Share：
Share this content in WeChat
X
[Chinese] [PDF] 204 8
• Review •
Research progress on predicting the prognosis of nasopharyngeal carcinoma based on magnetic resonance imaging features
CHEN Hongyu  LIU Daihong  REN Huanhuan  ZHANG Jiuquan 

DOI:10.12015/issn.1674-8034.2025.08.031.


[Abstract] Nasopharyngeal carcinoma is one of the most prevalent head and neck malignancies in China. While patients diagnosed at an early stage generally exhibit a favorable prognosis, those with locally advanced disease face relatively poorer outcomes. Accurate prognosis prediction plays a crucial role in enabling individualized treatment strategies and improving overall survival rates. Conventional MRI provides semantic features, such as tumor size, shape, and extent of invasion, that are closely associated with tumor staging, thereby offering direct insight into tumor burden and infiltration. Artificial intelligence approaches, including traditional radiomics and deep learning techniques, enable the automatic extraction of high-dimensional image features and facilitate further exploration of intratumoral heterogeneity. In recent years, multi-omics methodologies have integrated clinical, MRI, and pathological data through deep learning frameworks to enhance prognostic accuracy. Moreover, habitat imaging technology, which segments tumors into distinct sub-regions and captures microenvironmental variations among them, has demonstrated promising potential in predicting tumor recurrence. This article presents a systematic review of recent advances in the use of conventional MRI-based semantic features (e.g., T2WI and contrast-enhanced T1WI), radiomics, deep learning, and habitat imaging for the prognosis prediction of nasopharyngeal carcinoma. It also analyzes and compares the strengths and limitations of these approaches and explores potential future directions aimed at refining the prognostic evaluation system for this disease.
[Keywords] nasopharyngeal carcinoma；predicting prognosis；magnetic resonance imaging；artificial intelligence；habitat imaging

CHEN Hongyu1, 2   LIU Daihong1, 2   REN Huanhuan2   ZHANG Jiuquan1, 2*  

1 School of Medicine, Chongqing University, Chongqing 400030, China

2 Department of Radiology, Chongqing University Cancer Hospital, Chongqing 400030, China

Corresponding author: ZHANG J Q, E-mail: zhangjq_radiol@foxmail.com

Conflicts of interest   None.

Received  2025-05-16
Accepted  2025-08-05
DOI: 10.12015/issn.1674-8034.2025.08.031
DOI:10.12015/issn.1674-8034.2025.08.031.

[1]
WONG K C W, HUI E P, LO K W, et al. Nasopharyngeal carcinoma: an evolving paradigm[J]. Nat Rev Clin Oncol, 2021, 18(11): 679-695. DOI: 10.1038/s41571-021-00524-x.
[2]
SONG L N, LIU J J, SHANG Y, et al. Enhanced MRI radiomics based model for predicting recurrence or metastasis of nasopharyngeal cancer (NC) undergoing concurrent chemoradiotherapy: a retrospective study[J/OL]. Cancer Control, 2024, 31: 10732748241250208 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/38716756/. DOI: 10.1177/10732748241250208.
[3]
SUN Y, LI W F, CHEN N Y, et al. Induction chemotherapy plus concurrent chemoradiotherapy versus concurrent chemoradiotherapy alone in locoregionally advanced nasopharyngeal carcinoma: a phase 3, multicentre, randomised controlled trial[J]. Lancet Oncol, 2016, 17(11): 1509-1520. DOI: 10.1016/S1470-2045(16)30410-7.
[4]
ZHANG Y, CHEN L, HU G Q, et al. Gemcitabine and cisplatin induction chemotherapy in nasopharyngeal carcinoma[J]. N Engl J Med, 2019, 381(12): 1124-1135. DOI: 10.1056/NEJMoa1905287.
[5]
LIU X, ZHANG Y, YANG K Y, et al. Induction-concurrent chemoradiotherapy with or without sintilimab in patients with locoregionally advanced nasopharyngeal carcinoma in China (CONTINUUM): a multicentre, open-label, parallel-group, randomised, controlled, phase 3 trial[J]. Lancet, 2024, 403(10445): 2720-2731. DOI: 10.1016/S0140-6736(24)00594-4.
[6]
LIU J, ZHU J, WANG Y X, et al. Arterial spin labeling of nasopharyngeal carcinoma shows early therapy response[J/OL]. Insights Imaging, 2022, 13(1): 114 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/35796807/. DOI: 10.1186/s13244-022-01248-x.
[7]
LI Y G, LIU Q, WU W Q, et al. Intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) combined with conventional MRI for the detection of skull-base invasion in nasopharyngeal carcinoma: comparison with 18F-sodium fluoride (18F-NaF) positron emission tomography/computed tomography (PET/CT)[J]. Quant Imaging Med Surg, 2024, 14(9): 6908-6921. DOI: 10.21037/qims-24-745.
[8]
CHEN S Y, DAI J K, ZHAO J, et al. Synthetic MRI combined with clinicopathological characteristics for pretreatment prediction of chemoradiotherapy response in advanced nasopharyngeal carcinoma[J]. Korean J Radiol, 2025, 26(2): 135-145. DOI: 10.3348/kjr.2024.0385.
[9]
WANG Z P, FANG M J, ZHANG J, et al. Radiomics and deep learning in nasopharyngeal carcinoma: a review[J/OL]. IEEE Rev Biomed Eng, 2024, 17: 118-135 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/37097799/. DOI: 10.1109/RBME.2023.3269776.
[10]
MUI A W L, LEE A W M, LEE V H F, et al. Prognostic and therapeutic evaluation of nasopharyngeal carcinoma by dynamic contrast-enhanced (DCE), diffusion-weighted (DW) magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS)[J/OL]. Magn Reson Imag, 2021, 83: 50-56 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/34246785/. DOI: 10.1016/j.mri.2021.07.003.
[11]
LIU T, DONG D, ZHAO X, et al. Radiomic signatures reveal multiscale intratumor heterogeneity associated with tissue tolerance and survival in re-irradiated nasopharyngeal carcinoma: a multicenter study[J/OL]. BMC Med, 2023, 21(1): 464 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/38012705/. DOI: 10.1186/s12916-023-03164-3.
[12]
JIANG H Y, DIAO Z S, SHI T Y, et al. A review of deep learning-based multiple-lesion recognition from medical images: classification, detection and segmentation[J/OL]. Comput Biol Med, 2023, 157: 106726 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/36924732/. DOI: 10.1016/j.compbiomed.2023.106726.
[13]
PAUL R, SCHABATH M, BALAGURUNATHAN Y, et al. Explaining deep features using radiologist-defined semantic features and traditional quantitative features[J]. Tomography, 2019, 5(1): 192-200. DOI: 10.18383/j.tom.2018.00034.
[14]
PAN J J, MAI H Q, NG W T, et al. Ninth version of the AJCC and UICC nasopharyngeal cancer TNM staging classification[J]. JAMA Oncol, 2024, 10(12): 1627-1635. DOI: 10.1001/jamaoncol.2024.4354.
[15]
XIE D H, WU Z, LI W Z, et al. Individualized clinical target volume delineation and efficacy analysis in unilateral nasopharyngeal carcinoma treated with intensity-modulated radiotherapy (IMRT): 10-year summary[J]. J Cancer Res Clin Oncol, 2022, 148(8): 1931-1942. DOI: 10.1007/s00432-022-03974-7.
[16]
CUI C Y, LI H J, MA H L, et al. Staging of T2 and T3 nasopharyngeal carcinoma: proposed modifications for improving the current AJCC staging system[J]. Cancer Med, 2020, 9(20): 7572-7579. DOI: 10.1002/cam4.3328.
[17]
YANG F, PENG W J, WEI H R, et al. Model-free parameters derived from intravoxel inherent motion combined with tumor aggressiveness indicators in predicting 5-year treatment outcome in NPC[J/OL]. Oral Oncol, 2025, 162: 107187 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/39987710/. DOI: 10.1016/j.oraloncology.2025.107187.
[18]
KANG M, ZHOU P T, LIAO X Y, et al. Prognostic value of masticatory muscle involvement in nasopharyngeal carcinoma patients treated with intensity-modulated radiation therapy[J/OL]. Oral Oncol, 2017, 75: 100-105 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/29224805/. DOI: 10.1016/j.oraloncology.2017.11.002.
[19]
GUO C M, LIANG S B, HUANG W J, et al. Cluster analysis and prognosis study of skull base bone destruction in nasopharyngeal carcinoma[J]. Sichuan Med J, 2022, 43(2): 123-129. DOI: 10.16252/j.cnki.issn1004-0501-2022.02.004.
[20]
DU X J, WANG G Y, ZHU X D, et al. Refining the 8th edition TNM classification for EBV related nasopharyngeal carcinoma[J/OL]. Cancer Cell, 2024, 42(3): 464-473.e3 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/38242125/. DOI: 10.1016/j.ccell.2023.12.020.
[21]
LI S Q, LUO C, HUANG W J, et al. Value of skull base invasion subclassification in nasopharyngeal carcinoma: implication for prognostic stratification and use of induction chemotherapy[J]. Eur Radiol, 2022, 32(11): 7767-7777. DOI: 10.1007/s00330-022-08864-7.
[22]
KIM S Y, TANG M L, CHIH S Y, et al. Involvement of p38 MAPK and MAPKAPK2 in promoting cell death and the inflammatory response to ischemic stress associated with necrotic glioblastoma[J/OL]. Cell Death Dis, 2025, 16(1): 12 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/39805854/. DOI: 10.1038/s41419-025-07335-3.
[23]
SUN X S, XIAO Z W, LIU S L, et al. Nasopharyngeal necrosis contributes to overall survival in nasopharyngeal carcinoma without distant metastasis: a comprehensive nomogram model[J]. Eur Radiol, 2023, 33(5): 3682-3692. DOI: 10.1007/s00330-023-09431-4.
[24]
PENG W S, XING X, LI Y J, et al. Prognostic nomograms for nasopharyngeal carcinoma with nodal features and potential indication for N staging system: Validation and comparison of seven N stage schemes[J/OL]. Oral Oncol, 2023, 144: 106438 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/37437499/. DOI: 10.1016/j.oraloncology.2023.106438.
[25]
ZHU Y L, LUO C, ZHOU S M, et al. Optimal size threshold for MRI-detected retropharyngeal lymph nodes to predict outcomes in nasopharyngeal carcinoma: a two-center study[J/OL]. AJR Am J Roentgenol, 2024, 222(1): e2329984 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/37753859/. DOI: 10.2214/AJR.23.29984.
[26]
JIANG W, WANG G Y, QIN G J, et al. Advanced image-identified extranodal extension of retropharyngeal lymph nodes in the refinement of N classification for nasopharyngeal carcinoma[J/OL]. Cell Rep Med, 2025, 6(2): 101942 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/39938522/. DOI: 10.1016/j.xcrm.2025.101942.
[27]
FU Y C, LIANG S B, HUANG W J, et al. Prognostic value of lymph node necrosis at different N stages in patients with nasopharyngeal carcinoma[J]. J Cancer, 2023, 14(11): 2085-2092. DOI: 10.7150/jca.84854.
[28]
LI J, ZHAO Q, ZHANG Y, et al. Prognostic value of quantitative cervical nodal necrosis burden on MRI in nasopharyngeal carcinoma and its role as a stratification marker for induction chemotherapy[J]. Eur Radiol, 2022, 32(11): 7710-7721. DOI: 10.1007/s00330-022-08785-5.
[29]
ZHAO Q, DONG A N, CUI C Y, et al. MRI-based metastatic nodal number and associated nomogram improve stratification of nasopharyngeal carcinoma patients: potential indications for individual induction chemotherapy[J]. J Magn Reson Imaging, 2023, 57(6): 1790-1802. DOI: 10.1002/jmri.28435.
[30]
LIU Y F, CHEN S H, DONG A N, et al. Nodal grouping in nasopharyngeal carcinoma: prognostic significance, N classification, and a marker for the identification of candidates for induction chemotherapy[J]. Eur Radiol, 2020, 30(4): 2115-2124. DOI: 10.1007/s00330-019-06537-6.
[31]
DONG A N, ZHU S Y, MA H L, et al. Matted lymph nodes on MRI in nasopharyngeal carcinoma: prognostic factor and potential indication for induction chemotherapy benefits[J]. J Magn Reson Imaging, 2024, 59(6): 1976-1990. DOI: 10.1002/jmri.29012.
[32]
ESTEVA A, FENG J, VAN DER WAL D, et al. Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials[J/OL]. NPJ Digit Med, 2022, 5(1): 71 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/35676445/. DOI: 10.1038/s41746-022-00613-w.
[33]
ZHANG Y C, DENG Y S, ZOU Q H, et al. Artificial intelligence for diagnosis and prognosis prediction of natural killer/T cell lymphoma using magnetic resonance imaging[J/OL]. Cell Rep Med, 2024, 5(5): 101551 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/38697104/. DOI: 10.1016/j.xcrm.2024.101551.
[34]
SHEN H S, WANG Y, LIU D H, et al. Predicting progression-free survival using MRI-based radiomics for patients with nonmetastatic nasopharyngeal carcinoma[J/OL]. Front Oncol, 2020, 10: 618 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/32477932/. DOI: 10.3389/fonc.2020.00618.
[35]
BAO D, LIU Z, GENG Y Y, et al. Baseline MRI-based radiomics model assisted predicting disease progression in nasopharyngeal carcinoma patients with complete response after treatment[J/OL]. Cancer Imaging, 2022, 22(1): 10 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/35090572/. DOI: 10.1186/s40644-022-00448-4.
[36]
LIN D F, LI H L, LIU T, et al. Radiomic signatures associated with tumor immune heterogeneity predict survival in locally recurrent nasopharyngeal carcinoma[J]. J Natl Cancer Inst, 2024, 116(8): 1294-1302. DOI: 10.1093/jnci/djae081.
[37]
LIU L, PEI W, LIAO H, et al. A clinical-radiomics nomogram based on magnetic resonance imaging for predicting progression-free survival after induction chemotherapy in nasopharyngeal carcinoma[J/OL]. Front Oncol, 2022, 12: 792535 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/35814380/. DOI: 10.3389/fonc.2022.792535.
[38]
ZHANG F, ZHONG L Z, ZHAO X, et al. A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study[J/OL]. Ther Adv Med Oncol, 2020, 12: 1758835920971416 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/33403013/. DOI: 10.1177/1758835920971416.
[39]
HOU J, YI X C, LI H D, et al. Integrative radiopathomics model for predicting progression-free survival in patients with nonmetastatic nasopharyngeal carcinoma[J/OL]. J Cancer Res Clin Oncol, 2024, 150(9): 415 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/39249584/. DOI: 10.1007/s00432-024-05930-z.
[40]
BOLOGNA M, CORINO V, CALARESO G, et al. Baseline MRI-radiomics can predict overall survival in non-endemic EBV-related nasopharyngeal carcinoma patients[J/OL]. Cancers (Basel), 2020, 12(10): 2958 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/33066161/. DOI: 10.3390/cancers12102958.
[41]
JING B Z, DENG Y S, 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 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/32781421/. DOI: 10.1016/j.cmpb.2020.105684.
[42]
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/OL]. Radiother Oncol, 2020, 151: 1-9 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/32634460/. DOI: 10.1016/j.radonc.2020.06.050.
[43]
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]. Comb Chem High Throughput Screen, 2023, 26(7): 1351-1363. DOI: 10.2174/1386207325666220919091210.
[44]
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 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/35397409/. DOI: 10.1016/j.cmpb.2022.106785.
[45]
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 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/36034225/. DOI: 10.1016/j.isci.2022.104841.
[46]
KOU J, PENG J Y, LV W B, et al. A serial MRI-based deep learning model to predict survival in patients with locoregionally advanced nasopharyngeal carcinoma[J/OL]. Radiol Artif Intell, 2025, 7(2): e230544 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/39812582/. DOI: 10.1148/ryai.230544.
[47]
YI X C, YU X P, LI C R, et al. Deep learning Radiopathomics based on pretreatment MRI and whole slide images for predicting overall survival in locally advanced nasopharyngeal carcinoma[J/OL]. Radiother Oncol, 2025, 209: 110949 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/40409367/. DOI: 10.1016/j.radonc.2025.110949.
[48]
ZHONG Z, XIAO F, KUANG D, et al. Development and validation of a multi-omics model integrating MR radiomics and immune scores for prognostic prediction in locally advanced nasopharyngeal carcinoma[J]. Flavour Fragr J, 2025, 40(4): 687-697. DOI: 10.1002/ffj.3861.
[49]
ZHAO Y, WANG X Y, CHE T T, et al. Multi-task deep learning for medical image computing and analysis: a review[J/OL]. Comput Biol Med, 2023, 153: 106496 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/36634599/. DOI: 10.1016/j.compbiomed.2022.106496.
[50]
GU B X, MENG M Y, XU M Z, et al. Multi-task deep learning-based radiomic nomogram for prognostic prediction in locoregionally advanced nasopharyngeal carcinoma[J]. Eur J Nucl Med Mol Imaging, 2023, 50(13): 3996-4009. DOI: 10.1007/s00259-023-06399-7.
[51]
MENG M Y, GU B X, FULHAM M, et al. Adaptive segmentation-to-survival learning for survival prediction from multi-modality medical images[J/OL]. NPJ Precis Oncol, 2024, 8(1): 232 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/39402129/. DOI: 10.1038/s41698-024-00690-y.
[52]
GATENBY R A, GROVE O, GILLIES R J. Quantitative imaging in cancer evolution and ecology[J]. Radiology, 2013, 269(1): 8-15. DOI: 10.1148/radiol.13122697.
[53]
ZHANG X, SU G H, CHEN Y, et al. Decoding intratumoral heterogeneity: clinical potential of habitat imaging based on radiomics[J/OL]. Radiology, 2023, 309(3): e232047 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/38085080/. DOI: 10.1148/radiol.232047.
[54]
ZHU Y M, ZHENG D C, XU S G, et al. Intratumoral habitat radiomics based on magnetic resonance imaging for preoperative prediction treatment response to neoadjuvant chemotherapy in nasopharyngeal carcinoma[J]. Jpn J Radiol, 2024, 42(12): 1413-1424. DOI: 10.1007/s11604-024-01639-8.
[55]
PAN M L, LU L, MU X Y, et al. Prediction of induction chemotherapy efficacy in patients with locally advanced nasopharyngeal carcinoma using habitat subregions derived from multi-modal MRI radiomics[J/OL]. Front Oncol, 2025, 15: 1539574 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/40438690/. DOI: 10.3389/fonc.2025.1539574.
[56]
WU Q Q, QIANG W G, PAN L, et al. Performance of MRI-based radiomics for prediction of residual disease status in patients with nasopharyngeal carcinoma after radical radiotherapy[J/OL]. Sci Rep, 2025, 15(1): 16758 [2025-05-15]. https://pubmed.ncbi.nlm.nih.gov/40368928/. DOI: 10.1038/s41598-025-00186-0.

PREV Clinical application advances of cardiac magnetic resonance in assessing right atrial function
NEXT Research progress of diffusion-weighted magnetic resonance imaging technology in the diagnosis and treatment of lung cancer
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn