Diagnostic and Interventional Imaging最新文献

Despite the exponential growth of artificial intelligence (AI) solutions designed to assist radiologists in clinical practice, their actual impact on radiology departments remains below initial expectations. Daily workflows have not been profoundly transformed. The actual clinical benefit of these tools is often limited to single, modality-specific "narrow AI" tasks, and their return on investment is unclear. The purpose of this article was to analyze: (i), the human and perceptual challenges that shape attitudes toward AI among radiologists, referring clinicians, and patients; (ii), the technical and clinical limitations of current AI models, including the mismatches between target tasks and real-world needs, and between published versus real-life performances; (iii), the lack of objective return on investment quantification and the paucity of medicoeconomic studies in a context of constrained hospital budgets; (iv), the limitations of the current "assistive models" of human-AI interaction in radiology; (v), the technical and organizational difficulties that information and technology departments face in integrating, maintaining, and securing a growing number of AI applications across specialties within complex hospital information systems; (vi), the ethical and patient safety concerns related to bias, transparency, data protection, and regulatory compliance with respect to data protection officers and the European General Data Protection Regulation; and (vii), the underexplored environmental and energy implications of large-scale AI deployment. Finally, potential solutions relating to AI governance, national data infrastructures, user education, and the design of randomized clinical trials and cost-effectiveness studies, are discussed to promote the responsible, evidence-based integration of AI into radiology practice.

Purpose: The purpose of this study was to assess the image quality of color K-edge imaging obtained with a spectral photon-counting CT (SPCCT) scanner using a spectral phantom with a mixture of iodine-based and gadolinium-based contrast agents.

Materials and methods: A clinical SPCCT scanner prototype was used to scan a spectral phantom. Three dedicated cavities were filled with three contrast agents including iodine alone, gadolinium alone and a mixture of both. Two concentrations of 0.5 and 2 mg/mL were evaluated using nine helical PCCT scans at 120 kVp and 150 mAs. Conventional, color iodine and color K-edge gadolinium images were obtained through a material decomposition algorithm using three basis materials (water, iodine, gadolinium). Attenuation (in Hounsfield unit [HU]), iodine and gadolinium concentrations and task-based transfer function (TTF) were measured on each cavity and image. The noise power spectrum (NPS) was calculated on the phantom's background.

Results: Color K-edge imaging differentiated iodine and gadolinium but underestimated their concentrations. Gadolinium concentrations were underestimated by 9.4 ± 2.2 (standard deviation [SD]) % and 9.2 ± 1.0 (SD) % for gadolinium alone, 14.9 ± 2.3 (SD) % and 11.4 ± 1.2 (SD) % for the mixture, at 0.5 and 2 mg/mL, respectively. Similar TTF values at 50 % were found for color iodine (0.43 ± 0.01 [SD] mm^-1) and color K-edge gadolinium (0.45 ± 0.03 (SD) mm^-1) images for respective cavities at 2 mg/mL but the lowest values were found for color K-edge gadolinium images (0.43 ± 0.01 [SD] mm^-1vs. 0.29 ± 0.01 [SD] mm^-1) at 0.5 mg/mL. The value of noise magnitude was 24.75 HU, 0.06 mg/mL and 0.03 mg/mL for conventional, color iodine and color K-edge gadolinium images, respectively.

Conclusion: Color K-edge imaging helps distinguish between contrast agents while being associated with lownoise magnitude, high-frequency spatial noise and high spatial resolution.