A variety of psychological scales are utilized at present as the most important basis for clinical diagnosis of mood disorders. An experienced psychiatrist assesses and diagnoses mood disorders based on clinical symptoms and relevant assessment scores. This symptom based clinical criterion is limited by the psychiatrist's experience. In practice, it is difficult to distinguish the patients with bipolar disorder with depression episode (bipolar depression, BD) from those with major depressive disorder (MDD). The functional near-infrared spectroscopy (fNIRS) technology is commonly used to perceive the emotions of a human. It measures the hemodynamic parameters of the brain, which correlate with cerebral activation. Here, we propose a machine learning classification method based on deep neural network for the brain activations of mood disorders. Large time scale connectivity is determined using an attention long short term memory neural network and short-time feature information are considered using the InceptionTime neural network in this method. Our combined method is referred to as AttentionLSTM-InceptionTime (ALSTMIT). We collected fNIRS data of 36 MDD patients and 48 BD patients who were in the depressed state. All the patients were monitored by fNIRS during conducting the verbal fluency task (VFT). We trained the model with the ALSTMIT network. The algorithm can distinguish the two types of patients effectively: the average accuracy of classification on the test set can reach 96.2% stably. The classification can provide an objective diagnosis tool for clinicians, and this algorithm may be critical for the early detection and precise treatment for the patients with mood disorders.
1. Bahdanau, D., K. Cho, and Y. Bengio, "Neural machine translation by jointly learning to align and translate," ICLR 2015, 2015.
2. Barreiros, A. R., I. A. Breukelaar, W. Chen, M. Erlinger, and M. S. Korgaonkar, "Neurophysiological markers of attention distinguish bipolar disorder and unipolar depression," Journal of Affective Disorders, Vol. 274, 411-419, 2020.
3. Benavides-Varela, S., D. M. Gomez, and J. Mehler, "Studying neonates' language and memory capacities with functional near-infrared spectroscopy," Frontiers in Psychology, Vol. 2, 64, 2011.
4. Boas, D. A., C. E. Elwell, M. Ferrari, and G. Taga, "Twenty years of functional near-infrared spectroscopy: Introduction for the special issue," NeuroImage, Vol. 85, 1-5, 2014.
5. Cerullo, M. A., et al., "Bipolar I disorder and major depressive disorder show similar brain activation during depression," Bipolar Disorders, Vol. 16, No. 7, 703-712, 2015.
6. Chen, X., Z. Wei, M. Li, and P. Rocca, "A review of deep learning approaches for inverse scattering problems (invited review)," Progress In Electromagnetics Research, Vol. 167, 67-81, 2020.
7. Cho, K., et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation," Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1724-1734, 2014.
8. Cristia, A., et al., "An online database of infant functional near infrared spectroscopy studies: A community-augmented systematic review," PloS One, Vol. 8, No. 3, e58906, 2013.
9. Dieler, A. C., S. V. Tupak, and A. J. Fallgatter, "Functional near-infrared spectroscopy for the assessment of speech related tasks," Brain & Language, Vol. 121, No. 2, 90-109, 2012.
10. Ehlis, A.-C., S. Schneider, T. Dresler, and A. J. Fallgatter, "Application of functional near-infrared spectroscopy in psychiatry," NeuroImage, Vol. 85, 478-488, 2014.
11. Fawaz, H. I., et al., "InceptionTime: Finding alexnet for time series classification," Data Mining and Knowledge Discovery, Vol. 34, 1936-1962, 2020.
12. He, K., X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778, 2016.
13. Hochreiter, S. and J. Schmidhuber, "Long short-term memory," Neural Computation, Vol. 9, No. 8, 1735-1780, 1997.
14. Hoshi, Y. and M. Tamura, "Detection of dynamic changes in cerebral oxygenation coupled to neuronal function during mental work in man," Neuroscience Letters, Vol. 150, No. 1, 5-8, 1993.
15. Ioffe, S. and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," Proceedings of the 32nd International Conference on Machine Learning, PMLR, Vol. 37, 448-456, 2015.
16. Jobsis, F. F., "Noninvasive, infrared monitoring of cerebral and myocardial oxygen sufficiency and circulatory parameters," Science, Vol. 198, No. 4323, 1264-1267, 1977.
17. Jobsis-vander Vliet, F. F., "Discovery of the near-infrared window into the body and the early development of near-infrared spectroscopy," Journal of Biomedical Optics, Vol. 4, No. 4, 392-396, 1999.
18. Karim, F., S. Majumdar, H. Darabi, and S. Chen, "LSTM fully convolutional networks for time series classification," IEEE Access, Vol. 6, No. 99, 1662-1669, 2018.
19. Kato, T., A. Kamei, S. Takashima, and T. Ozaki, "Human visual cortical function during photic stimulation monitoring by means of near-infrared spectroscopy," Journal of Cerebral Blood Flow & Metabolism, Vol. 13, No. 3, 516-520, 1993.
20. Kawakami, K., Supervised sequence labelling with recurrent neural networks, Ph.D. dissertation, 2008.
21. Kim, Y.-K. and K.-S. Na, "Application of machine learning classification for structural brain MRI in mood disorders: Critical review from a clinical perspective," Progress in Neuropsychopharmacology and Biological Psychiatry, Vol. 80, 71-80, 2018.
22. Kopton, I. M. and P. Kenning, "Near-infrared spectroscopy (NIRS) as a new tool for neuroeconomic research," Frontiers in Human Neuroscience, Vol. 8, 549, 2014.
23. LeCun, Y., et al., "Convolutional networks for images, speech, and time series," The Handbook of Brain Theory and Neural Networks, Vol. 3361, No. 10, 1995, 1995.
24. Li, Z., Y. Wang, W. Quan, T. Wu, and B. Lv, "Evaluation of different classification methods for the diagnosis of schizophrenia based on functional near-infrared spectroscopy," Journal of Neuroence Methods, Vol. 241, 101-110, 2015.
25. Li, Z., Y. Wang, W. Quan, T. Wu, and B. Lv, "Evaluation of different classification methods for the diagnosis of schizophrenia based on functional near-infrared spectroscopy," Journal of Neuroscience Methods, Vol. 241, 101-110, 2015.
26. Maalouf, F. T., et al., "Impaired sustained attention and executive dysfunction: Bipolar disorder versus depression-specific markers of affective disorders," Neuropsychologia, Vol. 48, No. 6, 1862-1868, 2010.
27. McIntyre, R. S., M. Berk, E. Brietzke, B. I. Goldstein, C. L¶opez-Jaramillo, L. V. Kessing, G. S. Malhi, A. A. Nierenberg, J. D. Rosenblat, A. Majeed, et al., "Bipolar disorders," The Lancet, Vol. 396, No. 10265, 1841-1856, 2020.
28. Molavi, B., L. May, J. Gervain, M. Carreiras, J. F. Werker, and G. A. Dumont, "Analyzing the resting state functional connectivity in the human language system using near infrared spectroscopy," Frontiers in Human Neuroscience, Vol. 7, 921, 2014.
29. Naseer, N. and K.-S. Hong, "fNIRS-based brain-computer interfaces: A review," Frontiers in Human Neuroscience, Vol. 9, 3, 2015.
30. Nguyen, D. K., et al., "Non-invasive continuous EEG-fNIRS recording of temporal lobe seizures," Epilepsy Research, Vol. 99, No. 1-2, 112-126, 2012.
31. Obrig, H., "Nirs in clinical neurology --- A `promising' tool?," NeuroImage, Vol. 85, 535-546, 2014.
32. O'Halloran, M., B. McGinley, R. C. Conceicao, F. Morgan, E. Jones, and M. Glavin, "Spiking neural networks for breast cancer classification in a dielectrically heterogeneous breast," Progress In Electromagnetics Research, Vol. 113, 413-428, 2011.
33. Onishi, A., H. Furutani, T. Hiroyasu, and S. Hiwa, "An fNIRS study of brain state during letter and category uency tasks," Journal of Robotics, Networking and Artificial Life, Vol. 5, No. 4, 228-231, 2019.
34. Pascanu, R., C. Gulcehre, K. Cho, and Y. Bengio, "How to construct deep recurrent neural networks," Proceedings of the Second International Conference on Learning Representations (ICLR 2014), 2014.
35. Phillips, M. L. and D. J. Kupfer, "Bipolar disorder diagnosis: Challenges and future directions," Lancet, Vol. 381, No. 9878, 1663-1671, 2013.
36. Quan, W., T. Wu, Z. Li, Y. Wang, W. Dong, and B. Lv, "Reduced prefrontal activation during a verbal fluency task in chinese-speaking patients with schizophrenia as measured by near-infrared spectroscopy," Progress in Neuropsychopharmacology and Biological Psychiatry, Vol. 58, 51-58, 2015.
37. Quaresima, V., S. Bisconti, and M. Ferrari, "A brief review on the use of functional near-infrared spectroscopy (fNIRS) for language imaging studies in human newborns and adults," Brain and Language, Vol. 121, No. 2, 79-89, 2012.
38. Raucher-Chene, D., A. M. Achim, A. Kaladjian, and C. Besche-Richard, "Verbal uency in bipolar disorders: A systematic review and meta-analysis," Journal of Affective Disorders, Vol. 207, 359-366, 2017.
39. Santosa, H., M. J. Hong, and K.-S. Hong, "Lateralization of music processing with noises in the auditory cortex: An fNIRS study," Frontiers in Behavioral Neuroscience, Vol. 8, 418, 2014.
40. Sitaram, R., A. Caria, and N. Birbaumer, "Hemodynamic brain-computer interfaces for communication and rehabilitation," Neural Networks, Vol. 22, No. 9, 1320-1328, 2009.
41. Suto, T., M. Fukuda, M. Ito, T. Uehara, and M. Mikuni, "Multichannel near-infrared spectroscopy in depression and schizophrenia: Cognitive brain activation study," Biological Psychiatry, Vol. 55, No. 5, 501-511, 2004.
42. Luong, M.-T., H. Pham, and C. D. Manning, "Effective approaches to attention-based neural machine translation," Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 1412-1421, Lisbon, Portugal, September 17-21, 2015.
43. Szegedy, C., et al., "Going deeper with convolutions," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1-9, 2015.
44. Szegedy, C., S. Ioffe, V. Vanhoucke, and A. A. Alemi, "Inception-v4, inception-resnet and the impact of residual connections on learning," Thirty-first AAAI Conference on Artificial Intelligence, 2017.
45. Szegedy, C., V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818-2826, 2016.
46. Tomioka, H., et al., "A longitudinal functional neuroimaging study in medication-nave depression after antidepressant treatment," PLoS One, Vol. 10, No. 3, e0120828, 2015.
47. Tomioka, H., B. Yamagata, S. Kawasaki, S. Pu, A. Iwanami, J. Hirano, K. Nakagome, and M. Mimura, "A longitudinal functional neuroimaging study in medication-naive depression after antidepressant treatment," PLoS One, Vol. 10, No. 3, e0120828, 2015.
48. Villringer, A., J. Planck, C. Hock, L. Schleinkofer, and U. Dirnagl, "Near infrared spectroscopy (NIRS): A new tool to study hemodynamic changes during activation of brain function in human adults," Neuroscience Letters, Vol. 154, No. 1-2, 101-104, 1993.
49. Wang, S., Y. Zhang, T. Zhan, P. Phillips, Y.-D. Zhang, G. Liu, S. Lu, and X. Wu, "Pathological brain detection by artificial intelligence in magnetic resonance imaging scanning (invited review)," Progress In Electromagnetics Research, Vol. 156, 105-133, 2016.
50. Watanabe, E., Y. Nagahori, and Y. Mayanagi, "Focus diagnosis of epilepsy using near-infrared spectroscopy," Epilepsia, Vol. 43, 50-55, 2002.
51. Wise, T., J. Radua, G. Nortje, A. J. Cleare, A. H. Young, and D. Arnone, "Voxel-based meta-analytical evidence of structural disconnectivity in major depression and bipolar disorder," Biological Psychiatry, 2016.
52. Wolfe, J., E. Granholm, N. Butters, E. Saunders, and D. Janowsky, "Verbal memory deficits associated with major affective disorders: A comparison of unipolar and bipolar patients," Journal of Affective Disorders, Vol. 13, No. 1, 83-92, 1987.