Brain multi-contrast, multi-atlas segmentation of diffusion tensor imaging and ensemble learning automatically diagnose late-life depression.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
20 Dec 2023
20 Dec 2023
Historique:
received:
01
08
2023
accepted:
13
12
2023
medline:
21
12
2023
pubmed:
21
12
2023
entrez:
20
12
2023
Statut:
epublish
Résumé
We investigated the potential of machine learning for diagnostic classification in late-life major depression based on an advanced whole brain white matter segmentation framework. Twenty-six late-life depression and 12 never depressed individuals aged > 55 years, matched for age, MMSE, and education underwent brain diffusion tensor imaging and a multi-contrast, multi-atlas segmentation in MRIcloud. Fractional anisotropy volume, mean fractional anisotropy, trace, axial and radial diffusivity (RD) extracted from 146 white matter parcels for each subject were used to train and test the AdaBoost classifier using stratified 12-fold cross validation. Performance was evaluated using various measures. The statistical power of the classifier was assessed using label permutation test. Statistical analysis did not yield significant differences in DTI measures between the groups. The classifier achieved a balanced accuracy of 71% and an Area Under the Receiver Operator Characteristic Curve (ROC-AUC) of 0.81 by trace, and a balanced accuracy of 70% and a ROC-AUC of 0.80 by RD, in limbic, cortico-basal ganglia-thalamo-cortical loop, brainstem, external and internal capsules, callosal and cerebellar structures. Both indices shared important structures for classification, while fornix was the most important structure for classification by both indices. The classifier proved statistically significant, as trace and RD ROC-AUC scores after permutation were lower than those obtained with the actual data (P = 0.022 and P = 0.024, respectively). Similar results were obtained with the Gradient Boosting classifier, whereas the RBF-kernel Support Vector Machine with k-best feature selection did not exceed the chance level. Finally, AdaBoost significantly predicted the class using all features together. Limitations are discussed. The results encourage further investigation of the implemented methods for computer aided diagnostics and anatomically informed therapeutics.
Identifiants
pubmed: 38123613
doi: 10.1038/s41598-023-49935-z
pii: 10.1038/s41598-023-49935-z
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
22743Informations de copyright
© 2023. The Author(s).
Références
Allan, C. E., Ebmeier, K. B. & Valkanova, V. Depression in older people is underdiagnosed. Practitioner 58(1771), 19–23 (2014).
Byers, A. L. & Yaffe, K. Depression and risk of developing dementia. Nat. Rev. Neurol. 7(6), 323–331 (2011).
pubmed: 21537355
pmcid: 3327554
doi: 10.1038/nrneurol.2011.60
Robinson, A. C. et al. Mid to late-life scores of depression in the cognitively healthy are associated with cognitive status and Alzheimer’s disease pathology at death. Int. J. Geriatr. Psychiatry 36(5), 713–721. https://doi.org/10.1002/gps.5470 (2021).
doi: 10.1002/gps.5470
pubmed: 33176024
Smagula, S. F. & Aizenstein, H. J. Brain structural connectivity in late-life major depressive disorder. Biol. Psychiatry Cognit. Neurosci. Neuroimag. 1(3), 271–277 (2016).
Khundakar, A. A. & Thomas, A. J. Cellular morphometry in late-life depression: A review of postmortem studies. Am. J. Geriatric Psychiatry 22(2), 122–132 (2014).
doi: 10.1016/j.jagp.2013.06.003
Tsopelas, C. et al. Neuropathological correlates of late-life depression in older people. Br. J. Psychiatry 198(2), 109–114. https://doi.org/10.1192/bjp.bp.110.078816 (2011).
doi: 10.1192/bjp.bp.110.078816
pubmed: 21282780
Wen, M. C., Steffens, D. C., Chen, M. K. & Zainal, N. H. Diffusion tensor imaging studies in late-life depression: Systematic review and meta-analysis. Int. J. Geriatr. Psychiatry 29(12), 1173–1184 (2014).
pubmed: 24798480
doi: 10.1002/gps.4129
Wen, J. et al. Characterizing heterogeneity in neuroimaging, cognition, clinical symptoms, and genetics among patients with late-life depression. JAMA Psychiat. 79(5), 464 (2022).
doi: 10.1001/jamapsychiatry.2022.0020
Firbank, M. J. et al. Relationship between progression of brain white matter changes and late-life depression: 3-year results from the LADIS study. Br. J. Psychiatry 201(1), 40–45 (2012).
pubmed: 22626634
doi: 10.1192/bjp.bp.111.098897
Bezerra, D. M. et al. DTI voxelwise analysis did not differentiate older depressed patients from older subjects without depression. J. Psychiatr. Res. 46(12), 1643–1649 (2012).
pubmed: 23040088
doi: 10.1016/j.jpsychires.2012.09.001
Choi, K. S. et al. Reconciling variable findings of white matter integrity in major depressive disorder. Neuropsychopharmacology 39(6), 1332–1339 (2014).
pubmed: 24352368
pmcid: 3988550
doi: 10.1038/npp.2013.345
Jones, E. C., Liebel, S. W., Hallowell, E. S. & Sweet, L. H. Insula thickness asymmetry relates to risk of major depressive disorder in middle-aged to older adults. Psychiatry Res. Neuroimag. 283, 113–117 (2019).
doi: 10.1016/j.pscychresns.2018.12.011
Shatte, A. B. R., Hutchinson, D. M. & Teague, S. J. Machine learning in mental health: a scoping review of methods and applications. Psychol. Med. 49(9), 1426–1448 (2019).
pubmed: 30744717
doi: 10.1017/S0033291719000151
Zhang, L. et al. Hybrid representation learning for cognitive diagnosis in late-life depression over 5 years with structural MRI. https://doi.org/10.48550/arxiv.2212.12810 (2022).
Lin, C. et al. Automatic diagnosis of late-life depression by 3D convolutional neural networks and cross-sample Entropy analysis from resting-state fMRI. Brain Imaging Behav. 17(1), 125–135 (2023).
pubmed: 36418676
doi: 10.1007/s11682-022-00748-0
Patel, M. et al. Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction. Int. J. Geriatric Psychiatry. 30(10), 1056–1067 (2015).
Stolicyn, A. et al. Automated classification of depression from structural brain measures across two independent community-based cohorts. Hum. Brain Mapp. 41(14), 3922–3937 (2020).
pubmed: 32558996
pmcid: 7469862
doi: 10.1002/hbm.25095
Gao, S., Calhoun, V. D. & Sui, J. Machine learning in major depression: From classification to treatment outcome prediction. CNS Neurosci. Ther. 24(11), 1037–1052 (2018).
pubmed: 30136381
pmcid: 6324186
doi: 10.1111/cns.13048
Rashidi-Ranjbar, N., Miranda, D., Butters, M. A., Mulsant, B. H. & Voineskos, A. N. Evidence for structural and functional alterations of frontal-executive and corticolimbic circuits in late-life depression and relationship to mild cognitive impairment and dementia: A systematic review. Front. Neurosci. 14, 253. https://doi.org/10.3389/fnins.2020.00253 (2020).
doi: 10.3389/fnins.2020.00253
pubmed: 32362808
pmcid: 7182055
Winter, N. R. et al. Quantifying deviations of brain structure and function in major depressive disorder across neuroimaging modalities. JAMA Psychiat. 79(9), 879–888 (2022).
doi: 10.1001/jamapsychiatry.2022.1780
Oishi, K. et al. Atlas-based whole brain white matter analysis using large deformation diffeomorphic metric mapping: Application to normal elderly and Alzheimer’s disease participants. Neuroimage 46(2), 486–499 (2009).
pubmed: 19385016
doi: 10.1016/j.neuroimage.2009.01.002
Alexopoulos, G. S. Frontostriatal and limbic dysfunction in late-life depression. Am. J. Geriatr. Psychiatry 10(6), 687–695 (2002).
pubmed: 12427577
doi: 10.1097/00019442-200211000-00007
Phillips, M. L., Drevets, W. C., Rauch, S. L. & Lane, R. D. Neurobiology of emotion perception II: Implications for major psychiatric disorders. Biol. Psychiatry 54(5), 515–528 (2003).
pubmed: 12946880
doi: 10.1016/S0006-3223(03)00171-9
Smith, G. S. et al. Positron emission tomography imaging of serotonin degeneration and beta-amyloid deposition in late-life depression evaluated with multi-modal partial least squares. Transl. Psychiatry 11, 473 (2021).
pubmed: 34518514
pmcid: 8437937
doi: 10.1038/s41398-021-01539-9
Wilson, R. et al. Late-life depression is not associated with dementia-related pathology. Neuropsychology (Journal) 30(2), 135–142 (2016).
doi: 10.1037/neu0000223
Sexton, C. E. et al. Magnetic resonance imaging in late-life depression: Multimodal examination of network disruption. Arch. General Psychiatry 69(7), 680–689 (2012).
doi: 10.1001/archgenpsychiatry.2011.1862
Li, W. et al. Effects of the coexistence of late-life depression and mild cognitive impairment on white matter microstructure. J. Neurol. Sci. 338(1–2), 46–56 (2014).
pubmed: 24387897
doi: 10.1016/j.jns.2013.12.016
Shen, X. et al. White matter microstructure and its relation to longitudinal measures of depressive symptoms in mid- and late life. Biol. Psychiatry 86(10), 759–768 (2019).
pubmed: 31443934
pmcid: 6906887
doi: 10.1016/j.biopsych.2019.06.011
Touron, E. et al. Depressive symptoms in cognitively unimpaired older adults are associated with lower structural and functional integrity in a frontolimbic network. Mol. Psychiatry 27(12), 5086–5095 (2022).
pubmed: 36258017
pmcid: 9763117
doi: 10.1038/s41380-022-01772-8
Fang, P. et al. Increased cortical-limbic anatomical network connectivity in major depression revealed by diffusion tensor imaging. PLOS ONE 7(9), e45972 (2012).
pubmed: 23049910
pmcid: 3458828
doi: 10.1371/journal.pone.0045972
Sexton, C. E., Mackay, C. E. & Ebmeier, K. P. A systematic review and meta-analysis of magnetic resonance imaging studies in late-life depression. Am. J. Geriatric Psychiatry 21(2), 184–195 (2013).
doi: 10.1016/j.jagp.2012.10.019
Butters, M. A. et al. Three-dimensional surface mapping of the caudate nucleus in late-life depression. Am. J. Geriatric Psychiatry 17(1), 4–12 (2009).
doi: 10.1097/JGP.0b013e31816ff72b
Kumar, A. et al. Biophysical changes in normal-appearing white matter and subcortical nuclei in late-life major depression detected using magnetization transfer. Psychiatry Res. Neuroimaging 130(2), 131–140 (2004).
doi: 10.1016/j.pscychresns.2003.12.002
Laird, K. T. et al. Anxiety symptoms are associated with smaller insular and orbitofrontal cortex volumes in late-life depression. J. Affect. Disord. 256, 282–287 (2019).
pubmed: 31200165
pmcid: 6750975
doi: 10.1016/j.jad.2019.05.066
Yuen, G. S. et al. The salience network in the apathy of late-life depression. Int. J. Geriatr. Psychiatry 29(11), 1116–1124 (2014).
pubmed: 24990625
pmcid: 4197060
doi: 10.1002/gps.4171
Alalade, E., Denny, K., Potter, G. G., Steffens, D. C. & Wang, L. V. Altered cerebellar-cerebral functional connectivity in geriatric depression. PLOS ONE 6(5), e20035 (2011).
pubmed: 21637831
pmcid: 3102667
doi: 10.1371/journal.pone.0020035
Alexopoulos, G. S. et al. Functional connectivity in apathy of late-life depression: A preliminary study. J. Affect. Disord. 149(1–3), 398–405 (2013).
pubmed: 23261142
doi: 10.1016/j.jad.2012.11.023
Zang, J. et al. Effects of brain atlases and machine learning methods on the discrimination of schizophrenia patients: A multimodal MRI study. Front. Neurosci. 15, 697168. https://doi.org/10.3389/fnins.2021.697168 (2021).
doi: 10.3389/fnins.2021.697168
pubmed: 34385901
pmcid: 8353157
Folstein, M. F., Folstein, S. E. & McHugh, P. R. “Mini-mental state”. A practical method for grading the cognitive state of patients for the clinician. J. Psychiatric Res. 12(3), 189–198 (1975).
doi: 10.1016/0022-3956(75)90026-6
Fountoulakis, K. N. et al. The validation of the short form of the Geriatric Depression Scale (GDS) in Greece. Aging (Milan, Italy) 11(6), 367–372 (1999).
pubmed: 10738851
Mori, S. et al. MRICloud: Delivering high-throughput MRI neuroinformatics as cloud-based software as a service. Comput. Sci. Eng. 18(5), 21–35 (2016).
doi: 10.1109/MCSE.2016.93
Ceritoglu, C. et al. Multi-contrast large deformation diffeomorphic metric mapping for diffusion tensor imaging. NeuroImage 47(2), 618–627 (2009).
pubmed: 19398016
doi: 10.1016/j.neuroimage.2009.04.057
Rezende, T. J. R. et al. Test-retest reproducibility of a multi-atlas automated segmentation tool on multimodality brain MRI. Brain Behav. 9(10), e01363 (2019).
pubmed: 31483562
pmcid: 6790328
doi: 10.1002/brb3.1363
Penny, W. D., Friston, K. J., Ashburner, J. T., Kiebel, S. J. & Nichols, T. E. Statistical Parametric Mapping: The Analysis of Functional Brain Images (Academic Press, 2011).
Li, Y. et al. Image corruption detection in diffusion tensor imaging for post-processing and real-time monitoring. PLOS ONE 8(10), e49764 (2013).
pubmed: 24204551
pmcid: 3808367
doi: 10.1371/journal.pone.0049764
Tang, X. et al. Multi-contrast multi-atlas Parcellation of diffusion tensor imaging of the human brain. PLOS ONE 9(5), e96985 (2014).
pubmed: 24809486
pmcid: 4014574
doi: 10.1371/journal.pone.0096985
Wang, H. Multi-atlas segmentation with joint label fusion. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 611–623 (2013).
pubmed: 22732662
doi: 10.1109/TPAMI.2012.143
van Jiang, H., Zijl, P. C., Kim, J., Pearlson, G. D. & Mori, S. DtiStudio: Resource program for diffusion tensor computation and fiber bundle tracking. Computer Methods Programs Biomed. 81(2), 106–116 (2006).
doi: 10.1016/j.cmpb.2005.08.004
Freund, Y. & Schapire, R. E. A desicion-theoretic generalization of on-line learning and an application to boosting. SpringerLink (1995). https://doi.org/10.1007/3-540-59119-2_166 .
Zhu, J., Zou, H., Rosset, S. & Hastie, T. Multi-class AdaBoost. Stat. Interface. 2, 349–360 (2009).
doi: 10.4310/SII.2009.v2.n3.a8
Pedregosa, F. et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
Friedman, J. H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001).
Chang, C.-C. & Lin, C.-J. LIBSVM. ACM Trans. Intell. Syst. Technol. 2, 1–27 (2011).
doi: 10.1145/1961189.1961199
Galar, M., Fernández, A. Á., Barrenechea, E., Bustince, H. & Herrera, F. A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans. Syst. Man Cybernet. 42(4), 463–484 (2012).
doi: 10.1109/TSMCC.2011.2161285
Fawcett, T. An introduction to ROC analysis. Pattern Recognit. Lett. 27(8), 861–874 (2006).
doi: 10.1016/j.patrec.2005.10.010
Cui, Z., Xia, Z., Su, M., Shu, H. & Gong, G. Disrupted white matter connectivity underlying developmental dyslexia: A machine learning approach. Hum. Brain Mapp. 37(4), 1443–1458 (2016).
pubmed: 26787263
pmcid: 6867308
doi: 10.1002/hbm.23112
Good, P. I. Permutation Tests: A Practical Guide to Resampling Methods for Testing Hypotheses (Springer Science & Business Media, 2000).
doi: 10.1007/978-1-4757-3235-1