Can radiomics improve the prediction of metastatic relapse of myxoid/round cell liposarcomas?



The strongest adverse prognostic factor in myxoid/round cell liposarcomas (MRC-LPS) is the presence of a round cell component above 5% within the tumor bulk. Its identification is underestimated on biopsies and in the neoadjuvant setting. The aim was to improve the prediction of patients’ prognosis through a radiomics approach.


Thirty-five out of 89 patients with MRC-LPS managed at our sarcoma reference center from 2008 to 2017 were included in this IRB-approved retrospective study as they presented with a pre-treatment contrast-enhanced MRI (median age, 49 years old). Two radiologists reported usual conventional/semantic radiological variables. After signal intensity (SI) normalization, voxel size standardization of T2-WI, and whole tumor volume segmentation, 44 3D-radiomics features were extracted. Using least absolute shrinkage and selection operator penalized Cox regression on prefiltered features, a radiomics score based on 3 weighted radiomics features was generated. Four prognostic multivariate models for MRFS were compared using concordance index: (1) clinical model, (2) semantic radiological model, (3) radiomics model, and (4) radiomics + semantic radiological model.


Twelve patients showed a metastatic relapse. The radiomics score included FOS_Skewness, GLRLM_LRHGE, and SHAPE_Volume and correlated with MRFS (hazard ratio = 19.37, p = 0.0009) and visual heterogeneity on T2-WI (p < 0.0001). A high score indicated a poorer prognosis. After adjustment, the best predictive performances were obtained with model (4) (concordance index = 0.937) and the lowest with model (1) (concordance index = 0.637).


Adding selected radiomics features that quantify tumor heterogeneity and shape at baseline to a conventional radiological analysis improves prediction of MRC-LPS patients’ prognosis.

Key Points

• Fourteen radiomics features quantifying shape and heterogeneity of myxoid/round cell liposarcomas on T2-WI were associated with metastatic relapse in univariate analysis.

• A radiomics score based on 3 selected and weighted radiomics features was a strong and independent prognostic factor for metastatic relapse-free survival.

• The best prediction of metastatic relapse-free survival for myxoid/round cell liposarcomas was achieved by combining the radiomics score to relevant radiological features.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5





Contrast-enhanced T1-WI


95% confidence interval


Hazard ratio


Least absolute shrinkage and selection operator


Myxoid round cell liposarcoma


Metastatic relapse-free survival


Signal intensity




Turbo spin echo


World Health Organization performance status


Weighted imaging


  1. 1.

    Fletcher CDM, Bridge JA, Hogendoorn PCW, Mertens F (2013) WHO classification of tumours of soft tissue and bone, vol 5, 4th edn. IARC Press, Lyon

    Google Scholar 

  2. 2.

    Sreekantaiah C, Karakousis CP, Leong SP, Sandberg AA (1992) Cytogenetic findings in liposarcoma correlate with histopathologic subtypes. Cancer 69:2484–2495

    CAS  Article  Google Scholar 

  3. 3.

    Turc-Carel C, Limon J, Dal Cin P, Rao U, Karakousis C, Sandberg AA (1986) Cytogenetic studies of adipose tissue tumors. II. Recurrent reciprocal translocation t(12;16)(q13;p11) in myxoid liposarcomas. Cancer Genet Cytogenet 23:291–299

  4. 4.

    Engström K, Bergh P, Gustafson P et al (2008) Liposarcoma: outcome based on the Scandinavian Sarcoma Group register. Cancer 113:1649–1656.

    Article  PubMed  Google Scholar 

  5. 5.

    Haniball J, Sumathi VP, Kindblom L-G et al (2011) Prognostic factors and metastatic patterns in primary myxoid/round-cell liposarcoma. Sarcoma 2011:538085.

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  6. 6.

    Asano N, Susa M, Hosaka S et al (2012) Metastatic patterns of myxoid/round cell liposarcoma: a review of a 25-year experience. Sarcoma 2012:345161.

    Article  PubMed  PubMed Central  Google Scholar 

  7. 7.

    Fuglø HM, Maretty-Nielsen K, Hovgaard D, Keller JØ, Safwat AA, Petersen MM (2013) Metastatic pattern, local relapse, and survival of patients with myxoid liposarcoma: a retrospective study of 45 patients. Sarcoma 2013:548628.

  8. 8.

    Fiore M, Grosso F, Lo Vullo S et al (2007) Myxoid/round cell and pleomorphic liposarcomas: prognostic factors and survival in a series of patients treated at a single institution. Cancer 109:2522–2531.

    Article  PubMed  Google Scholar 

  9. 9.

    Antonescu CR, Tschernyavsky SJ, Decuseara R et al (2001) Prognostic impact of P53 status, TLS-CHOP fusion transcript structure, and histological grade in myxoid liposarcoma: a molecular and clinicopathologic study of 82 cases. Clin Cancer Res 7:3977–3987

    CAS  PubMed  Google Scholar 

  10. 10.

    Casali PG, Abecassis N, Aro HT et al (2018) Soft tissue and visceral sarcomas: ESMO-EURACAN Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol 29:iv268–iv269.

    CAS  Article  PubMed  Google Scholar 

  11. 11.

    Wardelmann E, Haas RL, Bovée JVMG et al (2016) Evaluation of response after neoadjuvant treatment in soft tissue sarcomas; the European Organization for Research and Treatment of Cancer-Soft Tissue and Bone Sarcoma Group (EORTC-STBSG) recommendations for pathological examination and reporting. Eur J Cancer 53:84–95.

    CAS  Article  PubMed  Google Scholar 

  12. 12.

    Petscavage-Thomas JM, Walker EA, Logie CI, Clarke LE, Duryea DM, Murphey MD (2014) Soft-tissue myxomatous lesions: review of salient imaging features with pathologic comparison. Radiographics 34:964–980.

  13. 13.

    Crombé A, Loarer FL, Alberti N et al (2018) Homogeneous myxoid liposarcomas mimicking cysts on MRI: a challenging diagnosis. Eur J Radiol 102:41–48.

    Article  PubMed  Google Scholar 

  14. 14.

    Gimber LH, Montgomery EA, Morris CD, Krupinski EA, Fayad LM (2017) MRI characteristics associated with high-grade myxoid liposarcoma. Clin Radiol 72:613.e1–613.e6.

  15. 15.

    Crombé A, Marcellin P-J, Buy X et al (2019) Soft-tissue sarcomas: assessment of MRI features correlating with histologic grade and patient outcome. Radiology 291:710–721.

  16. 16.

    Zhao F, Ahlawat S, Farahani SJ et al (2014) Can MR imaging be used to predict tumor grade in soft-tissue sarcoma? Radiology 272:192–201.

    Article  PubMed  Google Scholar 

  17. 17.

    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577.

    Article  PubMed  Google Scholar 

  18. 18.

    Yoo HJ, Hong SH, Kang Y et al (2014) MR imaging of myxofibrosarcoma and undifferentiated sarcoma with emphasis on tail sign; diagnostic and prognostic value. Eur Radiol 24:1749–1757.

    Article  PubMed  Google Scholar 

  19. 19.

    Lefkowitz RA, Landa J, Hwang S et al (2013) Myxofibrosarcoma: prevalence and diagnostic value of the “tail sign” on magnetic resonance imaging. Skeletal Radiol 42:809–818.

    Article  PubMed  PubMed Central  Google Scholar 

  20. 20.

    Tustison NJ, Avants BB, Cook PA et al (2010) N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 29:1310–1320.

    Article  PubMed  PubMed Central  Google Scholar 

  21. 21.

    Crombé A, Périer C, Kind M et al (2018) T2 -based MRI Delta-radiomics improve response prediction in soft-tissue sarcomas treated by neoadjuvant chemotherapy. J Magn Reson Imaging.

  22. 22.

    Nyúl LG, Udupa JK (1999) On standardizing the MR image intensity scale. Magn Reson Med 42:1072–1081

    Article  Google Scholar 

  23. 23.

    Nioche C, Orlhac F, Boughdad S et al (2018) LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res 78:4786–4789.

    CAS  Article  PubMed  Google Scholar 

  24. 24.

    Simon N, Friedman JH, Hastie T, Tibshirani R (2011) Regularization paths for Cox’s proportional hazards model via coordinate descent. J Stat Softw 39:1–13.

    Article  PubMed  PubMed Central  Google Scholar 

  25. 25.

    Heagerty PJ, Zheng Y (2005) Survival model predictive accuracy and ROC curves. Biometrics 61:92–105.

    Article  PubMed  Google Scholar 

  26. 26.

    Harrell FE, Lee KL, Mark DB (1996) Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat Med 15:361–387.<361::AID-SIM168>3.0.CO;2-4

    Article  PubMed  Google Scholar 

  27. 27.

    Schröder MS, Culhane AC, Quackenbush J, Haibe-Kains B (2011) survcomp: an R/Bioconductor package for performance assessment and comparison of survival models. Bioinformatics 27:3206–3208.

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  28. 28.

    Lu H, Arshad M, Thornton A et al (2019) A mathematical-descriptor of tumor-mesoscopic-structure from computed-tomography images annotates prognostic- and molecular-phenotypes of epithelial ovarian cancer. Nat Commun 10:764.

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  29. 29.

    Khorrami M, Khunger M, Zagouras A et al (2019) Combination of peri- and intratumoral radiomic features on baseline CT scans predicts response to chemotherapy in lung adenocarcinoma. Radiol Artif Intell 1:180012.

    Article  Google Scholar 

  30. 30.

    Kuyumcu G, Rubin BP, Bullen J, Ilaslan H (2018) Quantification of fat content in lipid-rich myxoid liposarcomas with MRI: a single-center experience with survival analysis. Skeletal Radiol 47:1411–1417.

    Article  PubMed  Google Scholar 

  31. 31.

    Tateishi U, Hasegawa T, Beppu Y, Kawai A, Satake M, Moriyama N (2004) Prognostic significance of MRI findings in patients with myxoid-round cell liposarcoma. AJR Am J Roentgenol 182:725–731.

  32. 32.

    Löwenthal D, Zeile M, Niederhagen M et al (2014) Differentiation of myxoid liposarcoma by magnetic resonance imaging: a histopathologic correlation. Acta Radiol 55:952–960.

    Article  PubMed  Google Scholar 

  33. 33.

    Nakamura T, Matsumine A, Matsubara T et al (2017) Infiltrative tumor growth patterns on magnetic resonance imaging associated with systemic inflammation and oncological outcome in patients with high-grade soft-tissue sarcoma. PLoS One 12:e0181787.

    CAS  Article  PubMed  PubMed Central  Google Scholar 

  34. 34.

    Hong JH, Jee WH, Jung CK, Jung JY, Shin SH, Chung YG (2019) Soft tissue sarcoma: adding diffusion-weighted imaging improves MR imaging evaluation of tumor margin infiltration. Eur Radiol 29(5):2589–2597.

  35. 35.

    Yoon MA, Chee CG, Shin MJ et al (2019) Added value of diffusion-weighted imaging to conventional MRI for predicting fascial involvement of soft tissue sarcomas. Eur Radiol 29:1863–1873.

    Article  PubMed  Google Scholar 

  36. 36.

    Lee JH, Yoon YC, Seo SW, Choi YL, Kim HS (2019) Soft tissue sarcoma: DWI and DCE-MRI parameters correlate with Ki-67 labeling index. Eur Radiol.

  37. 37.

    Crombé A, Le Loarer F, Cornelis F et al (2019) High-grade soft-tissue sarcoma: optimizing injection improves MRI evaluation of tumor response. Eur Radiol 29:545–555.

    Article  PubMed  Google Scholar 

Download references


The authors would like to thank Erwan Le Masson (MSc) for his help regarding the normalization of MRIs, as well as Mrs Camille Martinerie for medical writing services.


The authors state that this work has not received any funding.

Author information



Corresponding author

Correspondence to Amandine Crombé.

Ethics declarations


The scientific guarantor of this publication is Dr Xavier Buy, MD, head of the department of radiology at Bergonie Insitut, Bordeaux, France

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

One of the authors has significant statistical expertise (A.C., PhD student in applied mathematics and in statistical modelling at INRIA Bordeaux). No complex statistical methods were necessary for this paper. The R script for the main findings and figures can be available from the corresponding author on reasonable request.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.


• Retrospective

• Diagnostic or prognostic study

• Performed at one institution

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Supplementary Data 1

Inter-observer agreements for the semantic radiological variables. Supplementary Data 2. Correlation plot of the radiomics features associated with metastatic relapse-free survival in univariate analysis. (DOCX 420 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Crombé, A., Le Loarer, F., Sitbon, M. et al. Can radiomics improve the prediction of metastatic relapse of myxoid/round cell liposarcomas?. Eur Radiol 30, 2413–2424 (2020).

Download citation


  • Sarcoma
  • Patient-specific modeling
  • Liposarcomas, myxoid
  • Prognosis
  • Magnetic resonance imaging