Abstract
Radiation-induced xerostomia, as a major problem in radiation treatment of the head and neck cancer, is mainly due to the overdose irradiation injury to the parotid glands. Helical Tomotherapy-based megavoltage computed tomography (MVCT) imaging during the Tomotherapy treatment can be applied to monitor the successive variations in the parotid glands. While manual segmentation is time consuming, laborious, and subjective, automatic segmentation is quite challenging due to the complicated anatomical environment of head and neck as well as noises in MVCT images. In this article, we propose a localization-refinement scheme to segment the parotid gland in MVCT. After data pre-processing we use mask region convolutional neural network (Mask R-CNN) in the localization stage after data pre-processing, and design a modified U-Net in the following fine segmentation stage. To the best of our knowledge, this study is a pioneering work of deep learning on MVCT segmentation. Comprehensive experiments based on different data distribution of head and neck MVCTs and different segmentation models have demonstrated the superiority of our approach in terms of accuracy, effectiveness, flexibility, and practicability. Our method can be adopted as a powerful tool for radiation-induced injury studies, where accurate organ segmentation is crucial.
- [1] . 2016. Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. IEEE Transactions on Medical Imaging 35, 5 (
May 2016), 1229–1239.DOI : https://doi.org/10.1109/TMI.2016.2528821Google ScholarCross Ref
- [2] . 2016. Fast and robust segmentation of the striatum using deep convolutional neural networks. Journal of Neuroscience Methods 274, 1 (2016), 146–153.Google Scholar
Cross Ref
- [3] . 2016. 3D U-Net: Learning dense volumetric segmentation from sparse annotation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, , , , , and (Eds.), Springer International Publishing, Cham, 424.Google Scholar
- [4] . 2010. Radiotherapy dose-volume effects on salivary gland function. International Journal of Radiation Oncology*Biology*Physics 76, 3 (2010), S58–S63.Google Scholar
- [5] . 2017. CT image biomarkers to improve patient-specific prediction of radiation-induced xerostomia and sticky saliva. Radiotherapy Oncology 122, 2 (2017), 185–191.Google Scholar
- [6] . 2017. Mask R-CNN. In 2017 IEEE International Conference on Computer Vision. 2980–2988. https://doi.org/10.1109/ICCV.2017.322Google Scholar
- [7] . 2012. Lung tumor segmentation using electric flow lines for graph cuts. In Proceedings of the Image Analysis and Recognition, and (Eds.), Springer Berlin Heidelberg, Berlin, 206–213. Google Scholar
Digital Library
- [8] . 2018. Supervoxel based method for multi-atlas segmentation of brain MR images. Neuroimage 175, 15 (2018), 201–214.Google Scholar
Cross Ref
- [9] . 2017. Segmentation of organs-at-risks in head and neck CT images using convolutional neural networks. Medical Physics 44, 2 (2017), 547.Google Scholar
- [10] . 2012. NTCP models for patient-rated xerostomia and sticky saliva after treatment with intensity modulated radiotherapy for head and neck cancer: The role of dosimetric and clinical factors. Radiotherapy Oncology 105, 1 (2012), 101–106.Google Scholar
- [11] . 2016. Deep MRI brain extraction: A 3D convolutional neural network for skull stripping. NeuroImage 129, 1 (2016), 460–469.
DOI: https://doi.org/10.1016/j.neuroimage.2016.01.024Google Scholar - [12] . 2017. Residual and plain convolutional neural networks for 3D brain MRI classification. In Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging. 835–838.
DOI: https://doi.org/10.1109/ISBI.2017.7950647Google Scholar - [13] . 2015. A review of image segmentation methodologies in medical image. In Proceedings of the Advanced Computer and Communication Engineering Technology, , , , , and (Eds.), Springer International Publishing, Cham, 1069–1080.Google Scholar
- [14] . 2019. A Megavoltage CT image enhancement method for image-guided and adaptive helical tomotherapy. Frontiers in Oncology 9, 362 (2019), 362.
DOI: https://doi.org/10.3389/fonc.2019.00362Google Scholar - [15] . 2014. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis Machine Intelligence 39, 4 (2014), 640–651. Google Scholar
Digital Library
- [16] . 2017. Automatic segmentation of the clinical target volume and organs at risk in the planning CT for rectal cancer using deep dilated convolutional neural networks. Medical Physics 44, 12 (2017), 6377–6389.Google Scholar
- [17] . 2016. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. In Proceedings of the 2016 4th International Conference on 3D Vision. 565–571.
DOI: https://doi.org/10.1109/3DV.2016.79Google Scholar - [18] . 2016. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Transactions on Medical Imaging 35, 5 (2016), 1240–1251.Google Scholar
Cross Ref
- [19] . 2016. Deformable registration-based segmentation of the bowel on Megavoltage CT during pelvic radiotherapy. Physica Medica 32, 7 (2016), 898–904.Google Scholar
- [20] . 2017. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis Machine Intelligence 39, 6 (2017), 1137–1149. Google Scholar
Digital Library
- [21] . 2016. EP-1894: Evaluation of a novel method for automatic segmentation of rectum on daily MVCT prostate images. Radiotherapy Oncology 119, S1 (supplement) (2016), S896.Google Scholar
- [22] . 2015. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-assisted Intervention.Google Scholar
Cross Ref
- [23] . 2008. Patient dose from megavoltage computed tomography imaging. International Journal of Radiation Oncology*Biology*Physics 70, 5 (2008), 1579–1587.Google Scholar
- [24] . 1999. Megavoltage CT on a tomotherapy system. Physics in Medicine Biology 44, 10 (1999), 2597.Google Scholar
- [25] . 2013. Xerostomia after radiotherapy. Strahlentherapie Und Onkologie 189, 3 (2013), 216–222.Google Scholar
- [26] . 2009. Diffeomorphic demons: Efficient non-parametric image registration. Neuroimage 45, 1 (2009), S61–S72.Google Scholar
- [27] . 2014. OC-0178: Comparison of five workflows for automatic re-contouring in MIM software for the purpose of adaptive radiotherapy. Radiotherapy and Oncology 111, 1 (2014), S70.
DOI: https://doi.org/10.1016/S0167-8140(15)30283-8ESTRO 33, 4–8 April 2014, Vienna, Austria. Google Scholar - [28] . 2018. Early prediction of acute xerostomia during radiation therapy for head and neck cancer based on texture analysis of daily CT. International Journal of Radiation Oncology* Biology* Physics 102, 4 (2018), 1308–1318.Google Scholar
- [29] . 2016. Spatial clockwork recurrent neural network for muscle perimysium segmentation. In Proceedings of the Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, , , , , and (Eds.), Springer International Publishing, Cham, 185–193.Google Scholar
- [30] . 2017. Deep convolutional neural networks for automatic segmentation of left ventricle cavity from cardiac magnetic resonance images. Iet Computer Vision 11, 8 (2017), 643–649.Google Scholar
Cross Ref
- [31] . 2019. Knowledge-Aided convolutional neural network for small organ segmentation. IEEE Journal of Biomedical and Health Informatics 23, 4 (
July 2019), 1363–1373.DOI: https://doi.org/10.1109/JBHI.2019.2891526Google ScholarCross Ref
Index Terms
Automatic Parotid Gland Segmentation in MVCT Using Deep Convolutional Neural Networks
Recommendations
Brain Tumor Segmentation with Cascaded Deep Convolutional Neural Network
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain InjuriesAbstractCancer is the second leading cause of death globally and is responsible for an estimated 9.6 million deaths in 2018. Approximately 70% of deaths from cancer occur in low and middle-income countries. One defining feature of cancer is the rapid ...
Lung CT Image Segmentation Using Deep Neural Networks
Lung CT image segmentation is a necessary initial step for lung image analysis, it is a prerequisite step to provide an accurate lung CT image analysis such as lung cancer detection.In this work, we propose a lung CT image segmentation using the U-net ...
Gland segmentation in colorectal cancer histopathological images using U-net inspired convolutional network
AbstractThe accurate gland segmentation from digitized H&E (hematoxylin and eosin) histology images with a wide range of histologic grades of cancer is quite challenging. The methodologies proposed in recent researches have performed well in segmenting ...






Comments