3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
This work addresses a crucial prerequisite for computer-aided hepatic disease diagnosis and treatment, but it is incremental as it builds on existing deep learning methods with specific improvements.
The paper tackles automatic liver segmentation from CT volumes by proposing a 3D deeply supervised network (3D DSN) with a conditional random field model, achieving competitive segmentation results to state-of-the-art approaches with much faster processing speed on the MICCAI-SLiver07 dataset.
Automatic liver segmentation from CT volumes is a crucial prerequisite yet challenging task for computer-aided hepatic disease diagnosis and treatment. In this paper, we present a novel 3D deeply supervised network (3D DSN) to address this challenging task. The proposed 3D DSN takes advantage of a fully convolutional architecture which performs efficient end-to-end learning and inference. More importantly, we introduce a deep supervision mechanism during the learning process to combat potential optimization difficulties, and thus the model can acquire a much faster convergence rate and more powerful discrimination capability. On top of the high-quality score map produced by the 3D DSN, a conditional random field model is further employed to obtain refined segmentation results. We evaluated our framework on the public MICCAI-SLiver07 dataset. Extensive experiments demonstrated that our method achieves competitive segmentation results to state-of-the-art approaches with a much faster processing speed.