Reading path
Reading a Scan and Its Report
A radiology report can feel like a foreign language of doses, contrast agents, and structured scores. This path explains when imaging is appropriate, how to weigh radiation and contrast risks, how reporting systems turn a finding into a plan, and how to judge the AI now reading scans. It is for patients and readers who want to understand what a scan can and cannot tell them.
The path, step by step
Start before the scan itself, with how evidence decides whether a given imaging test is the right one to order at all.
Turn to the main cost of CT by learning to read a radiation dose and the principle of keeping it as low as reasonably achievable.
Weigh that dose against risk by examining the model used to estimate whether low-dose radiation causes cancer.
Add the other common exposure, contrast agents, and see how MRI agents are grouped by their safety profile.
Use the contrast-and-kidney story as a clean lesson in confounding before blaming a scan for a bad outcome.
See how a structured reporting system converts a raw finding, a lung nodule, into a defined management plan.
Read a second structured score to generalize what these numbered systems can and cannot promise.
Confront the unexpected finding and learn how radiologists decide which incidental spots are worth pursuing.
9 How to Judge an FDA Cleared Radiology AI Tool
5 min readMove to the software now reading scans and learn what a clearance does and does not certify about a radiology AI tool.
Finish with the first randomized trial of AI in mammography, the strongest current evidence for AI reading images.
Each step is a full article on the Reading the Evidence blog.