Metastasis risk prediction model in osteosarcoma using metabolic imaging phenotypes: A multivariable radiomics model

Autoři: Heesoon Sheen aff001;  Wook Kim aff001;  Byung Hyun Byun aff002;  Chang-Bae Kong aff003;  Won Seok Song aff003;  Wan Hyeong Cho aff003;  Ilhan Lim aff002;  Sang Moo Lim aff002;  Sang-Keun Woo aff001
Působiště autorů: Division of applied RI, Korea Institute of Radiological and Medical Sciences (KIRAMS), Seoul, Republic of Korea aff001;  Departments of Nuclear Medicine, Korea Institute of Radiological and Medical Sciences (KIRAMS), Seoul, Republic of Korea aff002;  Department of Orthopedic Surgery, Korea Institute of Radiology and Medical Sciences, Seoul, Republic of Korea aff003
Vyšlo v časopise: PLoS ONE 14(11)
Kategorie: Research Article
doi: 10.1371/journal.pone.0225242



Osteosarcoma (OS) is the most common primary bone tumor affecting humans and it has extreme heterogeneity. Despite modern therapy, it recurs in approximately 30–40% of patients initially diagnosed with no metastatic disease, with the long-term survival rates of patients with recurrent OS being generally 20%. Thus, early prediction of metastases in OS management plans is crucial for better-adapted treatments and survival rates. In this study, a radiomics model for metastasis risk prediction in OS was developed and evaluated using metabolic imaging phenotypes.

Methods and findings

The subjects were eighty-three patients with OS, and all were treated with surgery and chemotherapy for local control. All patients underwent a pretreatment 18F-FDG-PET scan. Forty-five features were extracted from the tumor region. The incorporation of features into multivariable models was performed using logistic regression. The multivariable modeling strategy involved cross validation in the following four steps leading to final prediction model construction: (1) feature set reduction and selection; (2) model coefficients computation through train and validation processing; and (3) prediction performance estimation. The multivariable logistic regression model was developed using two radiomics features, SUVmax and GLZLM-SZLGE. The trained and validated multivariable logistic model based on probability of endpoint (P) = 1/ (1+exp (-Z)) was Z = -1.23 + 1.53*SUVmax + 1.68*GLZLM-SZLGE with significant p-values (SUVmax: 0.0462 and GLZLM_SZLGE: 0.0154). The final multivariable logistic model achieved an area under the curve (AUC) receiver operating characteristics (ROC) curve of 0.80, a sensitivity of 0.66, and a specificity of 0.88 in cross validation.


The SUVmax and GLZLM-SZLGE from metabolic imaging phenotypes are independent predictors of metastasis risk assessment. They show the association between 18F-FDG-PET and metastatic colonization knowledge. The multivariable model developed using them could improve patient outcomes by allowing aggressive treatment in patients with high metastasis risk.

Klíčová slova:

Bone imaging – Cancer detection and diagnosis – Cancer chemotherapy – Cancer treatment – Metastasis – Positron emission tomography – Osteosarcoma


1. Lindsey BA, Markel JE, Kleinerman ES. Osteosarcoma Overview. Rheumatol Ther. Springer Healthcare 2017;4:25–43.

2. Durfee RA, Mohammed M, Luu HH. Review of osteosarcoma and current management. Rheumatol Ther. Springer Healthcare 2016;3:221–43.

3. Bailly C, Leforestier R, Campion L, Thebaud E, Moreau A, Kraeber-Bodere F, et al. Prognostic value of FDG-PET indices for the assessment of histological response to neoadjuvant chemotherapy and outcome in pediatric patients with Ewing sarcoma and osteosarcoma. Tsokos M, editor. PLoS One 2017 12:e0183841 doi: 10.1371/journal.pone.0183841 28841702

4. Analytics G, Nailon WH, Rai P, Srinivasan G, Shobha G, Thibault G, et al. Role of SUVmax obtained by 18F-FDG PET/CT in patients with a solitary pancreatic lesion: Predicting malignant potential and proliferation. Eur J Nucl Med Mol Imaging 2015;53:1149–54.

5. Whelan JS, Jinks RC, McTiernan A, Sydes MR, Hook JM, Trani L, et al. Survival from high-grade localised extremity osteosarcoma: Combined results and prognostic factors from three European osteosarcoma intergroup randomised controlled trials. Ann Oncol. 2012;23:1607–16. doi: 10.1093/annonc/mdr491 22015453

6. Daw NC, Chou AJ, Jaffe N, Rao BN, Billups CA, Meyers PA, et al. Survival after recurrence of osteosarcoma: A 20-year experience at a single institution. Br J Cancer. Nature Publishing Group; 2006;112:278–82.

7. Daw NC, Chou AJ, Jaffe N, Rao BN, Billups CA, Rodriguez-Galindo C, et al. Recurrent osteosarcoma with a single pulmonary metastasis: A multi-institutional review. Br J Cancer. Nature Publishing Group; 2015;112:278–82.

8. Heare T, Hensley MA, Dell’Orfano S. Bone tumors: Osteosarcoma and Ewing’s sarcoma. Curr Opin Pediatr. 2009;21:365–72. doi: 10.1097/MOP.0b013e32832b1111 19421061

9. Byun BH, Kong C-B, Park J, Seo Y, Lim I, Choi CW, et al. Initial metabolic tumor volume measured by 18F-FDG PET/CT can predict the outcome of osteosarcoma of the extremities. J Nucl Med. 2013;54:1725–32. doi: 10.2967/jnumed.112.117697 23949909

10. Chicklore S, Goh V, Siddique M, Roy A, Marsden PK, Cook GJR. Quantifying tumour heterogeneity in18F-FDG PET/CT imaging by texture analysis. Eur J Nucl Med Mol Imaging. 2013;40:133–40. doi: 10.1007/s00259-012-2247-0 23064544

11. Asselin MC, O’Connor JPB, Boellaard R, Thacker NA, Jackson A. Quantifying heterogeneity in human tumours using MRI and PET. Eur J Cancer. 2012;48:447–55. doi: 10.1016/j.ejca.2011.12.025 22265426

12. Tixier F, Le Rest CC, Hatt M, Albarghach N, Pradier O, Metges J-P, et al. Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer. J Nucl Med. 2011;52:369–78. doi: 10.2967/jnumed.110.082404 21321270

13. Lambin P, Van Stiphout RGPM, Starmans MHW, Rios-Velazquez E, Nalbantov G, Aerts HJWL, et al. Predicting outcomes in radiation oncology-multifactorial decision support systems. Nat Rev Clin Oncol. 2013;10:27–40. doi: 10.1038/nrclinonc.2012.196 23165123

14. Orlhac F, Nioche C, Buvat I. Texture—User Guide Local Image Features Extraction. 2018.

15. Nioche C, Orlhac F, Boughdad S, Reuze S, Goya-Outi J, Robert C, et al. Lifex: A freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res. 2018;78:4786–9. doi: 10.1158/0008-5472.CAN-18-0125 29959149

16. Orlhac F, Maisonobe J, Garcia CA, Vanderlinden B. Tumor texture analysis in 18 F-FDG PET: Relationships between texture parameters, histogram indices, standardized uptake values, metabolic volumes, and total lesion glycolysis. J Nucl Med. 2014;55:414–23. doi: 10.2967/jnumed.113.129858 24549286

17. Orlhac F, Soussan M, Chouahnia K, Martinod E, Buvat I. 18F-FDG PET-derived textural indices reflect tissue-specific uptake pattern in non-small cell lung cancer. Adusumilli PS, editor. PLoS One 2015; 10:1–16.

18. Kirienko M, Cozzi L, Antunovic L, Lozza L, Fogliata A, Voulaz E, et al. Prediction of disease-free survival by the PET/CT radiomic signature in non-small cell lung cancer patients undergoing surgery. Eur J Nucl Med Mol Imaging 2018;45:207–17. doi: 10.1007/s00259-017-3837-7 28944403

19. Hatt M, Tixier F, Pierce L, Kinahan PE, Cheze Le Rest C, Visvikis D, et al. Characterization of PET/CT images using texture analysis: The past, the present… any future? Eur J Nucl Med Mol Imaging 2017;44:151–65. doi: 10.1007/s00259-016-3427-0 27271051

20. Vallières M, Freeman CR, Skamene SR, El Naqa I. A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Phys Med Biol. 2015;60:5471–96. doi: 10.1088/0031-9155/60/14/5471 26119045

21. Eary JF, Sullivan FO, Sullivan JO, Conrad EU. Spatial heterogeneity in sarcoma 18 F-FDG uptake as a predictor of patient outcome. J Nucl Med. 2009;49:1973–9.

22. Eary JF, O’Sullivan F, Powitan Y, Chandhury K, Vernon C, Bruckner JD, et al. Sarcoma tumor FDG uptake measured by PET and patient outcome: A retrospective analysis. Eur J Nucl Med. 2002;29:1149–54.

23. Hwang JP, Lim I, Kong CB, Jeon DG, Byun BH, Kim B Il, et al. Prognostic value of SUVmax measured by pretreatment fluorine-18 fluorodeoxyglucose positron emission tomography/computed tomography in patients with Ewing sarcoma. PLoS One. 2016;11:1–9.

24. Skamene SR, Rakheja R, Dalhstrom KR, Roberge D, Nahal A, Charest M, et al. Metabolic activity measured on PET/CT correlates with clinical outcomes in patients with limb and girdle sarcomas. J Surg Oncol. 2014;109:410–4. doi: 10.1002/jso.23523 24310279

25. Kong CB, Byun BH, Lim I, Choi CW, Lim SM, Song WS, et al. 18F-FDG PET SUVmax as an indicator of histopathologic response after neoadjuvant chemotherapy in extremity osteosarcoma. Eur J Nucl Med Mol Imaging. 2013;40:728–36. doi: 10.1007/s00259-013-2344-8 23361860

26. Vander Heiden MG, Cantley LC, Thompson CB. Understanding the Warburg effect: The metabolic requirements of cell proliferation. Science 2009;324:1029–33. doi: 10.1126/science.1160809 19460998

27. Keith B, Simon MC. Hypoxia-inducible factors, stem cells, and cancer. Cell. 2007;129:465–72. doi: 10.1016/j.cell.2007.04.019 17482542

28. Gatenby RA, Gillies RJ. Why do cancers have high aerobic glycolysis? Nat Rev Cancer. Nature Publishing Group; 2004;4:891–9.

29. Cao J, Wang Y, Dong R, Lin G, Zhang N, Wang J, et al. Hypoxia-induced WSB1 promotes the metastatic potential of osteosarcoma cells. Cancer Res. 2015;75:4839–51. doi: 10.1158/0008-5472.CAN-15-0711 26424695

30. Guan G, Zhang Y, Lu Y, Liu L, Shi D, Wen Y, et al. The HIF-1α/CXCR4 pathway supports hypoxia-induced metastasis of human osteosarcoma cells. Cancer Lett. 2015;357:254–64. doi: 10.1016/j.canlet.2014.11.034 25444927

31. Thiery JP, Acloque H, Huang RYJ, Nieto MA. Epithelial-Mesenchymal Transitions in Development and Disease. Cell. 2009;39:871–90.

Článek vyšel v časopise


2019 Číslo 11