AUTHOR=Wu Yun-Ying , Hu Yun-Song , Wang Jue , Zang Yu-Feng , Zhang Yu 

TITLE=Toward Precise Localization of Abnormal Brain Activity: 1D CNN on Single Voxel fMRI Time-Series

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2022.822237

DOI=10.3389/fncom.2022.822237

ISSN=1662-5188

ABSTRACT=Functional magnetic resonance imaging (fMRI) is one of the best techniques for precise localization of abnormal brain activity noninvasively. Machine-learning approaches have been widely used in neuroimaging studies, however, few studies have investigated the single-voxel modelling of fMRI data under cognitive tasks. We proposed a hybrid 1D convolutional neural network (1D-CNN) based on the temporal dynamics of single-voxel fMRI time-series and successfully differentiated two continuous task states, i.e. self-initiated (SI) and visually guided (VG) motor tasks. First, 25 activation peaks were identified from the contrast maps of SI and VG tasks in a blocked design. Then, the fMRI time-series of each peak voxel was transformed into a temporal-frequency domain by using continuous wavelet transform across a broader frequency range (0.003 – 0.0313 Hz, with a step of 0.01 Hz). The transformed time-series were inputted into a 1D-CNN model for the binary classification of SI and VG continuous tasks. Compared to the univariate analysis, e.g. amplitude of low frequency fluctuation (ALFF) at each frequency band, namely Wavelet-ALFF, the 1D-CNN model highly outperformed Wavelet-ALFF, with more efficient decoding models (46% of 800 models showing AUC > 0.61) and higher decoding accuracies (94% of the efficient models), especially on the high-frequency bands (> 0.1 Hz). Moreover, our results also demonstrated the advantages of wavelet decompositions over the original fMRI-series by showing higher decoding performance on all peak voxels. Overall, the current study suggests a great potential of single-voxel analysis using 1D-CNN and wavelet transformation of fMRI series with continuous, naturalistic, steady-state task design or resting-state design. It opens new avenues to precise localization of abnormal brain activity and fMRI-guided precision brain stimulation therapy.