An unsupervised XAI framework for dementia detection with context enrichment

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. 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-by-example, and (iii) textual explanations. A qualitative evaluation by clinicians (N = 6) was performed to assess their clinical validity. 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-by-example 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. 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.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2025-11-12
DOI
https://doi.org/10.1038/s41598-025-26227-2
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

An unsupervised XAI framework for dementia detection with context enrichment

Emrah Düzel, Andrea Lohse, Silka Dawn Freiesleben, Jens Wiltfang et al.
Scientific Reports
Explainable Artificial Intelligence (XAI)
article

An unsupervised XAI framework for dementia detection with context enrichment

Emrah Düzel, Andrea Lohse, Silka Dawn Freiesleben, Jens Wiltfang, Ayda Rostamzadeh, Lukas Preis, Falk Lüesebrink, Robert Perneczky, Annika Spottke, Oliver Peters, Stefan Johannes Teipel, Michael Ewers, Matthis Synofzik, Boris‐Stephan Rauchmann, A. Bernhardt, Devesh Singh, Johannes Levin, Klaus Scheffler, Marc‐André Weber, Katharina Büerger, Klaus Fließbach, Martin Dyrba, Josef Priller, Andreas Hermann, Martin Becker, Okka Kimmich, Stefan Hetzer, Yusuf Brima, Doreen Görß, Johannes Prudlo, Ingo Kilimann, Anja Schneider, Michaela Butryn, Wenzel Glanz, Fedor Levin, Bjarne C. Hiller, Björn H. Schott, Nina Roy‐Kluth, Lukas Beichert, Peter Dechent, Matthias H. Munk, Christoph Laske, Frank Jessen, Diana Prychynenko, Louise Droste zu Senden, Irene Villar-Munoz
article en

Abstract

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. 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-by-example, and (iii) textual explanations. A qualitative evaluation by clinicians (N = 6) was performed to assess their clinical validity. 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-by-example 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. 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.

Scientific ReportsVol. 15(1)
University of Bonn (DE), University of Cologne (DE), University Hospital Bonn (DE), German Center for Neurodegenerative Diseases (DE), LMU Klinikum (DE), Munich Cluster for Systems Neurology (DE), European Neuroscience Institute Göttingen (DE), University Children's Hospital Tübingen (DE), UK Dementia Research Institute (GB), Cologne Excellence Cluster on Cellular Stress Responses in Aging Associated Diseases (DE), University Hospital Magdeburg (DE), Hertie Institute for Clinical Brain Research (DE), University of Rostock (DE), Imperial College London (GB), University of Aveiro (PT), Technical University of Munich (DE), Charité - Universitätsmedizin Berlin (DE), University of Tübingen (DE), Ludwig-Maximilians-Universität München (DE), University of Sheffield (GB), University of Edinburgh (GB)
Deutsche Forschungsgemeinschaft, Volkswagen Foundation, Bundesministerium für Bildung und Forschung
Openalex Percentile: Top 82%
Explainable Artificial Intelligence (XAI)
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.