a2z Radiology AI has received U.S. FDA clearance for its flagship product, a2z-Unified-Triage, a first-of-its-kind system that simultaneously flags and prioritizes seven urgent conditions on abdomen-pelvis CT scans. The announcement comes just days ahead of RSNA 2025, radiology’s largest annual conference, where the company plans to showcase its breakthrough capability.
Addressing the U.S.’s Highest-Volume CT Category
Abdomen-pelvis CT scans account for over 20 million exams annually in the U.S., making it the highest-volume CT category. Rising case volumes put pressure on radiology teams to quickly identify urgent findings. a2z-Unified-Triage works to flag suspected emergencies and push them to the top of the worklist within minutes, helping clinicians deliver faster care to critical patients.
“We set out to build a generalist system that could scale across conditions,” said Pranav Rajpurkar, PhD, co-founder of a2z Radiology AI and Associate Professor at Harvard Medical School. “We are starting with high-consequence acute conditions, cases where rapid triage can have the greatest immediate impact on patient care.”
Seven Conditions, One Integration
The system covers small bowel obstruction, acute cholecystitis, acute pancreatitis, acute diverticulitis, hydronephrosis, free air, and unruptured abdominal aortic aneurysm in a single integration. For five of these conditions, a2z is bringing AI triage to the U.S. market for the first time, a move that could transform workflow efficiency in high-volume radiology settings.
“For five of these seven conditions, we’re introducing AI triage to the U.S. market for the first time. And we’re not stopping at seven—there’s significant scaling potential ahead,” said Samir Rajpurkar, co-founder and CEO of a2z Radiology AI.
Implications for Radiology and Patient Care
By combining multi-condition triage into a single platform, a2z is positioning itself as a leader in abdomen-pelvis AI, potentially reducing diagnostic delays, easing radiologist workload, and improving outcomes for urgent cases. As adoption grows, this approach could set a new benchmark for AI-driven workflow optimization in radiology departments.
