We propose a fully 3D multi-path convolutional network to predict stroke lesions from 3D brain MRI images. Our multi-path model has independent encoders for different modalities containing residual convolutional blocks, weighted multi-path feature fusion from different modalities, and weighted fusion modules to combine encoder and decoder features. Compared to existing 3D CNNs like DeepMedic, 3D U-Net, and AnatomyNet, our networks achieves the highest statistically significant cross-validation accuracy of 60.5% on the large ATLAS benchmark of 220 patients. We also test our model on multi-modal images from the Kessler Foundation and Medical College Wisconsin and achieve a statistically significant cross-validation accuracy of 65%, significantly outperforming the multi-modal 3D U-Net and DeepMedic. Overall our model offers a principled, extensible multi-path approach that outperforms multi-channel alternatives and achieves high Dice accuracies on existing benchmarks.
@article{arxiv.1907.07807,
title = {A fully 3D multi-path convolutional neural network with feature fusion and feature weighting for automatic lesion identification in brain MRI images},
author = {Yunzhe Xue and Meiyan Xie and Fadi G. Farhat and Olga Boukrina and A. M. Barrett and Jeffrey R. Binder and Usman W. Roshan and William W. Graves},
journal= {arXiv preprint arXiv:1907.07807},
year = {2019}
}
Comments
Machine Learning for Health (ML4H) at NeurIPS 2019 - Extended Abstract