Deep Learning-Based Computed Tomography Imaging to Diagnose the Lung Nodule and Treatment Effect of Radiofrequency Ablation.

This study aimed to detect and diagnose the lung nodules as early as possible to effectively treat them, thereby reducing the burden on the medical system and patients. A lung computed tomography (CT) image segmentation algorithm was constructed based on the deep learning convolutional neural network (CNN). The clinical data of 69 patients with lung nodules diagnosed by needle biopsy and pathological comprehensive diagnosis at hospital were collected for specific analysis. The CT image segmentation algorithm was used to distinguish the nature and volume of lung nodules and compared with other computer aided design (CAD) software (Philips ISP). 69 patients with lung nodules were treated by radiofrequency ablation (RFA). The results showed that the diagnostic sensitivity of the CT image segmentation algorithm based on the CNN was obviously higher than that of the Philips ISP for solid nodules <5 mm (63 cases vs. 33 cases) (P < 0.05); it was the same result for the subsolid nodule <5 mm (33 case vs. 5 cases) (P < 0.05) that was slightly higher for solid and subsolid nodules with a diameter of 5-10 mm (37 cases vs. 28 cases) (P < 0.05). In addition, the CNN algorithm can reach all detection for calcified nodules and pleural nodules (7 cases; 5 cases), and the diagnostic sensitivities were much better than those of Philips ISP (2 cases; 3 cases) (P < 0.05). Patients with pulmonary nodules treated by RFA were in good postoperative condition, with a half-year survival rate of 100% and a one-year survival rate of 72.4%. Therefore, it could be concluded that the CT image segmentation algorithm based on the CNN could effectively detect and diagnose the lung nodules early, and the RFA could effectively treat the lung nodules.

Corrigendum: Transcriptional Activation of Matricellular Protein Spondin2 (SPON2) by BRG1 in Vascular Endothelial Cells Promotes Macrophage Chemotaxis.

[This corrects the article DOI: 10.3389/fcell.2020.00794.].

Transcriptional Activation of Matricellular Protein Spondin2 (SPON2) by BRG1 in Vascular Endothelial Cells Promotes Macrophage Chemotaxis.

The matricellular protein SPON2 plays diverse roles in the development of cardiovascular diseases. SPON2 is expressed in endothelial cells, but its transcription regulation in the context of atherogenesis remains incompletely appreciated. Here we report that SPON2 expression was up-regulated by pro-atherogenic stimuli (oxLDL and TNF-α) in vascular endothelia cells. In addition, endothelial SPON2 was elevated in Apoe -/- mice fed on a Western diet compared to the control mice. Induction of SPON2 in endothelial cells by pro-atherogenic stimuli was mediated by BRG1, a chromatin remodeling protein, both in vitro and in vivo. Further analysis revealed that BRG1 interacted with the sequence-specific transcription factor Egr-1 to activate SPON2 transcription. BRG1 contributed to SPON2 trans-activation by modulating chromatin structure surrounding the SPON2 promoter. Functionally, activation of SPON2 transcription by the Egr-1/BRG1 complex provided chemoattractive cues for macrophage trafficking. SPON2 depletion abrogated the ability of BRG1 or Egr-1 to stimulate endothelial derived chemoattractive cue for macrophage migration. On the contrary, recombinant SPON2 rescued endothelial chemo-attractability in the absence of BRG1 or Egr-1. In conclusion, our data have identified a novel transcriptional cascade in endothelial cells that may potentially promote macrophage recruitment and vascular inflammation leading to atherogenesis.

Cloning, expression and functional characterization of the polyunsaturated fatty acid elongase (ELOVL5) gene from sea cucumber (Apostichopus japonicus).

Long chain polyunsaturated fatty acid (PUFA) are beneficial for maintaining the health, growth and development of an organism and could reduce the risk of some diseases. The ability to endogenously produce PUFA, especially in invertebrates, is largely unknown. To study the function of elongase genes in the PUFA biosynthesis of Apostichopus japonicus, we cloned an ELOVL5 homology gene from intestinal cDNA of A. japonicus (Aj-ELOVL5). The Aj-ELOVL5 gene encoded a 318 amino acid (AA) protein that exhibited all the characteristics of the ELOVL5 family, such as a histidine box motif and four putative transmembrane-spanning domains. The results of the tissue expression profile of Aj-ELOVL5 revealed that the body wall exhibited the highest expression level compared with other adult tissues. We also found that the Aj-ELOVL5 enzyme exhibited the ability to elongate γ-linolenic acid (18:3 n-6) and eicosapentaenoic acid (20:5 n-3) to dihomo-γ-linolenic acid (20:3 n-6) and docosapentaenoic acid (22:5 n-3), respectively. Our results indicated that the Aj-ELOVL5 enzyme had the capacity to biosynthesize PUFA from C18/C20 PUFA substrates.