skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Fully automatic multi-organ segmentation for head and neck cancer radiotherapy using shape representation model constrained fully convolutional neural networks

Journal Article · · Medical Physics
DOI:https://doi.org/10.1002/mp.13147· OSTI ID:1612696
 [1];  [2];  [2];  [3];  [3]
  1. Xidian Univ., Xi'an (China). Key Lab of Intelligent Perception and Image Understanding of Ministry of Education; Univ. of California, Los Angeles, CA (United States)
  2. Xidian Univ., Xi'an (China). Key Lab of Intelligent Perception and Image Understanding of Ministry of Education
  3. Univ. of California, Los Angeles, CA (United States)
+ Show Author Affiliations

Purpose Intensity modulated radiation therapy (IMRT) is commonly employed for treating head and neck (H&N) cancer with uniform tumor dose and conformal critical organ sparing. Accurate delineation of organs‐at‐risk (OARs) on H&N CT images is thus essential to treatment quality. Manual contouring used in current clinical practice is tedious, time‐consuming, and can produce inconsistent results. Existing automated segmentation methods are challenged by the substantial inter‐patient anatomical variation and low CT soft tissue contrast. To overcome the challenges, we developed a novel automated H&N OARs segmentation method that combines a fully convolutional neural network (FCNN) with a shape representation model (SRM). Methods Based on manually segmented H&N CT, the SRM and FCNN were trained in two steps: (a) SRM learned the latent shape representation of H&N OARs from the training dataset; (b) the pre‐trained SRM with fixed parameters were used to constrain the FCNN training. The combined segmentation network was then used to delineate nine OARs including the brainstem, optic chiasm, mandible, optical nerves, parotids, and submandibular glands on unseen H&N CT images. Twenty‐two and 10 H&N CT scans provided by the Public Domain Database for Computational Anatomy (PDDCA) were utilized for training and validation, respectively. Dice similarity coefficient (DSC), positive predictive value (PPV), sensitivity (SEN), average surface distance (ASD), and 95% maximum surface distance (95%SD) were calculated to quantitatively evaluate the segmentation accuracy of the proposed method. The proposed method was compared with an active appearance model that won the 2015 MICCAI H&N Segmentation Grand Challenge based on the same dataset, an atlas method and a deep learning method based on different patient datasets. Results An average DSC = 0.870 (brainstem), DSC = 0.583 (optic chiasm), DSC = 0.937 (mandible), DSC = 0.653 (left optic nerve), DSC = 0.689 (right optic nerve), DSC = 0.835 (left parotid), DSC = 0.832 (right parotid), DSC = 0.755 (left submandibular), and DSC = 0.813 (right submandibular) were achieved. The segmentation results are consistently superior to the results of atlas and statistical shape based methods as well as a patch‐wise convolutional neural network method. Once the networks are trained off‐line, the average time to segment all 9 OARs for an unseen CT scan is 9.5 s. Conclusion Experiments on clinical datasets of H&N patients demonstrated the effectiveness of the proposed deep neural network segmentation method for multi‐organ segmentation on volumetric CT scans. The accuracy and robustness of the segmentation were further increased by incorporating shape priors using SMR. The proposed method showed competitive performance and took shorter time to segment multiple organs in comparison to state of the art methods.

Research Organization:
RadiaSoft, LLC, Boulder, CO (United States); RadiaBeam Technologies, Santa Monica, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC); National Institutes of Health (NIH); National Natural Science Foundation of China (NSFC)
Grant/Contract Number:
SC0017057; SC0017687; R44CA183390; R01CA18830; R43CA183390; 61472306; DE‐SC0017057; DE‐SC0017687
OSTI ID:
1612696
Alternate ID(s):
OSTI ID: 1472187
Journal Information:
Medical Physics, Vol. 45, Issue 10; ISSN 0094-2405
Publisher:
American Association of Physicists in MedicineCopyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 142 works
Citation information provided by
Web of Science

References (36)

Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks journal February 2017
Active appearance models journal June 2001
U-Net: Convolutional Networks for Biomedical Image Segmentation
  • Ronneberger, Olaf; Fischer, Philipp; Brox, Thomas
  • Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III https://doi.org/10.1007/978-3-319-24574-4_28
book November 2015
Automatic Segmentation of MR Brain Images With a Convolutional Neural Network journal May 2016
Active Shape Models-Their Training and Application journal January 1995
Multi-dimensional Gated Recurrent Units for the Segmentation of Biomedical 3D-Data book January 2016
Brain Tumor Segmentation with Deep Neural Networks text January 2015
A Deep Metric for Multimodal Registration preprint January 2016
Multi-input Cardiac Image Super-Resolution Using Convolutional Neural Networks book January 2016
Hyperthermia critical tissues automatic segmentation of head and neck CT images using atlas registration and graph cuts
  • Fortunati, V.; Verhaart, R. F.; van der Lijn, F.
  • 2012 IEEE 9th International Symposium on Biomedical Imaging (ISBI 2012), 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI) https://doi.org/10.1109/ISBI.2012.6235902
conference May 2012
Worldwide Trends in Incidence Rates for Oral Cavity and Oropharyngeal Cancers journal December 2013
Randomized Phase III Trial of Concurrent Accelerated Radiation Plus Cisplatin With or Without Cetuximab for Stage III to IV Head and Neck Carcinoma: RTOG 0522 journal September 2014
IMRT for head and neck cancer: reducing xerostomia and dysphagia journal August 2016
Hierarchical Vertex Regression-Based Segmentation of Head and Neck CT Images for Radiotherapy Planning journal February 2018
Measures of the Amount of Ecologic Association Between Species journal July 1945
Multiscale deep neural network based analysis of FDG-PET images for the early diagnosis of Alzheimer’s disease journal May 2018
Atlas-based global and local RF segmentation of head and neck organs on multimodal MRI images
  • Urban, Szabolcs; Tanacs, Attila
  • 2017 10th International Symposium on Image and Signal Processing and Analysis (ISPA), Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis https://doi.org/10.1109/ISPA.2017.8073577
conference September 2017
Deep features to classify skin lesions
  • Kawahara, Jeremy; BenTaieb, Aicha; Hamarneh, Ghassan
  • 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI 2016), 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI) https://doi.org/10.1109/ISBI.2016.7493528
conference April 2016
Evaluation of Segmentation Methods on Head and Neck CT: Auto-Segmentation Challenge 2015 text January 2017
Evaluation of segmentation methods on head and neck CT: Auto-segmentation challenge 2015 journal April 2017
Automatic segmentation of head and neck CT images for radiotherapy treatment planning using multiple atlases, statistical appearance models, and geodesic active contours: Segmentation of head-neck CT images using MABSInShape journal April 2014
Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks journal May 2016
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation journal February 2017
Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation journal May 2016
Deeply learnt hashing forests for content based image retrieval in prostate MR images conference March 2016
Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation text January 2017
Atlas-Based Auto-segmentation of Head and Neck CT Images book January 2008
2D image classification for 3D anatomy localization: employing deep convolutional neural networks conference March 2016
Learning image based surrogate relevance criterion for atlas selection in segmentation journal May 2016
A Deep Metric for Multimodal Registration book January 2016
Brain tumor segmentation with Deep Neural Networks journal January 2017
Self-Transfer Learning for Weakly Supervised Lesion Localization book January 2016
3D deeply supervised network for automated segmentation of volumetric medical images journal October 2017
Learning and Incorporating Shape Models for Semantic Segmentation book January 2017
A System for Continual Quality Improvement of Normal Tissue Delineation for Radiation Therapy Treatment Planning journal August 2012
Fully Automatic Segmentation of Head and Neck Organs using Active Appearance Models journal January 2016

Cited By (8)

Comparative clinical evaluation of atlas and deep-learning-based auto-segmentation of organ structures in liver cancer journal November 2019
Online daily adaptive proton therapy journal March 2020
Deep learning in medical imaging and radiation therapy journal November 2018
Dual-energy CT for automatic organs-at-risk segmentation in brain-tumor patients using a multi-atlas and deep-learning approach journal March 2019
Artificial intelligence in diagnostic imaging: impact on the radiography profession journal April 2020
Automatic segmentation of the mandible from computed tomography scans for 3D virtual surgical planning using the convolutional neural network journal September 2019
A preliminary application of intraoral Doppler ultrasound images to deep learning techniques for predicting late cervical lymph node metastasis in early tongue cancers journal November 2019
Clinically applicable deep learning framework for organs at risk delineation in CT images journal September 2019

Similar Records

Related Subjects

62 RADIOLOGY AND NUCLEAR MEDICINE
Radiology
nuclear medicine & medical imaging
fully convolutional neural network
head and neck cancer
image segmentation
shape representation model