Nicolo’ Rossini

Traditional evaluations of artificial intelligence (AI) systems in the dynamic, operator-dependent, and time-sensitive field of interventional radiology (IR), focusing solely on algorithmic performance, often fail to capture their real-world clinical impact. This narrative review aims to provide an overview of the current state of the art of AI integration in IR through human–AI interaction (HAI), while offering a critical perspective on their clinical integration, limitations, and future directions. A comprehensive survey of recent literature was performed, focusing on AI applications across procedural phases. The review emphasizes systems providing decision support, real-time procedural verification, and immersive interfaces (augmented and virtual reality), while critically evaluating determinants of effective clinical adoption. AI has shown preliminary potential to support operator performance in selected interventional radiology tasks, although most applications remain experimental, retrospective, or evaluated in phantom or preclinical settings. Potential benefits include structuring uncertainty in patient selection and procedural planning, supporting assessment of device positioning and treatment outcomes, and integrating AI-derived outputs into the operator’s spatial field through immersive technologies. The clinical utility of these systems appears to be influenced by human–AI interaction, with interpretability, workflow integration, and trust calibration representing key determinants of effective use beyond algorithmic accuracy alone. The potential value of AI in interventional radiology appears to derive from its integration into human decision-making rather than from standalone predictive performance alone. A human-centered, interaction-based model supports understanding current applications, address challenges, and guide the development of adaptive, real-time systems for dynamic procedural environments.

Type 2 endoleaks (EL2s) are potentially life-threatening complications, defined as persistent arterial perfusion of the excluded aneurysmal sac after endovascular aneurysm repair (EVAR). Most EL2s are managed endovascularly, through embolization of the aneurysmal sac and its arterial feeders. During embolization, attention should be given to anatomical variants such as “corona mortis”, an arterial anastomosis connecting external iliac (via inferior epigastric) and internal iliac (via obturator) arteries. We present the case of an 88-year-old male previously treated with EVAR for a left common iliac artery aneurysm (CIAA), complicated by EL2 originating from the ipsilateral ilio-lumbar branch of the internal iliac artery. Successful embolization of the endoleak was achieved through catheterization of the inferior epigastric artery, taking advantage of the “corona mortis” variant. This route allowed access to the sac and embolization with ethylene-vinyl-alcohol-copolymer. This approach represents a safe alternative to direct sac puncture or superior gluteal artery access in patients exhibiting this anatomical variant.

Background: Endovascular approach has emerged as the first-choice treatment of visceral artery aneurysms (VAAs). However, most published series include heterogeneous populations combining true aneurysms and pseudoaneurysms. Our single-center retrospective study aimed to evaluate a large and homogenous series of true VAAs treated endovascularly. Demographic, clinical and procedural details of patients with VAAs treated at our Interventional Radiology unit from January 2014 to January 2025 were collected in a dedicated database. Intraprocedural and perioperative outcomes included technical success, complications, mortality and need for reintervention. At long-term follow-up, overall survival, aneurysm-related complications, freedom from reintervention, and aneurysmal sac reperfusion were evaluated. Results: Ninety-four consecutive patients (41 men; median age: 67.3 years; range 29–98 years) with 97 VAAs were included in the study. VAAs had a median diameter of 2.93 cm (range 6–9.2 cm). Treatment strategies included sac packing in 45 VAAs, sandwich technique in 35, covered stent placement in 13, afferent artery occlusion in 5 and stent-assisted coiling in 4 cases. Technical success rate was 100% with no perioperative deaths. Perioperative major complication and reintervention rates were 5.2% and 2.1%, respectively. At a mean follow-up of 44.7 ± 28.9 months, overall survival, freedom from aneurysm-related complications, and freedom from reintervention were 89.4%, 92.8%, and 93.8%, respectively. Aneurysm sac reperfusion was observed in 8(8.2%) cases. No aneurysm-related deaths occurred. Conclusion: Endovascular approach is a safe and effective first-line option in patients with true VAAs, with notable results in terms of complication and freedom from reintervention rates and an excellent long-term overall survival. Graphical

Background: Visceral artery aneurysms (VAAs) are rare but potentially life-threatening vascular lesions often clinically silent until rupture. The widespread use of advanced imaging has increased incidental detection, highlighting the need for accurate, noninvasive diagnostic strategies. Dual-Energy Computed Tomography Angiography (DECTA) offers potential advantages over conventional CT across diagnostic and post-treatment settings; however, its role in VAAs remains incompletely defined. This narrative review summarizes current evidence on DECTA applications in VAAs, focusing on diagnosis, emergency evaluation, and post-treatment follow-up. Methods: A non-systematic literature search of PubMed and Embase focusing on English-language articles up to June 2025 was performed. The search included peer-reviewed original research articles, systematic reviews, and meta-analyses addressing dual-energy CT and spectral CT in vascular and aneurysmal imaging. Case reports without technical data and non-English articles were excluded. Results: In the diagnostic phase, DECTA enhances tissue differentiation through virtual monoenergetic images, iodine maps, and material decomposition reconstructions. In the post-treatment setting, DECTA supports assessment after endovascular procedures, including coil embolization or stent graft placement. In VAAs, these techniques may improve aneurysm delineation, reduce metal artifacts after endovascular treatment, enable accurate detection of endoleaks or residual perfusion, and support volumetric follow-up. Virtual Non-Contrast images may reduce radiation exposure without compromising diagnostic confidence. Conclusions: DECTA represents a versatile imaging modality with potential benefits across the diagnostic, emergency, and post-treatment phases of VAA management. Although many applications are extrapolated from aortic and peripheral vascular disease, emerging evidence supports its growing clinical relevance. Further dedicated studies are needed to define its role in VAA-specific decision-making and follow-up.

Purpose: Percutaneous endovascular embolization (PVE) of male varicocele is a widely adopted procedure performed in healthy young patients with long life expectancy. Dose-optimization systems are therefore essential to minimize procedural radiation risks. We aimed to investigate the effect of a recently implemented dose-reduction technology on dosimetric parameters and its potential implication in the definition of diagnostic reference levels (DRLs). Materials and Methods: A consecutive series of 113 patients (23.3 ± 9.1 yrs) submitted to PVE between January 2020 and December 2024 were retrospectively reviewed. Two groups based on the angiographic system used, 50 patients treated using the Philips Allura Xper FD20 and 63 patients using the newer Philips Azurion Clarity IQ technology, were compared in terms of demographic, procedural, and dosimetric data. Results: Despite similar fluoroscopy and procedure times, the recently implemented angiographic technology demonstrated a significant reduction in dose area product (DAP) and reference air kerma (Ka.ref) values (4394.5 vs 20,709 mGy·cm ² and 20.35 vs 83.6 mGy; p < 0.001, respectively) with a percentage reduction of approximately 71.15% and 64.41%, respectively. Subpopulation analyses showed significant dose reductions in younger patient population (< 18 years) and in high-grade varicoceles (grades III/IV), with similar fluoroscopy times. Conclusion: The use of advanced dose-optimization technologies, together with standardized protocols and appropriate operator training, leads to a significant reduction in radiation exposure during PVE, particularly in younger patients. These single-center, retrospective results provide preliminary data that may support the future introduction of procedure-specific DRLs for this routinely and widely performed interventional radiology procedure.

Purpose: Microwave ablation (MWA) and conventional transarterial chemoembolization (cTACE) are locoregional treatments commonly performed in very early, early and intermediate stages of hepatocellular carcinoma (HCC). Despite combined locoregional approaches have shown encouraging results in obtaining complete tumor necrosis, their application in a single session is poorly described. Our aim was to evaluate the safety and efficacy of single-session MWA and cTACE treatment in 5-cm HCCs and its influence on liver function. Materials and methods: All 5-cm HCCs treated by MWA and cTACE performed in a single-session in our Interventional Radiology unit between January 2020 and December 2022 were retrospectively recorded and analyzed. Patients with poor or missing pre- and post-treatment imaging were excluded. Technical success, clinical success, and complications rate were examined as primary endpoints. Pre- and post-treatment liver function laboratory parameters were also evaluated. Results: A total of 15 lesions (mean lesion diameter, 5.0 ± 1.4 cm) in 15 patients (11 men; mean age, 67.1 ± 8.9 years) were retrospectively evaluated. Technical and clinical success were 100% and 73%, respectively. Four (27%) cases of partial response and no cases of progressive or stable disease were recorded. AST and ALT values have found to be significantly higher in post-treatment laboratory tests. No other significant differences between pre- and post-treatment laboratory values were registered. AST and ALT pre- and post-treatment higher differences (ΔAST and ΔALT) were significantly associated with a lower clinical success rate. Conclusion: MWA and cTACE single-session approach is safe and effective for 5-cm HCCs, without significant liver function impairment. A post-treatment increase in AST and ALT values may be a predictor for clinical failure.

(1) Background: Type 2 diabetes is a major cause of incidences and the progression of peripheral artery disease (PAD). Bone marrow edema (BME) is an important finding suggestive of underlying bone inflammation in non-traumatic diabetic patients with PAD. Our aim was to evaluate the presence, severity, and clinical implications of BME detected by virtual non-calcium application (VNCa) of dual-energy CT angiography (DE-CTA). (2) Methods: A consecutive series of 76 diabetic patients (55 men; mean age 71.6 ± 11.2 yrs) submitted to lower limb DE-CTA for PAD evaluation and revascularization planning, which were retrospectively analyzed. VNCa images were independently and blindly revised for the presence, location, and severity of BME by two radiologists with 10 years of experience. BME and non-BME groups were evaluated in terms of PAD clinical severity and 6-month secondary major amputation rate. (3) Results: BME was present in 17 (22%) cases, while 59 (78%) patients were non-BME. The BME group showed a significantly higher incidence of major amputation (p < 0.001) and a significantly higher number of patients with advanced clinical stages of PAD compared to the non-BME group (p = 0.024). (4) Conclusions: Lower limb DE-CTA with VNCa application is a useful tool in the detection of BME in diabetic patients with PAD, simultaneously enabling the evaluation of the severity and location of the arterial disease for revascularization planning. BME presence could be a marker of clinically severe PAD and a possible risk factor for revascularization failure.

Lung cancer has one of the worst morbidity and fatality rates of any malignant tumour. Most lung cancers are discovered in the middle and late stages of the disease, when treatment choices are limited, and patients’ survival rate is low. The aim of lung cancer screening is the identification of lung malignancies in the early stage of the disease, when more options for effective treatments are available, to improve the patients’ outcomes. The desire to improve the efficacy and efficiency of clinical care continues to drive multiple innovations into practice for better patient management, and in this context, artificial intelligence (AI) plays a key role. AI may have a role in each process of the lung cancer screening workflow. First, in the acquisition of low-dose computed tomography for screening programs, AI-based reconstruction allows a further dose reduction, while still maintaining an optimal image quality. AI can help the personalization of screening programs through risk stratification based on the collection and analysis of a huge amount of imaging and clinical data. A computer-aided detection (CAD) system provides automatic detection of potential lung nodules with high sensitivity, working as a concurrent or second reader and reducing the time needed for image interpretation. Once a nodule has been detected, it should be characterized as benign or malignant. Two AI-based approaches are available to perform this task: the first one is represented by automatic segmentation with a consequent assessment of the lesion size, volume, and densitometric features; the second consists of segmentation first, followed by radiomic features extraction to characterize the whole abnormalities providing the so-called “virtual biopsy”. This narrative review aims to provide an overview of all possible AI applications in lung cancer screening.

Purpose Transarterial embolization of renal artery branches (RTE) is a minimally invasive procedure commonly performed in life-threatening renal bleeding of different etiologies. Despite the widespread use of RTE, no consensus guidelines are currently available. Our aim was to investigate clinical and technical efficacy and to identify potential predictors for clinical failure of this procedure. Methods All the RTE procedures performed in our Interventional Radiology unit in last 10 years were retrospectively collected and analyzed. All selected patients underwent both pre-procedural computed tomography angiography (CTA) and post-procedural CTA within 30 days. Clinical success was considered as primary endpoint. Demographic, laboratory, and diagnostic findings predictive of clinical failure of RTE were identified. Results Over a total of 51 patients enrolled, 27 (53%) were females and 33 (64.7%) had a renal bleeding of iatrogenic origin. Technical and clinical success was 100% and 80.4%, respectively. Hematoma volumes > 258.5 cm³ measured at CTA, higher pre- and post-procedural serum creatinine (Scr) levels, an increase in Scr value > 0.135 mg/dl after the procedure, a worse post-procedural estimated glomerular filtration rate (eGFR), a post-procedural reduction of eGFR < 3.350 ml/min, and a post-procedural reduction of platelet count (PLT) > 46.50 × 10³/mmc showed a significantly higher rate of clinical failure. Conclusion RTE is a safe and effective procedure in the management of acute renal bleeding of various origins. Hematoma volume, Scr, PLT, and eGFR values were found to be predictive factors of poor clinical outcome and should be closely monitored.

(1) Background: The value of dual-energy CT angiography (DE-CTA) in the detection of peripheral arterial disease (PAD) has been widely recognized. We aim to evaluate the diagnostic accuracy of virtual non-contrast (VNC) imaging of DE-CTA compared to true non-contrast phase (TNC). (2) Methods: Our Internal Review Board (IRB) approved prospective study enrolled 40 patients (28 men, 12 women; median age 69 y, range 41–93 y) who underwent lower extremity DE-CTA for symptomatic PAD. Mean attenuation values of TNC and VNC were obtained by placing circular regions of interest (ROI) at five levels from the aortic to the popliteal arterial lumen, reported in Hounsfield units (HU), and compared using a two-sample t-test. The subjective quality of VNC images was assessed by two independent radiologists with 10 and 4 years of CTA-imaging experience according to a 4-point scale and verified by the intra-class correlation coefficient (ICC). Dose Length Product (DLP) values of each DE-CTA examination were also considered. (3) Results: Except for the external iliac artery, VNC attenuation values were significantly lower than the corresponding TNC values at all levels, with a mean difference ranging from 14.1 and 8.7 HU. At qualitative analysis, VNC images were considered excellent to diagnose in 40%, good in 50%, and sufficient in 10% of cases. No cases of non-diagnostic VNC imaging were reported. Avoiding the TNC phase, a mean reduction in DLP of 54% for each DE-CTA was estimated. (4) Conclusions: TNC and VNC images showed comparable reliability and diagnostic accuracy in the detection of PAD. VNC may be considered a promising substitute for TNC from the perspectives of dose reduction and workflow optimization.