Multimodal PET/MRI radiomics model for the classification of Alzheimer's disease and other dementia subtypes: A multicenter study
Medical Physics · 2026
DOI: 10.1002/mp.70690 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Medical Physics, 2026. Verfasst von Bingjie Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Imaging Laboratory (BIG), Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Taipa…. Hauptthemen laut MEDLINE: Radiomics, Magnetic Resonance Imaging, Alzheimer Disease, Positron-Emission Tomography. Die Arbeit nennt 42 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Research Instrument Development Project of the Chinese Academy of Sciences.
Themen: Demenz
Abstract (Originalsprache)
Background
Accurate and early diagnosis of Alzheimer's disease (AD) remains a major clinical challenge. This study aims to explore the value of multimodal positron emission tomography (PET) and magnetic resonance imaging (MRI) radiomics to improve diagnostic accuracy.
Purpose
To develop and evaluate hippocampus‐based multimodal PET/MRI radiomics models for AD classification and exploratory five‐class classification, and to compare early fusion (EF) with multi‐criteria decision‐making (MCDM)‐based decision‐level fusion.
Method
A total of 758 patients who underwent both PET ([18F]FDG and Amyloid‐β) and MRI (3DT1, T1WI, T2WI, T2‐FLAIR) were retrospectively included as the primary dataset in this study. 945 radiomic features (RFs) per sequence were extracted from the bilateral hippocampus. Models were evaluated on the primary cohort using a five‐fold stratified cross‐validation at the subject level (80% training and 20% testing in each fold). Feature selection was performed independently for each sequence using the Least Absolute Shrinkage and Selection Operator (LASSO). For multimodal PET/MR models, features from all six sequences were concatenated, and feature selection was applied (EF). Six classifiers were used to construct classification models for two tasks, including (1) AD/non‐AD classification, and (2) exploratory five‐class classification among AD, FTD, VaD, MCI, and other dementia. In addition, an MCDM‐based strategy was implemented to fuse multimodal RFs and multi‐classifiers. Modality‐matched external validation was performed in an independent cohort of 45 patients with 3DT1 and Aβ PET available. Decision curve analysis (DCA) was employed to assess the clinical usefulness of the models. SHapley Additive exPlanations (SHAP) was applied to explore the interpretability of the EF‐based model.
Results
Among the 758 patients in the primary dataset, AD, FTD, VaD, and MCI were present in 481 (63.5%), 34 (4.5%), 15 (2.0%), 136 (17.9%) cases, with 92 (12.1%) classified as the other dementia subtypes. The MCDM‐based models achieved the highest area under the receiver operating characteristic curves (AUCs) for both tasks on the primary dataset (Task 1: AUC = 0.848; Task 2: AUC = 0.797), significantly higher than EF‐based models in Task 2 (AUC = 0.782, p < 0.001) and showing comparable performance in Task 1 (AUC = 0.839, p = 0.629). On the external dataset, EF and MCDM models achieved AUCs of 0.741 and 0.761, respectively, for Task 1. The MCDM model showed a higher AUC than EF. DCA suggested potential net‐benefit advantages for the multimodal models across selected threshold ranges. SHAP analysis identified wavelet‐transformed texture features as the key predictors.
Conclusion
Hippocampus‐based PET/MRI radiomics models showed promising performance for binary AD classification, with further improvement achieved by the MCDM strategy. The five‐class findings should be regarded as exploratory. External validation provides preliminary support for the reduced 3DT1–Aβ PET model and does not establish the generalizability of the complete six‐modality framework.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Biomedical Imaging Laboratory (BIG), Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Taipa, Macau SAR, China.
- Research Center for Medical AI, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
- Key Laboratory of Biomedical Imaging Science and System, State Key Laboratory of Biomedical Imaging Science and System, Chinese Academy of Sciences, Shenzhen, China.
- Department of Radiology & Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China.
- Centre for Cognitive and Brain Sciences, Institute of Collaborative Innovation, University of Macau, Taipa, Macau SAR, China.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Research Instrument Development Project of the Chinese Academy of Sciences
- Guangdong Basic and Applied Basic Research Foundation of China
- Shenzhen Science and Technology Program of China
Zitieren
APA
Wang, B., Bi, S., Xu, X., Zheng, H., Liang, D., Mok, G. S. P., Yan, S., & Hu, Z. (2026). Multimodal PET/MRI radiomics model for the classification of Alzheimer's disease and other dementia subtypes: A multicenter study. Medical Physics. https://doi.org/10.1002/mp.70690
Vancouver
Wang B, Bi S, Xu X, Zheng H, Liang D, Mok GSP, et al. Multimodal PET/MRI radiomics model for the classification of Alzheimer's disease and other dementia subtypes: A multicenter study. Medical Physics. 2026. doi:10.1002/mp.70690
BibTeX
@article{Wang2026,
author = {Wang, Bingjie and Bi, Sheng and Xu, Xiaoyin and Zheng, Hairong and Liang, Dong and Mok, Greta S P and Yan, Shaozhen and Hu, Zhanli},
title = {Multimodal PET/MRI radiomics model for the classification of Alzheimer's disease and other dementia subtypes: A multicenter study},
journal = {Medical Physics},
year = {2026},
doi = {10.1002/mp.70690}
}
EUVIMED