video1.0<iframe src="https://www.loom.com/embed/dc78f0d629994ba0adde62614fda7b8b" frameborder="0" width="1920" height="1440" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>14401920Loomhttps://www.loom.com14401920https://cdn.loom.com/sessions/thumbnails/dc78f0d629994ba0adde62614fda7b8b-a74493db834379b5.gif118.907In this video, I present our new AA second reader project designed to assist radiologists by generating structured clinical reports from chest x-ray images using a cognitive reasoning framework. The system processes raw x-ray images alongside patient clinical history, employing our PRO-FA model for hierarchical perception and multi-label classification to form diagnostic hypotheses. It then verifies these hypotheses with the RCTA model before generating a structured radiology report. This approach not only enhances diagnostic accuracy but also serves as a clinical decision support tool. I encourage you to review the details and consider how this system can be integrated into our workflow.