本研究目的在於重現Tustison研究中所使用的機器學習流程，提出一系統方法，將腦結構T1影像（T1-weight imaging）利用FreeSurfer切割出大腦皮質厚度，使用機器學習方法和大型數據庫推導出腦皮質厚度有效的MR生物標記物。利用線性回歸來預測性別和年齡，並計算出預測的準確率和預測年齡的誤差，藉此來比較三種腦皮質厚度的神經解剖分割方案的優劣，並將此流程方法運用在預測注意力缺陷及多動障礙（ADHD）和正常受試者的分類上。結果發現Desikan–Killiany Atlas大腦切割方案不論是預測性別還是年紀都有最高的準確率和最低的誤差值，而運用在判別ADHD的亞型分類上，Desikan–Killiany Atlas切割方案也是三種切割方案中擁有最高的準確率，且不論在哪一種參數，結果相較穩定。再藉由遞歸特徵消除分析各個特徵的權重做參數選擇，由此能分析出可能是因為哪些大腦區域的異常而影響此病症。

In this study, we reproduced the investigation of Tustison, which evaluated cortical thickness calculation algorithms by machine-learning approaches. First, we used FreeSurfer to measure cortical thickness from structural MR TI images. We applied machine-learning algorithms to a large-scale database to get effective MR biomarkers of cortical thickness. Subsequently, we used linear regression algorithms to predict genders and ages from the T1 data sets, and then analyze the accuracy of the prediction. We compared the performances of these three neuroanatomical parcellation schemes by using the area under the curve of receiver operating characteristic curve of gender and the root-mean-square error of age. We then applied the established machine learning procedures to the task of discriminating ADHD patients from normal subjects. In addition, we performed feature selection by using the weights produced during recursive feature elimination with cross validation to potentially provide localization information for brain regions related to ADHD. In summary, the results obtained using the Desikan–Killiany parcellation scheme generally outperformed the other schemes in all tasks, predicting the gender and age of each participant and discriminating ADHD types.

[1] Tustison, Nicholas J., et al. "Large-scale evaluation of ANTs and FreeSurfer cortical thickness measurements." Neuroimage 99 (2014): 166-179.
[2] Yang SY et al., "A General Cloud Computing Framework for Medical Image Analysis, Part 1: Implementing the System", #3545, Annual Meeting of OHBM 2015, June 14-18, 2015, Honolulu, Hawaii
[3] Willcutt, Erik G. "The prevalence of DSM-IV attention-deficit/hyperactivity disorder: a meta-analytic review." Neurotherapeutics 9.3 (2012): 490-499.
[4] Diamond, Adele. "Attention-deficit disorder (attention-deficit/hyperactivity disorder without hyperactivity): A neurobiologically and behaviorally distinct disorder from attention-deficit/hyperactivity disorder (with hyperactivity)." Development and psychopathology 17.3 (2005): 807-825.
[5] Shaw, Philip, et al. "Attention-deficit/hyperactivity disorder is characterized by a delay in cortical maturation." Proceedings of the National Academy of Sciences 104.49 (2007): 19649-19654.
[6] American Psychiatric Association. Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Pub, (2013).
[7] Bush, George. "Attention-deficit/hyperactivity disorder and attention networks." Neuropsychopharmacology 35.1 (2010): 278-300.
[8] Li, Shuyu, et al. "Abnormal surface morphology of the central sulcus in children with attention-deficit/hyperactivity disorder." Frontiers in neuroanatomy 9 (2015).
[9] Peng, Xiaolong, et al. "Extreme learning machine-based classification of ADHD using brain structural MRI data." PloS one 8.11 (2013): e79476.
[10] Hyatt, Christopher J., Emily Haney-Caron, and Michael C. Stevens. "Cortical thickness and folding deficits in conduct-disordered adolescents." Biological psychiatry 72.3 (2012): 207-214.
[11] Dai, Dai, et al. "Classification of ADHD children through multimodal magnetic resonance imaging." Frontiers in systems neuroscience 6 (2012).
[12] Desikan, Rahul S., et al. "An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest." Neuroimage 31.3 (2006): 968-980.
[13] Fischl, Bruce, et al. "Automatically parcellating the human cerebral cortex." Cerebral cortex 14.1 (2004): 11-22.
[14] Relaxation, Stochastic. "Gibbs Distributions, and the Bayesian Restoration of Images. S. Geman and D. Geman." IEEE Trans. on PAMI 6 (1984): 721-741.
[15] Destrieux, Christophe, et al. "Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclature." Neuroimage 53.1 (2010): 1-15.
[16] Duvernoy, Henri M. The human brain: surface, three-dimensional sectional anatomy with MRI, and blood supply. Springer Science & Business Media, (2012).
[17] Klein, Arno, and Jason Tourville. "101 labeled brain images and a consistent human cortical labeling protocol." Frontiers in neuroscience 6 (2012).
[18] Ono, Michio, Stefan Kubik, and Chad D. Abernathey. Atlas of the cerebral sulci. Tps, (1990).
[19] Yan, Xin, and Xiaogang Su. Linear regression analysis: theory and computing. World Scientific, (2009).
[20] Kohavi, Ron. "A study of cross-validation and bootstrap for accuracy estimation and model selection." Ijcai. Vol. 14. No. 2. 1995.
[21] Fawcett, Tom. "An introduction to ROC analysis." Pattern recognition letters 27.8 (2006): 861-874.
[22] Valera, Eve M., et al. "Meta-analysis of structural imaging findings in attention-deficit/hyperactivity disorder." Biological psychiatry 61.12 (2007): 1361-1369.
[23] Yao, Zhijun, et al. "Functional network disruption in attention deficit hyperactivity disorder." Bioinformatics and Biomedicine (BIBM), 2014 IEEE International Conference on. IEEE, 2014.
[24] Qureshi, Muhammad Naveed Iqbal, et al. "Multiclass classification for the differential diagnosis on the ADHD subtypes using recursive feature elimination and hierarchical extreme learning machine: structural MRI study." PloS one 11.8 (2016): e0160697.
[25] Shaw, Philip, et al. "Longitudinal mapping of cortical thickness and clinical outcome in children and adolescents with attention-deficit/hyperactivity disorder." Archives of general psychiatry 63.5 (2006): 540-549.
[26] Sowell, Elizabeth R., et al. "Longitudinal mapping of cortical thickness and brain growth in normal children." Journal of Neuroscience 24.38 (2004): 8223-8231.