Automated nasopharyngeal carcinoma segmentation in magnetic resonance images by combination of convolutional neural networks and graph cut

Ma,Zongqing; Wu,Xi; Song,Qi; Luo,Yong; Wang,Yan; Zhou,Jiliu

doi:10.3892/etm.2018.6478

Automated nasopharyngeal carcinoma segmentation in magnetic resonance images by combination of convolutional neural networks and graph cut

Authors:
- Zongqing Ma
- Xi Wu
- Qi Song
- Yong Luo
- Yan Wang
- Jiliu Zhou
View Affiliations

Affiliations: College of Computer Science, Sichuan University, Chengdu, Sichuan 610065, P.R. China, School of Computer Science, Chengdu University of Information Technology, Chengdu, Sichuan 610225, P.R. China, CuraCloud Corp., Seattle, WA 98104, USA, Department of Head and Neck and Mammary Oncology, West China Hospital, Sichuan University, Chengdu, Sichuan 610041, P.R. China
Published online on: July 18, 2018 https://doi.org/10.3892/etm.2018.6478
Pages: 2511-2521
Copyright: © Ma et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

Accurate and reliable segmentation of nasopharyngeal carcinoma (NPC) in medical images is an import task for clinical applications, including radiotherapy. However, NPC features large variations in lesion size and shape, as well as inhomogeneous intensities within the tumor and similar intensity to that of nearby tissues, making its segmentation a challenging task. The present study proposes a novel automated NPC segmentation method in magnetic resonance (MR) images by combining a deep convolutional neural network (CNN) model and a 3‑dimensional (3D) graph cut‑based method in a two‑stage manner. First, a multi‑view deep CNN‑based segmentation method is performed. A voxel‑wise initial segmentation is generated by integrating the inferential classification information of three trained single‑view CNNs. Instead of directly using the CNN classification results to achieve a final segmentation, the proposed method uses a 3D graph cut‑based method to refine the initial segmentation. Specifically, the probability response map obtained using the multi‑view CNN method is utilized to calculate the region cost, which represents the likelihood of a voxel being assigned to the tumor or non‑tumor. Structure information in 3D from the original MR images is used to calculate the boundary cost, which measures the difference between the two voxels in the 3D neighborhood. The proposed method was evaluated on T1‑weighted images from 30 NPC patients using the leave‑one‑out method. The experimental results demonstrated that the proposed method is effective and accurate for NPC segmentation.

View Figures

View References

1	Chang ET and Adami HO: The enigmatic epidemiology of nasopharyngeal carcinoma. Cancr Epidemiol Biomarkers Prev. 15:1765–1777. 2006. View Article : Google Scholar
2	Lee FK, Yeung DK, King AD, Leung SF and Ahuja A: Segmentation of nasopharyngeal carcinoma (NPC) lesions in MR images. Int J Radiat Oncol Biol Phys. 61:608–620. 2005. View Article : Google Scholar : PubMed/NCBI
3	Tatanun C, Ritthipravat P, Bhongmakapat T and Tuntiyatorn L: Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique. Signal Processing Systems (ICSPS), 2010. 2nd International Conference on. 2010.(DOI: 10.1109/ICSPS.2010.5555663). View Article : Google Scholar
4	Chanapai W, Bhongmakapat T, Tuntiyatorn L and Ritthipravat P: Nasopharyngeal carcinoma segmentation using a region growing technique. Int J Comput Assist Radiol Surg. 7:413–422. 2012. View Article : Google Scholar : PubMed/NCBI
5	Huang KW, Zhao ZY, Gong Q, Zha J, Chen L and Yang R: Nasopharyngeal carcinoma segmentation via HMRF-EM with maximum entropy. Conf Proc IEEE Eng Med Biol Soc. 2968–2972. 2015.(DOI: 10.1109/EMBC.2015.7319015). PubMed/NCBI
6	Fitton I, Cornelissen SA, Duppen JC, Steenbakkers RJ, Peeters ST, Hoebers FJ, Kaanders JH, Nowak PJ, Rasch CR and van Herk M: Semi-automatic delineation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer. Med Phys. 38:4662–4666. 2011. View Article : Google Scholar : PubMed/NCBI
7	Zhou J, Chan KL, Xu P and Chong VFH: Nasopharyngeal carcinoma lesion segmentation from MR images by support vector machine. In Biomedical Imaging: Nano to Macro, 2006. The 3rd IEEE International Symposium on. 2006.(DOI: 10.1109/ISBI.2006.1625180).
8	Zhou J, Lim TK, Chong V and Huang J: Segmentation and visualization of nasopharyngeal carcinoma using MRI. Comput Biol Med. 33:407–424. 2003. View Article : Google Scholar : PubMed/NCBI
9	LeCun Y, Bottou L, Bengio Y and Haffner P: Gradient-based learning applied to document recognition. Proc IEEE. 86:2278–2324. 1998. View Article : Google Scholar
10	Krizhevsky A, Sutskever I and Hinton GE: ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 1:1097–1105, 2012. 2012.
11	Prasoon A, Petersen K, Igel C, Lauze F, Dam E and Nielsen M: Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. Med Image Comput Comput Assist Interv. 16:246–253. 2013.PubMed/NCBI
12	Roth HR, Farag A, Lu L, Turkbey EB and Summers RM: Deep convolutional networks for pancreas segmentation in CT imaging. SPIE Med Imag. 94131G. 2015.(DOI: 10.1117/12.2081420).
13	Liskowski P and Krawiec K: Segmenting retinal blood vessels with deep neural networks. IEEE Trans Med Imaging. 35:2369–2380. 2016. View Article : Google Scholar : PubMed/NCBI
14	Zhang W, Li R, Deng H, Wang L, Lin W, Ji S and Shen D: Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. Neuroimage. 108:214–224. 2015. View Article : Google Scholar : PubMed/NCBI
15	Moeskops P, Viergever MA, Mendrik AM, de Vries LS, Benders MJ and Isgum I: Automatic segmentation of MR brain images with a convolutional neural network. IEEE Trans Med Imaging. 35:1252–1261. 2016. View Article : Google Scholar : PubMed/NCBI
16	Pereira S, Pinto A, Alves V and Silva CA: Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging. 35:1240–1251. 2016. View Article : Google Scholar : PubMed/NCBI
17	Zikic D, Ioannou Y, Brown M and Criminisi A: Segmentation of brain tumor tissues with convolutional neural networks. MICCAI Multi Brain Tumor Segment Challeng (BraTS). 2014:36–39. 2014.
18	Havaei M, Ddavy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin PM and Larochelle H: Brain tumor segmentation with deep neural networks. Med Image Anal. 35:18–31. 2017. View Article : Google Scholar : PubMed/NCBI
19	Ma ZQ, Wu X and Zhou JL: Automatic nasopharyngeal carcinoma segmentation in MR images with convolutional neural networks. 2017 Int Conference Front Adv Data. 147–150. 2017. View Article : Google Scholar
20	Tustison NJ, Avants BB, Cook PA, Zheng Y, Eqan A, Yushkevich PA and Gee JC: N4ITK: Improved N3 bias correction. IEEE Trans Med Imaging. 29:1310–1320. 2010. View Article : Google Scholar : PubMed/NCBI
21	Nyúl LG, Udupa JK and Zhang X: New variants of a method of MRI scale standardization. IEEE Trans Med Imaging. 19:143–150. 2000. View Article : Google Scholar : PubMed/NCBI
22	Hinton GE, Srivastava N, Krizhevsky A, Sutskever I and Salakhutdinov RR: Improving neural networks by preventing co-adaptation of feature detectors. Neural Evolution Comput. 2012.
23	Jarrett K, Kavukcuogly K, Ranzato M and LeCun Y: What is the best multi-stage architecture for object recognition? IEEE. 1–2153. 2009.
24	Boykov Y, Veksler O and Zabih R: Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Anal Mach Intell. 23:1222–1239. 2001. View Article : Google Scholar
25	Boykov Y and Funka-Lea G: Graph cuts and efficient N-D image segmentation. Int J Comput Vis. 70:109–131. 2006. View Article : Google Scholar
26	Grosgeorge D, Petitjean C, Dacher JN and Ruan S: Graph cut segmentation with a statistical shape model in cardiac MRI. Comput Vis Image Understand. 117:1027–1035. 2013. View Article : Google Scholar
27	Martinez-Muñoz S, Ruiz-Fernandez D and Galiana-Merino JJ: Automatic abdominal aortic aneurysm segmentation in MR images. Expert Syst Applicat. 54:78–87. 2016. View Article : Google Scholar
28	Mahapatra D and Buhmann JM: Prostate MRI segmentation using learned semantic knowledge and graph cuts. IEEE Trans Biomed Eng. 61:756–764. 2014. View Article : Google Scholar : PubMed/NCBI
29	Tian Z, Liu L, Zhang Z and Fei B: Superpixel-based segmentation for 3D prostate MR images. IEEE Trans Med Imaging. 35:791–801. 2016. View Article : Google Scholar : PubMed/NCBI
30	Song Q, Bai J, Han D, Bhatia S, Sun W, Rockey W, Bayouth JE, Buatti JM and Wu X: Optimal co-segmentation of tumor in PET-CT images with context information. IEEE Trans Med Imaging. 32:1685–1697. 2013. View Article : Google Scholar : PubMed/NCBI
31	Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S and Darrell T: Caffe: Convolutional architecture for fast feature embedding. Proceed of the 22nd ACM Int Conferen Multimedia. ACM; pp. 675–678. 2014
32	Glorot X and Bengio Y: Understanding the difficulty of training deep feedforward neural networks. in Proc Int Conf Artif Intell Stat. 2010:249–256. 2010.
33	Sutskever I, Martens J, Dahl G and Hinton G: On the importance of initialization and momentum in deep learning. PMLR. 28:1139–1147. 2013.