ASCO 2017: Applying radiomics to predict pathology of post chemotherapy retroperitoneal nodal masses in germ cell tumors
For the purpose of this study, pts with GCT who had an RPLND for nodal mass > 1cm after first line platinum chemotherapy were included. Preoperative contrast enhanced axial CT images of retroperitoneal ROI were manually contoured. 153 radiomics features trained a radial basis function support vector machine classifier to discriminate between viable GCT/Mature Teratoma vs fibrosis. Nested ten-fold cross-validation protocol was employed to determine classifier accuracy. Clinical variables and restricted size criteria were used to optimize the classifier.
Overall, 77 pts with 102 ROI were analyzed (GCT: 21; T: 41; F: 40). The discriminative accuracy of radiomics to identify GCT/T vs fibrosis was 72% (±2.2) (AUC: 0.74 (±0.03). No major predictive differences were identified when data was restricted by varying maximal axial diameters (AUC range: 0.58(±0.05) - 0.74(±0.03)). Prediction algorithm using clinical variables alone identified an AUC of 0.71 (±0.15). When these variables were added to the radiomic signature, the best performing classifier was identified when axial tumors were limited to diameter < 2cm (accuracy: 88.2 (±4.4); AUC: 0.80 (±0.05) (p = 0.02)).
In conclusion, a predictive radiomics algorithm had an overall discriminative accuracy of 72% that improved to 80% when combined with clinical details. This requires further independent validation to assess whether radiomics, in conjunction with standard clinical predictors, may allow pts with a high predicted likelihood of fibrosis to avoid RPLND.
Presented By: Jeremy Howard Lewin, Department of Medical Oncology and Hematology, Princess Margaret Cancer Centre, Toronto, ON, Canada
Written By: Hanan Goldberg, MD, Urologic Oncology Fellow (SUO), University of Toronto, Princess Margaret Cancer Centre
Twitter: @GoldbergHanan
at the 2017 ASCO Annual Meeting - June 2 - 6, 2017 – Chicago, Illinois, USA