Organ at Risk Segmentation in Head and Neck CT Images Using a Two-Stage Segmentation Framework Based on 3D U-Net

Accurate segmentation of organs at risk (OARs) plays a critical role in the treatment planning of image-guided radiotherapy of head and neck cancer. This segmentation task is challenging for both humans and automated algorithms because of the relatively large number of OARs to be segmented, the large variability in size and morphology across different OARs, and the low contrast between some OARs and the background. In this study, we propose a two-stage segmentation framework based on 3D U-Net. In this framework, the segmentation of each OAR is decomposed into two subtasks: locating a bounding box of the OAR and segmenting the OAR from a small volume within the bounding box, and each subtask is fulfilled by a dedicated 3D U-Net. The decomposition makes each subtask much easier so that it can be better completed. We evaluated the proposed method and compared it to state-of-the-art methods using the Medical Image Computing and Computer-Assisted Intervention 2015 Challenge dataset. In terms of the boundary-based metric 95% Hausdorff distance, the proposed method ranked first for seven of nine OARs and ranked second for the other OARs. In terms of the area-based metric dice similarity coefficient, the proposed method ranked first for five of nine OARs and ranked second for the other three OARs with a small difference from the method that ranked first.

[1]  Lubomir M. Hadjiiski,et al.  Automated volume analysis of head and neck lesions on CT scans using 3D level set segmentation. , 2007, Medical physics.

[2]  Wolfgang A. Tome,et al.  Emphasizing conformal avoidance versus target definition for IMRT planning in head-and-neck cancer. , 2010, International journal of radiation oncology, biology, physics.

[3]  Feng Chen,et al.  Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets , 2016, International Journal of Computer Assisted Radiology and Surgery.

[4]  Yingli Lu,et al.  An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U‐nets , 2019, Medical physics.

[5]  Xiaohui Xie,et al.  AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy , 2018, Medical physics.

[6]  Nico Karssemeijer,et al.  Using deep learning to segment breast and fibroglandular tissue in MRI volumes , 2017, Medical physics.

[7]  A. Lomax,et al.  Systematic evaluation of three different commercial software solutions for automatic segmentation for adaptive therapy in head-and-neck, prostate and pleural cancer , 2012, Radiation oncology.

[8]  Ping Xia,et al.  Repeat CT imaging and replanning during the course of IMRT for head-and-neck cancer. , 2006, International journal of radiation oncology, biology, physics.

[9]  Bulat Ibragimov,et al.  Segmentation of organs‐at‐risks in head and neck CT images using convolutional neural networks , 2017, Medical physics.

[10]  Hao Chen,et al.  Volumetric ConvNets with Mixed Residual Connections for Automated Prostate Segmentation from 3D MR Images , 2017, AAAI.

[11]  Xiao Han,et al.  Atlas-Based Auto-segmentation of Head and Neck CT Images , 2008, MICCAI.

[12]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[13]  Suresh Senan,et al.  Volumetric intensity-modulated arc therapy vs. conventional IMRT in head-and-neck cancer: a comparative planning and dosimetric study. , 2009, International journal of radiation oncology, biology, physics.

[14]  Yinghuan Shi,et al.  Pelvic Organ Segmentation Using Distinctive Curve Guided Fully Convolutional Networks , 2019, IEEE Transactions on Medical Imaging.

[15]  Bo Du,et al.  Deeply-supervised CNN for prostate segmentation , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[16]  Dinggang Shen,et al.  Interleaved 3D-CNNs for joint segmentation of small-volume structures in head and neck CT images. , 2018, Medical physics.

[17]  Blake Hannaford,et al.  Evaluation of segmentation methods on head and neck CT: Auto‐segmentation challenge 2015 , 2017, Medical physics.

[18]  Yaozong Gao,et al.  Hierarchical Vertex Regression-Based Segmentation of Head and Neck CT Images for Radiotherapy Planning , 2018, IEEE Transactions on Image Processing.

[19]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[20]  Steve B. Jiang,et al.  Fully automated organ segmentation in male pelvic CT images , 2018, Physics in medicine and biology.

[21]  Linghong Zhou,et al.  A recursive ensemble organ segmentation (REOS) framework: application in brain radiotherapy , 2019, Physics in medicine and biology.

[22]  Alan D. Lopez,et al.  Global, Regional, and National Cancer Incidence, Mortality, Years of Life Lost, Years Lived With Disability, and Disability-Adjusted Life-years for 32 Cancer Groups, 1990 to 2015: A Systematic Analysis for the Global Burden of Disease Study , 2017, JAMA oncology.

[23]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[24]  Lubomir M. Hadjiiski,et al.  Urinary bladder segmentation in CT urography using deep-learning convolutional neural network and level sets. , 2016, Medical physics.

[25]  Le Lu,et al.  Pancreas Segmentation in MRI Using Graph-Based Decision Fusion on Convolutional Neural Networks , 2016, MICCAI.

[26]  Guang Yang,et al.  A two-stage 3D Unet framework for multi-class segmentation on full resolution image , 2018, ArXiv.

[27]  G. Sharp,et al.  Vision 20/20: perspectives on automated image segmentation for radiotherapy. , 2014, Medical physics.

[28]  Seyed-Ahmad Ahmadi,et al.  Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound , 2016, Comput. Vis. Image Underst..

[29]  Nuo Tong,et al.  Fully automatic multi‐organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks , 2018, Medical physics.