Share:
Share this content in WeChat
X
Clinical Article
Value of MRI multi-sequence model fusion radiomics in predicting the response to concurrent chemoradiotherapy in patients with locally advanced nasopharyngeal carcinoma
WANG Xin  LIANG Liuke  SU Xiaohong  LI Xinyi  LIU Lu  JIN Guanqiao 

Cite this article as: Wang X, Liang LK, Su XH, et al. Value of MRI multi-sequence model fusion radiomics in predicting the response to concurrent chemoradiotherapy in patients with locally advanced nasopharyngeal carcinoma[J]. Chin J Magn Reson Imaging, 2022, 13(6): 10-16. DOI:10.12015/issn.1674-8034.2022.06.003.


[Abstract] Objective To investigate the value of MRI multi-sequence model fusion (MSMF) radiomics model in predicting the efficacy of concurrent chemoradiotherapy (CCRT) in patients with locally advanced nasopharyngeal carcinoma (NPC).Materials and Methods A total of 154 patients with locally advanced NPC were included in this study. All patients received CCRT treatment and MRI examination. RESIST 1.1 was used to evaluate the response after treatment, and the patients were divided into complete response group (83 cases) and incomplete response group (71 cases). The data were randomly divided into training and validation sets by a ratio of 3∶1, and the regions of interests of each sequence images were manually segmented. And 9766 radiomics features were respectively extracted from each of the three sequences using Matlab 2018a software, and the features were screened by t test and maximum correlation minimum redundancy algorithm. Support vector machines and logistic regression were used to build prediction models, and ROC curves were drawn. Delong test was used to compare the prediction performance.Results In the validation set, the area under the curve (AUC) values of the clinical model, T1WI, T2WI, contrast enhanced T1WI models were 0.542, 0.633, 0.711, and 0.842 (P values were 0.661, 0.161, 0.026, and <0.001, respectively). In the multi-sequence fusion models, the AUC values of the MSMF model and the clinical-MSMF model were 0.896 and 0.867, respectively (P<0.05 for both). The AUC of MSMF and clinical-MSMF radiomics models in predicting the response to CCRT in patients with locally advanced NPC was significantly higher than T2WI, T1WI and clinical models, and the differences were statistically significant (P<0.05).Conclusions The ability of MSMF radiomics model to predict the efficacy of CCRT is better than conventional single-sequence radiomics prediction models and clinical models. Therefore, this model is expected to be a method to predict the efficacy of CCRT and further promote the development of precision medicine.
[Keywords] radiomics;nasopharyngeal carcinoma;locally advanced;concurrent chemoradiotherapy;efficacy prediction;magnetic resonance imaging

WANG Xin1   LIANG Liuke2   SU Xiaohong1   LI Xinyi1   LIU Lu1   JIN Guanqiao1*  

1 Medical Imaging Center of Cancer Hospital affiliated to Guangxi Medical University, Nanning 530021, China

2 Radiotherapy Technology Center of Cancer Hospital affiliated to Guangxi Medical University, Nanning 530021, China

Jin GQ, E-mail: jinguanqiao77@gxmu.edu.cn

Conflicts of interest   None.

Received  2022-01-14
Accepted  2022-05-12
DOI: 10.12015/issn.1674-8034.2022.06.003
Cite this article as: Wang X, Liang LK, Su XH, et al. Value of MRI multi-sequence model fusion radiomics in predicting the response to concurrent chemoradiotherapy in patients with locally advanced nasopharyngeal carcinoma[J]. Chin J Magn Reson Imaging, 2022, 13(6): 10-16.DOI:10.12015/issn.1674-8034.2022.06.003

[1]
Chen YP, Chan ATC, Le QT, et al. Nasopharyngeal carcinoma[J]. Lancet, 2019, 394(10192): 64-80. DOI: 10.1016/S0140-6736(19)30956-0.
[2]
Sung H, Ferlay J, Siegel RL, 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.
[3]
Mao YP, Xie FY, Liu LZ, et al. re-evaluation of 6th edition of AJCC staging system for nasopharyngeal carcinoma and proposed improvement based on magnetic resonance imaging[J]. Int J Radiat Oncol Biol Phys, 2009, 73(5): 1326-1334. DOI: 10.1016/j.ijrobp.2008.07.062.
[4]
Chen YP, Ismaila N, Chua MLK, et al. Chemotherapy in combination with radiotherapy for definitive-intent treatment of stage II-IVA nasopharyngeal carcinoma: CSCO and ASCO guideline[J]. J Clin Oncol, 2021, 39(7): 840-859. DOI: 10.1200/JCO.20.03237.
[5]
Lee AWM, Ng WT, Chan JYW, et al. Management of locally recurrent nasopharyngeal carcinoma[J]. Cancer Treat Rev, 2019, 79: 101890. DOI: 10.1016/j.ctrv.2019.101890.
[6]
Tang XR, Li YQ, Liang SB, et al. Development and validation of a gene expression-based signature to predict distant metastasis in locoregionally advanced nasopharyngeal carcinoma: a retrospective, multicentre, cohort study[J]. Lancet Oncol, 2018, 19(3): 382-393. DOI: 10.1016/S1470-2045(18)30080-9.
[7]
Liu J, Mao Y, Li ZJ, et al. Use of texture analysis based on contrast-enhanced MRI to predict treatment response to chemoradiotherapy in nasopharyngeal carcinoma[J]. J Magn Reson Imaging, 2016, 44(2): 445-455. DOI: 10.1002/jmri.25156.
[8]
Qin YH, Yu XP, Hou J, et al. Predicting chemoradiotherapy response of nasopharyngeal carcinoma using texture features based on intravoxel incoherent motion diffusion-weighted imaging[J]. Medicine (Baltimore), 2018, 97(30): e11676. DOI: 10.1097/MD.0000000000011676.
[9]
Bulens P, Couwenberg A, Intven M, et al. Predicting the tumor response to chemoradiotherapy for rectal cancer: model development and external validation using MRI radiomics[J]. Radiother Oncol, 2020, 142: 246-252. DOI: 10.1016/j.radonc.2019.07.033.
[10]
Dong XZ, Sun XR, Sun L, et al. Early change in metabolic tumor heterogeneity during chemoradiotherapy and its prognostic value for patients with locally advanced non-small cell lung cancer[J]. PLoS One, 2016, 11(6): e0157836. DOI: 10.1371/journal.pone.0157836.
[11]
Zhao LN, Gong J, Xi YB, et al. MRI-based radiomics nomogram may predict the response to induction chemotherapy and survival in locally advanced nasopharyngeal carcinoma[J]. Eur Radiol, 2020, 30(1): 537-546. DOI: 10.1007/s00330-019-06211-x.
[12]
Hu CM, Zheng DC, Cao XS, et al. Application value of magnetic resonance radiomics and clinical nomograms in evaluating the sensitivity of neoadjuvant chemotherapy for nasopharyngeal carcinoma[J]. Front Oncol, 2021, 11: 740776. DOI: 10.3389/fonc.2021.740776.
[13]
Kang L, Niu YL, Huang R, et al. Predictive value of a combined model based on pre-treatment and mid-treatment MRI-radiomics for disease progression or death in locally advanced nasopharyngeal carcinoma[J]. Front Oncol, 2021, 11: 774455. DOI: 10.3389/fonc.2021.774455.
[14]
Zhang B, Lian ZY, Zhong LM, et al. Machine-learning based MRI radiomics models for early detection of radiation-induced brain injury in nasopharyngeal carcinoma[J]. BMC Cancer, 2020, 20(1): 502. DOI: 10.1186/s12885-020-06957-4.
[15]
Zhuo EH, Zhang WJ, Li HJ, et al. Radiomics on multi-modalities MR sequences can subtype patients with non-metastatic nasopharyngeal carcinoma (NPC) into distinct survival subgroups[J]. Eur Radiol, 2019, 29(10): 5590-5599. DOI: 10.1007/s00330-019-06075-1.
[16]
Yuan GS, Song YD, Li Q, et al. Development and validation of a contrast-enhanced CT-based radiomics nomogram for prediction of therapeutic efficacy of anti-PD-1 antibodies in advanced HCC patients[J]. Front Immunol, 2020, 11: 613946. DOI: 10.3389/fimmu.2020.613946.
[17]
Hu C, Wang P, Zhou T, et al. FDG-PET/CT radiomics models for the early prediction of locoregional recurrence in head and neck cancer[J]. Curr Med Imaging, 2021, 17(3): 374-383. DOI: 10.2174/1573405616666200712181135.
[18]
Antropova N, Huynh BQ, Giger ML. A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets[J]. Med Phys, 2017, 44(10): 5162-5171. DOI: 10.1002/mp.12453.
[19]
Jiang CD, Kong ZR, Liu SR, et al. Fusion radiomics features from conventional MRI predict MGMT promoter methylation status in lower grade gliomas[J]. Eur J Radiol, 2019, 121: 108714. DOI: 10.1016/j.ejrad.2019.108714.
[20]
Shen Y, Xu FY, Zhu WC, et al. Multiclassifier fusion based on radiomics features for the prediction of benign and malignant primary pulmonary solid nodules[J]. Ann Transl Med, 2020, 8(5): 171. DOI: 10.21037/atm.2020.01.135.
[21]
Liao H, Chen XB, Lu SL, et al. MRI-based back propagation neural network model as a powerful tool for predicting the response to induction chemotherapy in locoregionally advanced nasopharyngeal carcinoma[J/OL]. J Magn Reson Imaging, 2021 [2022-01-14]. https://onlinelibrary.wiley.com/doi/10.1002/jmri.28047. DOI: 10.1002/jmri.28047.
[22]
Eisenhauer EA, Therasse P, Bogaerts J, et al. New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1)[J]. Eur J Cancer, 2009, 45(2): 228-247. DOI: 10.1016/j.ejca.2008.10.026.
[23]
Piao YF, Jiang CE, Wang L, et al. The usefulness of pretreatment MR-based radiomics on early response of neoadjuvant chemotherapy in patients with locally advanced nasopharyngeal carcinoma[J]. Oncol Res, 2021, 28(6): 605-613. DOI: 10.3727/096504020X16022401878096.
[24]
Zhang WL, Yang RM, Liang FR, et al. Prediction of microvascular invasion in hepatocellular carcinoma with a multi-disciplinary team-like radiomics fusion model on dynamic contrast-enhanced computed tomography[J]. Front Oncol, 2021, 11: 660629. DOI: 10.3389/fonc.2021.660629.
[25]
Zheng DC, Xu SG, Lai GJ, et al. The performance of pretreatment MRI based nomogram in neoadjuvant chemotherapy response prediction in nasopharyngeal carcinoma: a primary study[J]. Chin J Magn Reson Imaging, 2021, 12(4): 23-29. DOI: 10.12015/issn.1674-8034.2021.04.005.
[26]
Wang GY, He L, Yuan C, et al. Pretreatment MR imaging radiomics signatures for response prediction to induction chemotherapy in patients with nasopharyngeal carcinoma[J]. Eur J Radiol, 2018, 98: 100-106. DOI: 10.1016/j.ejrad.2017.11.007.
[27]
Akram F, Koh PE, Wang FQ, et al. Exploring MRI based radiomics analysis of intratumoral spatial heterogeneity in locally advanced nasopharyngeal carcinoma treated with intensity modulated radiotherapy[J]. PLoS One, 2020, 15(10): e0240043. DOI: 10.1371/journal.pone.0240043.
[28]
Wei LS, Osman S, Hatt M, et al. Machine learning for radiomics-based multimodality and multiparametric modeling[J]. Q J Nucl Med Mol Imaging, 2019, 63(4): 323-338. DOI: 10.23736/S1824-4785.19.03213-8.
[29]
Zhang ZT, He K, Wang ZH, et al. Multiparametric MRI radiomics for the early prediction of response to chemoradiotherapy in patients with postoperative residual gliomas: an initial study[J]. Front Oncol, 2021, 11: 779202. DOI: 10.3389/fonc.2021.779202.
[30]
Yuan ZG, Frazer M, Rishi A, et al. Pretreatment CT and PET radiomics predicting rectal cancer patients in response to neoadjuvant chemoradiotherapy[J]. Rep Pract Oncol Radiother, 2021, 26(1): 29-34. DOI: 10.5603/RPOR.a2021.0004.
[31]
Cook GJR, Azad G, Owczarczyk K, et al. Challenges and promises of PET radiomics[J]. Int J Radiat Oncol Biol Phys, 2018, 102(4): 1083-1089. DOI: 10.1016/j.ijrobp.2017.12.268.

PREV Comparison of echo-planar and turbo spin-echo diffusion-weighted imaging sequence in the diagnosis of middle ear cholesteatoma
NEXT Value of syMRI and DWI quantitative parameters measured using different regions of interest method in differentiating benign and malignant breast lesions
  



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