FSE-CNN: Fusion of Training-Trajectory Neural Evidence and Spatial-Scale Morphology for Cross-Cohort Brain MRI Classification
- 1Qiushi Academy for Advanced Studies, Zhejiang University, Hangzhou 310027, China
- 2College of Biomedical Engineering and Instrument Science, Zhejiang University, Hangzhou 310027, China
- 3College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
Abstract
Structural magnetic resonance imaging supports the characterization of Alzheimer’s disease (AD)-related cognitive impairment. But existing cross-cohort AD classification methods remain limited in addressing acquisition and population shifts when source data cannot be revisited and target-side adaptation is excluded. In particular, current cross-cohort AD classification may underutilize diverse disease-related information learned from source data, while explicit characterization of regional, scale-dependent gray-matter morphology remains limited. To address these gaps, we propose FSE-CNN for source-free cross-cohort classification of AD-related cognitive status. First, the neural pathway derives decision evidence from model states retained during source training, with the inference configuration determined exclusively from source data. Second, the spatial-scale geometric evidence encoding module characterizes gray-matter morphology through subject-relative spatial organization and finite physical scales, providing complementary geometric evidence for cross-cohort classification. Finally, the resulting neural and geometric evidence are combined through protocol-specific fusion. We evaluated FSE-CNN on two cross-cohort protocols. In OASIS-2 → OASIS-1, FSE-CNN achieved 83.48% accuracy, 85.14% balanced accuracy, and 88.60% AUC, numerically exceeding Harmonizing Flows by 1.70, 1.26, and 0.39 percentage points, respectively. In ADNI → OASIS-2, it achieved 85.79% accuracy, 85.55% balanced accuracy, and 85.03% AUC, with corresponding gains of 0.71, 0.67, and 0.21 percentage points. Overall, these results demonstrate the effectiveness of FSE-CNN for cross-cohort AD-related cognitive-status classification.
Related
- Two-Stage Probabilistic Classification of Sperm Identity and Morphology
- Three-Part MRI Morphology of the Human Masseter Muscle: A Part-Dominance Classification
- MP-MNCA: Morphology-Prior Masked Neighbor Cross-Attention for Efficient Spatial Domain Identification
- Moving Beyond Morphology: Toward a Morpho-Molecular Classification of Pleural Mesothelioma
- Perineal Body Reconstruction for Anal Sphincter Insufficiency Following Obstetric Perineal Body Injury: Morphology-based Classification and Type-stratified Outcomes in 42 Cases.
BibTeX
@article{li2026fsecnn,
title = {{FSE-CNN: Fusion of Training-Trajectory Neural Evidence and Spatial-Scale Morphology for Cross-Cohort Brain MRI Classification}},
author = {Tuoru Li and Shurong Dong and Weidong Chen},
journal = {Fractal and Fractional},
year = {2026},
month = oct,
doi = {10.3390/fractalfract10110737},
url = {https://www.mdpi.com/2504-3110/10/11/737},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - FSE-CNN: Fusion of Training-Trajectory Neural Evidence and Spatial-Scale Morphology for Cross-Cohort Brain MRI Classification
AU - Tuoru Li
AU - Shurong Dong
AU - Weidong Chen
PY - 2026
DA - 2026/10/23
JO - Fractal and Fractional
DO - 10.3390/fractalfract10110737
UR - https://www.mdpi.com/2504-3110/10/11/737
AB - Structural magnetic resonance imaging supports the characterization of Alzheimer’s disease (AD)-related cognitive impairment. But existing cross-cohort AD classification methods remain limited in addressing acquisition and population shifts when source data cannot be revisited and target-side adaptation is excluded. In particular, current cross-cohort AD classification may underutilize diverse disease-related information learned from source data, while explicit characterization of regional, scale-dependent gray-matter morphology remains limited. To address these gaps, we propose FSE-CNN for source-free cross-cohort classification of AD-related cognitive status. First, the neural pathway derives decision evidence from model states retained during source training, with the inference configuration determined exclusively from source data. Second, the spatial-scale geometric evidence encoding module characterizes gray-matter morphology through subject-relative spatial organization and finite physical scales, providing complementary geometric evidence for cross-cohort classification. Finally, the resulting neural and geometric evidence are combined through protocol-specific fusion. We evaluated FSE-CNN on two cross-cohort protocols. In OASIS-2 → OASIS-1, FSE-CNN achieved 83.48% accuracy, 85.14% balanced accuracy, and 88.60% AUC, numerically exceeding Harmonizing Flows by 1.70, 1.26, and 0.39 percentage points, respectively. In ADNI → OASIS-2, it achieved 85.79% accuracy, 85.55% balanced accuracy, and 85.03% AUC, with corresponding gains of 0.71, 0.67, and 0.21 percentage points. Overall, these results demonstrate the effectiveness of FSE-CNN for cross-cohort AD-related cognitive-status classification.
SN - 2504-3110
ER -