Corpus ID: 235828914

Scalable, Axiomatic Explanations of Deep Alzheimer's Diagnosis from Heterogeneous Data

@article{Plsterl2021ScalableAE,
  title={Scalable, Axiomatic Explanations of Deep Alzheimer's Diagnosis from Heterogeneous Data},
  author={Sebastian P{\"o}lsterl and Christina Aigner and C. Wachinger},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.05997}
}
Deep Neural Networks (DNNs) have an enormous potential to learn from complex biomedical data. In particular, DNNs have been used to seamlessly fuse heterogeneous information from neuroanatomy, genetics, biomarkers, and neuropsychological tests for highly accurate Alzheimer’s disease diagnosis. On the other hand, their black-box nature is still a barrier for the adoption of such a system in the clinic, where interpretability is absolutely essential. We propose Shapley Value Explanation of… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 29 REFERENCES
A Wide and Deep Neural Network for Survival Analysis from Anatomical Shape and Tabular Clinical Data
TLDR
A wide and deep neural network is introduced for prediction of progression from patients with mild cognitive impairment to Alzheimer's disease and is trained end-to-end to combine information from a patient's hippocampus shape and clinical biomarkers. Expand
Invertible Network for Classification and Biomarker Selection for ASD
TLDR
This work proposes a novel method to classify ASD and identify biomarkers for ASD using the connectivity matrix calculated from fMRI as the input, and shows that the invertible network is both effective at ASD classification and interpretable, allowing for discovery of reliable biomarkers. Expand
Brain Biomarker Interpretation in ASD Using Deep Learning and fMRI
TLDR
This work proposes a 2-stage method that classifies ASD and control subjects using fMRI images and interprets the saliency features activated by the classifier and validate the detected biomarkers by neurological function decoding and comparing with the DNN activation maps. Expand
Opportunities and obstacles for deep learning in biology and medicine
TLDR
It is found that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Expand
A Unified Approach to Interpreting Model Predictions
TLDR
A unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), which unifies six existing methods and presents new methods that show improved computational performance and/or better consistency with human intuition than previous approaches. Expand
CSF total tau, Aβ42 and phosphorylated tau protein as biomarkers for Alzheimer’s disease
TLDR
Preliminary evidence strongly suggests that quantification of tau phosphorylated at specific sites in CSF improves early detection, differential diagnosis, and tracking of disease progression in AD. Expand
Learning Important Features Through Propagating Activation Differences
TLDR
DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of a neural network on a specific input by backpropagating the contributions of all neurons in the network to every feature of the input, is presented. Expand
Axiomatic Attribution for Deep Networks
We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms— Sensitivity andExpand
The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods
TLDR
The approach taken in ADNI to standardization across sites and platforms of the MRI protocol, postacquisition corrections, and phantom‐based monitoring of all scanners could be used as a model for other multisite trials. Expand
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
TLDR
This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers by introducing a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. Expand
...
1
2
3
...