Application of radiomics and artificial intelligence in lung cancer immunotherapy: a guide and hurdles from clinical trials

Abstract

Immunotherapy has shown promising results with improved progression-free survival and overall survival in lung cancer. However, novel immunotherapy could generate atypical response patterns, which is a big challenge for traditional imaging criteria. Radiomics, combined with artificial intelligence (AI), represents new quantitative methodologies that could serve as an additional imaging biomarker to predict immunotherapy benefits and assess responses to assist oncologists in decision-making in lung cancer treatment. This paper aims to review the latest advancement of AI-based radiomics applied to lung cancer patients receiving immunotherapy, focusing on the fundamentals of these approaches and commonly used techniques. We also address the hurdles in the AI and radiomic analysis pipeline to guide clinicians in approaching this new concept.

Keywords

Radiomics / artificial intelligence / lung cancer / immunotherapy

References

[1] Sung H,Siegel RL.Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries.CA Cancer J Clin2021;71:209-49

[2] Reck M,Robinson AG.Pembrolizumab versus chemotherapy for PD-L1-positive non-small-cell lung cancer.N Engl J Med2016;375:1823-33

[3] Mok TSK,Kudaba I.Pembrolizumab versus chemotherapy for previously untreated, PD-L1-expressing, locally advanced or metastatic non-small-cell lung cancer (KEYNOTE-042): a randomised, open-label, controlled, phase 3 trial.Lancet2019;393:1819-30

[4] Antonia SJ,Daniel D.Durvalumab after chemoradiotherapy in stage III non-small-cell lung cancer.N Engl J Med2017;377:1919-29

[5] Sharma P,Wargo JA.Primary, adaptive, and acquired resistance to cancer immunotherapy.Cell2017;168:707-23 PMCID:PMC5391692

[6] Davis AA.The role of PD-L1 expression as a predictive biomarker: an analysis of all US Food and Drug Administration (FDA) approvals of immune checkpoint inhibitors.J Immunother Cancer2019;7:278 PMCID:PMC6815032

[7] Boothman AM,Ratcliffe M.Impact of patient characteristics, prior therapy, and sample type on tumor cell programmed cell death ligand 1 expression in patients with advanced NSCLC screened for the ATLANTIC study.J Thorac Oncol2019;14:1390-9

[8] Binnewies M,Kersten K.Understanding the tumor immune microenvironment (TIME) for effective therapy.Nat Med2018;24:541-50 PMCID:PMC5998822

[9] Giustini N.Recognizing prognostic and predictive biomarkers in the treatment of non-small cell lung cancer (NSCLC) with immune checkpoint inhibitors (ICIs).Lung Cancer2021;12:21-34 PMCID:PMC8006757

[10] Brozos-Vázquez EM,García-González J.Immunotherapy in nonsmall-cell lung cancer: current status and future prospects for liquid biopsy.Cancer Immunol Immunother2021;70:1177-88

[11] Yang Y,Chen Y.Liquid biopsy on the horizon in immunotherapy of non-small cell lung cancer: current status, challenges, and perspectives.Cell Death Dis2023;14:230 PMCID:PMC10066332

[12] de Miguel-Perez D,Arrieta O.Extracellular vesicle PD-L1 dynamics predict durable response to immune-checkpoint inhibitors and survival in patients with non-small cell lung cancer.J Exp Clin Cancer Res2022;41:186 PMCID:PMC9161571

[13] Champiat S,Ammari S.Hyperprogressive disease is a new pattern of progression in cancer patients treated by anti-PD-1/PD-L1.Clin Cancer Res2017;23:1920-8

[14] Kim HK,Lee HS.Comparison of RECIST to immune-related response criteria in patients with non-small cell lung cancer treated with immune-checkpoint inhibitors.Cancer Chemother Pharmacol2017;80:591-8

[15] Tazdait M,Lahmar J.Patterns of responses in metastatic NSCLC during PD-1 or PDL-1 inhibitor therapy: comparison of RECIST 1.1, irRECIST and iRECIST criteria.Eur J Cancer2018;88:38-47

[16] Soria F,D’Andrea D.Pseudoprogression and hyperprogression during immune checkpoint inhibitor therapy for urothelial and kidney cancer.World J Urol2018;36:1703-9 PMCID:PMC6208670

[17] Seymour L,Perrone A.iRECIST: guidelines for response criteria for use in trials testing immunotherapeutics.Lancet Oncol2017;18:e143-52 PMCID:PMC5648544

[18] Mulkey F,Keegan P,Sridhara R.Comparison of iRECIST versus RECIST V.1.1 in patients treated with an anti-PD-1 or PD-L1 antibody: pooled FDA analysis.J Immunother Cancer2020;8:e000146 PMCID:PMC7057528

[19] Nguyen HS,Nguyen NN,Tam KW.Predicting EGFR mutation status in non-small cell lung cancer using artificial intelligence: a systematic review and meta-analysis.Acad Radiol2023;S1076-6332(23)00179-4

[20] Yip SS.Applications and limitations of radiomics.Phys Med Biol2016;61:R150-66 PMCID:PMC4927328

[21] Liu Z,Dong D.The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges.Theranostics2019;9:1303-22 PMCID:PMC6401507

[22] Dercle L,Sun S.Artificial intelligence and radiomics: fundamentals, applications, and challenges in immunotherapy.J Immunother Cancer2022;10:e005292 PMCID:PMC9528623

[23] Shur JD,Kumar S.Radiomics in oncology: a practical guide.Radiographics2021;41:1717-32 PMCID:PMC8501897

[24] Valentinuzzi D,Boc N.[18F]FDG PET immunotherapy radiomics signature (iRADIOMICS) predicts response of non-small-cell lung cancer patients treated with pembrolizumab.Radiol Oncol2020;54:285-94 PMCID:PMC7409607

[25] Léger MA,Juneau D.FDG PET/CT for evaluation of immunotherapy response in lung cancer patients.Semin Nucl Med2022;52:707-19

[26] Kaira K,Naruse I.Metabolic activity by (18)F-FDG-PET/CT is predictive of early response after nivolumab in previously treated NSCLC.Eur J Nucl Med Mol Imaging2018;45:56-66

[27] Seban RD,Latouche A.Total metabolic tumor volume and spleen metabolism on baseline [18F]-FDG PET/CT as independent prognostic biomarkers of recurrence in resected breast cancer.Eur J Nucl Med Mol Imaging2021;48:3560-70

[28] Pellegrino S,Mazziotti E.Total metabolic tumor volume by 18F-FDG PET/CT for the prediction of outcome in patients with non-small cell lung cancer.Ann Nucl Med2019;33:937-44

[29] Routy B,Derosa L.Gut microbiome influences efficacy of PD-1-based immunotherapy against epithelial tumors.Science2018;359:91-7

[30] Castello A,Mazziotti E,Lopci E.Hyperprogressive Disease in patients with non-small cell lung cancer treated with checkpoint inhibitors: the role of (18)F-FDG PET/CT.J Nucl Med2020;61:821-6

[31] Polverari G,Bertaglia V.(18)F-FDG pet parameters and radiomics features analysis in advanced nsclc treated with immunotherapy as predictors of therapy response and survival.Cancers2020;12:1163 PMCID:PMC7281558

[32] Wu X,Zhao Q.PD-L1 expression correlation with metabolic parameters of FDG PET/CT and clinicopathological characteristics in non-small cell lung cancer.EJNMMI Res2020;10:51 PMCID:PMC7237589

[33] Bak SH,Sohn I,Ahn MJ.Prognostic impact of longitudinal monitoring of radiomic features in patients with advanced non-small cell lung cancer.Sci Rep2019;9:8730 PMCID:PMC6584670

[34] Khorrami M,Gupta A.Changes in CT radiomic features associated with lymphocyte distribution predict overall survival and response to immunotherapy in non-small cell lung cancer.Cancer Immunol Res2020;8:108-19 PMCID:PMC7718609

[35] Gillies RJ,Hricak H.Radiomics: images are more than pictures, they are data.Radiology2016;278:563-77 PMCID:PMC4734157

[36] Clarke LP,Zhang H.The quantitative imaging network: NCI’s historical perspective and planned goals.Transl Oncol2014;7:1-4 PMCID:PMC3998696

[37] Han T,Luo W,Jin Z.Review of generative adversarial networks in mono- and cross-modal biomedical image registration.Front Neuroinform2022;16:933230 PMCID:PMC9724825

[38] Rios Velazquez E,Gu Y.A semiautomatic CT-based ensemble segmentation of lung tumors: comparison with oncologists’ delineations and with the surgical specimen.Radiother Oncol2012;105:167-73 PMCID:PMC3749821

[39] Hosny A,Mak RH.Handcrafted versus deep learning radiomics for prediction of cancer therapy response.Lancet Digit Health2019;1:e106-7

[40] Zhao P,Rahaman MM.A comparative study of deep learning classification methods on a small environmental microorganism image dataset (EMDS-6): from convolutional neural networks to visual transformers.Front Microbiol2022;13:792166 PMCID:PMC8924496

[41] Zwanenburg A,Abdalah MA.The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping.Radiology2020;295:328-38 PMCID:PMC7193906

[42] Liu Y,Zhang Y.Imaging biomarkers to predict and evaluate the effectiveness of immunotherapy in advanced non-small-cell lung cancer.Front Oncol2021;11:657615 PMCID:PMC8017283

[43] Cousin F,Dheur S.Radiomics and delta-radiomics signatures to predict response and survival in patients with non-small-cell lung cancer treated with immune checkpoint inhibitors.Cancers2023;15:1968 PMCID:PMC10093736

[44] Tunali I,Gray JE.Hypoxia-related radiomics and immunotherapy response: a multicohort study of non-small cell lung cancer.JNCI Cancer Spectr2021;5 PMCID:PMC8363765

[45] Tunali I,Qi J.Novel clinical and radiomic predictors of rapid disease progression phenotypes among lung cancer patients treated with immunotherapy: an early report.Lung Cancer2019;129:75-9 PMCID:PMC6450086

[46] Sun R,Vakalopoulou M.A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study.Lancet Oncol2018;19:1180-91

[47] Vaidya P,Patil PD.Novel, non-invasive imaging approach to identify patients with advanced non-small cell lung cancer at risk of hyperprogressive disease with immune checkpoint blockade.J Immunother Cancer2020;8:e001343 PMCID:PMC7555103

[48] Korpics MC,Bhave SR.A validated T cell radiomics score is associated with clinical outcomes following multisite SBRT and pembrolizumab.Int J Radiat Oncol Biol Phys2020;108:189-95

[49] He B,She Y.Predicting response to immunotherapy in advanced non-small-cell lung cancer using tumor mutational burden radiomic biomarker.J Immunother Cancer2020;8:e000550 PMCID:PMC7342823

[50] Incoronato M,Infante T.Radiogenomic analysis of oncological data: a technical survey.Int J Mol Sci2017;18:805 PMCID:PMC5412389

[51] Stanzione A,Ugga L.Oncologic imaging and radiomics: a walkthrough review of methodological challenges.Cancers2022;14:4871 PMCID:PMC9562166

[52] Jović A,Bogunović N.A review of feature selection methods with applications. In: Proceedings of the 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO): IEEE; 2015 May 25-29; Opatija, Croatia. pp. 1200-5.

[53] Nguyen LH.Ten quick tips for effective dimensionality reduction.PLoS Comput Biol2019;15:e1006907 PMCID:PMC6586259

[54] Avanzo M,Stancanello J.Machine and deep learning methods for radiomics.Med Phys2020;47:e185-202 PMCID:PMC8965689

[55] Choy G,Michalski M.Current applications and future impact of machine learning in radiology.Radiology2018;288:318-28 PMCID:PMC6542626

[56] Hajian-Tilaki K.Receiver operating characteristic (ROC) curve analysis for medical diagnostic test evaluation.Caspian J Intern Med2013;4:627-35 PMCID:PMC3755824

[57] Park SH.Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction.Radiology2018;286:800-9

[58] Lambin P,Deist TM.Radiomics: the bridge between medical imaging and personalized medicine.Nat Rev Clin Oncol2017;14:749-62

[59] Park JE,Kim HS.Quality of science and reporting of radiomics in oncologic studies: room for improvement according to radiomics quality score and TRIPOD statement.Eur Radiol2020;30:523-36

[60] Sollini M,Chiti A.Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics.Eur J Nucl Med Mol Imaging2019;46:2656-72 PMCID:PMC6879445

[61] MO,Gunduz S. Hyperprogression after immunotherapy: a comprehensive review. J BUON 2019;24:2232-41. Available from: https://napier-repository.worktribe.com/output/2452554/hyperprogression-after-immunotherapy-a-comprehensive-review [Last accessed on 3 Aug 2023]

[62] Sehgal K.Hyperprogression in patients with cancer receiving immune checkpoint inhibitors.JAMA Netw Open2021;4:e211839

[63] Reinstein ZZ,Sagar V.Overcoming immunosuppression in bone metastases.Crit Rev Oncol Hematol2017;117:114-27

[64] Ladwa R,O’Leary C,O’Byrne KJ.Computed tomography texture analysis of response to second-line nivolumab in metastatic non-small cell lung cancer.Lung Cancer Manag2020;9:LMT38 PMCID:PMC7399606

[65] Mu W,Gray JE,Schabath MB.Radiomics of (18)F-FDG PET/CT images predicts clinical benefit of advanced NSCLC patients to checkpoint blockade immunotherapy.Eur J Nucl Med Mol Imaging2020;47:1168-82 PMCID:PMC8663718

[66] Ravanelli M,Milanese G.Prognostic and predictive value of histogram analysis in patients with non-small cell lung cancer refractory to platinum treated by nivolumab: a multicentre retrospective study.Eur J Radiol2019;118:251-6

[67] Trebeschi S,Birkbak NJ.Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers.Ann Oncol2019;30:998-1004 PMCID:PMC6594459

[68] Dercle L,Lu L.Identification of non-small cell lung cancer sensitive to systemic cancer therapies using radiomics.Clin Cancer Res2020;26:2151-62 PMCID:PMC9239371

[69] Nardone V,Pastina P.Radiomics predicts survival of patients with advanced non-small cell lung cancer undergoing PD-1 blockade using Nivolumab.Oncol Lett2020;19:1559-66 PMCID:PMC6956423

[70] Zhu Z,Hu G.A pre-treatment CT-based weighted radiomic approach combined with clinical characteristics to predict durable clinical benefits of immunotherapy in advanced lung cancer.Eur Radiol2023;33:3918-30 PMCID:PMC9748402

[71] Tian P,Mu W.Assessing PD-L1 expression in non-small cell lung cancer and predicting responses to immune checkpoint inhibitors using deep learning on computed tomography images.Theranostics2021;11:2098-107 PMCID:PMC7797686

[72] Yoon J,Han K.Utility of CT radiomics for prediction of PD-L1 expression in advanced lung adenocarcinomas.Thorac Cancer2020;11:993-1004 PMCID:PMC7113038

[73] Yang B,Zhong J.Combination of computed tomography imaging-based radiomics and clinicopathological characteristics for predicting the clinical benefits of immune checkpoint inhibitors in lung cancer.Respir Res2021;22:189 PMCID:PMC8240400

[74] Bouhamama A,Faraz K.Radiomics combined with transcriptomics to predict response to immunotherapy from patients treated with PD-1/PD-L1 inhibitors for advanced NSCLC.Fron Radiol2023;3:1168448 PMCID:PMC10365090

[75] Jiang M,Guo Y.Assessing PD-L1 expression level by radiomic features from PET/CT in nonsmall cell lung cancer patients: an initial result.Acad Radiol2020;27:171-9

[76] Liu C,Yu H,Wang S.A CT-Based radiomics approach to predict nivolumab response in advanced non-small-cell lung cancer.Front Oncol2021;11:544339 PMCID:PMC7943844

[77] Shen L,Tao G,Yuan Z.Pre-immunotherapy contrast-enhanced CT texture-based classification: a useful approach to non-small cell lung cancer immunotherapy efficacy prediction.Front Oncol2021;11:591106 PMCID:PMC8103028

[78] Tang C,Amer A.Development of an immune-pathology informed radiomics model for non-small cell lung cancer.Sci Rep2018;8:1922 PMCID:PMC5792427