Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation
This work addresses segmentation accuracy in biomedical imaging for medical diagnosis, but it is incremental as it builds on existing deep learning methods.
The paper tackled 3D biomedical segmentation by proposing a deep encoder-decoder with cross-modality convolution and convolutional LSTM to better leverage multi-modal MRI data, and it outperformed state-of-the-art approaches on the BRATS-2015 dataset.
Deep learning models such as convolutional neural net- work have been widely used in 3D biomedical segmentation and achieve state-of-the-art performance. However, most of them often adapt a single modality or stack multiple modalities as different input channels. To better leverage the multi- modalities, we propose a deep encoder-decoder structure with cross-modality convolution layers to incorporate different modalities of MRI data. In addition, we exploit convolutional LSTM to model a sequence of 2D slices, and jointly learn the multi-modalities and convolutional LSTM in an end-to-end manner. To avoid converging to the certain labels, we adopt a re-weighting scheme and two-phase training to handle the label imbalance. Experimental results on BRATS-2015 show that our method outperforms state-of-the-art biomedical segmentation approaches.