Share this content in WeChat
Research progress of nasopharyngeal carcinoma using deep learning based on MRI
SU Xiaohong  JIN Guanqiao 

Cite this article as: SU X H, JIN G Q. Research progress of nasopharyngeal carcinoma using deep learning based on MRI[J]. Chin J Magn Reson Imaging, 2023, 14(3): 170-174, 188. DOI:10.12015/issn.1674-8034.2023.03.031.

[Abstract] MRI is the preferred non-invasive imaging method for nasopharyngeal carcinoma (NPC). At present, the image processing and analysis of NPC mainly relies on manual work, which is not only subjective but also time-consuming and labor-intensive. Deep learning (DL), as an implementation method of artificial intelligence, can independently detect and select the best features to complete image processing tasks, improve the efficiency and accuracy of image analysis, and show great application potential in the field of image analysis, its applications in NPC has also attracted much attention. This paper briefly introduces the concept of DL, and reviews the research progress of MRI based DL in tumor segmentation, image synthesis, diagnosis and prognosis prediction. It is expected to provide reference value for future research, promote the application of DL in NPC, and help clinicians make diagnosis and treatment decisions.
[Keywords] nasopharyngeal carcinoma;magnetic resonance imaging;deep learning;tumor segmentation;image synthesis;differential diagnosis;prognosis prediction

SU Xiaohong   JIN Guanqiao*  

Department of Radiology, Affiliated Cancer Hospital of Guangxi Medical University, Guangxi Clinical Medical Research Center of Imaging Medicine, Guangxi Key Clinical Specialty (Medical Imaging Department), Dominant Cultivation Discipline of Affiliated Cancer Hospital of Guangxi Medical University (Medical Imaging Department), Nanning 530021, China

Corresponding author: Jin GQ, E-mail:

Conflicts of interest   None.

Received  2022-10-24
Accepted  2023-02-15
DOI: 10.12015/issn.1674-8034.2023.03.031
Cite this article as: SU X H, JIN G Q. Research progress of nasopharyngeal carcinoma using deep learning based on MRI[J]. Chin J Magn Reson Imaging, 2023, 14(3): 170-174, 188. DOI:10.12015/issn.1674-8034.2023.03.031.

SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
CHEN Y P, CHAN A T C, LE Q T, et al. Nasopharyngeal carcinoma[J]. Lancet, 2019, 394(10192): 64-80. DOI: 10.1016/s0140-6736(19)30956-0.
BOSSI P, CHAN A T, LICITRA L, et al. Nasopharyngeal carcinoma: ESMO-EURACAN Clinical Practice Guidelines for diagnosis, treatment and follow-up[J]. Ann Oncol, 2021, 32(4): 452-465. DOI: 10.1016/j.annonc.2020.12.007.
TANG L L, CHEN Y P, CHEN C B, et al. The Chinese Society of Clinical Oncology (CSCO) clinical guidelines for the diagnosis and treatment of nasopharyngeal carcinoma[J]. Cancer Commun (Lond), 2021, 41(11): 1195-1227. DOI: 10.1002/cac2.12218.
SANTOS M K, FERREIRA JÚNIOR J R, WADA D T, et al. Artificial intelligence, machine learning, computer-aided diagnosis, and radiomics: advances in imaging towards to precision medicine[J]. Radiol Bras, 2019, 52(6): 387-396. DOI: 10.1590/0100-3984.2019.0049.
LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. DOI: 10.1038/nature14539.
JIN Z Y, GAN T Y, WANG P, et al. Deep learning for gastroscopic images: computer-aided techniques for clinicians[J/OL]. BioMed Eng OnLine, 2022, 21(1): 12 [2022-10-22]. DOI: 10.1186/s12938-022-00979-8.
NAGENDRAN M, CHEN Y, LOVEJOY C A, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies[J/OL]. BMJ, 2020, 368: m689 [2022-10-22]. DOI: 10.1136/bmj.m689.
SOFFER S, BEN-COHEN A, SHIMON O, et al. Convolutional neural networks for radiologic images: a radiologist's guide[J]. Radiology, 2019, 290(3): 590-606. DOI: 10.1148/radiol.2018180547.
SCHMIDHUBER J. Generative Adversarial Networks are special cases of Artificial Curiosity (1990) and also closely related to Predictability Minimization (1991)[J]. Neural Netw, 2020, 127: 58-66. DOI: 10.1016/j.neunet.2020.04.008.
LI Q L, XU Y Z, CHEN Z W, et al. Tumor segmentation in contrast-enhanced magnetic resonance imaging for nasopharyngeal carcinoma: deep learning with convolutional neural network[J/OL]. Biomed Res Int, 2018, 2018: 9128527 [2022-10-22]. DOI: 10.1155/2018/9128527.
KE L, DENG Y, XIA W, et al. Development of a self-constrained 3D DenseNet model in automatic detection and segmentation of nasopharyngeal carcinoma using magnetic resonance images[J/OL]. Oral Oncol, 2020, 110: 104862 [2022-10-22]. DOI: 10.1016/j.oraloncology.2020.104862.
LIN L, DOU Q, JIN Y M, et al. Deep learning for automated contouring of primary tumor volumes by MRI for nasopharyngeal carcinoma[J]. Radiology, 2019, 291(3): 677-686. DOI: 10.1148/radiol.2019182012.
ZHANG J J, GU L, HAN G H, et al. AttR2U-net: a fully automated model for MRI nasopharyngeal carcinoma segmentation based on spatial attention and residual recurrent convolution[J/OL]. Front Oncol, 2022, 11: 816672 [2022-10-22]. DOI: 10.3389/fonc.2021.816672.
LI Y, HAN G, LIU X. DCNet: densely connected deep convolutional encoder-decoder network for nasopharyngeal carcinoma segmentation[J/OL]. Sensors (Basel), 2021, 21(23): 7877 [2022-10-22]. DOI: 10.3390/s21237877.
CHEN Y, HAN G, LIN T, et al. CAFS: an attention-based Co-segmentation semi-supervised method for nasopharyngeal carcinoma segmentation[J/OL]. Sensors (Basel), 2022, 22(13): 5053 [2022-10-22]. DOI: 10.3390/s22135053.
LIU Y, HAN G, LIU X. Lightweight compound scaling network for nasopharyngeal carcinoma segmentation from MR images[J/OL]. Sensors (Basel), 2022, 22(15): 5875 [2022-10-22]. DOI: 10.3390/s22155875.
WONG L M, AI Q Y H, MO F K F, et al. Convolutional neural network in nasopharyngeal carcinoma: how good is automatic delineation for primary tumor on a non-contrast-enhanced fat-suppressed T2-weighted MRI?[J]. Jpn J Radiol, 2021, 39(6): 571-579. DOI: 10.1007/s11604-021-01092-x.
WONG L M, AI Q Y H, POON D M C, et al. A convolutional neural network combined with positional and textural attention for the fully automatic delineation of primary nasopharyngeal carcinoma on non-contrast-enhanced MRI[J]. Quant Imaging Med Surg, 2021, 11(9): 3932-3944. DOI: 10.21037/qims-21-196.
MA Z Q, WU X, SONG Q, et al. Automated nasopharyngeal carcinoma segmentation in magnetic resonance images by combination of convolutional neural networks and graph cut[J]. Exp Ther Med, 2018, 16(3): 2511-2521. DOI: 10.3892/etm.2018.6478.
MA Z, ZHOU S, WU X, et al. Nasopharyngeal carcinoma segmentation based on enhanced convolutional neural networks using multi-modal metric learning[J/OL]. Phys Med Biol, 2019, 64(2): 025005 [2022-10-22]. DOI: 10.1088/1361-6560/aaf5da.
YE Y, CAI Z, HUANG B, et al. Fully-automated segmentation of nasopharyngeal carcinoma on dual-sequence MRI using convolutional neural networks[J/OL]. Front Oncol, 2020, 10: 166 [2022-10-22]. DOI: 10.3389/fonc.2020.00166.
MARTIN R J, SHARMA U, KAUR K, et al. Multidimensional CNN-based deep segmentation method for tumor identification[J/OL]. Biomed Res Int, 2022, 2022: 5061112 [2022-10-22]. DOI: 10.1155/2022/5061112.
OWRANGI A M, GREER P B, GLIDE-HURST C K. MRI-only treatment planning: benefits and challenges[J/OL]. Phys Med Biol, 2018, 63(5): 05TR01 [2022-10-22]. DOI: 10.1088/1361-6560/aaaca4.
LIU Y X, CHEN A N, SHI H Y, et al. CT synthesis from MRI using multi-cycle GAN for head-and-neck radiation therapy[J/OL]. Comput Med Imaging Graph, 2021, 91: 101953 [2022-10-22]. DOI: 10.1016/j.compmedimag.2021.101953.
O'CONNOR L M, DOWLING J A, CHOI J H, et al. Validation of an MRI-only planning workflow for definitive pelvic radiotherapy[J/OL]. Radiat Oncol, 2022, 17(1): 55 [2022-10-22]. DOI: 10.1186/s13014-022-02023-4.
LEU S C, HUANG Z B, LIN Z W. Generation of pseudo-CT using high-degree polynomial regression on dual-contrast pelvic MRI data[J/OL]. Sci Rep, 2020, 10: 8118 [2022-10-22]. DOI: 10.1038/s41598-020-64842-3.
RANJAN A, LALWANI D, MISRA R. GAN for synthesizing CT from T2-weighted MRI data towards MR-guided radiation treatment[J]. MAGMA, 2022, 35(3): 449-457. DOI: 10.1007/s10334-021-00974-5.
HAN X. MR-based synthetic CT generation using a deep convolutional neural network method[J]. Med Phys, 2017, 44(4): 1408-1419. DOI: 10.1002/mp.12155.
CARNEIRO G, MATEUS D, PETER L, et al. Deep Learning and Data Labeling for Medical Applications: First International Workshop, LABELS 2016, and Second International Workshop, DLMIA 2016, Held in Conjunction with MICCAI 2016, Athens, Greece, October 21, 2016, Proceedings[M]. Cham: Springer International Publishing, 2016. DOI: 10.1007/978-3-319-46976-8.
WANG Y, LIU C, ZHANG X, et al. Synthetic CT generation based on T2 weighted MRI of nasopharyngeal carcinoma (NPC) using a deep convolutional neural network (DCNN)[J/OL]. Front Oncol, 2019, 9: 1333 [2022-10-22]. DOI: 10.3389/fonc.2019.01333.
EMAMI H, DONG M, NEJAD-DAVARANI S P, et al. Generating synthetic CTs from magnetic resonance images using generative adversarial networks[J/OL]. Med Phys, 2018 [2022-10-22]. DOI: 10.1002/mp.13047.
REZA K, CHRISTINA M, WINFIELD JESSICA M, et al. CT-based pelvic T1-weighted MR image synthesis using UNet, UNet++ and cycle-consistent generative adversarial network (cycle-GAN)[J/OL]. Front Oncol, 2021, 11: 665807 [2022-10-22]. DOI: 10.3389/fonc.2021.665807.
QI M K, LI Y B, WU A Q, et al. Multi-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapy[J]. Med Phys, 2020, 47(4): 1880-1894. DOI: 10.1002/mp.14075.
TIE X, LAM S K, ZHANG Y, et al. Pseudo-CT generation from multi-parametric MRI using a novel multi-channel multi-path conditional generative adversarial network for nasopharyngeal carcinoma patients[J]. Med Phys, 2020, 47(4): 1750-1762. DOI: 10.1002/mp.14062.
MA X, CHEN X, LI J, et al. MRI-only radiotherapy planning for nasopharyngeal carcinoma using deep learning[J/OL]. Front Oncol, 2021, 11: 713617 [2022-10-22]. DOI: 10.3389/fonc.2021.713617.
SONG L M, LI Y F, DONG G Y, et al. Artificial intelligence-based bone-enhanced magnetic resonance image-a computed tomography/magnetic resonance image composite image modality in nasopharyngeal carcinoma radiotherapy[J]. Quant Imaging Med Surg, 2021, 11(12): 4709-4720. DOI: 10.21037/qims-20-1239.
WONG L M, KING A D, AI Q Y H, et al. Convolutional neural network for discriminating nasopharyngeal carcinoma and benign hyperplasia on MRI[J]. Eur Radiol, 2021, 31(6): 3856-3863. DOI: 10.1007/s00330-020-07451-y.
ZHANG L, HUANG Y, HONG S D, et al. Gemcitabine plus cisplatin versus fluorouracil plus cisplatin in recurrent or metastatic nasopharyngeal carcinoma: a multicentre, randomised, open-label, phase 3 trial[J]. Lancet, 2016, 388(10054): 1883-1892. DOI: 10.1016/S0140-6736(16)31388-5.
YANG Q, GUO Y, OU X M, et al. Automatic T staging using weakly supervised deep learning for nasopharyngeal carcinoma on MR images[J]. J Magn Reson Imaging, 2020, 52(4): 1074-1082. DOI: 10.1002/jmri.27202.
JING B, DENG Y, ZHANG T, et al. Deep learning for risk prediction in patients with nasopharyngeal carcinoma using multi-parametric MRIs[J/OL]. Comput Methods Programs Biomed, 2020, 197: 105684 [2022-10-22]. DOI: 10.1016/j.cmpb.2020.105684.
QIANG M Y, LI C F, SUN Y Y, et al. A prognostic predictive system based on deep learning for locoregionally advanced nasopharyngeal carcinoma[J]. J Natl Cancer Inst, 2021, 113(5): 606-615. DOI: 10.1093/jnci/djaa149.
CAO X, CHEN X, LIN Z C, et al. Add-on individualizing prediction of nasopharyngeal carcinoma using deep-learning based on MRI: a multicentre, validation study[J/OL]. iScience, 2022, 25(9): 104841 [2022-10-22]. DOI: 10.1016/j.isci.2022.104841.
WU X J, DONG D, ZHANG L, et al. Exploring the predictive value of additional peritumoral regions based on deep learning and radiomics: a multicenter study[J]. Med Phys, 2021, 48(5): 2374-2385. DOI: 10.1002/mp.14767.
HUA H L, DENG Y Q, LI S, et al. Deep learning for predicting distant metastasis in patients with nasopharyngeal carcinoma based on pre-radiotherapy magnetic resonance imaging[J/OL]. Comb Chem High Throughput Screen, 2022 [2022-10-22]. DOI: 10.2174/1386207325666220919091210.
LI S, DENG Y Q, HUA H L, et al. Deep learning for locally advanced nasopharyngeal carcinoma prognostication based on pre- and post-treatment MRI[J/OL]. Comput Methods Programs Biomed, 2022, 219: 106785 [2022-10-22].
MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
ZHONG L Z, FANG X L, DONG D, et al. A deep learning MR-based radiomic nomogram may predict survival for nasopharyngeal carcinoma patients with stage T3N1M0[J]. Radiother Oncol, 2020, 151: 1-9. DOI: 10.1016/j.radonc.2020.06.050.
ZHONG L Z, DONG D, FANG X L, et al. A deep learning-based radiomic nomogram for prognosis and treatment decision in advanced nasopharyngeal carcinoma: a multicentre study[J/OL]. EBioMedicine, 2021, 70: 103522 [2022-10-22]. DOI: 10.1016/j.ebiom.2021.103522.
ZHANG L, WU X J, LIU J, et al. MRI-based deep-learning model for distant metastasis-free survival in locoregionally advanced nasopharyngeal carcinoma[J]. J Magn Reson Imaging, 2021, 53(1): 167-178. DOI: 10.1002/jmri.27308.

PREV Application progress of MRI in demonstrating the facial nerve in the parotid gland
NEXT The research progress in predicting the efficacy of neoadjuvant chemotherapy for breast cancer according to longitudinal images-based deep learning

Tel & Fax: +8610-67113815    E-mail: