Can deep learning improve image quality of low-dose CT: a prospective study in interstitial lung disease.

OBJECTIVES: To investigate whether deep learning reconstruction (DLR) could keep image quality and reduce radiation dose in interstitial lung disease (ILD) patients compared with HRCT reconstructed with hybrid iterative reconstruction (hybrid-IR). METHODS: Seventy ILD patients were prospectively enrolled and underwent HRCT (120 kVp, automatic tube current) and LDCT (120 kVp, 30 mAs) scans. HRCT images were reconstructed with hybrid-IR (Adaptive Iterative Dose Reduction 3-Dimensional [AIDR3D], standard-setting); LDCT images were reconstructed with DLR (Advanced Intelligence Clear-IQ Engine [AiCE], lung/bone, mild/standard/strong setting). Image noise, streak artifact, overall image quality, and visualization of normal and abnormal features of ILD were evaluated. RESULTS: The mean radiation dose of LDCT was 38% of HRCT. Objective image noise of reconstructed LDCT images was 33.6 to 111.3% of HRCT, and signal-to-noise ratio (SNR) was 0.9 to 3.1 times of the latter (p < 0.001). LDCT-AiCE was not significantly different from or even better than HRCT in overall image quality and visualization of normal lung structures. LDCT-AiCE (lung, mild/standard/strong) showed progressively better recognition of ground glass opacity than HRCT-AIDR3D (p < 0.05, p < 0.01, p < 0.001), and LDCT-AiCE (lung, mild/standard/strong; bone, mild) was superior to HRCT-AIDR3D in visualization of architectural distortion (p < 0.01, p < 0.01, p < 0.01; p < 0.05). LDCT-AiCE (bone, strong) was better than HRCT-AIDR3D in the assessment of bronchiectasis and/or bronchiolectasis (p < 0.05). LDCT-AiCE (bone, mild/standard/strong) was significantly better at the visualization of honeycombing than HRCT-AIDR3D (p < 0.05, p < 0.05, p < 0.01). CONCLUSION: Deep learning reconstruction could effectively reduce radiation dose and keep image quality in ILD patients compared to HRCT with hybrid-IR. KEY POINTS: • Deep learning reconstruction was a novel image reconstruction algorithm based on deep convolutional neural networks. It was applied in chest CT studies and received auspicious results. • HRCT plays an essential role in the whole process of diagnosis, treatment efficacy evaluation, and follow-ups for interstitial lung disease patients. However, cumulative radiation exposure could increase the risks of cancer. • Deep learning reconstruction method could effectively reduce the radiation dose and keep the image quality compared with HRCT reconstructed with hybrid iterative reconstruction in patients with interstitial lung disease.

[Testicular injection of lipopolysaccharide: An effective method for establishing the mouse model of orchitis].

OBJECTIVE: To search for a method of establishing a reliable mouse model of orchitis and investigate the association of orchitis with the activation of the inflammasome. METHODS: We equally randomized 40 adult male KM mice into groups A (sham operation), B (intraperitoneal injection of lipopolysaccharide ï¼»LPSï¼½), C (unilateral testicular injection of glacial acetic acid ï¼»GAAï¼½), and D (unilateral testicular injection of LPS). At 3 weeks after modeling, we measured the sperm concentration and percentage of progressively motile sperm (PMS) in the epididymis by computer-assisted semen analysis, observed the pathological changes in the testis tissue by HE staining, and determined the expressions of the Caspase-1 and interleukin (IL)-1ß proteins by Western blot. RESULTS: The sperm concentration in the epididymis was significantly decreased in groups B (ï¼»25.74 ± 3.19ï¼½ ×106/ml), C (ï¼»17.16 ± 4.41ï¼½ ×106/ml) and D (ï¼»16.92 ± 7.13ï¼½ ×106/ml) as compared with that in group A (ï¼»28.20 ± 1.63ï¼½ ×106/ml) (all P < 0.05), even more significantly in B than in C and D (P < 0.01), and so was PMS in groups B (ï¼»29.57 ± 2.16ï¼½%), C (ï¼»18.10 ± 2.38ï¼½%) and D (ï¼»7.34 ± 1.63ï¼½%) in comparison with group A (ï¼»59.34 ± 1.10ï¼½%) (P < 0.01), even more significantly in B and C than in D (P < 0.01). Light microscopy revealed different degrees of pathological changes in the testis tissue, most significant in group D, followed by C and B. Both the expressions of Caspase-1 and IL-1ß were remarkably up-regulated in groups B, C and D compared with those in group A (P < 0.01), even more markedly in D than in B and C (P < 0.05). CONCLUSIONS: Unilateral testicular injection of LPS is a more efficient method than either unilateral testicular injection of GAA or intraperitoneal injection of LPS for establishing the mouse model of orchitis. Orchitis may be pathologically associated with the activation of the NLRP3 inflammasome.

The anti-inflammatory effect of BML-111 on COPD may be mediated by regulating NLRP3 inflammasome activation and ROS production.

The aim of this study is to investigate whether the lipoxin receptor agonist BML-111 exerts a protective effect against inflammation in a mouse model of chronic obstructive pulmonary disease (COPD) by regulating NLRP3 inflammasome activation and reactive oxygen species (ROS) production. In this study, mice were randomly divided into the following five groups: control group (Control), COPD model group (Model), BML-111 low-dose group (Low-BML), BML-111 high-dose group (High-BML) and Dexamethasone group (Dex). NLRP3 involvement and oxidative stress were evaluated. Differential cell counts in the BALF were calculated to obtain a reliable enumeration of each cell type, and the levels of TGF-ß, TNF-α, IL-1ß, and IL-10 in BALF were evaluated using ELISA. We found that the white blood cell and lymphocyte numbers in the BALF were significantly lower in the High-BML group than in the Model group. ELISA of the BALF showed that BML-111 reduced TGF-ß and IL-1ß levels to some extent. HE staining showed various degrees of reduction in inflammatory cell infiltration in the bronchopulmonary tissue and blood vessels of the Low-BML, High-BML and Dex groups. Measurement of oxidative stress showed that SOD activity was significantly upregulated and that the increase in MDA content was prevented in the High-BML and Dex groups. According to the Western blotting analysis, the levels of NLRP3, Cleaved-IL-1ß and Cleaved-caspase-1 were decreased and Nrf-2 was increased to various extents in the Low-BML, High-BML and Dex groups. Based on these findings, BML-111 may prevent NLRP3 inflammasome activation and inhibit ROS production via upregulation of Nrf-2, thereby exerting an anti-inflammatory effect on COPD model mice.