Unsupervised deep image prior for sparse-view and limited-angle electron tomography

Electron tomography (ET) plays an important role in the three-dimensional (3D) characterization of nanomaterials. However, when the angular range is limited (limited-angle tomography) and the tilt increment is large (sparse-view tomography), conventional algorithms produce degraded reconstructions, which compromise the quality and interpretability of resulting 3D data. More specifically, limited-angle tomography leads to elongation and blurring artifacts, whereas sparse-view tomography results in streaking and star artifacts. In this paper, we present deep image prior (DIP), an unsupervised deep learning (DL) approach, for highly degraded tomography acquisitions and demonstrate, using simulated data, that its performance is comparable to that of supervised approaches requiring training datasets, even for tilt ranges as limited as 60° and tilt increments of 10° We then apply it to experimental data and show that it enables reliable 3D quantification under both sparse-view and limited-angle conditions, highlighting its potential for a wide range of materials and acquisition modalities.