Can AI Write Radiology Reports? A Study Suggests It Can — and Save Time Doing It

  • Home
  • Newsroom
  • Can AI Write Radiology Reports? A Study Suggests It Can — and Save Time Doing It
Can AI Write Radiology Reports? A Study Suggests It Can — and Save Time Doing It - Axcellant

Can AI Write Radiology Reports? A Study Suggests It Can — and Save Time Doing It

  1. sie 21, 2025

A recent publication in npj Digital Medicine explored the use of AI-generated radiology reports — and the results are worth watching.

In the study, radiologists used a model that generated full reports from short keyword prompts. The result? A nearly 30% reduction in reporting time, without compromising quality or accuracy. The goal: to improve efficiency and reduce variability in radiology workflows.

For clinical trials, especially those involving high volumes of imaging data, this approach has real potential. Consistency in documentation and faster turnaround times could benefit sponsors and CROs managing imaging-heavy protocols — while still keeping expert oversight in place.

At Axcellant, we believe AI won’t replace clinical experts, but it will increasingly support their work in subtle, meaningful ways — especially in high-pressure, data-intensive environments.

Read the full study here.

Resources

Axcellant Establishes Advisory Board to Strengthen Clinical and Strategic Leadership

Axcellant is pleased to announce the formation of its Advisory Board - a group of distinguished experts in clinical science,…

One trial is no longer enough. Regulators on both sides of the Atlantic are building a new model of clinical evidence

The FDA and the European Commission are changing the rules of the game simultaneously. The shift is from a single…

Imaging Core Lab in Nuclear Medicine: Standardization, Quality Control, and Regulatory Alignment in Clinical Trials 

Modern nuclear medicine is a high-tech discipline that requires advanced facilities, infrastructure, qualified staff, and know-how. The reliable supply of radionuclides,…