Accurate Lung Segmentation via Network-Wise Training of Convolutional Networks
This work improves lung segmentation accuracy for medical imaging applications, but it is incremental as it builds on existing deep learning methods.
The authors tackled lung segmentation in chest radiographs by proposing a model using atrous convolutional layers and a multi-stage network-wise training strategy, achieving state-of-the-art performance on the JSRT dataset with fewer parameters.
We introduce an accurate lung segmentation model for chest radiographs based on deep convolutional neural networks. Our model is based on atrous convolutional layers to increase the field-of-view of filters efficiently. To improve segmentation performances further, we also propose a multi-stage training strategy, network-wise training, which the current stage network is fed with both input images and the outputs from pre-stage network. It is shown that this strategy has an ability to reduce falsely predicted labels and produce smooth boundaries of lung fields. We evaluate the proposed model on a common benchmark dataset, JSRT, and achieve the state-of-the-art segmentation performances with much fewer model parameters.