Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits

TL;DR

This paper introduces a physics-regularized deep self-supervised learning method to accelerate 3D nanoscale imaging of integrated circuits via ptycho-laminography, reducing data acquisition and computation time significantly while improving reconstruction quality.

Contribution

The authors develop a novel deep learning architecture that accelerates ptycho-laminography for integrated circuits, enabling fewer projections and faster processing with enhanced image fidelity.

Findings

16-fold reduction in angular samples needed

4.67-fold faster reconstruction time

Improved image quality over full-sampling methods

Abstract

Three-dimensional inspection of nanostructures such as integrated circuits is important for security and reliability assurance. Two scanning operations are required: ptychographic to recover the complex transmissivity of the specimen; and rotation of the specimen to acquire multiple projections covering the 3D spatial frequency domain. Two types of rotational scanning are possible: tomographic and laminographic. For flat, extended samples, for which the full 180 degree coverage is not possible, the latter is preferable because it provides better coverage of the 3D spatial frequency domain compared to limited-angle tomography. It is also because the amount of attenuation through the sample is approximately the same for all projections. However, both techniques are time consuming because of extensive acquisition and computation time. Here, we demonstrate the acceleration of ptycho-laminographic reconstruction of integrated circuits with 16-times fewer angular samples and 4.67-times faster computation by using a physics-regularized deep self-supervised learning architecture. We check the fidelity of our reconstruction against a densely sampled reconstruction that uses full scanning and no learning. As already reported elsewhere [Zhou and Horstmeyer, Opt. Express, 28(9), pp. 12872-12896], we observe improvement of reconstruction quality even over the densely sampled reconstruction, due to the ability of the self-supervised learning kernel to fill the missing cone.