Subject-Specific Scalar-on-Image Regression
Volume 24, Issue 1 (2026): Special Issue: Statistical aspects of Trustworthy Machine Learning, pp. 167–186
Pub. online: 13 November 2025
Type: Statistical Data Science
Open Access
Open Access
†
Contributed equally.
Received
9 January 2025
9 January 2025
Accepted
9 October 2025
9 October 2025
Published
13 November 2025
13 November 2025
Abstract
Neuroimaging technology has received considerable attention in recent years. One of the key problems in the imaging data analysis is the heterogeneity among individual subjects. In particular, the relationship between the imaging biomarkers and the clinical outcomes may vary across different individuals. Popular existing statistical methodologies such as the functional linear regression and high dimensional linear regression can be inadequate because the homogeneous regression relationship is assumed for all subjects. In this paper, we propose the Subject-Specific Scalar-on-Image Regression (S3IR) model to handle heterogeneous populations. Specifically, we utilize a binary subject-specific masking image to capture the heterogeneous sparsity among individuals. The proposed S3IR model incorporates the spatial structure of the imaging data and is able to achieve both local smoothness and subject-specific sparsity of the estimated regression coefficients. Furthermore, we design an EM-type adaptive algorithm to estimate the model coefficients. Simulation studies are presented to show the superior performance of our proposed method over some existing ones in handling heterogeneity. Finally, we apply the S3IR model to analyze data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The results show that our model can effectively identify interpretable and significant disease-related regions and improve prediction performance of the cognitive scores.
Supplementary material
Supplementary MaterialThe detailed algorithms for the estimation procedure, model selection, and the prediction are included in supplementary materials.
References
Besag J (1986). On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society. Series B (Methodological), 259–302. https://doi.org/10.1111/j.2517-6161.1986.tb01412.x
Carroll MK, Cecchi GA, Rish I, Garg R, Rao AR (2009). Prediction and interpretation of distributed neural activity with sparse models. NeuroImage, 44(1): 112–122. https://doi.org/10.1016/j.neuroimage.2008.08.020
Casanova R, Barnard RT, Gaussoin SA, Saldana S, Hayden KM, Manson JE, et al. (2018). Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer’s disease across imaging databases. NeuroImage, 183: 401–411. https://doi.org/10.1016/j.neuroimage.2018.08.040
Chan D, Fox NC, Scahill RI, Crum WR, Whitwell JL, Leschziner G, et al. (2001). Patterns of temporal lobe atrophy in semantic dementia and Alzheimer’s disease. Annals of Neurology, 49(4): 433–442. https://doi.org/10.1002/ana.92
Cheng B, Zhang D, Chen S, Shen D (2011). Predicting clinical scores using semi-supervised multimodal relevance vector regression. In: Machine Learning in Medical Imaging. Suzuki K, Wang F, Shen D, Yan P (eds). Lecture Notes in Computer Science, Vol. 7009. Springer Berlin Heidelberg, Berlin, Heidelberg. 241–248. https://doi.org/10.1007/978-3-642-24319-6_30
Fan Y, Gur RE, Gur RC, Wu X, Shen D, Calkins ME, et al. (2008). Unaffected family members and schizophrenia patients share brain structure patterns: A high-dimensional pattern classification study. Biological Psychiatry, 63(1): 118–124. https://doi.org/10.1016/j.biopsych.2007.03.015
Feng X, Li T, Song X, Zhu H (2019). Bayesian scalar on image regression with nonignorable nonresponse. Journal of the American Statistical Association, 115(532): 1574–1597. https://doi.org/10.1080/01621459.2019.1686391
Fonov V, Evans AC, Botteron K, Almli CR, McKinstry RC, Collins DL (2011). Unbiased average age-appropriate atlases for pediatric studies. NeuroImage, 54(1): 313–327. https://doi.org/10.1016/j.neuroimage.2010.07.033
Goldsmith J, Bobb J, Crainiceanu CM, Caffo B, Reich D (2011). Penalized functional regression. Journal of Computational and Graphical Statistics, 20(4): 830–851. https://doi.org/10.1198/jcgs.2010.10007
Grosenick L, Klingenberg B, Katovich K, Knutson B, Taylor JE (2013). Interpretable whole-brain prediction analysis with GraphNet. NeuroImage, 72: 304–321. https://doi.org/10.1016/j.neuroimage.2012.12.062
Hirono N, Mori E, Ishii K, Ikejiri Y, Imamura T, Shimomura T, et al. (1998). Frontal lobe hypometabolism and depression in Alzheimer’s disease. Neurology, 50(2): 380–383. https://doi.org/10.1212/WNL.50.2.380
Hoerl AE, Kennard RW (1970). Ridge regression: Biased estimation for nonorthogonal problems. Technometrics, 12(1): 55–67. https://doi.org/10.1080/00401706.1970.10488634
Hoshikawa T (2013). Mixture regression for observational data, with application to functional regression models. arXiv preprint: https://arxiv.org/abs/1307.0170.
Huang L, Jin Y, Gao Y, Thung KH, Shen D (2016). Longitudinal clinical score prediction in Alzheimer’s disease with soft-split sparse regression based random forest. Neurobiology of Aging, 46: 180–191. https://doi.org/10.1016/j.neurobiolaging.2016.07.005
Hurn M, Justel A, Robert CP (2003). Estimating mixtures of regressions. Journal of Computational and Graphical Statistics, 12(1): 55–79. https://doi.org/10.1198/1061860031329
Jiang Z, He W, Kirby M, Asiri S, Yan D (2021). Weakly supervised spatial deep learning based on imperfect vector labels with registration errors. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD ’21). Association for Computing Machinery, New York, NY, USA. 767–775. https://doi.org/10.1145/3447548.3467301
Kang J, Reich BJ, Staicu AM (2018). Scalar-on-image regression via the soft-thresholded Gaussian process. Biometrika, 105(1): 165–184. https://doi.org/10.1093/biomet/asx075
Killiany RJ, Moss MB, Albert MS, Sandor T, Tieman J, Jolesz F (1993). Temporal lobe regions on magnetic resonance imaging identify patients with early Alzheimer’s disease. Archives of Neurology, 50(9): 949–954. https://doi.org/10.1001/archneur.1993.00540090052010
Li B, Qi P, Liu B, Di S, Liu J, Pei J, et al. (2023). Trustworthy AI: From principles to practices. ACM Computing Surveys, 55(9): 177. https://doi.org/10.1145/3555803
Li C, Wang X, Du G, Chen H, Brown G, Lewis MM, et al. (2021). Folded concave penalized learning of high-dimensional MRI data in Parkinson’s disease. Journal of Neuroscience Methods, 357: 109157. https://doi.org/10.1016/j.jneumeth.2021.109157
Liu LYF, Liu Y, Zhu H (2018). SMAC: Spatial multi-category angle-based classifier for high-dimensional neuroimaging data. NeuroImage, 175: 230–245. https://doi.org/10.1016/j.neuroimage.2018.03.040
Liu Y, Yan B, Merikangas K, Shou H (2017). Total variation regularized tensor-on-scalar regression. arXiv preprint: https://arxiv.org/abs/1703.05264.
Maheux E, Koval I, Ortholand J, Birkenbihl C, Archetti D, Bouteloup V, et al. (2023). Forecasting individual progression trajectories in Alzheimer’s disease. Nature Communications, 14(1): 761. https://doi.org/10.1038/s41467-022-35712-5
Morris JS (2015). Functional regression. Annual Review of Statistics and Its Application, 2: 321–359. https://doi.org/10.1146/annurev-statistics-010814-020413
Petersen RC, Thomas RG, Grundman M, Bennett D, Doody R, Ferris S, et al. (2005). Vitamin E and donepezil for the treatment of mild cognitive impairment. New England Journal of Medicine, 352(23): 2379–2388. https://doi.org/10.1056/NEJMoa050151
Ramsay JO, Silverman BW (2005). Functional Data Analysis. Wiley, Hoboken, NJ. https://doi.org/10.1002/0470013192.bsa239
Raz G, Svanera M, Singer N, Gilam G, Cohen MB, Lin T, et al. (2017). Robust inter-subject audiovisual decoding in functional magnetic resonance imaging using high-dimensional regression. NeuroImage, 163: 244–263. https://doi.org/10.1016/j.neuroimage.2017.09.032
Reiss PT, Huo L, Zhao Y, Kelly C, Ogden RT (2015). Wavelet-domain regression and predictive inference in psychiatric neuroimaging. The Annals of Applied Statistics, 9(2): 1076–1101. https://doi.org/10.1214/15-AOAS829
Reiss PT, Ogden RT (2007). Functional principal component regression and functional partial least squares. Journal of the American Statistical Association, 102(479): 984–996. https://doi.org/10.1198/016214507000000527
Rosen W, Mohs R, Davis K (1984). A new rating scale for Alzheimer’s disease. The American Journal of Psychiatry, 141(11): 1356–1364. https://doi.org/10.1176/ajp.141.11.1356
Santos S, Almeida I, Oliveiros B, Castelo-Branco M (2016). The role of the amygdala in facial trustworthiness processing: A systematic review and meta-analyses of fMRI studies. PLOS ONE, 11(11): 1–28. https://doi.org/10.1371/journal.pone.0167276
Stonnington CM, Chu C, Klöppel S, Jack Jr CR, Ashburner J, Frackowiak RS, et al. (2010). Predicting clinical scores from magnetic resonance scans in Alzheimer’s disease. Neuroimage, 51(4): 1405–1413. https://doi.org/10.1016/j.neuroimage.2010.03.051
Tibshirani R (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological), 58(1): 267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
Toiviainen P, Alluri V, Brattico E, Wallentin M, Vuust P (2014). Capturing the musical brain with Lasso: Dynamic decoding of musical features from fMRI data. NeuroImage, 88: 170–180. https://doi.org/10.1016/j.neuroimage.2013.11.017
Viele K, Tong B (2002). Modeling with mixtures of linear regressions. Statistics and Computing, 12(4): 315–330. https://doi.org/10.1023/A:1020779827503
Wang JL, Chiou JM, Müller HG (2016a). Functional data analysis. Annual Review of Statistics and Its Application, 3: 257–295. https://doi.org/10.1146/annurev-statistics-041715-033624
Wang S, Huang M, Wu X, Yao W (2016b). Mixture of functional linear models and its application to CO${_{2}}$–GDP functional data. Computational Statistics & Data Analysis, 97: 1–15. https://doi.org/10.1016/j.csda.2015.11.008
Wang X, Nan B, Zhu J, Koeppe R (2014). Regularized 3D functional regression for brain image data via Haar wavelets. The Annals of Applied Statistics, 8(2): 1045–1064. https://doi.org/10.1214/14-AOAS736
Wang X, Zhu H (2017). Generalized scalar-on-image regression models via total variation. Journal of the American Statistical Association, 112(519): 1156–1168. https://doi.org/10.1080/01621459.2016.1194846
Winston JS, Strange BA, O’Doherty J, Dolan RJ (2002). Automatic and intentional brain responses during evaluation of trustworthiness of faces. Nature Neuroscience, 5(3): 277–283. https://doi.org/10.1038/nn816
Yuan M, Cai TT (2010). A reproducing kernel Hilbert space approach to functional linear regression. The Annals of Statistics, 38(6): 3412–3444. https://doi.org/10.1214/09-AOS772
Zhang Y, Brady M, Smith S (2001). Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Transactions on Medical Imaging, 20(1): 45–57. https://doi.org/10.1109/42.906424
Zhu H, Li T, Zhao B (2023). Statistical learning methods for neuroimaging data analysis with applications. Annual Review of Biomedical Data Science, 6(1): 73–104. https://doi.org/10.1146/annurev-biodatasci-020722-100353
Zhu H, Shen D, Peng X, Liu LY (2017). MWPCR: Multiscale Weighted Principal Component Regression for High-Dimensional Prediction. Journal of the American Statistical Association, 112(519): 1009–1021. https://doi.org/10.1080/01621459.2016.1261710
Zou H, Hastie T (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2): 301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x
