Chung-Yao Chien1,2, Szu-Wei Hsu3, Tsung-Lin Lee2, Pi-Shan Sung2, Chou-Ching Lin1,2. 1. Department of Biomedical Engineering, National Cheng Kung University, Tainan 704, Taiwan. 2. Department of Neurology, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan. 3. Department of Nuclear Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan 704, Taiwan.
Abstract
BACKGROUND: The challenge of differentiating, at an early stage, Parkinson's disease from parkinsonism caused by other disorders remains unsolved. We proposed using an artificial neural network (ANN) to process images of dopamine transporter single-photon emission computed tomography (DAT-SPECT). METHODS: Abnormal DAT-SPECT images of subjects with Parkinson's disease and parkinsonism caused by other disorders were divided into training and test sets. Striatal regions of the images were segmented by using an active contour model and were used as the data to perform transfer learning on a pre-trained ANN to discriminate Parkinson's disease from parkinsonism caused by other disorders. A support vector machine trained using parameters of semi-quantitative measurements including specific binding ratio and asymmetry index was used for comparison. RESULTS: The predictive accuracy of the ANN classifier (86%) was higher than that of the support vector machine classifier (68%). The sensitivity and specificity of the ANN classifier in predicting Parkinson's disease were 81.8% and 88.6%, respectively. CONCLUSIONS: The ANN classifier outperformed classical biomarkers in differentiating Parkinson's disease from parkinsonism caused by other disorders. This classifier can be readily included into standalone computer software for clinical application.
BACKGROUND: The challenge of differentiating, at an early stage, Parkinson's disease from parkinsonism caused by other disorders remains unsolved. We proposed using an artificial neural network (ANN) to process images of dopamine transporter single-photon emission computed tomography (DAT-SPECT). METHODS: Abnormal DAT-SPECT images of subjects with Parkinson's disease and parkinsonism caused by other disorders were divided into training and test sets. Striatal regions of the images were segmented by using an active contour model and were used as the data to perform transfer learning on a pre-trained ANN to discriminate Parkinson's disease from parkinsonism caused by other disorders. A support vector machine trained using parameters of semi-quantitative measurements including specific binding ratio and asymmetry index was used for comparison. RESULTS: The predictive accuracy of the ANN classifier (86%) was higher than that of the support vector machine classifier (68%). The sensitivity and specificity of the ANN classifier in predicting Parkinson's disease were 81.8% and 88.6%, respectively. CONCLUSIONS: The ANN classifier outperformed classical biomarkers in differentiating Parkinson's disease from parkinsonism caused by other disorders. This classifier can be readily included into standalone computer software for clinical application.
Authors: Ronald B Postuma; Daniela Berg; Matthew Stern; Werner Poewe; C Warren Olanow; Wolfgang Oertel; José Obeso; Kenneth Marek; Irene Litvan; Anthony E Lang; Glenda Halliday; Christopher G Goetz; Thomas Gasser; Bruno Dubois; Piu Chan; Bastiaan R Bloem; Charles H Adler; Günther Deuschl Journal: Mov Disord Date: 2015-10 Impact factor: 10.338
Authors: Randel L Swanson; Andrew B Newberg; Paul D Acton; Andrew Siderowf; Nancy Wintering; Abass Alavi; P David Mozley; Karl Plossl; Michelle Udeshi; Howard Hurtig Journal: Eur J Nucl Med Mol Imaging Date: 2004-10-02 Impact factor: 9.236
Authors: Hans-Jürgen Huppertz; Leona Möller; Martin Südmeyer; Rüdiger Hilker; Elke Hattingen; Karl Egger; Florian Amtage; Gesine Respondek; Maria Stamelou; Alfons Schnitzler; Elmar H Pinkhardt; Wolfgang H Oertel; Susanne Knake; Jan Kassubek; Günter U Höglinger Journal: Mov Disord Date: 2016-10 Impact factor: 10.338
Authors: Simon Badoud; Dimitri Van De Ville; Nicolas Nicastro; Valentina Garibotto; Pierre R Burkhard; Sven Haller Journal: Neuroimage Clin Date: 2016-07-05 Impact factor: 4.881
Authors: Annemarie M M Vlaar; Marinus J P G van Kroonenburgh; Alfons G H Kessels; Wim E J Weber Journal: BMC Neurol Date: 2007-09-01 Impact factor: 2.474
Authors: Merijn Joling; Chris Vriend; Jessica J van der Zande; Afina W Lemstra; Odile A van den Heuvel; Jan Booij; Henk W Berendse Journal: Neuroimage Clin Date: 2018-04-06 Impact factor: 4.881