• Corpus ID: 239769276

Dual Shape Guided Segmentation Network for Organs-at-Risk in Head and Neck CT Images

  title={Dual Shape Guided Segmentation Network for Organs-at-Risk in Head and Neck CT Images},
  author={Shuai Wang and Theodore Yanagihara and Bhishamjit S. Chera and Colette J. Shen and Pew-Thian Yap and Jun Lian},
The accurate segmentation of organs-at-risk (OARs) in head and neck CT images is a critical step for radiation therapy of head and neck cancer patients. However, manual delineation for numerous OARs is time-consuming and laborious, even for expert oncologists. Moreover, manual delineation results are susceptible to high intraand inter-variability. To this end, we propose a novel dual shape guided network (DSGnet) to automatically delineate nine important OARs in head and neck CT images. To deal… 

Figures and Tables from this paper


Hierarchical Vertex Regression-Based Segmentation of Head and Neck CT Images for Radiotherapy Planning
A novel approach to incorporate shape priors into a hierarchical learning-based model to overcome drawbacks of the conventional shape-based segmentation methods is proposed and experimental results show that the approach can achieve much better results than state-of-the-art methods.
Fully automatic multi‐organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks
A novel automated H&N OARs segmentation method that combines a fully convolutional neural network (FCNN) with a shape representation model (SRM) that showed competitive performance and took shorter time to segment multiple organs in comparison to state of the art methods.
Atlas-Based Auto-segmentation of Head and Neck CT Images
A fully automated, atlas-based method for H&N CT image segmentation that employs a novel hierarchical atlas registration approach that makes use of object shape information in the atlas to help improve the registration efficiency and robustness while still being able to account for large inter-subject shape differences.
CT male pelvic organ segmentation using fully convolutional networks with boundary sensitive representation
Experimental results show that the performance of the proposed method outperforms the baseline fully convolutional networks, as well as other state‐of‐the‐art methods in CT male pelvic organ segmentation.
Iterative Label Denoising Network: Segmenting Male Pelvic Organs in CT From 3D Bounding Box Annotations
  • Shuai Wang, Qian Wang, +4 authors D. Shen
  • Medicine, Computer Science
    IEEE Transactions on Biomedical Engineering
  • 2020
This is the first work to achieve voxel-wise segmentation in CT images from simple 3D bounding box annotations, which can greatly reduce many labeling efforts and meet the demands of the practical clinical applications.
Dynamic Multi-Atlas Selection Based Consensus Segmentation of Head and Neck Structures from CT Images.
A dynamic multi-atlas selection-based approach for fast and reproducible segmentation of head and neck organ-at-risk structures for radiation therapy planning and generates segmentations and consensus maps indicating voxel-wise agreement between different atlases is developed.
Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks
This work proposed the first deep learning‐based algorithm, for segmentation of OARs in HaN CT images, and compared its performance against state‐of‐the‐art automated segmentation algorithms, commercial software, and interobserver variability.
CT Male Pelvic Organ Segmentation via Hybrid Loss Network With Incomplete Annotation
This work proposes a novel deep framework to segment male pelvic organs in CT images with incomplete annotation delineated in a very user-friendly manner and designs a hybrid loss network derived from both voxel classification and boundary regression, to jointly improve the organ segmentation performance in an iterative way.
A learning-based CT prostate segmentation method via joint transductive feature selection and regression
Experimental results show that the proposed method outperforms the state-of-the-arts in terms of higher Dice ratio, higher true positive fraction, and lower centroid distances, and the results demonstrate that simple manual specification can help improve the segmentation performance, which is clinically feasible in real practice.
Shape-aware label fusion for multi-atlas frameworks
This paper shows how one can directly incorporate shape regularization into the multi-atlas framework without relying on label fusion on the voxel level, and obtains qualitatively better segmentation boundaries, for instance, preserving topology and fine structures.