Amandine Crombé1,2,3,4, François Le Loarer5,6, Maxime Sitbon7, Antoine Italiano8, Eberhard Stoeckle9, Xavier Buy7, Michèle Kind7. 1. Department of Radiology, Institut Bergonie, F-33000, Bordeaux, France. a.crombe@bordeaux.unicancer.fr. 2. Department of Diagnostic and Interventional Radiology, Institut Bergonié, Comprehensive Cancer Center, 229 cours de l'Argonne, F-33000, Bordeaux, France. a.crombe@bordeaux.unicancer.fr. 3. Modelisation in Oncology (MOnc) Team, INRIA Bordeaux-Sud-Ouest, CNRS UMR 5251, F-33405, Talence, France. a.crombe@bordeaux.unicancer.fr. 4. University of Bordeaux, F-33000, Bordeaux, France. a.crombe@bordeaux.unicancer.fr. 5. University of Bordeaux, F-33000, Bordeaux, France. 6. Department of Pathology, Institut Bergonie, F-33000, Bordeaux, France. 7. Department of Radiology, Institut Bergonie, F-33000, Bordeaux, France. 8. Department of Surgery, Institut Bergonie, F-33000, Bordeaux, France. 9. Department of Medical Oncology, Institut Bergonie, F-33000, Bordeaux, France.
Abstract
OBJECTIVE: 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. METHODS: 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. RESULTS: 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). CONCLUSION: 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.
OBJECTIVE: 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. METHODS: 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. RESULTS: 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). CONCLUSION: Adding selected radiomics features that quantify tumor heterogeneity and shape at baseline to a conventional radiological analysis improves prediction of MRC-LPSpatients' 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.
Entities:
Keywords:
Liposarcomas, myxoid; Magnetic resonance imaging; Patient-specific modeling; Prognosis; Sarcoma
Authors: C R Antonescu; S J Tschernyavsky; R Decuseara; D H Leung; J M Woodruff; M F Brennan; J A Bridge; J R Neff; J R Goldblum; M Ladanyi Journal: Clin Cancer Res Date: 2001-12 Impact factor: 12.531
Authors: Jonelle M Petscavage-Thomas; Eric A Walker; Chika I Logie; Loren E Clarke; Dennis M Duryea; Mark D Murphey Journal: Radiographics Date: 2014 Jul-Aug Impact factor: 5.333
Authors: Marco Fiore; Federica Grosso; Salvatore Lo Vullo; Elisabetta Pennacchioli; Silvia Stacchiotti; Andrea Ferrari; Paola Collini; Laura Lozza; Luigi Mariani; Paolo G Casali; Alessandro Gronchi Journal: Cancer Date: 2007-06-15 Impact factor: 6.860
Authors: Katarina Engström; Peter Bergh; Pelle Gustafson; Ragnar Hultborn; Helena Johansson; Rickard Löfvenberg; Olga Zaikova; Clement Trovik; Ola Wahlström; Henrik C F Bauer Journal: Cancer Date: 2008-10-01 Impact factor: 6.860
Authors: Brandon K K Fields; Natalie L Demirjian; Darryl H Hwang; Bino A Varghese; Steven Y Cen; Xiaomeng Lei; Bhushan Desai; Vinay Duddalwar; George R Matcuk Journal: Eur Radiol Date: 2021-04-23 Impact factor: 5.315
Authors: Fernando Carrasco Ferreira Dionisio; Larissa Santos Oliveira; Mateus de Andrade Hernandes; Edgard Eduard Engel; Paulo Mazzoncini de Azevedo-Marques; Marcello Henrique Nogueira-Barbosa Journal: Radiol Bras Date: 2021 May-Jun