You and your co-workers are cordially invited to join us ..... "AI Tools in X-ray Computed Tomography: Applications, Drawbacks, and Key Insights." Julio-Cesar da Silva CNRS NÉEL Institute Grenoble, France August 20, 13:30(EDT) To register for virtual attendance: https://bnl.zoomgov.com/meeting/register/haKdzCvnReWMVziXnFXMZw Abstract: I will present the most commonly used AI tools in X-ray computed tomography, highlighting their potential drawbacks. Moreover, I will discuss the basic machine learning concepts essential for effectively utilizing these tools and their implementation at the Hub AI for Tomography, AIAX, located in Grenoble, France. After examining densely connected neural networks, convolutional neural networks, and encoder-decoder architectures, I will provide a brief explanation of how the U-Net, MSDNet, Noise2Noise, TomoGAN, and GANRec networks function within the field of tomography. Their primary applications focus on image denoising and 3D image segmentation. The examples provided will be sourced from hard X-ray tomography applied to both biological and materials science specimens. The key takeaway from this presentation is that while AI-generated results can be advantageous, they need to be critically evaluated, as they always require human involvement for refinement. ================= Vivian Stojanoff, PhD Education, Training, Outreach User Program p 1(631) 344 8375 e [email protected]mailto:[email protected] w https://www.bnl.gov/ps/lifesciences/https://www.bnl.gov/ps/lsbr/ Address: Center for Biomolecular Structure National Synchrotron Light Source II Building 745 Brookhaven National Laboratory Upton NY 11973