Recently it has been shown that radiomic features of computed tomography (CT) have prognostic information in stage I-III non-small cell lung cancer (NSCLC) patients. We aim to validate this prognostic radiomic signature in stage IV adenocarcinoma patients undergoing chemotherapy. Two datasets of chemo-naive stage IV adenocarcinoma patients were investigated, dataset 1: 285 patients with CTs performed in a single center; dataset 2: 223 patients included in a multicenter clinical trial. The main exclusion criteria were EGFR mutation or unknown mutation status and non-delineated primary tumor. Radiomic features were calculated for the primary tumor. The c-index of cox regression was calculated and compared to the signature performance for overall survival (OS). In total CT scans from 195 patients were eligible for analysis. Patients having a prognostic index (PI) lower than the signature median (n = 92) had a significantly better OS than patients with a PI higher than the median (n = 103, HR 1.445, 95% CI 1.07-1.95, p = 0.02, c-index 0.576, 95% CI 0.527-0.624). The radiomic signature, derived from daily practice CT scans, has prognostic value for stage IV NSCLC, however the signature performs less than previously described for stage I-III NSCLC stages. In the future, machine learning techniques can potentially lead to a better prognostic imaging based model for stage IV NSCLC.

Purpose: To assess the diagnostic concordance between contrast-enhanced mammography (CEM) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in the preoperative staging of breast cancer (BCa) and to evaluate the clinical, operational, and economic implications of substituting CEM for MRI in concordant cases. Methods: This retrospective single-center study included 280 patients who underwent both CEM and DCE-MRI within 15 days. Two experienced breast radiologists independently evaluated imaging concordance based on lesion detection, characterization, and clinical interpretability. A cost minimization analysis was performed assuming equivalent diagnostic performance in concordant cases. Direct procedural costs were derived from regional reimbursement rates (€215.20 for DCE-MRI; €74.00 for CEM). Operational efficiency was assessed using institutional time-motion data, and average radiologist reporting times were included to model overall organizational impact. Results: Complete diagnostic concordance was observed in 190 cases (67.9%), while 78 (27.9%) showed that clinically relevant discordance and 12 (4.3%) were indeterminate. Substituting CEM for MRI in the concordant group yielded a projected total cost reduction of €26,828, representing a 44.9% decrease and €141.20 saved per patient. Procedural modeling indicated a net scanner time saving of 3,800 min (63 h and 20 min). CEM reporting required 15 min less per case on average, totaling 2,850 min (47 h and 30 min) in cumulative reading time saved. Conclusion: CEM demonstrated substantial diagnostic concordance with MRI in a majority of cases, with significant benefits in cost reduction and workflow efficiency. Targeted CEM integration may support more sustainable, value-based breast imaging without compromising diagnostic quality.

Radiologists are crucial in the diagnostic workflow. They must maintain an independent perspective, being a “third party” to the patients and referral clinicians. This is important when documenting the absence of relevant abnormalities or providing information that contradicts the self-reported symptoms and/or the impression of the colleagues, as well as in the case of incidental findings that impact patient management. Appropriate communication is the outcome of this professional independence, becoming more and more important in the current era of application of generative artificial intelligence to the radiological world. In fact, while radiological reports could be improved by our smart use of large language models, patients are already using such tools to understand their meaning and practical implications.