T2-based MRI radiomic features for discriminating tumour grading in soft tissues sarcomas

Georgios C. Manikis, Katerina Nikiforaki, Eleni Lagoudaki, Eelco de Bree, Thomas G. Maris, Kostas Marias, Apostolos H. Karantanas


Purpose: The proposed study aims to develop an MRI-based radiomics analysis framework and investigate the feasibility of the calculated quantitative imaging features for differentiating low from high grade soft tissue sarcomas (STSs).

Material and Methods: A total of 22 patients (9 low grade and 13 high grade) who were pathologically diagnosed with soft tissue sarcomas were recruited for the analysis and corresponding T2-weighted MR images were acquired for further post-processing. Tumour delineations were manually traced slice by slice concluding to whole tumour annotated volumes from all enrolled patients.

A total of 1165 high-throughput patient-specific quantitative imaging features were exported from each volume using radiomics and evaluated using random forest machine learning classifiers. The overall analysis framework was coupled with feature selection and oversampling techniques to address high-dimensionality dataset issues and the unbalanced ratio between the two examined groups. Validation was performed using repeated nested cross-validation to eliminate overfitting problems and assess the stability of the classification performance.

Results: The classifier, using the three most important radiomic features selected though training, yielded an accuracy of 0.781 ± 0.15, an area under the receiver operating characteristic curve (AUROC) equal to 0.814 ± 0.186, F1-score of 0.704 ± 0.198, 0.762 ± 0.267 and 0.725 ± 0.283 for precision and recall respectively using multiple independent test sets.

Conclusions: Radiomic features from routine MR imaging protocols can provide a strong discriminatory performance between low and high grade soft tissue sarcomas.


Radiomics; Soft tissue sarcomas; Machine learning; Imaging biomarkers; Quantitative MRI

Full Text:



WHO Classification of Soft Tissue Tumours. 2006; 139: 35–39.

Guillou L, Coindre JM, Bonichon F, et al. Comparative study of the National Cancer Institute and French Federation of Cancer Centers Sarcoma Group grading systems in a population of 410 adult patients with soft tissue sarcoma. J Clin Oncol 1997; 15(1): 350-362.

Edge SB, Byrd DR, Compton CC, et al. AJCC cancer staging manual, 7th edition. France: Springer 2010.

Leithner A, Maurer-Ertl W, Windhager R. Biopsy of bone and soft tissue tumours: Hints and hazards. In: Tunn P-U, ed. Treatment of bone and soft tissue sarcomas. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009; pp. 3-10.

De La Hoz Polo M, Dick E, et al. Surgical considerations when reporting MRI studies of soft tissue sarcoma of the limbs. Skeletal Radiol 2017; 46(12): 1667-1678.

Papp DF, Khanna AJ, McCarthy EF, et al. Magnetic resonance imaging of soft-tissue tumours: determinate and indeterminate lesions. J Bone Joint Surg Am 2007; 89 Suppl 3: 103-115.

Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 2017; 14(12): 749-762.

Liu Z, Wang S, Dong D, et al. The applications of radiomics in precision diagnosis and treatment of oncology: Opportunities and challenges. Theranostics 2019; 9(5): 1303-1322.

Sanduleanu S, Woodruff HC, de Jong EEC, et al. Tracking tumour biology with radiomics: A systematic review utilizing a radiomics quality score. Radiother Oncol 2018; 127(3): 349-360.

Corino VDA, Montin E, Messina A, et al. Radiomic analysis of soft tissues sarcomas can distinguish intermediate from high-grade lesions. J Magn Reson Imaging 2018; 47(3): 829-840.

Spraker MB, Wootton LS, Hippe DS, et al. MRI radiomic features are independently associated with overall survival in soft tissue sarcoma. Adv Radiation Oncol 2019; 4(2): 413-421.

Crombé A, Périer C, Kind M, et al. T2-based MRI Delta-radiomics improve response prediction in soft-tissue sarcomas treated by neoadjuvant chemotherapy. J Magn Reson Imaging 2019; 50(2): 497-510.

Zhang Y, Zhu Y, Shi X, et al. Soft Tissue Sarcomas: Preoperative predictive histopathological grading based on radiomics of MRI. Acad Radiol 2019; 26(9): 1262-1268.

Papanikolaou N, Santinha J. An introduction to radiomics: Capturing tumour biology in space and time. Hell J Radiol 2018; 3(1): 61-71.

Manikis GC, Nikiforaki K, Papanikolaou N, et al. Diffusion modelling tool (DMT) for the analysis of diffusion weighted imaging (DWI) magnetic resonance imaging (MRI) data. CGI 2016; 97-100.

Griethuysen JJ M, Fedorov A, Parmar C, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res 2017; 77(21): e104-e107.

Pedregosa F, Varoquaux, G, Gramfort A, et al. Scikit-learn: Machine learning in Python. J Machine Learn Res 2011; 12: 2825-2830.

Ding C, Peng H. Minimum redundancy feature selection from microarray gene expression data. J Bioinforma Comput Biol 2005; 03(02): 185-205.

Chawla NV, Bowyer KW, Hall LO, et al. SMOTE: Synthetic minority over-sampling technique. J Artif Intell Res 2002; 16: 321-357.

Dutta S, Ghosh AK. On some transformations of high dimension, low sample size data for nearest neighbor classification. Machine Learning 2016; 102(1): 57-83.

DOI: http://dx.doi.org/10.36162/hjr.v4i3.301


  • There are currently no refbacks.