What question did this study set out to answer?

This research presents the AD-GCRS framework aimed at improving Alzheimer's classification stability and safety.

February 23, 20260 citationsOpen Access

AD-GCRS: A Generalized Clinical Reliability System For Multistage Alzheimer's Classification Leveraging Transfer Learning Across Heterogeneous MRI Datasets

SBShameer Basha PSProf. B. Sathyanarayana

Key Points

This research presents the AD-GCRS framework aimed at improving Alzheimer's classification stability and safety.
Utilized four transfer learning architectures (VGG16, Xception, ResNet50, EfficientNetB0) for MRI classification.
Implemented Clinical Deviation Error to penalize misclassifications during evaluations.
Calculated Index of Model Stability and Correct Class Index for cross-validation between ADNI and OASIS datasets.
Internal validation showed accuracies over 97%.
Cross-dataset testing revealed a significant generalization gap.
Xception model achieved highest robustness with a Correct Class Index of 0.9708.

Abstract

Objective: Standard Deep Learning(DL) evaluations for Alzheimer's Disease (AD) often prioritize raw accuracy over clinical safety and cross-institutional generalization. This research proposes the Alzheimer's Disease Generalized Clinical Reliability System (AD-GCRS), a novel framework designed to evaluate model stability and clinical risk across heterogeneous environments. Methods: The AD-GCRS framework leverages four transfer learning architectures VGG16, Xception, ResNet50, and EfficientNetB0 to classify MRI image scans into four progressive stages of impairment. We introduce a specialized evaluation suite, Clinical Deviation Error (CDE) to penalize stage-skipping misclassifications, the Index of Model Stability (IMS), and the Correct Class Index (CCI) for cross-dataset validation between ADNI and OASIS repositories. Results: Internal validation achieved accuracies exceeding 97%. However, cross-dataset testing revealed a significant \\\"generalization gap,\\\" where the Xception model emerged as the most robust architecture with a CCI of 0.9708 and a restricted Major Error Rate (MCR) of 23.96%. Furthermore, we successfully resolved the \\\"Scaling Paradox\\\" in EfficientNetB0. It can be possible through a custom Lambda layer, restoring its diagnostic capability. Conclusion: The AD-GCRS provides a transparent pathway. For deploying AI in clinical settings by quantifying not just if a model is wrong, but how safely it fails

Ask AI

Helpful

Bookmark

View Full Paper