Join CMITT at the IEEE NSS/MIC/RTSD Conference
The 2024 IEEE NSS/MIC/RTSD Conference will showcase groundbreaking work in nuclear science and medical imaging, with the CMITT playing a prominent role in two short courses, two posters, and two oral presentations.
Short Courses:
- Hybrid Nuclear Medicine Devices: Learn about the basics of PET, SPECT, CT, and MRI instrumentation and image processing, followed by promises and challenges of integrating these modalities.
- Tuesday, October 29, 8:30 - 17:20
- Course organizers: Chi Liu, Chao Ma, Thibault Marin
- PET Kinetic Modeling and Parametric Imaging: This course will provide an overview of the fundamentals of PET tracer kinetic modeling and parametric imaging, including key clinical applications. It will also cover recent advancements in total-body PET kinetic modeling. The course is designed for anyone looking to gain a clearer understanding of PET kinetic modeling and parametric imaging techniques.
- Monday, October 28, 8:30 - 17:00
- Course organizers: Guobao Wang, Marc Normandin
Poster Presentations:
- Multimodality Molecular Imaging of Brain Tumors: Discover how simultaneous [18F]FET-PET and MRSI enhance tumor characterization.
- C. Ma, P. K. Han, T. Marin, Y. Zhuo, H. A. Shih, G. El Fakhri
- Friday Nov 01, 16:20 - 18:00
- PET Motion Correction in PET/MR: Explore innovative subspace-based real-time MR imaging techniques for motion correction.
- I. B.G. Mounime, T. Marin, P. K. Han, J. Ouyang, P. Gori, E. Angelini, G. El Fakhri, C. Ma
- Thursday October 31, 14:00 - 15:45
Oral Presentations:
- Diffusion-based Bayesian posterior distribution prediction of kinetic parameters in dynamic PET: See how this deep learning approach is improving PET tracer kinetic modeling, offering faster and more accurate analysis of neurodegenerative disease processes.
- Y. Djebra, X. Liu, T. Marin, A. Tiss, M. Dhaynaut, N. Guehl, K. Johnson, G. El Fakhri, C. Ma, J. Ouyang
- Saturday November 02, 8:00
- Subject-aware PET Denoising with Contrastive Adversarial Domain Generalization: Learn how a novel contrastive adversarial learning framework improves PET denoising by tackling subject-wise variations, paving the way for a more reliable and generalizable deep learning model for clinical use.
- X. Liu, T. Marin, S. Vafay Eslahi, A. Tiss, Y. Chemli, K. A. Johson, G. El Fakhri, J. Ouyang
- Thursday October 31, 10:20
Don’t miss the chance to engage with CMITT’s cutting-edge research and contribute to the future of medical imaging.