A fully 3D multi-path convolutional neural network with feature fusion and feature weighting for automatic lesion identification in brain MRI images

TL;DR

This paper introduces a fully 3D multi-path CNN with feature fusion and weighting for automatic brain lesion detection in MRI, outperforming existing models on benchmark datasets.

Contribution

The paper presents a novel multi-path 3D CNN architecture with feature fusion and weighting, achieving superior accuracy in lesion segmentation tasks.

Findings

Achieves 60.5% accuracy on ATLAS benchmark

Achieves 65% accuracy on multi-modal datasets

Outperforms existing models like DeepMedic and 3D U-Net

Abstract

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.