Objective 

Structural MRI-based regional volumes are widely used for Alzheimer’s disease (AD) classification, but inter individual variability in intracranial volume (ICV) introduces confounding. Traditional adjustment methods use region-of interest (ROI)/ICV ratios or residual adjustment during pre-processing, yet no consensus exists on the optimal method. This study tests whether explicitly including ICV as a covariate (ROI + ICV) improves classification compared with ratio, residual adjustment, and the unadjusted baseline. 

Materials and methods 

T1-weighted MRIs from ADNI1 (n = 1423) and MIRIAD (n = 69) were processed with FreeSurfer to extract eight AD-related ROI volumes and ICV. Four feature configurations (ROI-only, ROI/ICV, Residual ROI, ROI + ICV) were benchmarked across six classifiers for cognitive normal (CN)–AD, CN–mild cognitive impairment (MCI), and MCI AD. Performance was assessed with AUROC and F1 using Friedman and post hoc tests. In addition, feature attribution was examined with permutation importance and SHAP. 

Results

ROI + ICV consistently produced the largest performance gains over ROI-only in CN–AD and CN–MCI, outper forming ratio and residual adjustment across most classifiers. These improvements generalized to the independent MIRIAD dataset. SHAP analyses showed that the directional effect of ICV reversed across strategies: under ratio or residual adjust ment, larger ICV decreased AD probability, whereas in ROI + ICV, larger ICV increased it. This highlights ICV’s contextual influence on model decisions. 

Discussion 

Pre-processing-based adjustments do not fully remove ICV effects and can distort ROI–ICV relationships. Explicit covariate inclusion avoids these issues and yields more consistent, generalizable improvements. Thus, ICV should be mod eled rather than removed, making ROI + ICV the preferred default ICV-handling strategy for MRI-based AD classification.

Keywords 

Alzheimer’s disease · Structural MRI · Intracranial volume · Covariate modeling · Machine learning

1. Department of Biomedical Engineering, Korea University, Seoul, Republic of Korea 

   Yongha Gi, A. Hyun Jung, Hyungjin Lim, Sangyoon Park,  Jeongwon Lee, Myonggeun Yoon

Received: 15 October 2025 / Revised: 5 December 2025 / Accepted: 22 December 2025