Abstract:

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 described based on our multi-disciplinary collaboration, such as image artifact disentanglement, feature dissection in radiographs, and hybrid reconstruction from low-quality data. Also, challenging issues specific to AI are discussed that involve the robustness and explainability of deep learning methods. Finally, directions are brainstormed for future opportunities.

This colloquium will not be in-person, but per zoom link.

*Click here for video of presentation.

*Click here for presentation slides.