Eirik Østmo / Torger Grytå

VI Seminar #54 – Generative AI for high quality 2D and 3D echo images

The program will be available shortly. Please check back later.

Generative AI for high quality 2D and 3D echo images

Presenter: Cristiana Tiago, PhD, Data Scientist at GE Healthcare

Cristiana Tiago (Photo: private)

Abstract:  In cardiovascular imaging, the integration of Generative Artificial Intelligence holds great promise for enhancing the quality and availability of diagnostic tools. This presentation explores the application of Generative AI,specifically adversarial diffusion models, to the synthesis of high-quality 2D and 3D echocardiography images. By employing cutting-edge techniques in AI, we aim to generate realistic and clinically relevant echo images.

By training adversarial diffusion models on extensive echocardiography datasets, we enable the generation of images that closely mimic real-world cardiac structures and motion patterns. These synthetic images serve as a valuable resource for the creation of comprehensive synthetic datasets, facilitating the development and refinement of robust AI models within the field, anticipating advancements in the accuracy and generalization capabilities of AI models dedicated to cardiovascular image analysis.

Our findings aim to demonstrate the efficacy of generative AI in the realm of echocardiography, showcasing its potential to revolutionize the landscape of cardiovascular imaging and contribute to the development of more precise and reliable diagnostic tools.

In compliance with GDPR consent requirements, presentations given in a Visual Intelligence context may be recorded with the consent of the speaker. All recordings are edited to remove all faces, names and voices of other participants. Questions and comments by the audience will hence be removed and will not appear in the recording.  With the freely given consent from the speaker, recorded presentation may be posted on the Visual Intelligence YouTube channel.

This seminar is open for members of the consortium. If you want to participate as a guest please sign up.

Sign up here