200x Low-dose PET Reconstruction using Deep Learning

TL;DR

This paper presents a deep learning approach using an encoder-decoder residual network with skip connections to reconstruct high-quality PET images from ultra-low-dose scans, significantly reducing radiation exposure while maintaining diagnostic quality.

Contribution

The study introduces a novel deep learning framework that effectively reconstructs standard-dose PET images from only 0.5% of the original dose, outperforming existing methods.

Findings

Reconstructed images with comparable quality using only 0.5% of the dose.

Proposed method outperforms state-of-the-art techniques on clinical data.

Multi-slice input enhances robustness to noise.

Abstract

Positron emission tomography (PET) is widely used in various clinical applications, including cancer diagnosis, heart disease and neuro disorders. The use of radioactive tracer in PET imaging raises concerns due to the risk of radiation exposure. To minimize this potential risk in PET imaging, efforts have been made to reduce the amount of radio-tracer usage. However, lowing dose results in low Signal-to-Noise-Ratio (SNR) and loss of information, both of which will heavily affect clinical diagnosis. Besides, the ill-conditioning of low-dose PET image reconstruction makes it a difficult problem for iterative reconstruction algorithms. Previous methods proposed are typically complicated and slow, yet still cannot yield satisfactory results at significantly low dose. Here, we propose a deep learning method to resolve this issue with an encoder-decoder residual deep network with concatenate skip connections. Experiments shows the proposed method can reconstruct low-dose PET image to a standard-dose quality with only two-hundredth dose. Different cost functions for training model are explored. Multi-slice input strategy is introduced to provide the network with more structural information and make it more robust to noise. Evaluation on ultra-low-dose clinical data shows that the proposed method can achieve better result than the state-of-the-art methods and reconstruct images with comparable quality using only 0.5% of the original regular dose.