Background/Objectives: Pancreatic cancer is a very aggressive disease with a poor prognosis, even when diagnosed at an early stage. This study aimed to validate and refine a radiomic-based [¹⁸F]FDG-PET model to predict distant relapse-free survival (DRFS) in patients with unresectable locally advanced pancreatic cancer (LAPC). Methods: A Cox regression model incorporating two radiomic features (RFs) and cancer stage (III vs. IV) was temporally validated using a larger cohort (215 patients treated between 2005–2022). Patients received concurrent chemoradiotherapy with capecitabine and hypo-fractionated Intensity Modulated Radiotherapy (IMRT). Data were split into training (145 patients, 2005–2017) and validation (70 patients, 2017–2022) groups. Seventy-eight RFs were extracted, harmonized, and analyzed using machine learning to develop refined models. Results: The model incorporating Statistical-Percentile10, Morphological-ComShift, and stage demonstrated moderate predictive accuracy (training: C-index = 0.632; validation: C-index = 0.590). When simplified to include only Statistical-Percentile10, performance improved slightly in the validation group (C-index = 0.601). Adding GLSZM3D-grayLevelVariance to Statistical-Percentile10, while excluding Morphological-ComShift, further enhanced accuracy (training: C-index = 0.654; validation: C-index = 0.623). Despite these refinements, all versions showed similar moderate ability to stratify patients into risk classes. Conclusions: [¹⁸F]FDG-PET radiomic features are robust predictors of DRFS after chemoradiotherapy in LAPC. Despite moderate performance, these models hold promise for patient risk stratification. Further validation with external cohorts is ongoing.

Purpose: This paper aimed to identify dosimetric, clinical, and CT-based densitometric predictors of radiation-induced pulmonary events in breast cancer patients treated with moderately hypofractionated radiotherapy. Materials and Methods: A single-institution cohort of 1172 consecutive patients treated with 3D conformal whole-breast radiotherapy (40 Gy/15 fractions) before 2017 was analyzed. Ipsilateral lung DVHs and CT densitometry metrics were extracted. Clinical variables and cardiac calcification (CAC) scores (Agatston_score, CAC_volume, Max_HU_Heart) were included. Univariable and multivariable logistic regressions were performed; collinearity was assessed via Spearman correlation and VIF. Optimal thresholds were derived using the Youden index. Internal validation used bootstrap resampling. Results: After a median follow-up of 6.5 years, 18 patients developed moderate/severe pulmonary events. The univariable analysis showed associations with lung densitometric features (median/mean HU, 10th percentile, the lung volume with HU < −850 (V850)), V37 Gy, lung volume, and CAC scores. Lower lung HU values and larger lung volumes were linked to higher risk. The best models combined V850 (or lung volume) with a CAC metric. The model including V850 > 175 cc and continuous Max_HU_Heart achieved an optimism-corrected AUC of 0.68, with good fit and calibration (Hosmer–Lemeshow p = 0.33, R² = 0.847). Conclusions: The baseline cardiopulmonary status, captured by lung and heart densitometry, predicts pulmonary toxicity better than dosimetry. V850 > 175 cc was associated with a 4-fold higher risk, consistent with air trapping, known as a marker of emphysema.

Background and purpose: Cardiac calcifications (CAC) are emerging as relevant predictors of cardiac toxicity after breast cancer radiotherapy. This study aimed to investigate the association between quantitative CAC scores and specific subgroups of cardiac events in patients treated with moderate hypofractionation, and to assess the interplay between dosimetric and clinical predictors for different families of events. Materials and methods: Data from 1172 consecutive breast cancer patients treated at a single institution with 40 Gy in 15 fractions were analyzed. Mean heart dose (MHD) was extracted after automatic heart segmentation. Agatston score (AS), CAC volume, and maximum heart HU value (Max_HU) were quantified from planning CT scans. Available clinical variables included laterality, chemotherapy, age, smoking status, and respiratory toxicity occurring within 3 years after radiotherapy. Cardiac events were classified into two groups: CAC_corr (coronary artery disease, acute myocardial infarction, congestive heart failure, and valvular disease) and CAC_uncorr (conduction abnormalities, atrial premature beats, atrial fibrillation, pericarditis, and tachyarrhythmia). Associations between predictors and outcomes were tested using logistic regression. Results: After excluding patients with pacemakers/electrodes, 1091 patients were available. With a median follow-up of 6.5 years, 29 cardiac events were recorded. Among them, 15/29 were CAC_corr and were similarly distributed between right-and left-sided tumors (8 vs 7). Conversely, 13/14 CAC_uncorr events occurred in left breast cancer patients; therefore, analyses for this subgroup were restricted to left-sided cases (13/561). For CAC_corr events, the combination of AS/CAC_volume/Max_HU with age showed the best predictive performance (AUC=0.80/0.79, p<0.0001), while respiratory toxicity had no impact. For CAC_uncorr events, age and anthracycline-based chemotherapy (FEC) were the strongest predictors (AUC=0.73, p=0.0125). Including respiratory toxicity significantly improved model performance (AUC=0.77, p=0.0003). MHD was not independently associated with cardiac events. Conclusion: CAC_corr events were mainly associated with CAC burden and age, independently of tumor laterality. In contrast, CAC_uncorr events appeared more related to treatment-related factors, as most occurred after left-sided irradiation. Within left breast cancer patients, these events were mainly associated with age, anthracycline-based chemotherapy, and respiratory toxicity rather than with MHD.