Organ at Risk Segmentation in Head and Neck CT Images by Using a Two-Stage Segmentation Framework Based on 3D U-Net
This work addresses the problem of accurate OAR segmentation for head and neck cancer treatment planning, offering a method that outperforms state-of-the-art approaches on a standard benchmark, though it is incremental as it builds on existing 3D U-Net architectures.
The paper tackled the challenging task of segmenting organs at risk (OARs) in head and neck CT images for radiation treatment planning by proposing a two-stage framework based on 3D U-Net, achieving top rankings in boundary-based and area-based metrics on the MICCAI 2015 dataset, including first place in eight of nine OARs for 95HD and six of nine for DSC.
Accurate segmentation of organ at risk (OAR) play a critical role in the treatment planning of image guided radiation treatment of head and neck cancer. This segmentation task is challenging for both human and automatic algorithms because of the relatively large number of OARs to be segmented, the large variability of the size and morphology across different OARs, and the low contrast of between some OARs and the background. In this paper, we proposed a two-stage segmentation framework based on 3D U-Net. In this framework, the segmentation of each OAR is decomposed into two sub-tasks: locating a bounding box of the OAR and segment it from a small volume within the bounding box, and each sub-tasks is fulfilled by a dedicated 3D U-Net. The decomposition makes each of the two sub-tasks much easier, so that they can be better completed. We evaluated the proposed method and compared it to state-of-the-art methods by using the MICCAI 2015 Challenge dataset. In terms of the boundary-based metric 95HD, the proposed method ranked first in eight of all nine OARs and ranked second in the other OAR. In terms of the area-based metric DSC, the proposed method ranked first in six of the nine OARs and ranked second in the other three OARs with small difference with the first one.