We have built AI-driven tools to automate the assessment of key heart parameters from point-of-care ultrasound, including Right Atrial Pressure (RAP) and Ejection Fraction (EF). In collaboration with UCSF, we trained deep learning models on a proprietary dataset of over 15,000 labeled ultrasound studies and deployed the full pipeline in a real-time iOS app integrated with the Butterfly probe. A UCSF-led clinical trial has validated the RAP workflow, and we are actively expanding the system to support EF prediction using both A4C and PLAX views. This talk will present our end-to-end pipeline, from dataset development and model training to mobile deployment—demonstrating how AI can enable real-time heart assessments directly at the point of care.
talk-data.com
Speaker
Jeffrey Gao
7
talks
Jeffrey Gao is a PhD candidate at Caltech, working at the intersection of machine learning and medical imaging. His research focuses on developing clinically deployable AI systems for ultrasound-based heart assessments, with an emphasis on real-time, edge-based inference and system integration.
Bio from: June 26 - Visual AI in Healthcare
Filter by Event / Source
Talks & appearances
7 activities · Newest first
We have built AI-driven tools to automate the assessment of key heart parameters from point-of-care ultrasound, including Right Atrial Pressure (RAP) and Ejection Fraction (EF). In collaboration with UCSF, we trained deep learning models on a proprietary dataset of over 15,000 labeled ultrasound studies and deployed the full pipeline in a real-time iOS app integrated with the Butterfly probe. A UCSF-led clinical trial has validated the RAP workflow, and we are actively expanding the system to support EF prediction using both A4C and PLAX views. This talk will present our end-to-end pipeline, from dataset development and model training to mobile deployment—demonstrating how AI can enable real-time heart assessments directly at the point of care.
We have built AI-driven tools to automate the assessment of key heart parameters from point-of-care ultrasound, including Right Atrial Pressure (RAP) and Ejection Fraction (EF). In collaboration with UCSF, we trained deep learning models on a proprietary dataset of over 15,000 labeled ultrasound studies and deployed the full pipeline in a real-time iOS app integrated with the Butterfly probe. A UCSF-led clinical trial has validated the RAP workflow, and we are actively expanding the system to support EF prediction using both A4C and PLAX views. This talk will present our end-to-end pipeline, from dataset development and model training to mobile deployment—demonstrating how AI can enable real-time heart assessments directly at the point of care.
We have built AI-driven tools to automate the assessment of key heart parameters from point-of-care ultrasound, including Right Atrial Pressure (RAP) and Ejection Fraction (EF). In collaboration with UCSF, we trained deep learning models on a proprietary dataset of over 15,000 labeled ultrasound studies and deployed the full pipeline in a real-time iOS app integrated with the Butterfly probe. A UCSF-led clinical trial has validated the RAP workflow, and we are actively expanding the system to support EF prediction using both A4C and PLAX views. This talk will present our end-to-end pipeline, from dataset development and model training to mobile deployment—demonstrating how AI can enable real-time heart assessments directly at the point of care.
We have built AI-driven tools to automate the assessment of key heart parameters from point-of-care ultrasound, including Right Atrial Pressure (RAP) and Ejection Fraction (EF). In collaboration with UCSF, we trained deep learning models on a proprietary dataset of over 15,000 labeled ultrasound studies and deployed the full pipeline in a real-time iOS app integrated with the Butterfly probe. A UCSF-led clinical trial has validated the RAP workflow, and we are actively expanding the system to support EF prediction using both A4C and PLAX views. This talk will present our end-to-end pipeline, from dataset development and model training to mobile deployment—demonstrating how AI can enable real-time heart assessments directly at the point of care.
We have built AI-driven tools to automate the assessment of key heart parameters from point-of-care ultrasound, including Right Atrial Pressure (RAP) and Ejection Fraction (EF). In collaboration with UCSF, we trained deep learning models on a proprietary dataset of over 15,000 labeled ultrasound studies and deployed the full pipeline in a real-time iOS app integrated with the Butterfly probe. A UCSF-led clinical trial has validated the RAP workflow, and we are actively expanding the system to support EF prediction using both A4C and PLAX views.\n\nThis talk will present our end-to-end pipeline, from dataset development and model training to mobile deployment—demonstrating how AI can enable real-time heart assessments directly at the point of care.
We have built AI-driven tools to automate the assessment of key heart parameters from point-of-care ultrasound, including Right Atrial Pressure (RAP) and Ejection Fraction (EF). In collaboration with UCSF, we trained deep learning models on a proprietary dataset of over 15,000 labeled ultrasound studies and deployed the full pipeline in a real-time iOS app integrated with the Butterfly probe. A UCSF-led clinical trial has validated the RAP workflow, and we are actively expanding the system to support EF prediction using both A4C and PLAX views.\n\nThis talk will present our end-to-end pipeline, from dataset development and model training to mobile deployment—demonstrating how AI can enable real-time heart assessments directly at the point of care.