Despite its overall dismal prognosis, recent research has identified specific molecular subtypes with distinct therapy response and outcome. Tumors exhibit heterogeneity on a genetic, transcriptomic, and proteomic level, which manifests itself in a complex tissue architecture including tumor cells, various fibroblast, and immune cell populations embedded in a poorly vascularized, dense stroma. Pancreatic ductal adenocarcinoma (PDAC) carries amongst the poorest prognoses of all cancers. The high overlap of clinically relevant histopathological subtypes with model predictions underlines the potential of quantitative imaging in PDAC pre-operative subtyping and prognosis. ML application to ADC radiomics allowed OS prediction with a high diagnostic accuracy in an IVC.
Of the 21 patients with determined histopathological subtype, 8/9 patients predicted to experience below-median OS exhibited the quasi-mesenchymal subtype, whilst 11/12 patients predicted to experience above-median OS exhibited a non-quasi-mesenchymal subtype ( p < 0.001). Heterogeneity-related features were highly ranked by the model. The ML algorithm achieved 87% sensitivity (95% IC 67.3–92.7), 80% specificity (95% CI 74.0–86.7), and ROC-AUC 90% for the prediction of above- versus below-median OS in the IVC. Fisher’s exact test, 95% confidence intervals (CI), and receiver operating characteristic area under the curve (ROC-AUC) were used. Individual radiomic feature importance was evaluated by assessment of tree node Gini impurity decrease and recursive feature elimination. Histopathological subtype of tumor samples was assessed by immunohistochemistry in 21 IVC patients. A random forest ML algorithm was fit to the training cohort and tested in the IVC. Tumors were segmented on preoperative apparent diffusion coefficient (ADC) maps, and radiomic features were extracted. One hundred two patients with histopathologically proven PDAC were retrospectively assessed as training cohort, and 30 prospectively accrued and retrospectively enrolled patients served as independent validation cohort (IVC).
To develop a supervised machine learning (ML) algorithm predicting above- versus below-median overall survival (OS) from diffusion-weighted imaging-derived radiomic features in patients with pancreatic ductal adenocarcinoma (PDAC).
0 kommentar(er)
