Fonksiyonel Nöronal Görüntülerde Aktivasyonların Yerini Belirlemek için Değişim Noktası Algılama Yöntemleri

Abstract

fMRI görüntüleri için en yaygın analizde amaç, deneyde görevler olarak verilen ilgili uyaranlara karşılık beyinde görsel işleme veya motor işlevler gibi belirli işlevlere yanıt veren konumları bulan aktivasyon tespitidir. Öte yandan, aktivasyonun tetiklendiği anın tespit edilmesi de önemlidir. Herhangi bir verinin anormal davranışını analiz edebilen güçlü tekniklerden biri de değişim noktası (DN) analizidir. CP algılama algoritmalarının, fonksiyonel manyetik rezonans görüntüleme (fMRI) dizilerindeki aktivasyonları bulmak için de kullanılabileceğini öneriyoruz. Makalemiz bu açıdan iki yönlü yenilikçi bir çalışma sunmaktadır. İlk olarak, son teknoloji bir konu olarak fMRI sinyallerindeki aktivasyonları bulmak için CP algılama algoritmalarını kullanmayı öneriyoruz. Ayrıca, bu tür noktaları bulmak için bir dizi değişim noktası analiz yöntemi, regresyon tabanlı yöntem, istatistiksel yöntem ve kayan çift pencere yöntemi öneriyor ve karşılaştırıyoruz. İkinci olarak, bu yöntemleri, fMRI görevlerini gerçekleştirirken gerçek deneklerden elde edilen fMRI sinyallerine uyguluyoruz. Önerilen yöntemler, bir motor görev, bir görsel görev ve bir dilsel görev olmak üzere üç farklı fMRI deneyine uygulandı. Analiz, yöntemlerin, istatistiksel parametrik haritalar (SPM) gibi yerleşik yöntemlere uygun aktivasyonlar bulduğunu göstermektedir. Elde edilen %94'e varan sonuçlar, aynı zamanda önerilen yöntemlerin fMRI zaman serilerinde aktivasyon anlarını bulmak için etkin bir şekilde kullanılabileceğini göstermektedir.

Keywords

• Aktivasyon Tespiti
• Aktivasyon Anları
• Değişim Noktası Problemi
• fMRI
• Regresyon

Change Point Detection Methods for Locating Activations in Functional Neuronal Images

Abstract

The most common analysis for fMRI images is activation detection, in which the purpose is to find the locations in the brain that respond to specific functions, such as visual processing or motor functions by providing related stimuli as tasks in the experiment. On the other hand, it is also important to detect the instance the activation is triggered. One of the powerful techniques that can analyze the abnormal behavior of any data is change point (CP) analysis. We suggest that CP detection algorithms also can be used to locate the activations in functional magnetic resonance imaging (fMRI) sequences, as well. Our paper presents a two-fold innovative study in that respect. First, we propose to use CP detection algorithms to locate the activations in fMRI signals as a state-of-art topic. Furthermore, we propose and compare a set of change point analysis methods, a regression-based method (RBM), a statistical method (SM), and a mean difference of double sliding windows method (MDSW)) to locate such points. Second, we apply these methods to the fMRI signals, which are acquired from the real subjects, while they were performing fMRI tasks. Proposed methods were applied to three different fMRI experiments with a motor task, a visual task, and a linguistic task. The analysis shows that the methods find activations in accordance with established methods such as statistical parametric maps (SPM). The acquired up to 94 % results also show that the proposed methods can be used effectively to locate the activation times on fMRI time series.

Keywords

• Activation Detection
• Activation Instance
• Change Point Problem
• fMRI
• Regression

References

1. Sargun, D., & Koksal C.E. (2021). “Robust Change Detection via Information Projection,” IEEE Journal on Selected Areas in Information. Theory, 2(2), 774-784.
2. Kass-Hout T.A., Xu, Z., Mc Murray, P., Park, S. Buckeridge, D.L. Brownstein, J.S., Finelli, L., & Groseclose, S.L. (2012). “Application of change point analysis to daily influenza-like illness emergency department visits,” J. Am. Med. Inform. Assoc. JAMIA, 19(6), 1075–1081.
3. Zhang, N.R., Siegmund, D. O., Ji, H., & Li, J. Z. (2010). “Detecting simultaneous change points in multiple sequences,” Biometrika, 97(3), 631–645.
4. Feber, A., Guilhamon, P., Lechner, M., Fenton, T., Wilson, G.A., Thirlwell, C., Morris, T. J., Flanagan, A.M., Teschendorff, A.E., Kelly, J.D., & Beck, S. (2014). “Using high-density DNA methylation arrays to profile copy number alterations”, Genome Bio., 15(2), R30.
5. Ruggieri,E., Herbert,T., Lawrence, K. T., & Lawrence, C. E.(2009). Change point method for detecting regime shifts in paleoclimatic time series: Application to δ18O time series of the Plio-Pleistocene, Paleoceanography, 24(1), PA1204.
6. Gallagher, C., Lund, R. & Robbins, M., (2012). Change point detection in daily precipitation data, Environmetrics, 23(5), 407–419.
7. Perreault, L., Bernier, J., Bobée, B., & Parent, B. (2000). Bayesian change-point analysis in hydrometeorological time series. Part 1. The normal model revisited, J. Hydrol., 235(3), 221–241.
8. Mostafa, A. A., & Ghorbal, A. B. (2011). Bayesian and Non-Bayesian Analysis for Random Change Point Problem Using Standard Computer Packages, Int. J. Math. Arch., 2(10), 1963–1979.

9. Elliott, R. J., and Siu, T. K. (2014). Filtering and change point estimation for hidden Markov-modulated Poisson processes, Appl. Math. Lett., 28, 66–71.
10. Gazor, S., Derakhtian, M., & Tadaion, A.A. (2010) Computationally Efficient Maximum Likelihood Estimation and Activity Detection for M-PSK Signals in Unknown Flat Fading Channels, IEEE Signal Proc. Letters, 17(10), 871–874.
11. Bardet, J.-M., Kengne, W., & Wintenberger, O. (2012). Multiple breaks detection in general causal time series using penalized quasi-likelihood, Electron. J. Stat., 6, 435–477.
12. Toms, J. D., & Lesperance, M. L. (2003). Piecewise Regression: A Tool for Identifying Ecological Thresholds, Ecology, 84(8), 2034–2041.
13. Wu, W. B., Woodroofe, M., & Mentz, G. (2001). Isotonic Regression: Another Look at the Change Point Problem, Biometrika, 88(3), 793–804.
14. Hu, S., & Zhao, L. (2015). A Support Vector Machine Based Multi-Kernel Method for Change Point Estimation on Control Chart, IEEE Int’l Conf. on Systems, Man, and Cybernetics, Hong Kong, China, 492–496.
15. Kazemi, M. S., Kazemi, K., Yaghoobi, M. A. & Bazargan, H. (2016). A hybrid method for estimating the process change point using support vector machine and fuzzy statistical clustering, Appl. Soft Comput., (40), 507–516.
16. Aminikhanghahi, S., & Cook, D. J. (2017). A survey of methods for time series change point detection, Knowl. Inf. Syst., 51(2), 339–367.
17. Candemir, C., & Oğuz, K., (2017). A Comparative Study on Parameter Selection and Outlier Removal for Change Point Detection in Time Series, IEEE European conf. on Elec. Engineering and comp. Sci. (EECS), Bern, Switzerland, doi: 10.1109/EECS.2017.48
18. Deichmann, R. (2009). Principles of MRI and Functional MRI, in fMRI Techniques and Protocols, Humana Press, Totowa, NJ, 3–29.
19. Ogawa, S., Lee, T. M., Kay, A. R., & Tank, D. W. (1990). Brain magnetic resonance imaging with contrast dependent on blood oxygenation, Proc. Natl. Acad. Sci. U. S. A., 87(24), 9868–9872.
20. Handwerker, D. A., Ollinger, J. M., & D’Esposito, M. (2004). Variation of BOLD hemodynamic responses across subjects and brain regions and their effects on statistical analyses, NeuroImage, 21(4), 1639–1651.
21. Xin L., Yu P.L.H., & Lam K. (2013). An Application of CUSUM Chart on Financial Trading, 9th Int’l Conf. on Computational Intelligence and Security, 14-15 December, China.
22. Callegari C., Pagano M., & Giordiano S., (2017). CUSUM-based and entropy-based anomaly detection: An Experimental comparison, 8th Int’l Conference on the Network of the Future, 22-24 Nov., London
23. Polunchenko, A.S., (2018). Optimal Design of the Shiryaev-Roberts Chart: Give Your Shiryaev-Roberts a Headstar, Frontiers in Statistical Quality Control, 12, 65-86.
24. Pollak, M. & Siegmund, D. (1985). On robustness of the Shiryaev–Roberts change-point detection procedure under parameter misspecification in the post-change distribution, Communications in Statistics - Theory and Methods, 72(2), 2185-2206.
25. Wen Y.,Wu J., Zhou Q., & Tseng T., (2019). Multiple-Change-Point Modeling and Exact Bayesian Inference of Degradation Signal for Prognostic Improvement, IEEE Trans. on Auto. Sci and Eng., 16(2), 613-628.
26. Nath S., Wu J., (2018). Bayesian Quickest Change Point Detection with Multiple Candidates of Post-Change Models, IEEE Global Conf. on Signal and Information Processing, 26-29 Nov, Anaheim, USA.
27. Geng J., & Lai L., (2013). Bayesian Quickest change point detection and localization in sensor networks, IEEE Global Conf. on Signal and Information Processing, 3-5 Dec., Austin TX, USA.
28. Adams, R. P., & MacKay, D. J., (2007). Bayesian online change point detection, ArXivPrepr. ArXiv:0710.3742.
29. Saatçi, Y., Turner, R. D., & Rasmussen, C. E. (2010). Gaussian process change point models, Proceedings of the 27th Int’l Conf. on Mach. Learn. (ICML-10), 10, 927–934.
30. Carlin, B. P., Gelfand, A. E., & Smith, A. F. M. (1992). Hierarchical Bayesian Analysis of Changepoint Problems, J. R. Stat. Soc. Ser. C Appl. Stat., 41(2), 389–405.
31. Loschi, R. H. & Cruz, F. R. B.(2005). Bayesian identification of multiple change points in poisson data, Adv. Complex Syst., 08(4), 465–482.
32. Yao, Y.-C. (1988). Estimating the number of change-points via Schwarz’ criterion,” Stat. Probab. Lett., 6(3), 181–189.
33. Whiteley, N., Andrieu, C. & Doucet, A. (2011). Bayesian computational methods for inference in multiple change-points models, submitted for publication.
34. Ruggieri, E., & Antonellis, M. (2016). An exact approach to Bayesian sequential change point detection, Comput. Stat. Data Anal., 97, 71–86.
35. Chopin, N. (2007). Dynamic Detection of Change Points in Long Time Series, Ann. Inst. Stat. Math., 59(2), 349–366.
36. Barry, D., & Hartigan, J. A., (1993). A Bayesian Analysis for Change Point Problems, J. Am. Stat. Assoc., 88(421), 309–319.
37. Hinkley, D. V. (1970). Inference About the Change-Point in a Sequence of Random Variables, Biometrika, 57(1), 1–17.
38. Hinkley, D. V. (1972). Time-Ordered Classification, Biometrika, 59(3), 509–523.
39. Joseph, L. & Wolfson, D. B. (1992). Estimation in multi-path change-point problems, Commun. Stat.- Theory Methods, 21(4), 897–913.
40. Zou, C., Liu, Y., Qin, P., & Wang, Z. (2007). Empirical likelihood ratio test for the change-point problem, Stat. Probab. Lett., 77(4), 374–382.
41. Diop M.L., & Kengne W., (2020). Poisson QMLE for change-point detection in general integer-valued series, arxiv.org, doi: https://doi.org/10.48550/arXiv.2007.13858.
42. Bai, J. (2000). Vector autoregressive models with structural changes in regression coefficients and in variance-covariance matrices, Ann. Econ. Finance, 1(2), 303-339.
43. Geng J., Zhang B., Huie L.M., & Lai L., (2019). Online Change-Point Detectşon of Linear Regression Models, IEEE Trans. on Signal Processing, 67(12), 3316–3329.
44. Loschi R., Pontel J.G., & Cruz F.R.B., (2010). Multiple Change -Point Analysis for Linear Regression Models, Chilean Journal of Statistics, 1(2), 93-112.
45. Brown, R.L., Durbin, J., & Evans, J. M., (1975). Techniques for Testing the Constancy of Regression Relationships over Time, J. R. Stat. Soc. Ser. B Methodol., 37(2), 149–192.
46. Bai, J. (1997). Estimation of a Change Point in Multiple Regression Models, Rev. Econ. Stat., 79(4), 551–563.
47. Jandhyala, V. K., & MacNeill, I. B. (1991), Tests for parameter changes at unknown times in linear regression models, J. Stat. Plan. Inference,.27(3), 291–316.
48. Gurevich, G., & Vexler, A. (2005). Change point problems in the model of logistic regression, J. Stat. Plan. Inference, 131(2), 313–331.
49. Preminger, A., & Wettstein, D. (2005). Using the Penalized Likelihood Method for Model Selection with Nuisance Parameters Present only under the Alternative: An Application to Switching Regression Models, J. Time Ser. Anal., 26(5), 715–741.
50. Winkler, S. Affenzeller, M., Kronberger, G., Kommenda, M., Burlacu, B., & Wagner, S. (2015). Sliding Window Symbolic Regression for Detecting Changes of System Dynamics, in Genetic Programming Theory and Practice XII, Springer, Cham, 91–107.
51. Bandettini, P.A., Jesmanowicz, A., Wong, E. C., & Hyde, J. S. (1993). Processing strategies for time-course data sets in functional mri of the human brain, Magn. Reson. Med., 30(2), 161–173.
52. Xiong, J., Gao, J.-H., Lancaster, J. L., & Fox, P. T. (1996). Assessment and optimization of functional MRI analyses, Hum. Brain Mapp., 4(3), 153–167.
53. Hossein-Zadeh, G. A., Ardekani, B. A., & Soltanian-Zadeh, H. (2003). Activation detection in fMRI using a maximum energy ratio statistic obtained by adaptive spatial filtering, IEEE Trans. Med. Img., 22(7), 795–805.
54. Roche, A., Lahaye, P. J., & Poline, J. B. (2004). Incremental activation detection in fMRI series using Kalman filtering, 2nd IEEE Int’l Symp. on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821), Arlington, VA, USA, 1, 376–379.
55. M. Singh, J. J. L. Al-Dayeh, Kim, T., & P. Colletti, (1999). Cross-correlation technique to identify activated pixels in a three-condition fMRI task, IEEE Trans. Nucl. Sci., 46(3), 520–526.
56. Ruttimann, U. E., & Unser M., Rawlings, R.R., Rio, D., Ramsey, N.F., Mattay, V.S., Hommer, D.W., Frank, J.A., Weinberger, D.R. (1998). Statistical analysis of functional MRI data in the wavelet domain, IEEE Trans. Med. Imaging, 17(2), 142–154.
57. Lai, S.-H. & Fang, M., (1999). A novel local PCA-Based method for detecting activation signals in fMRI, Magn. Reson. Imaging, 17(6), 827–836.
58. Tzikas, D. G., Likas, A., Galatsanos, N. P., Lukic, A. S. & Wernick, M. N. (2004). Bayesian regression of functional neuroimages, 12th European Signal Proc. Conf., Vienna, Austria, 801–804.
59. Ferreira da Silva, A. R. (2011). A Bayesian multilevel model for fMRI data analysis, Comput. Meth. Prog Biomed., 102(3), 238–252.
60. Akhbari, M., Babaie-Zadeh, M., Fatemizadeh, E. & Jutten, C., (2010). An entropy based method for activation detection of functional MRI data using Independent Component Analysis, IEEE Int’l Conf. on Acoustics, Speech and Signal Processing, Dallas, TX, USA, 2014–2017.
61. Tang, X., Zeng, W., Shi, Y., & Zhao, L. (2018). Brain activation detection by modified neighborhood one-class SVM on fMRI data, Biomed. Signal Process. Control, 39(Supp. C), 448–458.
62. Efron, B., Hastie, T., Johnstone, I. & Tibshirani, R. (2004). Least Angle Regression, Ann. Stat., 32(2), 407–499
63. Friston, K. J., Jezzard, P. & Turner, R., (1994). Analysis of functional MRI time-series, Hum. Brain Mapp., 1(2), 153–171
64. Friston, K. J., Holmes, A.P., Poline, J.B., Grasby, P.J., Williams, S.C., Frackowiak, R.S., & Turner, R. ( 1995) Analysis of fMRI Time-Series Revisited, NeuroImage, 2(1), 45–53
65. Robinson, L. F., Wager, T. D., & Lindquist, M. A. (2010). Change point estimation in multi-subject fMRI studies, NeuroImage, 49(2), 1581–1592.
66. Lindquist, M. A., Waugh, C., & Wager, T. D. (2007). Modeling state-related fMRI activity using change-point theory, NeuroImage, 35(3), 1125–1141.
67. Barnett, I. & Onnela, J.-P. (2016). Change Point Detection in Correlation Networks, Sci. Rep., 6, 18893.
68. Gorgolewski, K. J., Storkey, A., Bastin, M.E., Whittle, I.R., Wardlaw, J.M., & Pernet, C.R. (2013). A test-retest fMRI dataset for motor, language and spatial attention functions, GigaScience, 2(1), 6
69. Friston, K. J., Frith, C. D., Frackowiak, R. S. J. & Turner, R., (1995). Characterizing Dynamic Brain Responses with fMRI: A Multivariate Approach, NeuroImage, 2(2 Part A): 166–172.
70. Collignon, A., Maes, F., Delaere, D., Vandermeulen, D., Suetens, P. &Marchal, G., (2015). Automated multi-modality image registration based on information theory, Compt. Imag. and Vis., 3, 263–274.
71. Evans, A. C., Collins, D. L., Mills, S. R., Brown, E. D., Kelly, R.L. & Peters, T. M. (1993). 3D statistical neuroanatomical models from 305 MRI volumes, IEEE Nucl. Sci. Symp. and Med. Imag. Conf., San Francisco, CA, USA, 3, 813–1817.
72. Ebner, N. C., Riediger, M., & Lindenberger, U., (2010). FACES--a database of facial expressions in young, middle-aged, and older women and men: development and validation, Behav. Res. Methods, 42(1), 351–362.
73. Grubbs, F. E., (1969). Procedures for Detecting Outlying Observations in Samples, Technometrics, 11(1), 1–21.
74. Candemir, C., (2018). Change Point Estimation in Multi Subject Social Support fMRI Studies, PhD Thesis, Int’l Computer Institute, Ege University, Izmir, Turkey.