Terahertz Spatio-Temporal Deep Learning Computed Tomography

TL;DR

This paper introduces a deep learning framework for terahertz computed tomography that significantly improves image quality and generalizes well to multi-material objects without prior information.

Contribution

It presents a supervised deep learning approach based on spatio-temporal THz signals, enhancing image reconstruction beyond traditional physics-based methods.

Findings

Achieves over 50% improvement in RMSE and SSIM compared to conventional methods.

Successfully generalizes to multi-material systems without prior knowledge.

Provides a new pathway for non-invasive functional imaging.

Abstract

Terahertz computed tomography (THz CT) has drawn significant attention because of its unique capability to bring multi-dimensional object information from invisible to visible. However, current physics-model-based THz CT modalities present low data use efficiency on time-resolved THz signals and low model fusion extensibility, limiting their application fields' practical use. In this paper, we propose a supervised THz deep learning computed tomography (THz DL-CT) framework based on time-domain information. THz DL-CT restores superior THz tomographic images of 3D objects by extracting features from spatio-temporal THz signals without any prior material information. Compared with conventional and machine learning based methods, THz DL-CT delivers at least 50.2%, and 52.6% superior in root mean square error (RMSE) and structural similarity index (SSIM), respectively. Additionally, we have experimentally demonstrated that the pretrained THz DL-CT model can generalize to reconstruct multi-material systems with no prerequisite information. THz CT through the DL data fusion approach provides a new pathway for non-invasive functional imaging in object investigation.