Pediatric rhabdomyosarcomas: Three-dimensional radiological assessments after induction chemotherapy predict survival better than one-dimensional and two-dimensional measurements

Radiological response to neoadjuvant chemotherapy is currently used to assess the efficacy of treatment in pediatric patients with rhabdomyosarcoma (RMS), but the association between early tumor response on imaging and survival is still controversial. The aim of this study was to investigate the prognostic value of assessing radiological response after induction therapy in pediatric RMS, comparing four different methods. This retrospective, two-center study was conducted on 66 non-metastatic RMS patients. Two radiologists measured tumor size on pre-and post-treatment magnetic resonance (MR) or computed tomography (CT) images using four methods: considering maximal diameter with the 1D-RECIST (Response Evaluation Criteria in Solid Tumors); multiplying the two maximal diameters with the 2D-WHO (World Health Organization); multiplying the three maximal diameters with the 3D-EpSSG (European pediatric Soft tissue sarcoma Study Group); obtaining a software-assisted volume assessment with the 3D-Osirix. Each patient was classified as a responder or non-responder based on the proposed thresholds for each method. Tumor response was compared with survival using Kaplan–Meier plots, the log-rank test, and Cox’s regression. Agreement between methods and observers (weighted-κ) was also calculated. The 5-year event-free survival (5yr-EFS) calculated with the Kaplan–Meier plots was significantly longer for responders than for non-responders with all the methods, but the 3D assessments differentiated between the two groups better than the 1D-RECIST or 2D-WHO (p1D-RECIST = 0.018, p2D-WHO = 0.007, p3D-EpSSG and p3D-Osirix < 0.0001). Comparing the 5yr-EFS of responders and non-responders also produced adjusted hazard ratios of 3.57 (p = 0.0158) for the 1D-RECIST, 5.05 for the 2D-WHO (p = 0.0042), 14.40 for the 3D-EpSSG (p < 0.0001) and 11.60 for the 3D-Osirix (p < 0.0001), indicating that the volumetric measurements were significantly more strongly associated with EFS. Inter-method agreement was excellent between the 3D-EpSSG and the 3D-Osirix (κ = 0.98), and moderate for the other comparisons (0.5 < κ < 0.8). The 1D-RECIST and the 2D-WHO tended to underestimate response to treatment. Inter-observer agreement was excellent with all methods (κ > 0.8) except for the 2D-WHO (κ = 0.7). In conclusion, early tumor response was confirmed as a significant prognostic factor in RMS, and the 3D-EpSSG and 3D-Osirix methods predicted response to treatment better than the 1D-RECIST or 2D-WHO measurements.