Deep Learning-based Low-dose Tomography Reconstruction with Hybrid-dose Measurements

TL;DR

This paper introduces a deep learning method that enhances low-dose X-ray tomography reconstructions using hybrid-dose measurements, significantly improving detail and noise reduction while being faster than existing methods.

Contribution

The study presents a novel deep learning framework, HDrec, for hybrid-dose tomography that outperforms traditional methods in quality and speed, enabling better imaging of dose-sensitive samples.

Findings

Significantly improved structural detail and noise reduction in reconstructions.

HDrec performs 410x faster than the Xlearn method with better quality.

Effective application to experimental datasets under various hybrid-dose conditions.

Abstract

Synchrotron-based X-ray computed tomography is widely used for investigating inner structures of specimens at high spatial resolutions. However, potential beam damage to samples often limits the X-ray exposure during tomography experiments. Proposed strategies for eliminating beam damage also decrease reconstruction quality. Here we present a deep learning-based method to enhance low-dose tomography reconstruction via a hybrid-dose acquisition strategy composed of extremely sparse-view normal-dose projections and full-view low-dose projections. Corresponding image pairs are extracted from low-/normal-dose projections to train a deep convolutional neural network, which is then applied to enhance full-view noisy low-dose projections. Evaluation on two experimental datasets under different hybrid-dose acquisition conditions show significantly improved structural details and reduced noise levels compared to uniformly distributed acquisitions with the same number of total dosage. The resulting reconstructions also preserve more structural information than reconstructions processed with traditional analytical and regularization-based iterative reconstruction methods from uniform acquisitions. Our performance comparisons show that our implementation, HDrec, can perform denoising of a real-world experimental data 410x faster than the state-of-the-art Xlearn method while providing better quality. This framework can be applied to other tomographic or scanning based X-ray imaging techniques for enhanced analysis of dose-sensitive samples and has great potential for studying fast dynamic processes.