Review on applications of metastatic lymph node based radiomic assessment in nasopharyngeal carcinoma

Abstract

Nasopharyngeal carcinoma (NPC) has a distinct geographical prevalence in Southern China and Southeast Asia with a high overall survival rate (> 90%) in the early stage of the disease. However, almost 85% of patients suffer from the locally advanced disease with nodal metastasis at diagnosis. The overall survival rate would drastically drop to 63%. In addition to the generic tumor, nodal, and metastasis (TNM) staging, radiomic studies focusing on primary nasopharyngeal tumors have gained attention in precision medicine with artificial intelligence. While the heterogeneous presentation of cervical lymphadenopathy in locally advanced NPC is regarded as the same clinical stage under TNM criteria, radiomic analysis provides more insights into risk stratification, treatment differentiation, and survival prediction. There appears to be a lack of a review that consolidates radiomics-related studies on lymph node metastasis in NPC. The aim of this paper is to summarize the state-of-the-art of radiomics for lymph node analysis in NPC, including its potential use in prognostic prediction, treatment response, and overall survival for this cohort of patients.

Keywords

Nasopharyngeal carcinoma / radiomics / deep learning / NPC nodal metastasis / artificial intelligence / review / head and neck oncology / cervical lymphadenopathy

References

[1] Nasopharyngeal cancer statistics. Available from: https://www.wcrf.org/cancer-trends/nasopharyngeal-cancer-statistics [Last accessed on 17 Mar 2023]

[2] Centre for Health Protection. department of health - nasopharyngeal cancer. 2022. Available from: https://www.chp.gov.hk/en/healthtopics/content/25/54.html [Last accessed on 20 Mar 2023]

[3] Pan JJ,Zong JF.Proposal for the 8th edition of the AJCC/UICC staging system for nasopharyngeal cancer in the era of intensity-modulated radiotherapy.Cancer2016;122:546-58 PMCID:PMC4968037

[4] Lee AW,Au JS.Treatment results for nasopharyngeal carcinoma in the modern era: the Hong Kong experience.Int J Radiat Oncol Biol Phys2005;61:1107-16

[5] Ho FC,Earnest A,Lu JJ.Patterns of regional lymph node metastasis of nasopharyngeal carcinoma: a meta-analysis of clinical evidence.BMC Cancer2012;12:98 PMCID:PMC3353248

[6] Li S,Zhu ZL,Tao ZZ.A comprehensive review on radiomics and deep learning for nasopharyngeal carcinoma imaging.Diagnostics2021;11:1523 PMCID:PMC8465998

[7] Ng WT,Choi HCW.Application of artificial intelligence for nasopharyngeal carcinoma management - a systematic review.Cancer Manag Res2022;14:339-66 PMCID:PMC8801370

[8] Zhong LZ,Dong D.A deep learning MR-based radiomic nomogram may predict survival for nasopharyngeal carcinoma patients with stage T3N1M0.Radiother Oncol2020;151:1-9

[9] Xia C,Vardhanabhuti V.Primary tumour and lymph node radiomics assessment in PET-CT in non-metastatic nasopharyngeal carcinoma patients. In European Congress of Radiology (ECR). Germany: European Society of Radiology/SpringerOpen; 2020. Available from: http://www.springer.com/medicine/radiology/journal/13244 [Last accessed on 20 Mar 2023]

[10] Mccarthy J.Some philosophical problems from the standpoint of artificial intelligence. In: Webber BL, Nilsson NJ, editors. Readings in artificial intelligence. Burlington, USA: Morgan Kaufmann; 1981, pp. 431-50.

[11] Luger GF. Artificial intelligence: structures and strategies for complex problem solving, 6th ed. Pearson Addison-Wesley; 2009. Available from: http://www.uoitc.edu.iq/images/documents/informatics-institute/exam_materials/artificial%20intelligence%20structures%20and%20strategies%20for%20%20complex%20problem%20solving.pdf [Last accessed on 17 Mar 2023]

[12] Erickson BJ,Akkus Z.Machine learning for medical imaging.Radiographics2017;37:505-15 PMCID:PMC5375621

[13] Anwar SM,Qayyum A,Alnowami M.Medical image analysis using convolutional neural networks: a review.J Med Syst2018;42:226

[14] Park JE,Kim HJ.Reproducibility and generalizability in radiomics modeling: possible strategies in radiologic and statistical perspectives.Korean J Radiol2019;20:1124-37 PMCID:PMC6609433

[15] Wagner MW,Biswas A,Khalvati F.Radiomics, machine learning, and artificial intelligence-what the neuroradiologist needs to know.Neuroradiology2021;63:1957-67 PMCID:PMC8449698

[16] Lambin P,Leijenaar R.Radiomics: extracting more information from medical images using advanced feature analysis.Eur J Cancer2012;48:441-6 PMCID:PMC4533986

[17] Bogowicz M,Guckenberger M.Combined CT radiomics of primary tumor and metastatic lymph nodes improves prediction of loco-regional control in head and neck cancer.Sci Rep2019;9:15198 PMCID:PMC6811564

[18] Lee CK,Jang C.Tumor metastasis to lymph nodes requires YAP-dependent metabolic adaptation.Science2019;363:644-9

[19] Li S,Hou Z.Use of radiomics combined with machine learning method in the recurrence patterns after intensity-modulated radiotherapy for nasopharyngeal carcinoma: a preliminary study.Front Oncol2018;8:648 PMCID:PMC6308146

[20] Yu TT,To LH.Pretreatment prediction of adaptive radiation therapy eligibility using MRI-based radiomics for advanced nasopharyngeal carcinoma patients.Front Oncol2019;9:1050 PMCID:PMC6805774

[21] Kang L,Huang R.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.Front Oncol2021;11:774455

[22] Lam SK,Zhang J.Multi-organ omics-based prediction for adaptive radiation therapy eligibility in nasopharyngeal carcinoma patients undergoing concurrent chemoradiotherapy.Front Oncol2021;11:792024 PMCID:PMC8842229

[23] Lam SK,Zhang YP.A multi-center study of CT-based neck nodal radiomics for predicting an adaptive radiotherapy trigger of ill-fitted thermoplastic masks in patients with nasopharyngeal carcinoma.Life2022;12:241 PMCID:PMC8876942

[24] Registry, HKC. Report of Stage-specific surival of nasopharyngeal cancer in Hong Kong 2019. Available from: https://www3.ha.org.hk/cancereg/pdf/survival/Stage-specific%20Survival%20of%20NPC%20in%20HK.pdf [Last accessed on 17 Mar 2023]

[25] Xu H,Huang Y,Ren J.MRI-based radiomics as response predictor to radiochemotherapy for metastatic cervical lymph node in nasopharyngeal carcinoma.Br J Radiol2021;94:20201212 PMCID:PMC8173687

[26] Wang Y,Yin G.Extraction parameter optimized radiomics for neoadjuvant chemotherapy response prognosis in advanced nasopharyngeal carcinoma.Clin Transl Radiat Oncol2022;33:37-44 PMCID:PMC8728047

[27] Yang K,Zhang B.A multidimensional nomogram combining overall stage, dose volume histogram parameters and radiomics to predict progression-free survival in patients with locoregionally advanced nasopharyngeal carcinoma.Oral Oncol2019;98:85-91

[28] Ming X,Zhai R.MRI-based radiomics signature is a quantitative prognostic biomarker for nasopharyngeal carcinoma.Sci Rep2019;9:10412 PMCID:PMC6639299

[29] Bologna M,Calareso G.Baseline MRI-radiomics can predict overall survival in non-endemic ebv-related nasopharyngeal carcinoma patients.Cancers2020;12:2958 PMCID:PMC7601980

[30] Zhang F,Zhao X.A deep-learning-based prognostic nomogram integrating microscopic digital pathology and macroscopic magnetic resonance images in nasopharyngeal carcinoma: a multi-cohort study.Ther Adv Med Oncol2020;12:1758835920971416 PMCID:PMC7739087

[31] Chen X,Li X.An interpretable machine learning prognostic system for locoregionally advanced nasopharyngeal carcinoma based on tumor burden features.Oral Oncol2021;118:105335

[32] Qiang M,Sun Y.A prognostic predictive system based on deep learning for locoregionally advanced nasopharyngeal carcinoma.J Natl Cancer Inst2021;113:606-15

[33] Zhang L,Liu J.MRI-based deep-learning model for distant metastasis-free survival in locoregionally advanced nasopharyngeal carcinoma.J Magn Reson Imaging2021;53:167-78

[34] Aussem A,Corbex M.Analysis of nasopharyngeal carcinoma risk factors with Bayesian networks.Artif Intell Med2012;54:53-62

[35] Lundberg SM. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, California, USA. 2022. Available from: https://dl.acm.org/doi/10.5555/3295222.3295230#sec-cit [Last accessed on 17 Mar 2023]

[36] Du R,Yuan H.Radiomics model to predict early progression of nonmetastatic nasopharyngeal carcinoma after intensity modulation radiation therapy: a multicenter study.Radiol Artif Intell2019;1:e180075 PMCID:PMC8017427

[37] Chao KS,Chen H.Reduce in variation and improve efficiency of target volume delineation by a computer-assisted system using a deformable image registration approach.Int J Radiat Oncol Biol Phys2007;68:1512-21

[38] Stapleford LJ,Perkins C.Evaluation of automatic atlas-based lymph node segmentation for head-and-neck cancer.Int J Radiat Oncol Biol Phys2010;77:959-66

[39] Zhou JY,Chan KL,Khoo JB.Extraction of metastatic lymph nodes from MR images using two deformable model-based approaches.J Digit Imaging2007;20:336-46 PMCID:PMC3043914

[40] Yang J,Garden AS.Auto-segmentation of low-risk clinical target volume for head and neck radiation therapy.Pract Radiat Oncol2014;4:e31-7

[41] Cardenas CE,Garden AS.Generating high-quality lymph node clinical target volumes for head and neck cancer radiation therapy using a fully automated deep learning-based approach.Int J Radiat Oncol Biol Phys2021;109:801-12 PMCID:PMC9472456

[42] Men K,Zhang Y.Deep deconvolutional neural network for target segmentation of nasopharyngeal cancer in planning computed tomography images.Front Oncol2017;7:315 PMCID:PMC5770734

[43] Johnson WE,Rabinovic A.Adjusting batch effects in microarray expression data using empirical Bayes methods.Biostatistics2007;8:118-27

[44] Da-Ano R,Hatt M.Harmonization strategies for multicenter radiomics investigations.Phys Med Biol2020;65:24TR02

[45] Boellaard R,Oyen WJ.FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0.Eur J Nucl Med Mol Imaging2015;42:328-54 PMCID:PMC4315529

[46] Kaalep A,Rijnsdorp S.Feasibility of state of the art PET/CT systems performance harmonisation.Eur J Nucl Med Mol Imaging2018;45:1344-61 PMCID:PMC5993859

[47] Schick U,Dissaux G.MRI-derived radiomics: methodology and clinical applications in the field of pelvic oncology.Br J Radiol2019;92:20190105 PMCID:PMC6913356

[48] Fujita S,Yasaka K.Radiomics with 3-dimensional magnetic resonance fingerprinting: influence of dictionary design on repeatability and reproducibility of radiomic features.Eur Radiol2022;32:4791-800 PMCID:PMC9213334

[49] Aerts HJ,Leijenaar RT.Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.Nat Commun2014;5:4006 PMCID:PMC4059926

[50] Berenguer R,Canales-Vázquez J.Radiomics of CT features may be nonreproducible and redundant: influence of CT acquisition parameters.Radiology2018;288:407-15

[51] Mahon RN,Hugo GD.ComBat harmonization for radiomic features in independent phantom and lung cancer patient computed tomography datasets.Phys Med Biol2020;65:015010

[52] Horng H,Yousefi B.Generalized ComBat harmonization methods for radiomic features with multi-modal distributions and multiple batch effects.Sci Rep2022;12:4493 PMCID:PMC8927332

[53] Ibrahim A,Beuque M.Radiomics for precision medicine: Current challenges, future prospects, and the proposal of a new framework.Methods2021;188:20-9