{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/dc78f0d629994ba0adde62614fda7b8b\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/dc78f0d629994ba0adde62614fda7b8b-a74493db834379b5.gif","duration":118.907,"title":"AI-Driven Clinical Report Generation from Chest X-Ray Images","description":"In 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."}