Toward more frugal models for functional cerebral networks automatic recognition with resting-state fMRI
This work addresses the need for more efficient models in neuroimaging analysis for patients with brain tumors, representing an incremental improvement in method efficiency.
The paper tackled the problem of reducing model complexity for automatic recognition of functional cerebral networks from resting-state fMRI data, achieving a 26-fold optimization in model parameters while maintaining performance comparable to classical convolutional neural networks.
We refer to a machine learning situation where models based on classical convolutional neural networks have shown good performance. We are investigating different encoding techniques in the form of supervoxels, then graphs to reduce the complexity of the model while tracking the loss of performance. This approach is illustrated on a recognition task of resting-state functional networks for patients with brain tumors. Graphs encoding supervoxels preserve activation characteristics of functional brain networks from images, optimize model parameters by 26 times while maintaining CNN model performance.