Explainable artificial intelligence for neuroimaging-based dementia diagnosis and prognosis
Martin, S. A.; Zhao, A.; Qu, J.; Imms, P.; Irimia, A.; Barkhof, F.; Cole, J. H.; Alzheimer's Disease Neuroimaging Initiative,
Show abstract
INTRODUCTION: Artificial intelligence and neuroimaging enable accurate dementia prediction, but black box models can be difficult to trust. Explainable artificial intelligence (XAI) describes techniques to understand model behaviour and the influence of features, however deciding which method is most appropriate is non-trivial. Vision transformers (ViT) have also gained popularity, providing a self-explainable, alternative to traditional convolutional neural networks (CNN). METHODS: We used T1-weighted MRI to train models on two tasks: Alzheimers disease (AD) classification (diagnosis) and predicting conversion from mild-cognitive impairment (MCI) to AD (prognosis). We compared ten XAI methods across CNN and ViT architectures. RESULTS: Models achieved balanced accuracies of 81% and 67% for diagnosis and prognosis. XAI outputs highlighted brain regions relevant to AD and contained useful information for MCI prognosis. DISCUSSION: XAI can be used to verify that models are utilising relevant features and to generate valuable measures for further analysis.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- WMH-DualTasker: A weakly-supervised deep learning model for automated white matter hyperintensities segmentation and visual rating prediction 97%
- Cross-dataset Evaluation of Dementia Longitudinal Progression Prediction Models 97%
- Identifying the regional substrates predictive of Alzheimer’s disease progression through a convolutional neural network model and occlusion 96%
Similar papers in this journal
- ReMiND: Recovery of Missing Neuroimaging using Diffusion Models with Application to Alzheimer’s Disease 95%
- Leveraging multimodal neuroimaging and GWAS for identifying modality-level causal pathways to Alzheimer’s disease 93%
- Automated quality control of T1-weighted brain MRI scans for clinical research: methods comparison and design of a quality prediction classifier 93%
Similar papers in this journal
- Comparison and aggregation of event sequences across ten cohorts to describe the consensus biomarker evolution in Alzheimer’s disease 95%
- An explainable self-attention deep neural network for detecting mild cognitive impairment using multi-inputbdigital drawing tasks 94%
- Machine learning applications in vascular neuroimaging for the diagnosis and prognosis of cognitive impairment and dementia: a systematic review and meta-analysis 93%
Similar papers in this journal
- Simulating the outcome of amyloid treatments in Alzheimer's Disease from multi-modal imaging and clinical data 94%
- Whole-brain functional connectivity predicts regional tau PET in preclinical Alzheimer's disease 94%
- Assessment of white matter hyperintensity severity using multimodal MRI in Alzheimer's Disease 93%
Similar papers in this journal
- Cortical thickness and grey-matter volume anomaly detection in individual MRI scans: Comparison of two methods 95%
- Preliminary Validation of a Structural Magnetic Resonance Imaging Metric for Tracking Dementia-Related Neurodegeneration and Future Decline 94%
- ComBat Harmonization: Empirical Bayes versus Fully Bayes Approaches 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.