Artificial intelligence in ultrasound: divergent pathways, shared challenges

Artificial intelligence (AI) in ultrasound is often reviewed as a unified field, though in practice it spans 3 distinct deployment environments: clinical radiology (traditional imaging) ultrasound, point-of-care users, and ultrasound education. The 3 environments share the same underlying AI methods but differ in image quality, operator skill, time allotted to scan, regulatory exposure, and acceptable failure modes. In clinical radiology ultrasound, FDA-cleared decision support is routine for breast and thyroid lesion characterization, obstetric biometry, and cardiac quantification, and emerging in liver, vascular, and interventional imaging. In point-of-care ultrasound, AI enables bedside clinicians to acquire diagnostic images under real-time guidance and to document examinations that would otherwise go unrecorded. In education, AI reshapes competency assessment and scales instruction. This article offers the practicing radiologist and imaging specialist a framework for matching AI to deployment context, names the mature applications in each pathway, and addresses cross-cutting challenges (data, validation, regulation, bias, liability, reimbursement, environmental cost) that every deployment must navigate. The recurring message: treating "ultrasound AI" as a monolith is a repeated error, and honest attention to deployment context matters most.