PyTorch implementation of DeepTaskGen, a convolutional neural network designed to predict individual task contrasts from voxel-to-ROI resting state connectomes. This model is an adaptation of BrainSurfCNN (Ngo et al., 2021) and includes three distinct architectures: UNet (Ronneberger et al., 2015), Residual-UNet (Zhang et al., 2018), and VNet (Milletari et al., 2016).

Please note that this project is currently in the development phase and may not be fully functional. Contributions and suggestions are welcome.

1. Milletari, Fausto, Nassir Navab, and Seyed-Ahmad Ahmadi. "V-net: Fully convolutional neural networks for volumetric medical image segmentation." 2016 fourth international conference on 3D vision (3DV). IEEE, 2016.
2. Ngo, Gia H., et al. "Predicting individual task contrasts from resting‐state functional connectivity using a surface‐based convolutional network." NeuroImage 248 (2022): 118849.
3. Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation." International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015.
4. Zhang, Zhengxin, Qingjie Liu, and Yunhong Wang. "Road extraction by deep residual u-net." IEEE Geoscience and Remote Sensing Letters 15.5 (2018): 749-753.