Hepatic Hemangioma

The purpose of this multicenter pragmatic randomized controlled trial is to determine whether AI-assisted interpretation of multiphasic liver contrast-enhanced computed tomography (CE-CT) is non-inferior to standard radiology reporting with respect to missed clinically significant malignant focal liver lesions, \*\*with the non-inferiority margin prespecified in the statistical analysis plan before enrollment\*\*, and whether it improves lesion detection, diagnostic characterization, downstream clinical management, and reporting efficiency. On AI-assisted center-days, AI results will be revealed only after the first-line radiologist has saved an unaided initial assessment and may be used to revise the final report. On control center-days, examinations will be interpreted using the standard radiology workflow without access to AI tools.

The macroscopic vascular supply of liver tumors varies considerably according to histological subtype, lesion size, and disease stage. Current clinical imaging modalities primarily characterize liver tumors based on their macroscopic vascular perfusion patterns. Conventional color Doppler ultrasonography enables qualitative assessment of tumor vascularity, facilitates the differentiation of benign from malignant hepatic lesions, delineates the anatomical relationship between tumors and major intrahepatic vessels, and detects vascular invasion. Nevertheless, these macroscopic vascular characteristics arise from complex microvascular architectures, including vascular distribution patterns, microvessel density, vessel morphology and tortuosity, blood flow velocity, and flow direction. Despite the critical role of tumor microcirculation in tumor progression and therapeutic response, the heterogeneity of microvascular hemodynamics among different liver tumors remains inadequately characterized. The emergence of Super Resolution Ultrasound Imaging (SRUS) has markedly advanced ultrasound imaging by overcoming the acoustic diffraction limit, enabling visualization of microvessels with diameters as small as approximately 20 μm. Unlike conventional ultrasound techniques, SRUS preserves the inherent advantages of ultrasound, including deep tissue penetration and a large field of view, while achieving an approximately tenfold improvement in spatial resolution. This unique combination effectively bridges the long-standing gap between imaging depth and spatial resolution in vascular imaging. Furthermore, by localizing and tracking individual circulating microbubbles,SRUS enables quantitative assessment of microvascular blood flow velocity over a broad dynamic range without Doppler angle dependence. Consequently, super-resolution ultrasound imaging offers an unprecedented opportunity to characterize and compare the microvascular hemodynamic features of benign and malignant liver lesions, thereby improving the accuracy of preoperative differential diagnosis, tumor staging, therapeutic response assessment, and prognostic evaluation.