本研究目的在於使用靜息態磁振造影(rsfMRI)的方式對大腦掃描產生影像，並利用機器學習中的支持向量機(SVM)的分類方法對注意力缺陷過動症（ADHD）患者，來做分析與分辨。運行過程以自動化的方式來進行，因此能輕易處理大量的資料。實驗上改進自動化前處理，使用不同正規化流程，來降低影像偏移的情況，讓後續SVM的分類分析更為良好。經由SVM分析中各特徵對應的權重來製做出特徵腦區域圖，由此能分析出可能是因那些大腦區域的異常而影響此病症。

This study aims to develop an automatic processing system to analyse resting state fMRI data and a classification method based on the support vector machine (SVM) to classify subject groups based on the brain connectivity information extracted from resting state fMRI. The system is evaluated using a database of attention deficit hyperactivity disorder (ADHD) patients. The analysis procedures are automatic and unsupervised. Therefore, it is able to handle large database and the whole system could be transferred into a cloud computing environment. It provides a multivariate analysis platform for clinical users. We improved the SVM classification accuracy by using suitable procedures of image normalisation. We further reconstructed feature selection maps using the weights produced during SVM optimization. This map could potentially provide localisation information for brain regions related to ADHD.

1.Ogawa, S., et al., Oxygenation‐sensitive contrast in magnetic resonance image of rodent brain at high magnetic fields. Magnetic resonance in medicine, 1990. 14(1): p. 68-78.
2.Biswal, B., et al., Functional connectivity in the motor cortex of resting human brain using echo‐planar mri. Magnetic resonance in medicine, 1995. 34(4): p. 537-541.
3.Tian, L., et al., Altered resting-state functional connectivity patterns of anterior cingulate cortex in adolescents with attention deficit hyperactivity disorder. Neurosci Lett, 2006. 400(1-2): p. 39-43.
4.Bohland, J.W., et al., Network, anatomical, and non-imaging measures for the prediction of ADHD diagnosis in individual subjects. Front Syst Neurosci, 2012. 6: p. 78.
5.Broyd, S.J., et al., Default-mode brain dysfunction in mental disorders: a systematic review. Neurosci Biobehav Rev, 2009. 33(3): p. 279-96.
6.Buckner, R.L., J.R. Andrews-Hanna, and D.L. Schacter, The brain's default network: anatomy, function, and relevance to disease. Ann N Y Acad Sci, 2008. 1124: p. 1-38.
7.Nair, J., et al., Clinical review: evidence-based diagnosis and treatment of ADHD in children. Missouri medicine, 2005. 103(6): p. 617-621.
8.Association, A.P., The Diagnostic and Statistical Manual of Mental Disorders: DSM 5. 2013: bookpointUS.
9.Castellanos, F.X., et al., Cingulate-precuneus interactions: a new locus of dysfunction in adult attention-deficit/hyperactivity disorder. Biol Psychiatry, 2008. 63(3): p. 332-7.
10.Bush, G., Attention-deficit/hyperactivity disorder and attention networks. Neuropsychopharmacology, 2010. 35(1): p. 278-300.
11.Cristianini, N. and J. Shawe-Taylor, An introduction to support vector machines and other kernel-based learning methods. 2000: Cambridge university press.
12.Heckemann, R.A., et al., Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. Neuroimage, 2006. 33(1): p. 115-26.
13.Posner, J., et al., Abnormal amygdalar activation and connectivity in adolescents with attention-deficit/hyperactivity disorder. J Am Acad Child Adolesc Psychiatry, 2011. 50(8): p. 828-37 e3.
14.Brotman, M.A., et al., Amygdala activation during emotion processing of neutral faces in children with severe mood dysregulation versus ADHD or bipolar disorder. American Journal of Psychiatry, 2010. 167(1): p. 61-69.
15.Plessen, K.J., et al., Hippocampus and amygdala morphology in attention-deficit/hyperactivity disorder. Archives of general psychiatry, 2006. 63(7): p. 795-807.
16.Amunts, K., et al., Cytoarchitectonic mapping of the human amygdala, hippocampal region and entorhinal cortex: intersubject variability and probability maps. Anat Embryol (Berl), 2005. 210(5-6): p. 343-52.
17.McAlonan, G.M., et al., Mapping brain structure in attention deficit-hyperactivity disorder: a voxel-based MRI study of regional grey and white matter volume. Psychiatry Res, 2007. 154(2): p. 171-80.
18.Sasayama, D., et al., Neuroanatomical correlates of attention-deficit-hyperactivity disorder accounting for comorbid oppositional defiant disorder and conduct disorder. Psychiatry Clin Neurosci, 2010. 64(4): p. 394-402.
19.Hickok, G. and D. Poeppel, The cortical organization of speech processing. Nature Reviews Neuroscience, 2007. 8(5): p. 393-402.
20.Tian, L., et al., Enhanced resting-state brain activities in ADHD patients: a fMRI study. Brain Dev, 2008. 30(5): p. 342-8.
21.Delano-Wood, L., et al., Posterior cingulum white matter disruption and its associations with verbal memory and stroke risk in mild cognitive impairment. J Alzheimers Dis, 2012. 29(3): p. 589-603.