Publications by authors named "R Golfieri"

Based on the well-known role of peritumour characterization in cancer imaging to improve the early diagnosis and timeliness of clinical decisions, this study innovated a state-of-the-art approach for peritumour analysis, mainly relying on extending tumour segmentation by a predefined fixed size. We present a novel, adaptive method to investigate the zone of transition, bestriding tumour and peritumour, thought of as an annular-like shaped area, and detected by analysing gradient variations along tumour edges. For method validation, we applied it on two datasets (hepatocellular carcinoma and locally advanced rectal cancer) imaged by different modalities and exploited the zone of transition regions as well as the peritumour ones derived by adopting the literature approach for building predictive models.

View Article and Find Full Text PDF

Purpose: Transarterial radioembolization (TARE) with Yttrium-90 resin microspheres is a treatment option for patients with intrahepatic cholangiocarcinoma (ICC). However, optimising the timing of TARE in relation to systemic therapies and patient selection remains challenging. We report here on the effectiveness, safety, and prognostic factors associated with TARE for ICC in a combined analysis of the prospective observational CIRT studies (NCT02305459 and NCT03256994).

View Article and Find Full Text PDF
Article Synopsis
  • Benign renal tumors like renal oncocytoma (RO) can be misdiagnosed as malignant renal cell carcinomas (RCC) due to similar imaging characteristics, prompting the need for better diagnostic systems using machine learning and radiomic features.* -
  • A study analyzed CT images from 77 patients, extracting features from tumor volumes and surrounding transition zones (ZOT), and used a genetic algorithm to select the most effective features to build a decision tree classifier for distinguishing RO from clear cell RCC (ccRCC).* -
  • Results showed that ZOT features were the most predictive, with the best model achieving a ROC AUC score of 0.87 when feature selection was applied to the entire dataset, while the version
View Article and Find Full Text PDF