A Multi-Task Deep Learning Framework to Localize the Eloquent Cortex in Brain Tumor Patients Using Dynamic Functional Connectivity
This method offers improved preoperative mapping of eloquent cortex for brain tumor patients, potentially enhancing surgical planning and outcomes.
This paper introduces a deep learning framework that localizes language and motor areas in brain tumor patients using dynamic functional connectivity. The model achieves higher localization accuracies compared to conventional deep learning methods and can identify bilateral language areas even when trained on unilateral data.
We present a novel deep learning framework that uses dynamic functional connectivity to simultaneously localize the language and motor areas of the eloquent cortex in brain tumor patients. Our method leverages convolutional layers to extract graph-based features from the dynamic connectivity matrices and a long-short term memory (LSTM) attention network to weight the relevant time points during classification. The final stage of our model employs multi-task learning to identify different eloquent subsystems. Our unique training strategy finds a shared representation between the cognitive networks of interest, which enables us to handle missing patient data. We evaluate our method on resting-state fMRI data from 56 brain tumor patients while using task fMRI activations as surrogate ground-truth labels for training and testing. Our model achieves higher localization accuracies than conventional deep learning approaches and can identify bilateral language areas even when trained on left-hemisphere lateralized cases. Hence, our method may ultimately be useful for preoperative mapping in tumor patients.