Brain decoding has been a hot issue in neuroscience research in recent years, which has great application prospects. Our artificial intelligence system uses deep learning algorithms modeled on the human brain neural network combined with Functional Magnetic Resonance Imaging (fMRI) to successfully decode human brain functions with an accuracy rate of up to 94%.
Brain decoding has been a hot issue in neuroscience research in recent years, which has great application prospects. Based on deep learning, the brain decoding model in our artificial intelligence system uses 3D Convolutional Neural Network (3DCNN) combined with Functional Magnetic Resonance Imaging (fMRI) to extract high-dimensional features in brain functional images, and classification of functional magnetic resonance data under different task states, with an accuracy rate of up to 94%, thereby realizing the decoding of the human brain state, providing researchers engaged in brain diseases and mental diseases a more accurate, efficient and intuitive research tool.
Split and Labelled fMRI Data for Deep Learning
Figure 1 shows the process of segmenting and labeling fMRI data. We collected more than 1,000 participants’ data in the seven aspects: emotional, gambling, language, sports, relationship, social and working memory (WM) functional magnetic resonance as the model training data set, performed 3T and MRI on these data, then, standardized the preprocessed fMRI data to reduce training errors. Each task input sample in the data set is a continuous 3D sequence. After excluding non-brain regions and adding the time dimension, we obtained a total of more than 34,000 fMRI 4D data, of which 60% were used as training data and 40% were used as verification data and test data.
Figure 1 Split and Labelled fMRI Data for Deep Learning
Deep Neural Network Classification and Visualization
Figure 2 and Figure 3 show our CNN network classification and classification results visualization process. The 3DCNN classification network in the brain decoding model is composed of some 3D convolution layers and fully connected layers. The convolution kernel in the convolution layer generates a time description and extracts high-dimensional features for each voxel of the input data. The fully connected layer uses the softmax function and contains 64 feature channels and 7 categories (respectively corresponding to 7 features of the data set). Finally, we use instructive back-propagation to visualize the deep network, create a corresponding 3D model by drawing each voxel with an absolute maximum in the time domain, and then map it to the fsaverage surface.
Figure 2 Deep Neural Network Classification
Figure 3 Visualization Results
CD ComputaBio has formed a team of experts excellent in imaging science and clinical domain knowledge, providing AI-driven solutions for Brain Decoding according to your detailed requirements.
Tech Trends in Artificial Intelligence What's up, what's down, what lies ahead, only found in MedAI!