Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Prognostic Value of 18F-FDG PET/CT Radiomics in Extranodal Nasal-Type NK/T Cell Lymphoma

  • Yu Luo (Department of Medical Imaging, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University) ;
  • Zhun Huang (Department of Medical Imaging, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University) ;
  • Zihan Gao (Department of Medical Imaging, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University) ;
  • Bingbing Wang (Department of Medical Imaging, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University) ;
  • Yanwei Zhang (Department of Bethune International Peace Hospital, Department of Radiology) ;
  • Yan Bai (Department of Medical Imaging, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University) ;
  • Qingxia Wu (Beijing United Imaging Research Institute of Intelligent Imaging) ;
  • Meiyun Wang (Department of Medical Imaging, Henan Provincial People's Hospital, The People's Hospital of Zhengzhou University)
  • Received : 2023.06.30
  • Accepted : 2023.11.16
  • Published : 2024.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To investigate the prognostic utility of radiomics features extracted from 18F-fluorodeoxyglucose (FDG) PET/CT combined with clinical factors and metabolic parameters in predicting progression-free survival (PFS) and overall survival (OS) in individuals diagnosed with extranodal nasal-type NK/T cell lymphoma (ENKTCL). Materials and Methods: A total of 126 adults with ENKTCL who underwent 18F-FDG PET/CT examination before treatment were retrospectively included and randomly divided into training (n = 88) and validation cohorts (n = 38) at a ratio of 7:3. Least absolute shrinkage and selection operation Cox regression analysis was used to select the best radiomics features and calculate each patient's radiomics scores (RadPFS and RadOS). Kaplan-Meier curve and Log-rank test were used to compare survival between patient groups risk-stratified by the radiomics scores. Various models to predict PFS and OS were constructed, including clinical, metabolic, clinical + metabolic, and clinical + metabolic + radiomics models. The discriminative ability of each model was evaluated using Harrell's C index. The performance of each model in predicting PFS and OS for 1-, 3-, and 5-years was evaluated using the time-dependent receiver operating characteristic (ROC) curve. Results: Kaplan-Meier curve analysis demonstrated that the radiomics scores effectively identified high- and low-risk patients (all P < 0.05). Multivariable Cox analysis showed that the Ann Arbor stage, maximum standardized uptake value (SUVmax), and RadPFS were independent risk factors associated with PFS. Further, β2-microglobulin, Eastern Cooperative Oncology Group performance status score, SUVmax, and RadOS were independent risk factors for OS. The clinical + metabolic + radiomics model exhibited the greatest discriminative ability for both PFS (Harrell's C-index: 0.805 in the validation cohort) and OS (Harrell's C-index: 0.833 in the validation cohort). The time-dependent ROC analysis indicated that the clinical + metabolic + radiomics model had the best predictive performance. Conclusion: The PET/CT-based clinical + metabolic + radiomics model can enhance prognostication among patients with ENKTCL and may be a non-invasive and efficient risk stratification tool for clinical practice.

Keywords

Acknowledgement

This study was funded by the Medical Science and Technology Research Project of Henan Province (SBGJ202101002).

References

  1. Han L, Liu F, Li R, Li Z, Chen X, Zhou Z, et al. Role of programmed death ligands in effective T-cell interactions in extranodal natural killer/T-cell lymphoma. Oncol Lett 2014;8:1461-1469
  2. Ryu KJ, Lee JY, Choi ME, Yoon SE, Cho J, Ko YH, et al. Serum-derived exosomal MicroRNA profiles can predict poor survival outcomes in patients with extranodal natural killer/T-cell lymphoma. Cancers (Basel) 2020;12:3548
  3. Peng YY, Xiong YY, Zhang LX, Wang J, Zhang HB, Xiao Q, et al. Allogeneic hematopoietic stem cell transplantation in extranodal natural killer/T-cell lymphoma. Turk J Haematol 2021;38:126-137
  4. Fox CP, Civallero M, Ko YH, Manni M, Skrypets T, Pileri S, et al. Survival outcomes of patients with extranodal natural-killer T-cell lymphoma: a prospective cohort study from the international T-cell project. Lancet Haematol 2020;7:e284-e294
  5. Wang L, Wang H, Wang JH, Xia ZJ, Lu Y, Huang HQ, et al. Posttreatment plasma EBV-DNA positivity predicts early relapse and poor prognosis for patients with extranodal NK/T cell lymphoma in the era of asparaginase. Oncotarget 2015;6:30317-30326
  6. Li H, Shao G, Zhang Y, Chen X, Du C, Wang K, et al. Nomograms based on SUVmax of 18F-FDG PET/CT and clinical parameters for predicting progression-free and overall survival in patients with newly diagnosed extranodal natural killer/T-cell lymphoma. Cancer Imaging 2021;21:9
  7. Wang H, Shen G, Jiang C, Li L, Cui F, Tian R. Prognostic value of baseline, interim and end-of-treatment 18F-FDG PET/CT parameters in extranodal natural killer/T-cell lymphoma: a meta-analysis. PLoS One 2018;13:e0194435
  8. Chang Y, Fu X, Sun Z, Xie X, Wang R, Li Z, et al. Utility of baseline, interim and end-of-treatment 18F-FDG PET/CT in extranodal natural killer/T-cell lymphoma patients treated with L-asparaginase/pegaspargase. Sci Rep 2017;7:41057
  9. Kim CY, Hong CM, Kim DH, Son SH, Jeong SY, Lee SW, et al. Prognostic value of whole-body metabolic tumour volume and total lesion glycolysis measured on 18F-FDG PET/CT in patients with extranodal NK/T-cell lymphoma. Eur J Nucl Med Mol Imaging 2013;40:1321-1329
  10. Guidetti A, Dodero A, Lorenzoni A, Pizzamiglio S, Argiroffi G, Chiappella A, et al. Combination of Deauville score and quantitative positron emission tomography parameters as a predictive tool of anti-CD19 chimeric antigen receptor T-cell efficacy. Cancer 2023;129:255-263
  11. Hinzpeter R, Mirshahvalad SA, Kulanthaivelu R, Ortega C, Metser U, Liu ZA, et al. Prognostic value of [18F]-FDG PET/CT radiomics combined with sarcopenia status among patients with advanced gastroesophageal cancer. Cancers (Basel) 2022;14:5314
  12. Zheng X, He B, Hu Y, Ren M, Chen Z, Zhang Z, et al. Diagnostic accuracy of deep learning and radiomics in lung cancer staging: a systematic review and meta-analysis. Front Public Health 2022;10:938113
  13. Wu L, Zhao Y, Lin P, Qin H, Liu Y, Wan D, et al. Preoperative ultrasound radiomics analysis for expression of multiple molecular biomarkers in mass type of breast ductal carcinoma in situ. BMC Med Imaging 2021;21:84
  14. Lue KH, Huang CH, Hsieh TC, Liu SH, Wu YF, Chen YH. Systemic inflammation index and tumor glycolytic heterogeneity help risk stratify patients with advanced epidermal growth factor receptor-mutated lung adenocarcinoma treated with tyrosine kinase inhibitor therapy. Cancers (Basel) 2022;14:309
  15. Li Y, Zhang Y, Fang Q, Zhang X, Hou P, Wu H, et al. Radiomics analysis of [18F]FDG PET/CT for microvascular invasion and prognosis prediction in very-early- and early-stage hepatocellular carcinoma. Eur J Nucl Med Mol Imaging 2021;48:2599-2614
  16. Kirienko M, Sollini M, Corbetta M, Voulaz E, Gozzi N, Interlenghi M, et al. Radiomics and gene expression profile to characterise the disease and predict outcome in patients with lung cancer. Eur J Nucl Med Mol Imaging 2021;48:3643-3655
  17. Peng H, Dong D, Fang MJ, Li L, Tang LL, Chen L, et al. Prognostic value of deep learning PET/CT-based radiomics: potential role for future individual induction chemotherapy in advanced nasopharyngeal carcinoma. Clin Cancer Res 2019;25:4271-4279
  18. Guo H, Li B, Diao L, Wang H, Chen P, Jiang M, et al. An immune-based risk-stratification system for predicting prognosis in pulmonary sarcomatoid carcinoma (PSC). Oncoimmunology 2021;10:1947665
  19. Camp RL, Dolled-Filhart M, Rimm DL. X-tile: a new bioinformatics tool for biomarker assessment and outcome-based cut-point optimization. Clin Cancer Res 2004;10:7252-7259
  20. Parvez A, Tau N, Hussey D, Maganti M, Metser U. 18F-FDG PET/CT metabolic tumor parameters and radiomics features in aggressive non-Hodgkin's lymphoma as predictors of treatment outcome and survival. Ann Nucl Med 2018;32:410-416
  21. Wu W, Ren K, Chen X, Li N, Zhou H, Jiang M, et al. A controlling nutritional status score is an independent predictor for patients with newly diagnosed nasal-type extranodal NK/T-cell lymphoma based on asparaginase-containing regimens. Cancer Med 2023;12:9439-9448
  22. McGrath LA, Ryan DA, Warrier SK, Coupland SE, Glasson WJ. Conjunctival lymphoma. Eye (Lond) 2023;37:837-848
  23. Kang S, Cho H, Kim S, Lee K, Kang EH, Park JS, et al. A new prognostic index for extranodal natural killer/T-cell lymphoma: incorporation of serum β-2 microglobulin to PINK. Cancer Res Treat 2023;55:314-324
  24. Kim HD, Cho H, Kim S, Lee K, Kang EH, Park JS, et al. Prognostic stratification of patients with Burkitt lymphoma using serum β2-microglobulin levels. Cancer Res Treat 2021;53:847-856
  25. Prizment AE, Linabery AM, Lutsey PL, Selvin E, Nelson HH, Folsom AR, et al. Circulating beta-2 microglobulin and risk of cancer: the atherosclerosis risk in communities study (ARIC). Cancer Epidemiol Biomarkers Prev 2016;25:657-664
  26. Semere W, Althouse AD, Rosland AM, White D, Arnold R, Chu E, et al. Poor patient health is associated with higher caregiver burden for older adults with advanced cancer. J Geriatr Oncol 2021;12:771-778
  27. Wang H, Fu BB, Gale RP, Liang Y. NK-/T-cell lymphomas. Leukemia 2021;35:2460-2468
  28. Chen SY, Yang Y, Qi SN, Wang Y, Hu C, He X, et al. Validation of nomogram-revised risk index and comparison with other models for extranodal nasal-type NK/T-cell lymphoma in the modern chemotherapy era: indication for prognostication and clinical decision-making. Leukemia 2021;35:130-142
  29. Huang JJ, Zhu YJ, Xia Y, Zhao W, Lin TY, Jiang WQ, et al. A novel prognostic model for extranodal natural killer/T-cell lymphoma. Med Oncol 2012;29:2183-2190
  30. Suzuki R, Suzumiya J, Yamaguchi M, Nakamura S, Kameoka J, Kojima H, et al. Prognostic factors for mature natural killer (NK) cell neoplasms: aggressive NK cell leukemia and extranodal NK cell lymphoma, nasal type. Ann Oncol 2010;21:1032-1040
  31. Onate-Ocana LF, Cortes V, Castillo-Llanos R, Terrazas A, Garcia-Perez O, Pitalua-Cortes Q, et al. Metabolic tumor volume changes assessed by interval 18fluorodeoxyglucose positron emission tomography-computed tomography for the prediction of complete response and survival in patients with diffuse large B-cell lymphoma. Oncol Lett 2018;16:1411-1418
  32. Bai B, Huang HQ, Cai QC, Fan W, Wang XX, Zhang X, et al. Predictive value of pretreatment positron emission tomography/computed tomography in patients with newly diagnosed extranodal natural killer/T-cell lymphoma. Med Oncol 2013;30:339
  33. Guo R, Xu P, Xu H, Miao Y, Li B. The predictive value of pretreatment 18F-FDG PET/CT on treatment outcome in early-stage extranodal natural killer/T-cell lymphoma. Leuk Lymphoma 2020;61:2659-2664
  34. Khong PL, Huang B, Lee EY, Chan WK, Kwong YL. Midtreatment 18F-FDG PET/CT scan for early response assessment of SMILE therapy in natural killer/T-cell lymphoma: a prospective study from a single center. J Nucl Med 2014;55:911-916
  35. Ko KY, Liu CJ, Ko CL, Yen RF. Intratumoral heterogeneity of pretreatment 18F-FDG PET images predict disease progression in patients with nasal type extranodal natural killer/T-cell lymphoma. Clin Nucl Med 2016;41:922-926
  36. Wang H, Zhao S, Li L, Tian R. Development and validation of an 18F-FDG PET radiomic model for prognosis prediction in patients with nasal-type extranodal natural killer/T cell lymphoma. Eur Radiol 2020;30:5578-5587
  37. Zhai TT, Langendijk JA, van Dijk LV, van der Schaaf A, Sommers L, Vemer-van den Hoek JGM, et al. Pre-treatment radiomic features predict individual lymph node failure for head and neck cancer patients. Radiother Oncol 2020;146:58-65
  38. Peng Z, Wang Y, Wang Y, Jiang S, Fan R, Zhang H, et al. Application of radiomics and machine learning in head and neck cancers. Int J Biol Sci 2021;17:475-486
  39. An P, Lin Y, Hu Y, Qin P, Ye Y, Gu W, et al. Predicting model of biochemical recurrence of prostate carcinoma (PCa-BCR) using MR perfusion-weighted imaging-based radiomics. Technol Cancer Res Treat 2023;22:15330338231166766
  40. Yu Q, Liu J, Lin H, Lei P, Fan B. Application of radiomics model of CT images in the identification of ureteral calculus and phlebolith. Int J Clin Pract 2022;2022:5478908
  41. Yang H, Wang L, Shao G, Dong B, Wang F, Wei Y, et al. A combined predictive model based on radiomics features and clinical factors for disease progression in early-stage non-small cell lung cancer treated with stereotactic ablative radiotherapy. Front Oncol 2022;12:967360