Jing Tang1, Bao Yang2, Matthew P Adams2, Nikolay N Shenkov3, Ivan S Klyuzhin4, Sima Fotouhi5, Esmaeil Davoodi-Bojd6, Lijun Lu7, Hamid Soltanian-Zadeh6,8, Vesna Sossi3, Arman Rahmim5,9. 1. Department of Electrical and Computer Engineering, Oakland University, Rochester, MI, USA. jingtang@gmail.com. 2. Department of Electrical and Computer Engineering, Oakland University, Rochester, MI, USA. 3. Department of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada. 4. Department of Medicine, University of British Columbia, Vancouver, BC, Canada. 5. Department of Radiology, Johns Hopkins University, Baltimore, MD, USA. 6. Departments of Radiology and Research Administration, Henry Ford Health System, Detroit, MI, USA. 7. Department of Biomedical Engineering, Southern Medical University, Guangzhou, China. 8. School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran. 9. Departments of Radiology and Physics & Astronomy, University of British Columbia, Vancouver, BC, Canada.
Abstract
PURPOSE: Quantitative analysis of dopamine transporter (DAT) single-photon emission computed tomography (SPECT) images can enhance diagnostic confidence and improve their potential as a biomarker to monitor the progression of Parkinson's disease (PD). In the present work, we aim to predict motor outcome from baseline DAT SPECT imaging radiomic features and clinical measures using machine learning techniques. PROCEDURES: We designed and trained artificial neural networks (ANNs) to analyze the data from 69 patients within the Parkinson's Progressive Marker Initiative (PPMI) database. The task was to predict the unified PD rating scale (UPDRS) part III motor score in year 4 from 92 imaging features extracted on 12 different regions as well as 6 non-imaging measures at baseline (year 0). We first performed univariate screening (including the adjustment for false discovery) to select 4 regions each having 10 features with significant performance in classifying year 4 motor outcome into two classes of patients (divided by the UPDRS III threshold of 30). The leave-one-out strategy was then applied to train and test the ANNs for individual and combinations of features. The prediction statistics were calculated from 100 rounds of experiments, and the accuracy in appropriate prediction (classification of year 4 outcome) was quantified. RESULTS: Out of the baseline non-imaging features, only the UPDRS III (at year 0) was predictive, while multiple imaging features depicted significance. The different selected features reached a predictive accuracy of 70 % if used individually. Combining the top imaging features from the selected regions significantly improved the prediction accuracy to 75 % (p < 0.01). The combination of imaging features with the year 0 UPDRS III score also improved the prediction accuracy to 75 %. CONCLUSION: This study demonstrated the added predictive value of radiomic features extracted from DAT SPECT images in serving as a biomarker for PD progression tracking.
PURPOSE: Quantitative analysis of dopamine transporter (DAT) single-photon emission computed tomography (SPECT) images can enhance diagnostic confidence and improve their potential as a biomarker to monitor the progression of Parkinson's disease (PD). In the present work, we aim to predict motor outcome from baseline DAT SPECT imaging radiomic features and clinical measures using machine learning techniques. PROCEDURES: We designed and trained artificial neural networks (ANNs) to analyze the data from 69 patients within the Parkinson's Progressive Marker Initiative (PPMI) database. The task was to predict the unified PD rating scale (UPDRS) part III motor score in year 4 from 92 imaging features extracted on 12 different regions as well as 6 non-imaging measures at baseline (year 0). We first performed univariate screening (including the adjustment for false discovery) to select 4 regions each having 10 features with significant performance in classifying year 4 motor outcome into two classes of patients (divided by the UPDRS III threshold of 30). The leave-one-out strategy was then applied to train and test the ANNs for individual and combinations of features. The prediction statistics were calculated from 100 rounds of experiments, and the accuracy in appropriate prediction (classification of year 4 outcome) was quantified. RESULTS: Out of the baseline non-imaging features, only the UPDRS III (at year 0) was predictive, while multiple imaging features depicted significance. The different selected features reached a predictive accuracy of 70 % if used individually. Combining the top imaging features from the selected regions significantly improved the prediction accuracy to 75 % (p < 0.01). The combination of imaging features with the year 0 UPDRS III score also improved the prediction accuracy to 75 %. CONCLUSION: This study demonstrated the added predictive value of radiomic features extracted from DAT SPECT images in serving as a biomarker for PD progression tracking.
Entities:
Keywords:
Artificial neural network; DAT SPECT imaging; Motor outcome prediction; Parkinson’s disease
Authors: Bruce Fischl; David H Salat; Evelina Busa; Marilyn Albert; Megan Dieterich; Christian Haselgrove; Andre van der Kouwe; Ron Killiany; David Kennedy; Shuna Klaveness; Albert Montillo; Nikos Makris; Bruce Rosen; Anders M Dale Journal: Neuron Date: 2002-01-31 Impact factor: 17.173
Authors: Arman Rahmim; Yousef Salimpour; Saurabh Jain; Stephan A L Blinder; Ivan S Klyuzhin; Gwenn S Smith; Zoltan Mari; Vesna Sossi Journal: Neuroimage Clin Date: 2016-02-23 Impact factor: 4.881
Authors: Stephen S F Yip; Ying Liu; Chintan Parmar; Qian Li; Shichang Liu; Fangyuan Qu; Zhaoxiang Ye; Robert J Gillies; Hugo J W L Aerts Journal: Sci Rep Date: 2017-06-14 Impact factor: 4.379
Authors: Chelsea Caspell-Garcia; Tanya Simuni; Duygu Tosun-Turgut; I-Wei Wu; Yu Zhang; Mike Nalls; Andrew Singleton; Leslie A Shaw; Ju-Hee Kang; John Q Trojanowski; Andrew Siderowf; Christopher Coffey; Shirley Lasch; Dag Aarsland; David Burn; Lana M Chahine; Alberto J Espay; Eric D Foster; Keith A Hawkins; Irene Litvan; Irene Richard; Daniel Weintraub Journal: PLoS One Date: 2017-05-17 Impact factor: 3.240