A Reproducible Approach to the Analysis of Data Consistency in Neuroimaging Using Open-Source Tools

Studies involving multi-source data analysis often require representation harmonization to address discrepancies caused by technical differences in data acquisition. We describe a reproducible software pipeline for multi-echo functional MRI (fMRI) data, aimed at mapping signals from different echo channels into a common, aligned latent space. The pipeline is based on open data and tools (BIDS, DataLad) and includes preprocessing, time-windowing, and training of lightweight representation alignment models. Efficacy is evaluated using a protocol based on the gain in inter-echo first principal component (ΔPC1) correlation. Using a sample of 100 sessions with a fixed configuration of procedures and hyperparameters, the median ΔPC1 gain was ≈ +0.11, and the proportion of sessions with a positive effect was ≈ 61%, confirming a moderate but consistent improvement. The 95% bootstrap CI for the median does not include zero. This pipeline serves as an open, reproducible baseline for comparison against more complex harmonization methods.

1. Sucholutsky I., Muttenthaler L., Weller A., Peng A., Bobu A., Kim B., Love B. C., Cueva C. J., Grant E., Groen I., Achterberg J., Tenenbaum J. B., Collins K. M., Hermann K. L., Oktar K., Greff K., Hebart M. N., Cloos N., Kriegeskorte N., Jacoby N., Zhang Q., Marjieh R., Geirhos R., Chen S., Kornblith S., Rane S., Konkle T., O'Connell T. P., Unterthiner T., Lampinen A. K., Müller K.-R., Toneva M., Griffiths T. L. Getting aligned on representational alignment. arXiv preprint arXiv:2310.13018, version 3, 2024. DOI: 10.48550/arXiv.2310.13018.

2. Yu M., Linn K. A., Cook P. A., et al. Statistical harmonization corrects site effects in functional connectivity measurements from multi-site fMRI data. Human Brain Mapping, vol. 39, issue 11, 2018, pp. 4213-4227. DOI: 10.1002/hbm.24241.

3. El-Gazzar A., Thomas R. M., van Wingen G. Harmonization techniques for machine learning studies using multi-site functional MRI data. bioRxiv, 2023. DOI: 10.1101/2023.06.14.544758.

4. Kundu P., Inati S.J., Evans J.W., Luh W.M., Bandettini P.A. Differentiating BOLD and non-BOLD signals in fMRI time series using multi-echo EPI. NeuroImage, vol. 60, issue 3, 2012, pp. 1759-1770. DOI: 10.1016/j.neuroimage.2011.12.028.

5. Davis T., Poldrack R. A. Measuring neural representations with fMRI: practices and pitfalls. Annals of the New York Academy of Sciences, vol. 1296, issue 1, 2013, pp. 108–134. DOI: 10.1111/nyas.12156.

6. Lu Z., Wang Y. Teaching CORnet human fMRI representations for enhanced model-brain alignment. Cognitive Neurodynamics, vol. 19, 2025, pp. 61–72. DOI: 10.1007/s11571-025-10252-y.

7. Baker M. 1,500 scientists lift the lid on reproducibility. Nature, vol. 533, issue 7604, 2016, pp. 452-454. DOI: 10.1038/533452a.

8. Lynch C. J., Elbau I., Liston C. Improving precision functional mapping routines with multi-echo fMRI. Current Opinion in Behavioral Sciences, vol. 40, 2021, pp. 113-119. DOI: 10.1016/j.cobeha.2021.03.017.

9. Dorin D., Kiselev N., Grabovoy A., et al. Forecasting fMRI images from video sequences: linear model analysis. Health Information Science and Systems, vol. 12, 2024, 55. DOI: 10.1007/s13755-024-00315-5.

10. Giubergia A., Ferrazzi G., Castellaro M., et al. Multi-echo versus single-echo EPI sequences for task-fMRI: A comparative study. Imaging Neuroscience, vol. 3, 2025, IMAG.a.94. DOI: 10.1162/IMAG.a.94.

11. Halchenko Y. O., Meyer K., Poldrack B. et al. DataLad: distributed system for joint management of code, data, and their relationship. Journal of Open Source Software, vol. 6, issue 63, 2021, 3262. DOI: 10.21105/joss.03262.

12. Поляков А. Н., Енягина И. М., Коковин Д. С. Распределенная модульная платформа «Цифровая Лаборатория» как среда для проведения научных исследований и разработок НИЦ «Курчатовский Институт». Труды ИСП РАН, том 32, вып. 5, 2020 г., стр. 143-152. DOI: 10.15514/ISPRAS-2020-32(5)-11. / Polyakov A.N., Enyagina I.M., Kokovin D.S. "Digital Lab" Platform as an Environment for Scientific Research and Development at the Kurchatov Institute. Trudy ISP RAN/Proc. ISP RAS, 2020, vol. 32, issue 5, pp. 143-152 (in Russian). DOI: 10.15514/ISPRAS-2020-32(5)-11.

13. Рогов А., Гамилов Т., Брагина А., и др. Synthetic pulse wave dataset for analysis of vascular ageing in elderly patients. Mathematical Modelling of Natural Phenomena, 19, 2024, 20. DOI: 10.1051/mmnp/2024017.

14. Spreng R. N., Setton R., Alter U., et al. Neurocognitive aging data release with behavioral, structural, and multi-echo functional MRI measures. OpenNeuro, 2022. DOI: 10.18112/openneuro.ds003592.v1.0.13.

15. Friston K. J., Holmes A. P., Worsley K. J., et al. Statistical parametric maps in functional imaging: a general linear approach. Human Brain Mapping, vol. 2, issue 4, 1994, pp. 189-210. DOI: 10.1002/hbm.460020402.

16. Friston K. J., Frith C. D., Liddle P. F., Frackowiak R. S. J. Functional connectivity: the principal-component analysis of large (PET) data sets. Journal of Cerebral Blood Flow & Metabolism, 1993, vol. 13, issue 1, pp. 5-14. DOI: 10.1038/jcbfm.1993.4.

17. Pearson K. Mathematical Contributions to the Theory of Evolution. III. Regression, Heredity, and Panmixia. Philosophical Transactions of the Royal Society of London. A, vol. 187, 1896, pp. 253-318. DOI: 10.1098/rsta.1896.0007.

18. Van Den Heuvel M. P., Pol H. E. H. Exploring the Brain Network: A Review on Resting-State fMRI Functional Connectivity. European neuropsychopharmacology, vol. 20, issue 8, 2010, pp. 519-534. DOI: 10.1016/j.euroneuro.2010.03.008.

19. Ingalhalikar M., Shinde S., Karmarkar A., Rajan A., Rangaprakash D., Deshpande G. Functional connectivity-based prediction of Autism on site harmonized ABIDE dataset. IEEE Transactions on Biomedical Engineering, vol. 68, issue 11, 2021, pp. 3254-3263. DOI: 10.1109/TBME.2021.3080259.

20. Hoerl A. E., Kennard R. W. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, vol. 12, issue 1, 1970, pp. 55-67. DOI: 10.1080/00401706.1970.10488634.

21. Sun Y., et al. RSAD: Region-Specific Anomaly Detection in fMRI for Disease Diagnosis. В: Medical Image Computing and Computer Assisted Intervention – MICCAI 2025. Lecture Notes in Computer Science, vol 15975. Springer, Cham, 2025, pp. 516-526. DOI: 10.1007/978-3-032-05325-1_46.

22. Scotti P., Banerjee A., Goode J., et al. Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors. In Proc. of the 37th Conference on Neural Information Processing Systems (NeurIPS), 2023, pp 24705-24728.

23. Yousefnezhad M., Selvitella A., Han L., Zhang D. Supervised hyperalignment for multisubject fMRI data alignment. IEEE Transactions on Cognitive and Developmental Systems, vol. 13, issue 3, 2020, pp. 475–490. DOI: 10.1109/TCDS.2020.2965981.

24. Anderson A., Dinov I. D., Sherin J. E., Quintana J., Yuille A. L., Cohen M. S. Classification of spatially unaligned fMRI scans. NeuroImage, vol. 49, issue 3, 2010, pp. 2509–2519. DOI: 10.1016/j.neuroimage.2009.08.036.

25. Bromley J., Guyon I., LeCun Y., et al. Signature verification using a "siamese" time delay neural network. Advances in Neural Information Processing Systems, vol. 6, 1993.

26. Li X., Zhou Y., Dvornek N., et al. Braingnn: Interpretable brain graph neural network for fmri analysis. Medical Image Analysis, vol. 74, 2021, 102233. DOI: 10.1016/j.media.2021.102233.

27. Kim, P., Kwon, J., Joo, S., Bae, S., Lee, D., Jung, Y., et al. Swift: Swin 4d fmri transformer. Advances in Neural Information Processing Systems, 36, 2023, 42015-42037.

28. Liu, Y., Han, S., Wu, J., Dillenseger, J. L., & Nunes, J. C. Diffusion Model Enhancements for Reliable MRI-to-CT Image Translation. In synthRad2025 Challenge, MICCAI 2025.

29. Tran D., Bourdev L., Fergus R., et al. Learning spatiotemporal features with 3d convolutional networks. Proceedings of the IEEE international conference on computer vision, 2015, pp. 4489-4497. DOI: 10.1109/ICCV.2015.510.

30. Bergstra J., Bengio Y. Random search for hyper-parameter optimization. Journal of Machine Learning Research, vol. 13, 2012, pp. 281-305.

31. Akiba T., Sano S., Yanase T., et al. Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 2623–2631.

32. Kornblith S., Norouzi M., Lee H., et al. Similarity of neural network representations revisited. Proceedings of the 36th International Conference on Machine Learning (ICML), 2019, pp. 3519-3529.

33. Самохина А. М., Нейчев Р. Г., Гончаренко В. В. и др. Модели классификации выборки вызванных потенциалов Р300. Системы и Средства Информатики, том 32, вып. 3, 2022 г., стр. 36-49. DOI: 10.14357/08696527220304. / Samokhina A. M., Neychev R. G., Goncharenko V. V., et al. Classification models for P300 evoked potentials. Sistemy i Sredstva Informatiki, 2022, vol. 32, issue 3, pp. 36-49 (in Russian). DOI: 10.14357/08696527220304.

34. Zhao Q., Kwon D., Pohl K.M. A Riemannian Framework for Longitudinal Analysis of Resting-State Functional Connectivity. В: Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. Lecture Notes in Computer Science, vol 11072. Springer, Cham, 2018, pp. 145-153. DOI: 10.1007/978-3-030-00931-1_17.

35. Andreella, A., De Santis, R., Vesely, A. et al. Procrustes-based distances for exploring between-matrices similarity. Stat Methods Appl, 32, 2023, 867-882. DOI: 10.1007/s10260-023-00689-y.

36. Li, C. et al. (2025). Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15141. Springer, Cham. DOI: 10.1007/978-3-031-73010-8_21.

37. Zvereva A. K., Kaprielova M., Grabovoy A. AnomLite: Efficient binary and multiclass video anomaly detection. Results in Engineering, vol. 25, 2025, 104162. DOI: 10.1016/j.rineng.2025.104162.

38. Yin W., Li L., Wu F. X. Deep learning for brain disorder diagnosis based on fMRI images. Neurocomputing, vol. 469, 2022, pp. 332-345. DOI: 10.1016/j.neucom.2020.05.113.

39. Malkiel, I., Rosenman, G., Wolf, L., & Hendler, T. (2021). Pre-training and fine-tuning transformers for fmri prediction tasks. arXiv preprint arXiv:2112.05761, 105.

40. Kazerouni A., Aghdam E. K., Heidari M., et al. Diffusion models for medical image analysis: A comprehensive survey. arXiv preprint arXiv:2211.07804, 2022. DOI: 10.48550/arXiv.2211.07804.

41. DuPre et al. TE-dependent analysis of multi-echo fMRI with tedana. Journal of Open Source Software, 6(66), 3669. DOI: 10.21105/joss.03669.

42. Thomas A., Ré C., Poldrack R. Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data. Advances in Neural Information Processing Systems, vol. 35, 2022, pp. 21255-21269.

43. Зверева А. К. fMRI_VicReg: программная реализация и результаты анализа. Доступно по адресу: https://github.com/AnnaZverev/fMRI_VicReg, дата обращения: 12.03.2026.