Transformer for low concentration image denoising in magnetic particle imaging.

Objective.Magnetic particle imaging (MPI) is an emerging tracer-basedin vivoimaging technology. The use of MPI at low superparamagnetic iron oxide nanoparticle concentrations has the potential to be a promising area of clinical application due to the inherent safety for humans. However, low tracer concentrations reduce the signal-to-noise ratio of the magnetization signal, leading to severe noise artifacts in the reconstructed MPI images. Hardware improvements have high complexity, while traditional methods lack robustness to different noise levels, making it difficult to improve the quality of low concentration MPI images.Approach.Here, we propose a novel deep learning method for MPI image denoising and quality enhancing based on a sparse lightweight transformer model. The proposed residual-local transformer structure reduces model complexity to avoid overfitting, in which an information retention block facilitates feature extraction capabilities for the image details. Besides, we design a noisy concentration dataset to train our model. Then, we evaluate our method with both simulated and real MPI image data.Main results.Simulation experiment results show that our method can achieve the best performance compared with the existing deep learning methods for MPI image denoising. More importantly, our method is effectively performed on the real MPI image of samples with an Fe concentration down to 67µgFeml-1.Significance.Our method provides great potential for obtaining high quality MPI images at low concentrations.

Neonatal exposure to low-dose X-ray causes behavioral defects and abnormal hippocampal development in mice.

Development of the hippocampus is critical for its normal maturation. However, there is no systematic study on the effects of low-dose (≤2 Gy) neonatal X-ray exposure on different cells at different developmental stages of the mouse hippocampus. The present study demonstrated that irradiation with 2 Gy at postnatal day (PD) 3 in mice induced anxiety and impairment of spatial learning and memory in adult mice. Neuroinflammatory cells were observed in the dentate gyrus (DG) and CA3 areas of the hippocampus at PD3 + 1. X-ray irradiation impaired neuronal complexity and neurogenesis. However, the number of astrocytes and microglia in the hippocampus was increased the first day after irradiation, and then decreased 21 days later. The protein expression levels of NF-κB, C/EBP homologous protein (CHOP), and γH2 A histone family member X (γH2 AX) increased from 7 to 21 days after irradiation, or till 90 days after irradiation for IL-1ß, whereas those of hippocampal sirtuin1 (SIRT1) decreased after 21 days of irradiation at PD3. These results suggest that neonatal X-ray irradiation-induced neuroinflammation impaired neuroplasticity and neurogenesis in the hippocampus, leading to the anxiety and spatial memory disorder during adulthood. The mechanisms involved in the induction of developmental neurotoxicity following low-dose irradiation may involve the inflammation-mediated signaling pathway IL-1ß/ SIRT1/CHOP.