An unsupervised XAI framework for dementia detection with context enrichment

Tools

Item Type:	Preprint
Title:	An unsupervised XAI framework for dementia detection with context enrichment
Creators Name:	Singh, D., Brima, Y., Levin, F., Becker, M., Hiller, B., Hermann, A., Villar-Munoz, I., Beichert, L., Bernhardt, A., Buerger, K., Butryn, M., Dechent, P., Duezel, E., Ewers, M., Fliessbach, K., Freiesleben, S.D., Glanz, W., Hetzer, S., Janowitz, D., Goerss, D., Kilimann, I., Kimmich, O., Laske, C., Levin, J., Lohse, A., Luesebrink, F., Munk, M., Perneczky, R., Peters, O., Preis, L., Priller, J., Prudlo, J., Prychynenko, D., Rauchmann, B.S., Rostamzadeh, A., Roy-Kluth, N., Scheffler, K., Schneider, A., Droste zu Senden, L., H. Schott, B., Spottke, A., Synofzik, M., Wiltfang, J., Jessen, F., Weber, M.A., Teipel, S.J. and Dyrba, M.
Abstract:	INTRODUCTION: Explainable Artificial Intelligence (XAI) methods enhance the diagnostic efficiency of clinical decision support systems by making the predictions of a convolutional neural network’s (CNN) on brain imaging more transparent and trustworthy. However, their clinical adoption is limited due to limited validation of the explanation quality. Our study introduces a framework that evaluates XAI methods by integrating neuroanatomical morphological features with CNN-generated relevance maps for disease classification. METHODS: We trained a CNN using brain MRI scans from six cohorts: ADNI, AIBL, DELCODE, DESCRIBE, EDSD, and NIFD (N=3253), including participants that were cognitively normal, with amnestic mild cognitive impairment, dementia due to Alzheimer's disease and frontotemporal dementia. Clustering analysis benchmarked different explanation space configurations by using morphological features as proxy-ground truth. We implemented three post-hoc explanations methods: i) by simplifying model decisions, ii) explanation-byexample, and iii) textual explanations. A qualitative evaluation by clinicians (N=6) was performed to assess their clinical validity. RESULTS: Clustering performance improved in morphology enriched explanation spaces, improving both homogeneity and completeness of the clusters. Post hoc explanations by model simplification largely delineated converters and stable participants, while explanation-byexample presented possible cognition trajectories. Textual explanations gave rule-based summarization of pathological findings. Clinicians’ qualitative evaluation highlighted challenges and opportunities of XAI for different clinical applications. CONCLUSION: Our study refines XAI explanation spaces and applies various approaches for generating explanations. Within the context of AI-based decision support system in dementia research we found the explanations methods to be promising towards enhancing diagnostic efficiency, backed up by the clinical assessments.
Keywords:	Neurodegenerative Diseases, Alzheimer’s Disease, Frontotemporal Dementia, Magnetic Resonance Imaging, Brain Volumetry, Explainable Artificial Intelligence (XAI), Qualitative Evaluation
Source:	medRxiv
Publisher:	Cold Spring Harbor Laboratory Press
Article Number:	2025.05.28.25327435
Date:	4 June 2025
Official Publication:	https://doi.org/10.1101/2025.05.28.25327435

Repository Staff Only: item control page