Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network
| العنوان: | Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network |
|---|---|
| المؤلفون: | Teppei Matsui, Masato Taki, Trung Quang Pham, Junichi Chikazoe, Koji Jimura |
| المصدر: | Frontiers in neuroinformatics. 15 |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Computer Science - Machine Learning, decoding, Computer Vision and Pattern Recognition (cs.CV), fMRI, Biomedical Engineering, Neuroscience (miscellaneous), counterfactual explanation, Computer Science - Computer Vision and Pattern Recognition, deep learning, Computer Science Applications, explainable AI, Machine Learning (cs.LG), FOS: Biological sciences, Quantitative Biology - Neurons and Cognition, Neurons and Cognition (q-bio.NC), generative neural network |
| الوصف: | Deep neural networks (DNNs) can accurately decode task-related information from brain activations. However, because of the nonlinearity of the DNN, the decisions made by DNNs are hardly interpretable. One of the promising approaches for explaining such a black-box system is counterfactual explanation. In this framework, the behavior of a black-box system is explained by comparing real data and realistic synthetic data that are specifically generated such that the black-box system outputs an unreal outcome. Here we introduce a novel generative DNN (counterfactual activation generator, CAG) that can provide counterfactual explanations for DNN-based classifiers of brain activations. Importantly, CAG can simultaneously handle image transformation among multiple classes associated with different behavioral tasks. Using CAG, we demonstrated counterfactual explanation of DNN-based classifiers that learned to discriminate brain activations of seven behavioral tasks. Furthermore, by iterative applications of CAG, we were able to enhance and extract subtle spatial brain activity patterns that affected the classifier's decisions. Together, these results demonstrate that the counterfactual explanation based on image-to-image transformation would be a promising approach to understand and extend the current application of DNNs in fMRI analyses. 28 pages, 6 figures, 3 tables, 2 supplementary figures, 1 supplementary table |
| تدمد: | 1662-5196 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db9b0bc1d9a24e1129883512dec18d74 https://pubmed.ncbi.nlm.nih.gov/35369003 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....db9b0bc1d9a24e1129883512dec18d74 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 16625196 |
|---|