Chemotherapy-associated liver injuries (CALI) have a major clinical impact, but their non-invasive diagnosis is still an unmet need. The present work aims at presenting a web-app for personalized risk prediction of developing CALI, elucidating the contribution of radiomic analysis. Patients undergoing liver resection for colorectal metastases after oxaliplatin-based or irinotecan-based chemotherapy between January 2018 and February 2020 were retrospectively analyzed. Radiomic features were extracted from a standardized volume of non-tumoral liver parenchyma. Multivariate logistic regression models and CART were applied to identify predictors and were internally validated. Results show that radiomic analysis of liver parenchyma may provide a signature that, in combination with clinical and laboratory data, improves diagnosis of CALI.
Virtual biopsy in action: a radiomic-based model for CALI prediction
Francesca Ieva;Giulia Baroni;Lara Cavinato;Chiara Masci;
2021-01-01
Abstract
Chemotherapy-associated liver injuries (CALI) have a major clinical impact, but their non-invasive diagnosis is still an unmet need. The present work aims at presenting a web-app for personalized risk prediction of developing CALI, elucidating the contribution of radiomic analysis. Patients undergoing liver resection for colorectal metastases after oxaliplatin-based or irinotecan-based chemotherapy between January 2018 and February 2020 were retrospectively analyzed. Radiomic features were extracted from a standardized volume of non-tumoral liver parenchyma. Multivariate logistic regression models and CART were applied to identify predictors and were internally validated. Results show that radiomic analysis of liver parenchyma may provide a signature that, in combination with clinical and laboratory data, improves diagnosis of CALI.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
