Substantial endeavors have been recently dedicated to developing artificial intelligence (AI) solutions, especially deep learning-based, tailored to enhance radiological procedures, in particular algorithms designed to minimize radiation exposure and enhance image clarity. Thus, not only better diagnostic accuracy but also reduced potential harm to patients was pursued, thereby exemplifying the intersection of technological innovation and the highest standards of patient care. We provide herein an overview of recent AI developments in computed tomography and magnetic resonance imaging. Major AI results in CT regard: optimization of patient positioning, scan range selection (avoiding “overscanning”), and choice of technical parameters; reduction of the amount of injected contrast agent and injection flow rate (also avoiding extravasation); faster and better image reconstruction reducing noise level and artifacts. Major AI results in MRI regard: reconstruction of undersampled images; artifact removal, including those derived from unintentional patient’s (or fetal) movement or from heart motion; up to 80–90% reduction of GBCA dose. Challenges include limited generalizability, lack of external validation, insufficient explainability of models, and opacity of decision-making. Developing explainable AI algorithms that provide transparent and interpretable outputs is essential to enable seamless AI integration into CT and MRI practice. Relevance statement: This review highlights how AI-driven advancements in CT and MRI improve image quality and enhance patient safety by leveraging AI solutions for dose reduction, contrast optimization, noise reduction, and efficient image reconstruction, paving the way for safer, faster, and more accurate diagnostic imaging practices. Key Points: Advancements in AI are revolutionizing the way radiological images are acquired, reconstructed, and interpreted. AI algorithms can assist in optimizing radiation doses, reducing scan times, and enhancing image quality. AI techniques are paving the way for a future of more efficient, accurate, and safe medical imaging examinations. Graphical

Pancreatic ductal adenocarcinoma (PDAC) is among the most lethal cancers, characterized by late diagnosis, rapid progression, and limited therapeutic options. Despite advancements, only 20% of patients are eligible for surgical resection at diagnosis, the sole curative treatment. Multidisciplinary evaluation is critical to optimize care, stratifying patients based on resectability into resectable, borderline resectable, locally advanced, and metastatic stages. Preoperative imaging, such as computed tomography (CT) and endoscopic ultrasound (EUS), remains central for staging, for vascular assessment, and tissue acquisition. Endoscopic and systemic approaches are pivotal for addressing complications like biliary obstruction and improving outcomes. Endoscopic retrograde cholangiopancreatography (ERCP) has been considered for years the gold standard for biliary drainage, although EUS-guided drainage is increasingly utilized due to its efficacy in both resectable and unresectable disease. Systemic therapies play a key role in neoadjuvant, adjuvant, and palliative settings, with ongoing trials exploring their impact on survival and resectability chance. This review highlights the evolving multidisciplinary approaches tailored to the disease stage, focusing on biliary drainage techniques, systemic therapies, and their integration into comprehensive care pathways for PDAC. The continuous refinement of these strategies offers incremental survival benefits and underscores the importance of personalized, multidisciplinary management.

The Prostate Imaging Quality scoring system version 2 (PI-QUAL v2) is a new scoring system used to assess the diagnostic quality of prostate magnetic resonance imaging (pMRI). This study investigated the impact of a focused training module on the ability of MRI technologists (MRI-Tech) and MRI-Tech students to evaluate pMRI image quality. Thirty-nine subjects including MRI-Tech students and experienced MRI-Tech with different levels of experience in pMRI participated in the study. The image quality of twenty pMRIs was evaluated before and after a dedicated lecture on pMRI image quality assessment using PI-QUAL v2 score. Receiver Operating Characteristic (ROC) curves were calculated for each scorer before and after the lecture, stratified by experience, and compared to the PI-QUAL v2 score assigned by a radiologist specialized in pMRI, using DeLong test. A significant improvement in AUC of pMRI image quality assessment was observed: from the baseline (0.31 ± 0.05) to the post-intervention (0.97 ± 0.01), with an improvement of 0.66 (p < 0.001). The ROC curves stratified by experience, demonstrated an improvement of 0.44 [0.50 ± 0.07-0.94 ± 0.01] for II-year MRI-Tech students (p < 0.001), of 0.48 [0.46 ± 0.09-0.94 ± 0.01] for III-year MRI-Tech students (p < 0.032) and 0.60 [0.33 ± 0.10-0.93 ± 0.01] for board-certified MRI-Techs (p < 0.001). The PI-QUAL v2 training module improved the ability of both MRI-Tech students and board-certified MRI-Techs to assess the quality of pMRI images.

Objective. Lung cancer remains the leading cause of cancer-related mortality worldwide, with Non-Small Cell Lung Cancer (NSCLC) accounting for approximately 85% of all cases. Programmed cell Death Ligand-1 (PD-L1) is a well-established biomarker that guides immunotherapy in advanced-stage NSCLC, currently evaluated via invasive biopsy procedures. This study aims to develop and validate a non-invasive pipeline for stratifying PD-L1 expression using quantitative analysis of IVIM parameter maps—diffusion (D), pseudo-diffusion (D*), perfusion fraction (pf)—and T1-VIBE MRI acquisitions. Approach. MRI data from 43 NSCLC patients were analysed and labelled as PD-L1 positive (≥1%) or negative (<1%) based on immunohistochemistry exam. After pre-processing, 1,171 radiomic features and 512 deep learning features were obtained. Three feature sets (radiomic, deep learning, and fusion) were tested with Logistic Regression, Random Forest, and XGBoost. Four discriminative features were selected using the Mann–Whitney U-test, and model performance was primarily assessed using the area under the receiver operating characteristic curve (AUC). Robustness was ensured through repeated stratified 5-fold cross-validation, bootstrap-derived confidence intervals, and permutation test. Main Results. Logistic Regression generally demonstrated the highest classification performance, with AUC values ranging from 0.78 to 0.92 across all feature sets. Fusion models outperformed or matched the performance of the best standalone radiomics or deep learning model. Among multisequence MRI, the IVIM-D fusion features yielded the best performance with an AUC of 0.92, followed by IVIM-D* radiomic features that showed a similar AUC of 0.91. For IVIM-pf and T1-VIBE derived features, the fusion model yielded the best AUC values of 0.87 and 0.90, respectively. Significance. The obtained results highlight the potential of a combined radiomic-deep learning approach to effectively detect PD-L1 expression from MRI acquisitions, paving the way for a non-invasive PD-L1 evaluation procedure.

Background Three-dimensional (3D) Non-Small Cell Lung Cancer (NSCLC) models provide controlled experimental systems for investigating tumor-cell phenotypes and treatment-induced changes. However, quantitative characterization of 3D architecture remains technically challenging. We established a micro-computed tomography (micro-CT) workflow combined with radiomic analysis to characterize 3D NSCLC cultures and assess structural remodeling following exposure to IFN-γ, cytokine released by immune checkpoint inhibitor (ICI)-mediated T-cell reactivation. Methods 3D cultures from the A549 cell line and ADK-18, a model derived from a NSCLC patient who rapidly progressed on immune-checkpoint inhibitors, were left untreated or IFN-γ-exposed at 0.1 or 100 ng/mL. Samples were fixed, stained with 1% Lugol’s iodine, embedded in 2% agarose, and imaged using micro-CT. Semi-automated segmentations were analyzed using PyRadiomics v3.0.1 to extract IBSI-compliant radiomic features. Results In A549 cultures, 50 and 68 radiomic features were significantly changed between untreated samples and those exposed to 0.1 and 100 ng/mL IFN-γ, respectively, while 61 features differed significantly between the two IFN-γ concentrations. In ADK-18 cultures, the corresponding comparisons identified 7, 14, and 11 significantly different features, respectively. These changes were associated with structural modifications in the organoids, with A549 cultures exhibiting a more clearly concentration-dependent radiomic remodeling, whereas ADK-18 cultures showed fewer significant changes, indicating a distinct radiomic response pattern. Conclusions Micro-CT radiomics detected IFN-γ-shaped structural changes beyond conventional size-based measurements and identified model-specific response patterns in 3D NSCLC cultures. These proof-of-concept findings highlight its potential as a quantitative imaging endpoint, while underscoring the need for further validation of feature robustness and biological relevance.