Support vector machine (SVM)‐based multivariate pattern analysis (MVPA) has delivered promising performance in decoding specific task states based on functional magnetic resonance imaging (fMRI) of the human brain. Conventionally, the SVM‐MVPA requires careful feature selection/extraction according to expert knowledge. In this study, we propose a deep neural network (DNN) for directly decoding multiple brain task states from fMRI signals of the brain without any burden for feature handcrafts. We trained and tested the DNN classifier using task fMRI data from the Human Connectome Project's S1200 dataset (N = 1,034). In tests to verify its performance, the proposed classification method identified seven tasks with an average accuracy of 93.7%. We also showed the general applicability of the DNN for transfer learning to small datasets (N = 43), a situation encountered in typical neuroscience research. The proposed method achieved an average accuracy of 89.0 and 94.7% on a working memory task and a motor classification task, respectively, higher than the accuracy of 69.2 and 68.6% obtained by the SVM‐MVPA. A network visualization analysis showed that the DNN automatically detected features from areas of the brain related to each task. Without incurring the burden of handcrafting the features, the proposed deep decoding method can classify brain task states highly accurately, and is a powerful tool for fMRI researchers.
Image saliency detection is an active research topic in the community of computer vision and multimedia. Fusing complementary RGB and thermal infrared data has been proven to be effective for image saliency detection. In this paper, we propose an effective approach for RGB-T image saliency detection. Our approach relies on a novel collaborative graph learning algorithm. In particular, we take superpixels as graph nodes, and collaboratively use hierarchical deep features to jointly learn graph affinity and node saliency in a unified optimization framework. Moreover, we contribute a more challenging dataset for the purpose of RGB-T image saliency detection, which contains 1000 spatially aligned RGB-T image pairs and their ground truth annotations. Extensive experiments on the public dataset and the newly created dataset suggest that the proposed approach performs favorably against the state-of-the-art RGB-T saliency detection methods.
One hypothesis in visual perceptual learning is that the amount of transfer depends on the difficulty of the training and transfer tasks (Ahissar & Hochstein, 1997; Liu, 1995, 1999). Jeter, Dosher, Petrov, and Lu (2009), using an orientation discrimination task, challenged this hypothesis by arguing that the amount of transfer depends only on the transfer task but not on the training task. Here we show in a motion direction discrimination task that the amount of transfer indeed depends on the difficulty of the training task. Specifically, participants were first trained with either 4° or 8° direction discrimination along one average direction. Their transfer performance was then tested along an average direction 90° away from the trained direction. A variety of transfer measures consistently demonstrated that transfer performance depended on whether the participants were trained on 4° or 8° directional difference. The results contradicted the prediction that transfer was independent of the training task difficulty.
The authors declare that they have no conflicts of interest with the contents of this article. This article contains Tables S1-S6 and Figs. S1-S4. The data discussed in this publication have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE115075.
Brain imaging studies in the general population have demonstrated that markers of cerebral small vessel disease (CSVD), including white matter hyperintensities (WMH), lacunes, cerebral microbleeds (CMBs), and enlarged perivascular spaces (ePVS), are highly prevalent in individuals over 60 years of age [1-4]. CSVD markers, and their progression, have been recognized as important vascular contributors to cognitive impairment and dementia [5, 6]. Therefore, investigation on progression of these markers is crucial to better understanding of both etiology and consequences of CSVD.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.