runs school sciences segmentation segmented sensitivity signifies slab slice slices space spacing spatially specificity studied subject subjects suffers support system systems table terms thalamus tissue true unified validation variation various vector volume white years