Видео

F24 MI23 (OCT Multimodality Imaging for medical imaging students at RPI)

My Dropbox is not large enough so I use RUclips 8-)

My Dropbox is not large enough so I use RUclips 8-)

The advent of AI foundation models promises transformative advancements in medical applications, an area central to our research. In this presentation, I will highlight two key developments: Specialty-Oriented Generalist Medical AI (SOGMAI) models and physics-inspired generative AI models for medical imaging. First, I will describe the Medical Multimodal Multitask Foundation Model (M3FM), a SOG...

Ulrich Bonse's contributions to X-ray imaging have been instrumental. This talk honors his legacy by exploring the connection linking his foundational work in interferometry and micro-CT to the modern advancement in generative AI for tomographic imaging, emphasizing how generative AI can enhance interferometric imaging and clinical micro-CT (presented at the SPIE Conference 13152: Developments ...

Why foundation models work is briefly explained. Then, two examples of ours are reported, which are (1) the medical multimodal multitask foundation model (M3FM) for lung cancer screening and related tasks and (2) the Poisson flow consistency model (PFCM) for low-dose CT denoising. Future directions are also mentioned.

Ge Wang's award talk on AI for medical imaging, Vancouver, Canada, Nov. 8, 2023 (IEEE Nuclear and Plasma Sciences Society Edward J. Hoffman Medical Imaging Scientist Award: “For pioneering contributions to medical computed tomography, multi-modality imaging, and AI-based tomographic imaging, as well as exemplary mentorship in medical imaging training and education.”)

Our team won the 1st place in the 2023 AAPM DGM-Image Challenge. This talk explains our winning strategy. We are open to collaboration.

Our team won the 1st place in the 2023 AAPM DGM-Image Challenge. This talk explains our winning strategy. We are open to collaboration.

RPI presentation in the 4th Deep Recon Workshop, Yale University, collected presented by Yongyi Shi, Wenjun Xi, Chuang Niu, and Ge Wang, March 25, 2023

This was given on April 23, 2023 for the Forum of Intelligent Imaging Science and Technology (FINIST), organized by the Intelligent Imaging Branch (IIB), the Chinese Society for Stereology (CSS), and the Journal of Computerized Tomography Theory and Applications (CTTA) (www.cttacn.org.cn/indexen.htm). Abstract: In our perspective on deep learning-based imaging (ieeexplore.ieee.org/document/7733...

Ge Wang's award talk on future of medical imaging, Washington DC, USA, Nov. 4, 2022 (Sigma Xi Scientific Research Honor Society Walston Chubb Award for Innovation: “For pioneering contributions to medical imaging and major impacts on research, development, and healthcare, including his cone-beam CT method and AI-based imaging leadership.”)

Artificial intelligence (AI), especially deep learning, has become a mainstream approach today, and enabled major advances in medical imaging, including not only image analysis (from images to features) but also image reconstruction (from data/features to images). In this presentation, a general background is provided on deep learning-based tomographic imaging. Then, some new results are descri...

The first NIH AI imaging workshop was held in 2018, which was globally video-cast and publicly shared. In that workshop, Ge Wang gave two talks on big data and deep reconstruction respectively. His student Mengzhou Li combined the two talks and associated Q&A sessions into this video file of about one hour. For more details, please see www.nibib.nih.gov/news-events/meetings-events/artificial-in...

Stanford Seminar "Deep Tomographic Imaging" Given by Ge Wang on Nov. 19, 2020

CT - Ideas & Impacts (in Chinese)

Deep CT Recon

ShanghaiTech BME Seminar Series: Medical Imaging Research & Teaching @ RPI by Ge Wang, Sept. 2, 2021

SPIE O P Plenary Speech "X-ray Imaging Meets Deep Learning" by Ge Wang, Aug. 2, 2021

Machine Learning for Tomographic Imaging

Hybrid CT-MRI

Deep Learning (DL) & Computed Tomography (CT)

Computed Tomography- Scanning into the Future