Neuroendocrine neoplasms (NENs) are a diverse group of tumors with varying clinical behaviors. Their incidence has risen due to increased awareness, improved diagnostics, and aging populations. The 2019 World Health Organization classification emphasizes integrating radiology and histopathology to characterize NENs and create personalized treatment plans. Imaging methods like CT, MRI, and PET/CT are crucial for detection, staging, treatment planning, and monitoring, but each of them poses different interpretative challenges and none are immune to pitfalls. Treatment options include surgery, targeted therapies, and chemotherapy, based on the tumor type, stage, and patient-specific factors. This review aims to provide insights into the latest developments and challenges in NEN imaging, diagnosis, and management.

Background: The Ejection Fraction (EF) represents a fundamental pillar for the phenotypic classification and clinical management of cardiovascular diseases. Although trans-thoracic echocardiography (TTE) acts as the first-line examination and cardiac magnetic resonance (CMR) is the reference gold standard, cardiac computed tomography (CCT) has undergone a technological evolution. The advent of wide-detector scanners and artificial intelligence (AI) models has enabled CCT to transition from a purely morphological tool to a modality capable of comprehensive, three-dimensional morpho-functional assessments. Methods: This narrative review evaluates the literature across Scopus, MEDLINE, and Web of Science regarding the calculation of biventricular function and EF using CCT. It provides an updated summary of current clinical applications, technological advancements, and comparative diagnostic reliability against TTE and CMR. Results: The CCT “one-stop-shop” concept allows for the simultaneous acquisition of anatomical data and systolic function metrics (EDV, ESV, SV, EF), optimizing clinical workflows at no additional cost. Being intrinsically three-dimensional, CCT bypasses the geometric assumptions and apical foreshortening artifacts typical of 2D-TTE, demonstrating high volumetric concordance with CMR. Nevertheless, structural limitations persist, primarily regarding ionizing radiation exposure, contrast media toxicity, dependence on heart rhythm stability, and lower temporal resolution compared to CMR. Conclusions: EF determination via CCT has achieved technical maturity and clinical validation. While it does not intend to replace TTE or CMR, it offers synergistic data when integrated with primary anatomical indications. Furthermore, AI integration has been shown to potentially automate this workflow, transforming CCT into an opportunistic screening tool for subclinical cardiac dysfunction.

Background: To compare the quality and clinical usefulness of large language model (LLM)-generated lumbar spine magnetic resonance imaging (MRI) reports with radiologist-written ones and assess whether medical professionals can distinguish between them. Materials and methods: This retrospective observational single-center study was approved by the local ethics committee. A total of 125 lumbar spine MRI reports (104 human-written, 21 LLM-generated using ChatGPT-4o) were anonymized, randomized, and blindly evaluated by five medical professionals (one board-certified radiologist, two radiology residents, one general practitioner, one orthopedic surgeon), all with basic familiarity with LLM. Each report was scored on a five-point Likert scale for clinical relevance, clarity, completeness, diagnostic accuracy, and intelligibility, whereas general practitioner and orthopedic surgeon evaluated intelligibility only. Evaluators also classified each report as AI-generated or human-written. Accuracy was defined as the proportion of correctly classified reports in distinguishing LLM-generated from radiologist-written texts. Mann-Whitney U or Student's t- tests were used. Results: Radiologists' reports consistently received higher median scores across all domains ( p < 0.001). No differences were found in the description of the imaging technique ( p > 0.175). No clinically false statements were identified in the LLM-generated reports. Identification accuracy varied widely among evaluators: Board-certified radiologist achieved 88.0% accuracy (sensitivity 66.7%, specificity 92.3%), Resident 1 65.6% (14.3%, 76.0%), Resident 2 94.4% (66.7%, 100%), orthopedic surgeon 78.4% (90.5%, 76.0%) and general practitioner 65.6% (81.0%, 62.5%). Conclusion: Radiologist-written lumbar spine MRI reports outperform LLM-generated reports in quality and structure. However, some AI-generated reports were indistinguishable from human ones, particularly for non-specialized readers. LLMs may support radiologists in structured reporting and improve workflow efficiency, while maintaining diagnostic reliability. Relevance statement: Large language models can draft lumbar spine MRI reports, but currently lack the quality and consistency of radiologist reports. With radiologist supervision, large language models may improve reporting efficiency while preserving diagnostic reliability and supporting clinical decision-making. Key Points: LLM-generated reports are clinically coherent and stylistically comparable to those written by expert radiologists. Radiologist-written reports scored significantly higher for clinical relevance, findings, and structure. LLM-generated reports were sometimes misclassified as human-written by clinicians. Graphical