Nikolakakis, M. (ECE) – Learned Gridless Representations of Cone Beam Computed Tomography Scans

Medical image representation has long been dominated by voxel-grid matrices. While
their inherent structure and order work efficiently for various linear transformations and
provide a seamless visualization method on monitors, they fail to preserve the topology
of the scan and to encode sparse information in a memory-efficient way.   The recent emergence of machine learning-based continuous coordinate-based
scene representations such as neural radiance fields and Gaussian splatting has provided alternative representation techniques. These approaches overfit the weights of
a model by iterative differentiable rendering and have been shown to be more compact than grid representations. They are then able to perform novel view
synthesis from any given camera pose.
Off-grid representations translate directly to Cone Beam Computed Tomography
sparse-view acquisitions, where streaking and quantum noise artifacts are dominant.
Using differentiable rendering, a continuous representation is achieved, with interpolation providing a path to recover some of the lost signal.
In this dissertation, we apply a variety of methodologies, including Gaussian splatting, implicit occupancy fields, and Neural Attenuation Fields regularized with an
anatomic prior, to Cone Beam Computed Tomography reconstruction, and evaluate
their performance across a range of anatomic datasets. Our models show that learned
gridless representations achieve substantial memory reduction, recover signal under
extreme view sparsity, and preserve scene topology.

Event Host: Manolis Nikolakakis, Ph.D. Candidate, Electrical and Computer Engineering 

Advisor: Razvan Marinescu

Zoom: https://ucsc.zoom.us/j/5964517596?pwd=c1AwRlJLNk5pVzFBUENibEw3by85Zz09