Skip to content
2000
Volume 18, Issue 3
  • ISSN: 1874-4710
  • E-ISSN: 1874-4729

Abstract

Introduction

Nasopharyngeal Carcinoma (NPC) exhibits high incidence in southern China. Despite improved survival with intensity-modulated radiotherapy (IMRT), 10%-20% of patients experience local recurrence. Traditional TNM staging fails to reflect tumor heterogeneity, necessitating robust recurrence prediction models. This study aimed to develop an MRI-based NPC recurrence prediction model by integrating radiomics, deep learning, and clinical features.

Methods

A total of 184 pathologically confirmed NPC patients receiving radical radiotherapy were included. After propensity score matching (1:1), 136 cases were analyzed. Stacked denoising autoencoder (SDAE) extracted deep features from contrast-enhanced T1-weighted MRI. Radiomic features (morphology, texture, first-order statistics), clinical parameters (gender, age, TNM stage), and SDAE features were combined to construct 12 models using SVM, MLP, logistic regression (LR), and random forest (RF). Performance was evaluated AUC, accuracy, sensitivity, and specificity, with external validation (91 cases).

Results

Model 1 (radiomics + SDAE + clinical features + SVM) achieved the highest AUC (0.89, 95% CI: 0.84-0.93), accuracy (81.5%), sensitivity (67.3%), and specificity (97.9%). External validation showed AUC 0.83, sensitivity 88.9%, and specificity 78%. The DeLong test confirmed no significant AUC difference between internal and external cohorts ( >0.05).

Discussion

The fusion of SDAE-enhanced features outperformed traditional radiomics. SVM demonstrated optimal performance in small samples, likely due to its high-dimensional feature handling and anti-overfitting capability. Limitations include single-center retrospective design and lack of functional imaging (DWI/PET) or molecular markers (EBV-DNA). Future multicenter prospective studies and multimodal data integration are warranted to enhance biological interpretability and clinical utility.

Conclusion

This model provides a tool for early recurrence risk stratification and personalized therapy optimization, advancing precision medicine in NPC management.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/crp/10.2174/0118744710384129250327060846
2025-04-15
2025-11-16

  • From This Site

    /content/journals/crp/10.2174/0118744710384129250327060846
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. ChenY.P. ChanA.T.C. LeQ.T. BlanchardP. SunY. MaJ. Nasopharyngeal carcinoma.Lancet201939410192648010.1016/S0140‑6736(19)30956‑031178151
     [Google Scholar]
  2. HanB. ZhengR. ZengH. WangS. SunK. ChenR. LiL. WeiW. HeJ. Cancer incidence and mortality in China, 2022.J. Natl. Cancer Cent.202441475310.1016/j.jncc.2024.01.00639036382
     [Google Scholar]
  3. TangL.L. ChenL. XuG.Q. ZhangN. HuangC.L. LiW.F. MaoY.P. ZhouG.Q. LeiF. ChenL.S. HuangS.H. ChenL. ChenY.P. ZhangY. LiuX. XuC. ZhaoY. LiJ.B. LiuN. XieF.Y. GuoR. SunY. MaJ. Reduced‐volume radiotherapy versus conventional‐volume radiotherapy after induction chemotherapy in nasopharyngeal carcinoma: An open‐label, noninferiority, multicenter, randomized phase 3 trial.CA Cancer J. Clin.2025caac.2188110.3322/caac.2188139970442
     [Google Scholar]
  4. LeeA.W.M. NgW.T. ChanJ.Y.W. CorryJ. MäkitieA. MendenhallW.M. RinaldoA. RodrigoJ.P. SabaN.F. StrojanP. SuárezC. VermorkenJ.B. YomS.S. FerlitoA. Management of locally recurrent nasopharyngeal carcinoma.Cancer Treat. Rev.20197910189010.1016/j.ctrv.2019.10189031470314
     [Google Scholar]
  5. AuK.H. NganR.K.C. NgA.W.Y. PoonD.M.C. NgW.T. YuenK.T. LeeV.H.F. TungS.Y. ChanA.T.C. SzeH.C.K. ChengA.C.K. LeeA.W.M. KwongD.L.W. TamA.H.P. Treatment outcomes of nasopharyngeal carcinoma in modern era after intensity modulated radiotherapy (IMRT) in Hong Kong: A report of 3328 patients (HKNPCSG 1301 study).Oral Oncol.201877162110.1016/j.oraloncology.2017.12.00429362121
     [Google Scholar]
  6. ChenJ.W. ShenR.N. ZhuJ.Q. WangY.H. FuL.M. ChenY.H. CaoJ.Z. WeiJ.H. LuoJ.H. LiJ.Y. GuiC.P. Transcriptomic profiling reveals mechanism, therapeutic potential, and prognostic value of cancer stemness characteristic in nasopharyngeal carcinoma.Funct. Integr. Genom.20252515610.1007/s10142‑025‑01561‑w40053129
     [Google Scholar]
  7. AminM.B. GreeneF.L. EdgeS.B. The eighth edition AJCC cancer staging manual: Continuing to build a bridge from a population-based to a more "personalized" approach to cancer staging.CA Cancer J. Clin.2017672939910.3322/caac.21388
     [Google Scholar]
  8. Dagogo-JackI. ShawA.T. Tumour heterogeneity and resistance to cancer therapies.Nat. Rev. Clin. Oncol.2018152819410.1038/nrclinonc.2017.16629115304
     [Google Scholar]
  9. ZhangB. ZhangS. RE: A prognostic predictive system based on deep learning for locoregionally advanced nasopharyngeal carcinoma.J. Natl. Cancer Inst.2021113121783178410.1093/jnci/djab09834021355
     [Google Scholar]
  10. ChanS.C. ChangK.P. FangY.H.D. TsangN.M. NgS.H. HsuC.L. LiaoC.T. YenT.C. Tumor heterogeneity measured on F‐18 fluorodeoxyglucose positron emission tomography/computed tomography combined with plasma epstein‐barr virus load predicts prognosis in patients with primary nasopharyngeal carcinoma.Laryngoscope20171271E22E2810.1002/lary.2617227435352
     [Google Scholar]
  11. GuoR. TangL.L. MaoY.P. DuX.J. ChenL. ZhangZ.C. LiuL.Z. TianL. LuoX.T. XieY.B. RenJ. SunY. MaJ. Proposed modifications and incorporation of plasma Epstein‐Barr virus DNA improve the TNM staging system for Epstein‐Barr virus‐related nasopharyngeal carcinoma.Cancer20191251798910.1002/cncr.3174130351466
     [Google Scholar]
  12. TangX.R. LiY.Q. LiangS.B. JiangW. LiuF. GeW.X. TangL.L. MaoY.P. HeQ.M. YangX.J. ZhangY. WenX. ZhangJ. WangY.Q. ZhangP.P. SunY. YunJ.P. ZengJ. LiL. LiuL.Z. LiuN. MaJ. Development and validation of a gene expression-based signature to predict distant metastasis in locoregionally advanced nasopharyngeal carcinoma: A retrospective, multicentre, cohort study.Lancet Oncol.201819338239310.1016/S1470‑2045(18)30080‑929428165
     [Google Scholar]
  13. XuH. LiW. WangD. The promising role of miRNAs in radioresistance and chemoresistance of nasopharyngeal carcinoma.Front. Oncol.202414129924910.3389/fonc.2024.129924938482204
     [Google Scholar]
  14. WuZ. ZhouT. SunH.Y. DNA methylation-based diagnostic and prognostic biomarkers of nasopharyngeal carcinoma patients.Medicine20209924e2068210.1097/MD.000000000002068232541515
     [Google Scholar]
  15. LiangY. LiJ. LiQ. TangL. ChenL. MaoY. HeQ. YangX. LeiY. HongX. ZhaoY. HeS. GuoY. WangY. ZhangP. LiuN. LiY. MaJ. Plasma protein-based signature predicts distant metastasis and induction chemotherapy benefit in Nasopharyngeal Carcinoma.Theranostics202010219767977810.7150/thno.4788232863958
     [Google Scholar]
  16. WangY.Q. ChenL. MaoY.P. LiY.Q. JiangW. XuS.Y. ZhangY. ChenY.P. LiX.M. HeQ.M. HeS.W. YangX.J. LeiY. ZhaoY. YunJ.P. LiuN. LiY. MaJ. Prognostic value of immune score in nasopharyngeal carcinoma using digital pathology.J. Immunother. Cancer202082e00033410.1136/jitc‑2019‑00033432690665
     [Google Scholar]
  17. LiY.Q. TianY.M. TanS.H. LiuM.Z. KusumawidjajaG. OngE.H.W. ZhaoC. TanT.W.K. FongK.W. SommatK. SoongY.L. WeeJ.T.S. HanF. ChuaM.L.K. Prognostic model for stratification of radioresistant nasopharynx carcinoma to curative salvage radiotherapy.J. Clin. Oncol.201836989189910.1200/JCO.2017.75.516529412781
     [Google Scholar]
  18. FanM. XiaP. ClarkeR. WangY. LiL. Radiogenomic signatures reveal multiscale intratumour heterogeneity associated with biological functions and survival in breast cancer.Nat. Commun.2020111486110.1038/s41467‑020‑18703‑232978398
     [Google Scholar]
  19. LiZ.Y. WuS.N. LinP. JiangM.C. ChenC. LinW.J. XueE.S. LiangR.X. LinZ.H. Habitat-based radiomics for revealing tumor heterogeneity and predicting residual cancer burden classification in breast cancer.Clin. Breast Cancer2025S1526-8209(25)00028-X10.1016/j.clbc.2025.01.01440000353
     [Google Scholar]
  20. ZhuC. HuangH. LiuX. ChenH. JiangH. LiaoC. PangQ. DangJ. LiuP. LuH. A clinical-radiomics nomogram based on computed tomography for predicting risk of local recurrence after radiotherapy in nasopharyngeal carcinoma.Front. Oncol.20211163768710.3389/fonc.2021.63768733816279
     [Google Scholar]
  21. AertsH.J.W.L. VelazquezE.R. LeijenaarR.T.H. ParmarC. GrossmannP. CarvalhoS. BussinkJ. MonshouwerR. Haibe-KainsB. RietveldD. HoebersF. RietbergenM.M. LeemansC.R. DekkerA. QuackenbushJ. GilliesR.J. LambinP. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.Nat. Commun.201451400610.1038/ncomms500624892406
     [Google Scholar]
  22. ZhaoX. LiangY.J. ZhangX. WenD.X. FanW. TangL.Q. DongD. TianJ. MaiH.Q. Deep learning signatures reveal multiscale intratumor heterogeneity associated with biological functions and survival in recurrent nasopharyngeal carcinoma.Eur. J. Nucl. Med. Mol. Imaging.20224982972298210.1007/s00259‑022‑05793‑x35471254
     [Google Scholar]
  23. WangC. LiJ. ChenJ. WangZ. ZhuG. SongL. WuJ. LiC. QiuR. ChenX. ZhangL. LiW. Multi-omics analyses reveal biological and clinical insights in recurrent stage I non-small cell lung cancer.Nat. Commun.2025161147710.1038/s41467‑024‑55068‑239929832
     [Google Scholar]
  24. HuQ. WangG. SongX. WanJ. LiM. ZhangF. ChenQ. CaoX. LiS. WangY. Machine learning based on MRI DWI radiomics features for prognostic prediction in nasopharyngeal carcinoma.Cancers20221413320110.3390/cancers1413320135804973
     [Google Scholar]
  25. KimM.J. ChoiY. SungY.E. LeeY.S. KimY.S. AhnK.J. KimM.S. Early risk-assessment of patients with nasopharyngeal carcinoma: The added prognostic value of MR-based radiomics.Transl. Oncol.2021141010118010.1016/j.tranon.2021.10118034274801
     [Google Scholar]
  26. Raghavan NairJ.K. VallièresM. MascarellaM.A. El SabbaghN. DuchatellierC.F. ZeitouniA. ShenoudaG. ChankowskyJ. Magnetic resonance imaging texture analysis predicts recurrence in patients with nasopharyngeal carcinoma.Cancer Assoc. Radiol. J.201970439440210.1016/j.carj.2019.06.00931519372
     [Google Scholar]
  27. ZhangL.L. HuangM.Y. LiY. LiangJ.H. GaoT.S. DengB. YaoJ.J. LinL. ChenF.P. HuangX.D. KouJ. LiC.F. XieC.M. LuY. SunY. Pretreatment MRI radiomics analysis allows for reliable prediction of local recurrence in non-metastatic T4 nasopharyngeal carcinoma.EBioMedicine20194227028010.1016/j.ebiom.2019.03.05030928358
     [Google Scholar]
  28. LiuJ. XuL. XieY. MaT. WangJ. TangZ. GuiW. YinH. JahanshahiH. Toward robust fault identification of complex industrial processes using stacked sparse-denoising autoencoder with softmax classifier.IEEE Trans. Cybern.202353142844210.1109/TCYB.2021.310961834550897
     [Google Scholar]
  29. SunW. ZhengB. QianW. Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis.Comput. Biol. Med.20178953053910.1016/j.compbiomed.2017.04.00628473055
     [Google Scholar]
  30. ZhaoQ. WangH. Application of unsupervised transfer technique based on deep learning model in physical training.Comput. Intell. Neurosci.2022202211210.1155/2022/867922135463226
     [Google Scholar]
  31. ObayyaM. ArasiM.A. AlmalkiN.S. AlotaibiS.S. Al SadigM. SayedA. Internet of things-assisted smart skin cancer detection using metaheuristics with deep learning model.Cancers20231520501610.3390/cancers1520501637894383
     [Google Scholar]
  32. ZhengY. XueF. OuD. NiuX. HuC. HeX. Long-term results of locoregionally advanced nasopharyngeal carcinoma treated with cisplatin and 5-fluorouracil induction chemotherapy with or without docetaxel in young and middle aged adults.J. Cancer Res. Clin. Oncol.202515139910.1007/s00432‑025‑06145‑640035865
     [Google Scholar]
  33. DiaoJ. WeiZ. PeiY. GeJ. QingY. WeiY. ChenY. PengX. Association of lymphocyte subsets percentage with prognosis for recurrent or metastatic nasopharyngeal carcinoma patients receiving PD-L1 inhibitors.Cancer Immunol. Immunother.202574412910.1007/s00262‑024‑03885‑140024914
     [Google Scholar]
  34. VincentP. LarochelleH. LajoieI. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion.J. Mach. Learn. Res.2010111233713408
     [Google Scholar]
  35. HintonG.E. SalakhutdinovR.R. Reducing the dimensionality of data with neural networks.Science2006313578650450710.1126/science.112764716873662
     [Google Scholar]
  36. CaoS. YuS. HuangL. SeeryS. XiaY. ZhaoY. SiZ. ZhangX. ZhuJ. LangR. KouJ. ZhangH. WeiL. ZhouG. SunL. WangL. LiT. HeQ. ZhuZ. Deep learning for hepatocellular carcinoma recurrence before and after liver transplantation: A multicenter cohort study.Sci. Rep.2025151773010.1038/s41598‑025‑91728‑z40044774
     [Google Scholar]
  37. Nanjappan JothirajS. MillsC. IrvingZ.C. KamJ.W.Y. Detection of freely moving thoughts using SVM and EEG signals.J. Neural Eng.202510.1088/1741‑2552/adbd7740048826
     [Google Scholar]
  38. Na’araS. AmitM. BillanS. CohenJ.T. GilZ. Outcome of patients undergoing salvage surgery for recurrent nasopharyngeal carcinoma: A meta-analysis.Ann. Surg. Oncol.20142193056306210.1245/s10434‑014‑3683‑924743908
     [Google Scholar]
  39. HeY. YanL. ZhangR. YangR. KongZ. WangX. Down-regulation of PCK2 enhanced the radioresistance phenotype of nasopharyngeal carcinoma.Int. J. Radiat. Biol.2025101511110.1080/09553002.2025.247022640009793
     [Google Scholar]
  40. WangL. ZhaoY. WangY. XingL. DuanY. ZangH. The IL-10/STAT3 axis nasopharyngeal carcinoma cancer stem cell and radio resistance.Sci. Rep.20241413194310.1038/s41598‑024‑83423‑239738457
     [Google Scholar]
  41. QiuW.Z. PengX.S. XiaH.Q. HuangP.Y. GuoX. CaoK.J. A retrospective study comparing the outcomes and toxicities of intensity-modulated radiotherapy versus two-dimensional conventional radiotherapy for the treatment of children and adolescent nasopharyngeal carcinoma.J. Cancer Res. Clin. Oncol.201714381563157210.1007/s00432‑017‑2401‑y28342002
     [Google Scholar]
  42. LiJ.X. LuT.X. HuangY. HanF. Clinical characteristics of recurrent nasopharyngeal carcinoma in high-incidence area.Scientific World J.201220121810.1100/2012/71975422448138
     [Google Scholar]
  43. AkramF. KohP.E. WangF. ZhouS. TanS.H. PaknezhadM. ParkS. HennedigeT. ThngC.H. LeeH.K. SommatK. Exploring MRI based radiomics analysis of intratumoral spatial heterogeneity in locally advanced nasopharyngeal carcinoma treated with intensity modulated radiotherapy.PLoS One20201510e024004310.1371/journal.pone.024004333017440
     [Google Scholar]
  44. OostendorpM. PostM.J. BackesW.H. Vessel growth and function: Depiction with contrast-enhanced MR imaging.Radiology2009251231733510.1148/radiol.251208048519401568
     [Google Scholar]
  45. AndersonC.M. SunW. BuattiJ.M. MaleyJ.E. PoliceniB. MottS.L. BayouthJ.E. Interobserver and intermodality variability in GTV delineation on simulation CT, FDG-PET, and MR Images of Head and Neck Cancer.Jacobs J. Radiat. Oncol.20141100625568889
     [Google Scholar]
  46. DongL. MaY. CaoG. ChenD. DongF. JiaoX. CaoY. LiuC. WangY. ZhuoN. WangF. GuoY. DaiT. ZhangS. JiaoH. ZouX. LiJ. ShenL. HeZ. ZhangY. LuZ. An integrated prognosis prediction model based on real-word clinical characteristics for immunotherapy in advanced esophageal squamous cell carcinoma.Cancer Immunol. Immunother.202574411210.1007/s00262‑025‑03963‑y39998564
     [Google Scholar]
/content/journals/crp/10.2174/0118744710384129250327060846
Loading
Prediction of Recurrence using a Stacked Denoising Autoencoder and Multifaceted Feature Analysis of Pretreatment MRI in Patients with Nasopharyngeal Carcinoma
Current Radiopharmaceuticals 18, 224 (2025); https://doi.org/10.2174/0118744710384129250327060846
/content/journals/crp/10.2174/0118744710384129250327060846
/content/journals/crp/10.2174/0118744710384129250327060846
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): magnetic resonance imaging; Nasopharyngeal carcinoma; prediction model; recurrence; stacked denoising autoencoder; support vector machine

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test