The purpose of this study was to evaluate the capabilities of photon-counting (PC) CT combined with artificial intelligence-derived coronary computed tomography angiography (PC-CCTA) stenosis quantification and fractional flow reserve prediction (FFRai) for the assessment of coronary artery disease (CAD) in transcatheter aortic valve replacement (TAVR) work-up. Consecutive patients with severe symptomatic aortic valve stenosis referred for pre-TAVR work-up between October 2021 and June 2023 were included in this retrospective tertiary single-center study. All patients underwent both PC-CCTA and ICA within three months for reference standard diagnosis. PC-CCTA stenosis quantification (at 50% level) and FFRai (at 0.8 level) were predicted using two deep learning models (CorEx, Spimed-AI). Diagnostic performance for global CAD evaluation (at least one significant stenosis ≥ 50% or FFRai ≤ 0.8) was assessed. A total of 260 patients (138 men, 122 women) with a mean age of 78.7 ± 8.1 (standard deviation) years (age range: 51-93 years) were evaluated. Significant CAD on ICA was present in 126/260 patients (48.5%). Per-patient sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy were 96.0% (95% confidence interval [CI]: 91.0-98.7), 68.7% (95% CI: 60.1-76.4), 74.3 % (95% CI: 69.1-78.8), 94.8% (95% CI: 88.5-97.8), and 81.9% (95% CI: 76.7-86.4) for PC-CCTA, and 96.8% (95% CI: 92.1-99.1), 87.3% (95% CI: 80.5-92.4), 87.8% (95% CI: 82.2-91.8), 96.7% (95% CI: 91.7-98.7), and 91.9% (95% CI: 87.9-94.9) for FFRai. Area under the curve of FFRai was 0.92 (95% CI: 0.88-0.95) compared to 0.82 for PC-CCTA (95% CI: 0.77-0.87) (P < 0.001). FFRai-guidance could have prevented the need for ICA in 121 out of 260 patients (46.5%) vs. 97 out of 260 (37.3%) using PC-CCTA alone (P < 0.001). Deep learning-based photon-counting FFRai evaluation improves the accuracy of PC-CCTA ≥ 50% stenosis detection, reduces the need for ICA, and may be incorporated into the clinical TAVR work-up for the assessment of CAD.

The purpose of this study was to evaluate the diagnostic performance of automated deep learning in the detection of coronary artery disease (CAD) on photon-counting coronary CT angiography (PC-CCTA). Consecutive patients with suspected CAD who underwent PC-CCTA between January 2022 and December 2023 were included in this retrospective, single-center study. Non-ultra-high resolution (UHR) PC-CCTA images were analyzed by artificial intelligence using two deep learning models (CorEx, Spimed-AI), and compared to human expert reader assessment using UHR PC-CCTA images. Diagnostic performance for global CAD assessment (at least one significant stenosis ≥ 50 %) was estimated at patient and vessel levels. A total of 140 patients (96 men, 44 women) with a median age of 60 years (first quartile, 51; third quartile, 68) were evaluated. Significant CAD on UHR PC-CCTA was present in 36/140 patients (25.7 %). The sensitivity, specificity, accuracy, positive predictive value), and negative predictive value of deep learning-based CAD were 97.2 %, 81.7 %, 85.7 %, 64.8 %, and 98.9 %, respectively, at the patient level and 96.6 %, 86.7 %, 88.1 %, 53.8 %, and 99.4 %, respectively, at the vessel level. The area under the receiver operating characteristic curve was 0.90 (95 % CI: 0.83-0.94) at the patient level and 0.92 (95 % CI: 0.89-0.94) at the vessel level. Automated deep learning shows remarkable performance for the diagnosis of significant CAD on non-UHR PC-CCTA images. AI pre-reading may be of supportive value to the human reader in daily clinical practice to target and validate coronary artery stenosis using UHR PC-CCTA.

To provide clinically relevant criteria for differentiation between the athlete’s heart and similar appearing hypertrophic (HCM), dilated (DCM), and arrhythmogenic right-ventricular cardiomyopathy (ARVC) in MRI. 40 top-level athletes were prospectively examined with cardiac MR (CMR) in two university centres and compared to retrospectively recruited patients diagnosed with HCM (n = 14), ARVC (n = 18), and DCM (n = 48). Analysed MR imaging parameters in the whole study cohort included morphology, functional parameters and late gadolinium enhancement (LGE). Mean left-ventricular enddiastolic volume index (LVEDVI) was high in athletes (105 ml/m²) but significantly lower compared to DCM (132 ml/m²; p = 0.001). Mean LV ejection fraction (EF) was 61% in athletes, below normal in 7 (18%) athletes vs. EF 29% in DCM, below normal in 46 (96%) patients (p < 0.0001). Mean RV-EF was 54% in athletes vs. 60% in HCM, 46% in ARVC, and 41% in DCM (p < 0.0001). Mean interventricular myocardial thickness was 10 mm in athletes vs. 12 mm in HCM (p = 0.0005), 9 mm in ARVC, and 9 mm in DCM. LGE was present in 1 (5%) athlete, 8 (57%) HCM, 10 (56%) ARVC, and 21 (44%) DCM patients (p < 0.0001). Healthy athletes’ hearts are characterized by both hypertrophy and dilation, low EF of both ventricles at rest, and increased interventricular septal thickness with a low prevalence of LGE. Differentiation of athlete’s heart from other non-ischemic cardiomyopathies in MRI can be challenging due to a significant overlap of characteristics also seen in HCM, ARVC, and DCM.

Purpose: To investigate technical success, technique efficacy, safety and outcome of MR-guided microwave ablation (MWA) in hepatic malignancies. Material and methods: In this prospective IRB-approved study, patients scheduled for percutaneous treatment of hepatic malignancies underwent MR-guided MWA in a closed-bore 1.5 T MR system. Technical success was assessed on post-procedural MR control imaging. Technique efficacy was evaluated 4 weeks after the procedure on multi-parametric MRI. Assessment of safety followed the Society of Interventional Radiology grading system. Kaplan–Meier survival estimates were calculated to evaluate overall survival (OS), time to local tumor progression (TLTP), and time to non-target progression (TNTP). Results: Between 2015 and 2019, 47 patients (60.5 ± 12.2 years; 39 male) underwent 50 procedures for 58 hepatic tumors (21 hepatocellular carcinomas; 37 metastases). Mean target tumor size was 16 ± 7mm (range: 6–39 mm). Technical success and technique efficacy were 100% and 98%, respectively. Lesions were treated using 2.6 applicator positions (range: 1–6). Mean energy, ablation duration per tumor, and procedure duration were 43.2 ± 23.5 kJ, 26.7 ± 13.1 min and 211.2 ± 68.7 min, respectively. 10 minor (20%) and 3 major (6%) complications were observed. Median post-interventional hospital admission was 1 day (range: 1–19 days). Median OS was 41.6 (IQR: 26.4–) months. Local recurrence occurred after 4 procedures (8%) with TLTP ranging between 3.1 and 41.9 months. Non-target recurrence was observed in 64% of patients after a median TNTP of 13.8 (IQR 2.3–) months. Conclusion: MR-guided MWA allows for safe and successful treatment of hepatic malignancies with a high technique efficacy however with relatively long procedure durations.

Purpose: Evaluation of technique effectiveness, patient safety and ablation parameters of MR-guided microwave ablation in hepatic malignancies using an MR-conditional high-power microwave ablation system. Materials and Methods: Institutional review board approval and informed patient consent were obtained. Patients who underwent MR-guided microwave ablation of hepatic malignancies in a 1.5T wide-bore scanner using a perfusion-cooled high-power microwave ablation system with a maximum generator power of 150 W were included. Ablation parameters comprising procedure durations, net ablation duration, applicator positions and ablation zone dimensions were recorded. Adverse events were classified according to the CIRSE classification system. Technique effectiveness was assessed after 1 month. Follow-up was conducted with contrast-enhanced MRI and ranged from 1 to 20 months (mean: 6.1 ± 5.4 months). Results: Twenty-one consecutive patients (age: 63.4 ± 10.5 years; 5 female) underwent 22 procedures for 28 tumours (9 hepatocellular carcinomas, 19 metastases) with a mean tumour diameter of 14.6 ± 5.4 mm (range: 6–24 mm). Technique effectiveness was achieved in all lesions. Tumours were treated using 1.7 ± 0.7 applicator positions (range: 1–3). Mean energy and ablation duration per tumour were 75.3 ± 35.4 kJ and 13.3 ± 6.2 min, respectively. Coagulation zone short- and long-axis diameters were 29.1 ± 6.4 mm and 39.9 ± 7.4 mm, respectively. Average procedure duration was 146.4 ± 26.2 min (range: 98–187 min). One minor complication was reported. Five patients developed new tumour manifestations in the untreated liver. Local tumour progression was not observed during initial follow-up. Conclusion: MR-guided high-power microwave ablation provides safe and effective treatment of hepatic malignancies with short ablation times and within acceptable procedure durations.

Purpose: This study evaluates the diagnostic performance of artificial intelligence (AI)-based coronary computed tomography angiography (CCTA) for detecting coronary artery disease (CAD) and assessing fractional flow reserve (FFR) in asymptomatic male marathon runners. Material and methods: We prospectively recruited 100 asymptomatic male marathon runners over the age of 45 for CAD screening. CCTA was analyzed using AI models (CorEx and Spimed-AI) on a local server. The models focused on detecting significant CAD (≥ 50% diameter stenosis, CAD-RADS 3, 4, or 5) and distinguishing hemodynamically significant stenosis (FFR ≤ 0.8) from non-significant stenosis (FFR > 0.8). Statistical analysis included sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Results: The AI model demonstrated high sensitivity, with 91.2% for any CAD and 100% for significant CAD, and high NPV, with 92.7% for any CAD and 100% for significant CAD. The diagnostic accuracy was 73.4% for any CAD and 90.4% for significant CAD. However, the PPV was lower, particularly for significant CAD (25.0%), indicating a higher incidence of false positives. Conclusion: AI-enhanced CCTA is a valuable non-invasive tool for detecting CAD in asymptomatic, low-risk populations. The AI model exhibited high sensitivity and NPV, particularly for identifying significant stenosis, reinforcing its potential role in screening. However, limitations such as a lower PPV and overestimation of disease indicate that further refinement of AI algorithms is needed to improve specificity. Despite these challenges, AI-based CCTA offers significant promise when integrated with clinical expertise, enhancing diagnostic accuracy and guiding patient management in low-risk groups.