У нас вы можете посмотреть бесплатно Choosing Smartly- How Deephealth and CARPL enable RadNet to select the 'Right' AI | RSNA'24 или скачать в максимальном доступном качестве, видео которое было загружено на ютуб. Для загрузки выберите вариант из формы ниже:
Если кнопки скачивания не
загрузились
НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием видео, пожалуйста напишите в поддержку по адресу внизу
страницы.
Спасибо за использование сервиса ClipSaver.ru
At RSNA'24, DeepHealth and CARPL.ai share a behind-the-scenes look at one of the largest chest X-ray AI validation studies ever conducted—driven by RadNet's need to evaluate, compare, and scale AI adoption in outpatient imaging. Led by Dr. Christopher Austin and Dr. Venkatesh Balasubramanian, this session breaks down how CARPL’s platform helped RadNet and DeepHealth evaluate 9 AI vendors using over 100,000 chest X-rays, all while maintaining clinical relevance, speed, and scientific rigor. 🔍 Key insights: RadNet’s motivation: Reduce radiologist burden in high-volume modalities like chest X-rays. Study design: Concordance-discordance model to triage 100K+ studies efficiently. Ground truth extraction via LLMs and structured report parsing. Vendor-neutral validation: 9 global AI companies participated, regardless of FDA status. Integrated review dashboards, threshold tuning, and monitoring capabilities. Workflow integration into DeepHealth OS for real-world deployment and future scalability. 💡 “We didn’t just evaluate chest X-ray AI—we built a repeatable framework to validate any imaging AI at scale.” #RSNA2024 #RadiologyAI #ChestXRay #AIValidation #CARPLai #DeepHealth #RadNet #AIinHealthcare #ClinicalAI #VendorNeutralAI