An unsupervised XAI framework for dementia detection with context enrichment.
Authors
Affiliations (42)
Affiliations (42)
- German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany. [email protected].
- Institute of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, University Medical Centre Rostock, Rostock, Germany. [email protected].
- German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany.
- Institute for Visual and Analytic Computing, University of Rostock, Rostock, Germany.
- Translational Neurodegeneration Section "Albrecht Kossel", Department of Neurology, University Hospital Rostock, Rostock, Germany.
- German Center for Neurodegenerative Diseases (DZNE), Berlin, Germany.
- Department of Psychiatry and Neuroscience, Charité - Universitätsmedizin Berlin, Hindenburgdamm 30, 12203, Berlin, Germany.
- Division Translational Genomics of Neurodegenerative Diseases, Hertie Institute for Clinical Brain Research and Center of Neurology, University of Tübingen, Tübingen, Germany.
- German Center for Neurodegenerative Diseases (DZNE), Munich, Germany.
- Department of Neurology, University Hospital of Munich, Ludwig-Maximilians- Universität (LMU) Munich, Munich, Germany.
- Institute for Stroke & Dementia Research, University Hospital, LMU Munich, Munich, Germany.
- German Center for Neurodegenerative Diseases (DZNE), Magdeburg, Germany.
- Institute for Cognitive Neurology and Dementia Research, Faculty of Medicine, University Hospital Magdeburg, Magdeburg, Germany.
- MR-Research in Neurosciences, Department of Cognitive Neurology, University Medical Center Goettingen, Goettingen, Germany.
- German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany.
- Department for Neurodegenerative Diseases and Gerontopsychiatry, University of Bonn, Bonn, Germany.
- Experimental and Clinical Research Center (ECRC), Charité - Universitätsmedizin Berlin, Lindenberger Weg 80, 13125, Berlin, Germany.
- Berlin Center for Advanced Neuroimaging, Charité University Medicine Berlin, Berlin, Germany.
- Department of Psychosomatic Medicine, Rostock University Medical Center, Rostock, Germany.
- German Center for Neurodegenerative Diseases (DZNE), Tübingen, Germany.
- Section for Dementia Research, Hertie Institute for Clinical Brain Research, Department of Psychiatry and Psychotherapy, University Hospital Tübingen, Tübingen, Germany.
- Munich Cluster for Systems Neurology (SyNergy), Munich, Germany.
- Department of Psychiatry and Psychotherapy, Charité - Universitätsmedizin Berlin, Berlin, Germany.
- Department of Psychiatry and Psychotherapy, University Hospital Tübingen, Tübingen, Germany.
- Department of Psychiatry and Psychotherapy, University Hospital, LMU Munich, Munich, Germany.
- Ageing Epidemiology Research Unit, School of Public Health, Faculty of Medicine, Imperial College London, London, United Kingdom.
- Department of Psychiatry and Psychotherapy, School of Medicine and Health, Technical University of Munich, Munich, Germany.
- University of Edinburgh and UK Dementia Research Institute, Edinburgh, United Kingdom.
- German Center for Mental Health (DZPG), Munich, Germany.
- Department of Neurology, University Medical Centre, Rostock, Germany.
- Sheffield Institute for Translational Neuroscience, The University of Sheffield, Sheffield, United Kingdom.
- Department of Neuroradiology, University Hospital, LMU Munich, Munich, Germany.
- Department of Psychiatry, Medical Faculty, University of Cologne, Cologne, Germany.
- Department for Biomedical Magnetic Resonance, University of Tübingen, Tübingen, Germany.
- German Center for Neurodegenerative Diseases (DZNE), Goettingen, Germany.
- Department of Psychiatry and Psychotherapy, University Medical Center Goettingen, Goettingen, Germany.
- Department of Psychiatry and Psychotherapy, University Hospital Magdeburg, Magdeburg, Germany.
- Department of Neurology, University Hospital Bonn, Bonn, Germany.
- Neurosciences and Signaling Group, Institute of Biomedicine (iBiMED), Department of Medical Sciences, University of Aveiro, Aveiro, Portugal.
- Cologne Excellence Cluster on Cellular Stress Responses in Aging-Associated Diseases, Faculty of Medicine, University of Cologne, Cologne, Germany.
- Institute of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, University Medical Centre Rostock, Rostock, Germany.
- German Center for Neurodegenerative Diseases (DZNE), Rostock, Germany. [email protected].
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.