Lunit
Back to List

Accurate Lung Segmentation via Network-Wise Training of Convolutional Networks

Sangheum Hwang et al. — MICCAI 2017 DLMIA Workshop

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.

전체 내용 보기
AUTHORS

Sangheum Hwang1 and Sunggyun Park1

1Lunit Inc.

PUBLISHED
MICCAI 2017 DLMIA Workshop

Read more