A Comparative Study of White Matter, Gray Matter, and Cerebrospinal Fluid Volumes in Schizophrenia and Healthy Controls Using MRI

This study reports significant changes in cerebrospinal fluid (CSF) volumes in people with schizophrenia and shows that global tissue volumes have sufficient discriminative power. Out of the classifiers that were tested, the one that performed best was the Random Forest classifier, with accuracy of 75.3% and ROC-AUC of 0.780. The study highlights the importance of structural MRI volumetry and also sheds light on the usefulness of ensembles in neuroimaging classification tasks. Future research should focus on employing more sophisticated techniques in segmentation, regional morphometry analysis, and using multiple modality features.

[1] M. R. Arbabshirani, S. Plis, J. Sui, and V. D. Calhoun, “Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls,” NeuroImage, vol. 145, pp. 137–165, 2017, doi: 10.1016/j.neuroimage.2016.02.079. [2] M. S. Bagary, M. R. Symms, G. J. Barker, S. H. Mutsatsa, E. M. Joyce, and M. A. Ron, “Gray and white matter brain abnormalities in first-episode schizophrenia inferred from magnetization transfer imaging,” Archives of General Psychiatry, vol. 60, no. 8, pp. 779–788, 2003, doi: 10.1001/archpsyc.60.8.779. [3] V. L. Cropley, P. Klauser, R. K. Lenroot, J. Bruggemann, S. Sundram, C. Bousman, A. Pereira, M. A. Di Biase, T. W. Weickert, C. S. Weickert, C. Pantelis, and A. Zalesky, “Accelerated gray and white matter deterioration with age in schizophrenia,” American Journal of Psychiatry, vol. 174, no. 3, pp. 286–295, 2017, doi: 10.1176/appi.ajp.2016.16050610. [4] R. De Filippis, E. Carbone, R. Gaetano, A. Bruni, V. Pugliese, C. Segura-Garcia, and P. De Fazio, “Machine learning techniques in a structural and functional MRI diagnostic approach in schizophrenia: A systematic review,” Neuropsychiatric Disease and Treatment, vol. 15, pp. 1605–1627, 2019, doi: 10.2147/NDT.S202418. [5] H. Göker, “1D-convolutional neural network approach and feature extraction methods for automatic detection of schizophrenia,” Signal, Image and Video Processing, vol. 17, no. 5, pp. 2627–2636, 2023, doi: 10.1007/s11760-022-02479-7. [6] S. V. Haijma, N. van Haren, W. Cahn, P. C. Koolschijn, H. E. Hulshoff Pol, and R. S. Kahn, “Brain volumes in schizophrenia: A meta-analysis in over 18,000 subjects,” Schizophrenia Bulletin, vol. 39, no. 5, pp. 1129–1138, 2013, doi: 10.1093/schbul/sbs118. [7] D. K. Lee, H. Lee, K. Park, E. Joh, C. E. Kim, and S. Ryu, “Common gray and white matter abnormalities in schizophrenia and bipolar disorder,” PLoS ONE, vol. 15, no. 5, Art. no. e0232826, 2020, doi: 10.1371/journal.pone.0232826. [8] J. Oh, B. L. Oh, K. U. Lee, J. H. Chae, and K. Yun, “Identifying schizophrenia using structural MRI with a deep learning algorithm,” Frontiers in Psychiatry, vol. 11, Art. no. 16, 2020, doi: 10.3389/fpsyt.2020.00016. [9] N. N. Raju, “Psychiatry training in India,” Indian Journal of Psychiatry, vol. 64, no. 5, pp. 433–439, 2022, doi: 10.4103/indianjpsychiatry.indianjpsychiatry_649_22. [10] M. E. Shenton, C. C. Dickey, M. Frumin, and R. W. McCarley, “A review of MRI findings in schizophrenia,” Schizophrenia Research, vol. 49, nos. 1–2, pp. 1–52, 2001, doi: 10.1016/S0920-9964(01)00163-3.