نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد، گروه مهندسی پزشکی، دانشکده‌ی مهندسی برق، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران

2 استادیار، گروه مهندسی پزشکی، دانشکده‌ی مهندسی برق، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران

10.22041/ijbme.2020.115779.1527

چکیده

تشخیص به موقع و صحیح اختلال دوقطبی (BD) و متعاقب آن انجام فرایندهای درمانی، برای جلوگیری از پیش‌رفت و وخیم شدن این بیماری ضروری است. اگر چه استفاده از داده‌های مبتنی بر تصویربرداری تشدید مغناطیسی عمل‌کردی در حال استراحت (rs-fMRI) و ویژگی‌های استخراج شده از آن‌ها ممکن است نقش موثری در تشخیص اختلال دوقطبی داشته باشد، اما تا کنون تحقیقات اندکی روی تشخیص افراد مبتلا به BD به کمک rs-fMRI صورت گرفته و نتایج به دست آمده نیز از صحت بالایی برخوردار نبوده است. در این تحقیق یک روش جدید مبتنی بر ارتباطات عمل‌کردی برای تشخیص BD I ارائه شده است. برای این منظور با استفاده از ارتباطات عمل‌کردی بر پایه‌ی دانه، چهار ناحیه‌ی PCC، dlPFC، amygdala و sgACC به ترتیب به عنوان نماینده‏های شبکه‌ی DMN، FPN و SN در نظر گرفته شده تا ارتباطات عمل‌کردی میان آن‏ها و سایر نواحی مغز محاسبه گردد. پس از محاسبه‌ی ارتباطات عمل‌کردی برای هر فرد، با استفاده از آستانه‌گذاری مقدار t ویژگی‏های مفیدتر انتخاب شده و سپس با یک ماشین بردار پشتیبان (SVM) و روش اعتبارسنجی متقابل LOOCV و تنها با استفاده از چهار ویژگی ترکیبی، طبقه‏بندی افراد سالم و افراد دارای اختلال BD I انجام شده است. نتایج روش پیشنهادی روی داده‌های rs-fMRI مربوط به 49 فرد سالم و 34 فرد مبتلا به BD I مورد استفاده قرار گرفته و صحت طبقه‌بندی بیش از 90% حاصل شده است. هم‌چنین در بررسی ارتباطات عمل‌کردی بین چهار ناحیه‏ی مذکور و سایر نواحی مغز در افراد مبتلا به BD I نسبت به افراد سالم کاهش معنی‌داری در ارتباطات مشاهده شده است.  ناحیه‌های Ag و OFC (با دانه‏ی PCC)، ACC (با دانه‏‏های dlPFC و amygdala) و ITG (با دانه‏ی sgACC) در افراد دارای اختلال بیش‌ترین افت ارتباطات عمل‌کردی را با چهار ناحیه‏ی مذکور داشته‌اند که این نتایج با نتایج تحقیقات پیشین در این زمینه سازگار می‌باشد. 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Functional Connectivity Based Diagnosis of Bipolar Disorder by using Resting State fMRI

نویسندگان [English]

  • Amirhossein Chalechale 1
  • Ali Khadem 2

1 M.Sc. Student, Department of Biomedical Engineering, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran

2 Assistant Professor, Department of Biomedical Engineering, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran

چکیده [English]

The well-timed and correct diagnosis of Bipolar Disorder (BD) followed by proper treatment is vital for avoiding the progress of the illness. Although using resting-state functional magnetic resonance imaging (rs-fMRI) data and the features extracted from them may have an important role in diagnosing this kind of brain disorder, few researches have been conducted on this illness and the obtained results are not accurate.  In this research we used a new approach to diagnose BD I. By using seed-based correlation we used the following 4 regions of interest in order to extract the connectivity maps for each subject: the posterior cingulate cortex (PCC) to probe the default mode network (DMN), the amygdala and the subgenual cingulate cortex (sgACC) to probe the salience network (SN) and the dorsolateral prefrontal cortex (dlPFC) to probe the frontoparietal network (FPN). After computing the connectivity maps for each subject we extracted the most important connectivities using different threshold on the t-value from the t-test that we applied on them and then we used a support vector machine (SVM) using only four combined features and a leave one out cross-validation (LOOCV) method to classify the two groups. The proposed method was done on rs-fMRI data from 49 healthy control subjects and 34 BD I patients and an accuracy of higher than 90% was obtained in differentiating the two groups from each other. Also there were no hyper-connectivity between the 4 ROIs and the rest of the brain regions for the BD I groups in relation with the healthy controls. The regions that had most of the hypo-connectivity with the 4 ROI’s that we used were: the angular gyrus (Ag) and the orbitofrontal cortex (OFC) with the PCC, the anterior cingulate cortex with the amygdala and the dlPFC and the inferior temporal gyrus (ITG) with the sgACC.

کلیدواژه‌ها [English]

  • Bipolar disorder
  • resting state functional magnetic resonance imaging (rs-fMRI)
  • seed-based correlation
  • T-test
  • Support Vector Machine (SVM)
[1]   J. H. Barnett and J. W. Smoller, "The genetics of bipolar disorder," Neuroscience, vol. 164, pp. 331-343, 2009.
[2]   Renk, Kimberly and White, "Bipolar disorder in children," Psychiatry journal, vol. 1, 2014.
[3]   X. Wang, M. Xia and Y. Lai, "Disrupted resting-state functional connectivity in minimally treated chronic schizophrenia," Schizophrenia research, vol. 156, pp. 150-156, 2014.
[4]   M. Li, T. Das, W. Deng, Q. Wang, Y. Li, L. Zhao, X. Ma and Y. Wang, "Clinical utility of a short resting-state MRI scan in differentiating bipolar from unipolar depression," Acta psychiatrica Scandinavica, vol. 136, pp. 288-299, 2017.
[5]   V. Menon, "Large-scale brain networks and psychopathology: a unifying triple network model," Trends in cognitive sciences, vol. 15, pp. 483-506, 2011.
[6]   L. Palaniyappan, G. Deshpande, P. Lanka and D. Rangaprakash, "Effective connectivity within a triple network brain system discriminates schizophrenia spectrum disorders from psychotic bipolar disorder at the single-subject level," Schizophrenia research, 2018.
[7]   R. L. Buckner, J. R. Andrews-Hanna and D. L. Schacter, "The brain's default network: anatomy, function, and relevance to disease," Annals of the New York Academy of Sciences, vol. 1124, pp. 1-38, 2008.
[8]   V. Menon and L. Q. Uddin, "Saliency, switching, attention and control: a network model of insula function," Brain Structure and Function, vol. 214, pp. 655-667, 2010.
[9]   D. Sridharan, D. J. Levitin and V. Menon, "A critical role for the right fronto-insular cortex in switching between central-executive and default-mode networks," {Proceedings of the National Academy of Sciences, vol. 105, pp. 12569-12574, 2008.
[10]J. Long, Q. Xie, Q. Ma, M. Urbin and L. Liu, "Distinct interactions between fronto-parietal and default mode networks in impaired consciousness," Scientific reports, vol. 6, p. 38866, 2016.
[11]M.-J. Liang, Q. Zhou, K.-R. Yang and X.-L. Yang, "Identify changes of brain regional homogeneity in bipolar disorder and unipolar depression using resting-state FMRI," PloS one, vol. 8, p. e79999, 2013.
[12]C.-H. Liu, F. Li, S.-F. Li and Y.-J. Wang, "Abnormal baseline brain activity in bipolar depression: a resting state functional magnetic resonance imaging study," Psychiatry Research: Neuroimaging, vol. 203, pp. 175-179, 2012.
[13]C. Vargas, C. Lopez-Jaramillo and E. Vieta, "A systematic literature review of resting state network—functional MRI in bipolar disorder," Journal of affective disorders, vol. 150, pp. 727-735, 2013.
[14]K. Xu, H. Liu, H. Li and Y. Tang, "Amplitude of low-frequency fluctuations in bipolar disorder: a resting state fMRI study," Journal of affective disorders, vol. 152, pp. 237-242, 2014.
[15]D. Ongur, M. Lundy, I. Greenhouse and A. K. Shinn, "Default mode network abnormalities in bipolar disorder and schizophrenia," Psychiatry Research: Neuroimaging, vol. 183, pp. 59-68, 2010.
[16]R. Goya-Maldonado, K. Brodmann, M. Keil and S. Trost, "Differentiating unipolar and bipolar depression by alterations in large-scale brain networks," Human brain mapping, vol. 37, pp. 808-818, 2016.
[17]P. Magioncalda, M. Martino, B. Conio and A. Escelsior, "Functional connectivity and neuronal variability of resting state activity in bipolar disorder—reduction and decoupling in anterior cortical midline structures," Human brain mapping, vol. 36, pp. 666-682, 2015.
[18]N.-F. Jie, M.-H. Zhu, X.-Y. Ma and E. A. Osuch, "Discriminating bipolar disorder from major depression based on SVM-FoBa: efficient feature selection with multimodal brain imaging data," IEEE transactions on autonomous mental development, vol. 7, pp. 320-331, 2015.
[19]B. Rashid, M. R. Arbabshirani, E. Damaraju and M. S. Cetin, "Classification of schizophrenia and bipolar patients using static and dynamic resting-state fMRI brain connectivity," Neuroimage, vol. 134, pp. 645-657, 2016.
[20]S. Teng, C.-F. Lu, P.-S. Wang and C.-I. Hung, "Classification of bipolar disorder using basal-ganglia-related functional connectivity in the resting state," in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, 2013, pp. 1057-1060.
[21]M. Li, T. a. D. W. Das and Q. Wang, "Clinical utility of a short resting-state MRI scan in differentiating bipolar from unipolar depression," Acta psychiatrica Scandinavica, vol. 136, pp. 288-299, 2017.
[22]Anticevic, M. W. Cole, G. Repovs and J. D. Murray, "Characterizing thalamo-cortical disturbances in schizophrenia and bipolar illness," Cerebral cortex, vol. 24, pp. 3116-3130, 2013.
[23]Y. Du, G. D. Pearlson, J. Liu and J. Sui, "A group ICA based framework for evaluating resting fMRI markers when disease categories are unclear: application to schizophrenia, bipolar, and schizoaffective disorders," Neuroimage, vol. 122, pp. 272-280, 2015.
[24]J. Gong, G. Chen, Y. Jia and S. Zhong, "Disrupted functional connectivity within the default mode network and salience network in unmedicated bipolar II disorder," Progress in Neuro-Psychopharmacology and Biological Psychiatry, vol. 88, pp. 11-18, 2019.
[25]R. A. Poldrack, E. Congdon, W. Triplett and K. Gorgolewski, "A phenome-wide examination of neural and cognitive function," Scientific data, vol. 3, p. 160110, 2016.
[26]G. S. Alexopoulos, M. J. Hoptman, D. Kanellopoulos and C. F. Murphy, "Functional connectivity in the cognitive control network and the default mode network in late-life depression," Journal of affective disorders, vol. 139, pp. 56-65, 2012.
[27]R. L. Bluhm, C. R. Clark, A. C. McFarlane and K. A. Moores, "Default network connectivity during a working memory task," Human brain mapping, vol. 32, pp. 1029-1035, 2011.
[28]R. Jacobs, A. Barba, J. Gowins and H. Klumpp, "Decoupling of the amygdala to other salience network regions in adolescent-onset recurrent major depressive disorder," Psychological medicine, vol. 46, pp. 1055-1067, 2016.
[29]C. Kelly, A. Di Martino, L. Q. Uddin and Z. Shehzad, "Development of anterior cingulate functional connectivity from late childhood to early adulthood," Cerebral cortex, vol. 19, pp. 640-657, 2008.
[30]D. S. Margulies, A. C. Kelly, L. Q. Uddin and B. B. Biswal, "Mapping the functional connectivity of anterior cingulate cortex," Neuroimage, vol. 37, pp. 579-588, 2007.
[31]C. McCabe and Z. Mishor, "Antidepressant medications reduce subcortical--cortical resting-state functional connectivity in healthy volunteers," Neuroimage, vol. 57, pp. 1317-1323, 2011.
[32]J. N. Pannekoek, I. M. Veer, M.-J. van Tol and S. J. van der Werff, "Aberrant limbic and salience network resting-state functional connectivity in panic disorder without comorbidity," Journal of affective disorders, vol. 145, pp. 29-35, 2013.
[33]H. McCarthy, N. Skokauskas, A. Mulligan and G. Donohoe, "Attention network hypoconnectivity with default and affective network hyperconnectivity in adults diagnosed with attention-deficit/hyperactivity disorder in childhood," JAMA psychiatry, vol. 70, pp. 1329-1337, 2013.
[34]Y. I. Sheline, J. L. Price, Z. Yan and M. A. Mintun, "Resting-state functional MRI in depression unmasks increased connectivity between networks via the dorsal nexus," Proceedings of the National Academy of Sciences, vol. 107, pp. 11020-11025, 2010.
[35]M. Vinod, "Large-Scale brain networks and psycopathology: a unifying triple network model," Trends in cognitive sciences, vol. 15, pp. 483-506, 2011.
[36]M. Vinod, "The Triple Network Model, Insight, and Large-Scale Brain Organization in Autism," Biological psychiatry, vol. 10, pp. 61-74, 1999.      
[37]J. Platt and others, "Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods," Advances in large margin classifiers, vol. 84, pp. 236, 2018.
[38]"The angular gyrus: multiple functions and multiple subdivisions," Seghier, Mohamed L, vol. 19, pp. 43-61, Seghier, Mohamed L.
[39]D. Lv, W. Lin, Z. Xue and W. Pu, "Decreased functional connectivity in the language regions in bipolar patients during depressive episodes but not remission," Journal of affective disorders, vol. 197, pp. 116-124, 2016.
[40]D. Lv, W. Lin, Z. Xue and W. Pu, "Decreased functional connectivity in the language regions in bipolar patients during depressive episodes but not remission," Journal of affective disorders, vol. 197, pp. 116-124, 2016.
[41]Y. Wang, S. Zhong, Y. Jia and Y. Sun, "Disrupted resting-state Functional connectivity innonmedicated Bipolar Disorder," Radiology, vol. 280, pp. 529-536, 2016.
[42]Hahn, P. Stein, C. Windischberger and A. Weissenbacher, "Reduced resting-state functional connectivity between amygdala and orbitofrontal cortex in social anxiety disorder," Neuroimage, vol. 56, pp. 881-889, 2011.
[43]F. Wang, J. H. Kalmar, Y. He and M. Jackowski, "Functional and structural connectivity between the perigenual anterior cingulate and amygdala in bipolar disorder," Biological psychiatry, vol. 66, pp. 516-521, 2009.
[44]D. G. Amaral and J. Price, "Amygdalo-cortical projections in the monkey (Macaca fascicularis)," Journal of Comparative Neurology, vol. 230, pp. 465-496, 1984.
[45]D. Pandya, G. Van Hoesen and M.-M. Mesulam, "Efferent connections of the cingulate gyrus in the rhesus monkey," Experimental brain research, vol. 42, pp. 319-330, 1981.
[46]Etkin, T. Egner, D. M. Peraza and E. R. Kandel, "Resolving emotional conflict: a role for the rostral anterior cingulate cortex in modulating activity in the amygdala," Neuron, vol. 51, pp. 871-882, 2006.
[47]J. N. Bae, J. R. MacFall, K. R. R. Krishnan and M. E. Payne, "Dorsolateral prefrontal cortex and anterior cingulate cortex white matter alterations in late-life depression," Biological psychiatry, vol. 60, pp. 1356-1363, 2006.
[48]H. He, Q. Yu, Y. Du and V. Vergara, "Resting-state functional network connectivity in prefrontal regions differs between unmedicated patients with bipolar and major depressive disorders," Journal of affective disorders, vol. 190, pp. 483-493, 2016.
[49]T. Onitsuka, M. E. Shenton, D. F. Salisbury and C. C. Dickey, "Middle and inferior temporal gyrus gray matter volume abnormalities in chronic schizophrenia: an MRI study," American Journal of Psychiatry, vol. 161, pp. 1603-1611, 2004.
[50]P. Magioncalda, M. Martino, B. Conio and A. Escelsior, "Functional connectivity and neuronal variability of resting state activity in bipolar disorder—reduction and decoupling in anterior cortical midline structures," Human brain mapping, vol. 36, pp. 666-682, 2015.
[51]Q. Zhou, F. Y. Womer, L. Kong and F. Wu, "Trait-Related Cortical-Subcortical Dissociation in Bipolar Disorder: Analysis of Network Degree Centrality.," The Journal of clinical psychiatry, vol. 78, pp. 584-591, 2017.