Pulmonary arteries segmentation from CT images using PA-Net with attention module and contour loss.

BACKGROUND: Pulmonary embolism is a kind of cardiovascular disease that threatens human life and health. Since pulmonary embolism exists in the pulmonary artery, improving the segmentation accuracy of pulmonary artery is the key to the diagnosis of pulmonary embolism. Traditional medical image segmentation methods have limited effectiveness in pulmonary artery segmentation. In recent years, deep learning methods have been gradually adopted to solve complex problems in the field of medical image segmentation. PURPOSE: Due to the irregular shape of the pulmonary artery and the adjacent-complex tissues, the accuracy of the existing pulmonary artery segmentation methods based on deep learning needs to be improved. Therefore, the purpose of this paper is to develop a segmentation network, which can obtain higher segmentation accuracy and further improve the diagnosis effect. METHODS: In this study, the pulmonary artery segmentation performance from the network model and loss function is improved, proposing a pulmonary artery segmentation network (PA-Net) to segment the pulmonary artery region from 2D CT images. Reverse Attention and edge attention are used to enhance the expression ability of the boundary. In addition, to better use feature information, the channel attention module is introduced in the decoder to highlight the important channel features and suppress the unimportant channels. Due to blurred boundaries, pixels near the boundaries of the pulmonary artery may be difficult to segment. Therefore, a new contour loss function based on the active contour model is proposed in this study to segment the target region by assigning dynamic weights to false positive and false negative regions and accurately predict the boundary structure. RESULTS: The experimental results show that the segmentation accuracy of this proposed method is significantly improved in comparison with state-of-the-art segmentation methods, and the Dice coefficient is 0.938 ± 0.035, which is also confirmed from the 3D reconstruction results. CONCLUSIONS: Our proposed method can accurately segment pulmonary artery structure. This new development will provide the possibility for further rapid diagnosis of pulmonary artery diseases such as pulmonary embolism. Code is available at https://github.com/Yuanyan19/PA-Net.

The SGK3-triggered ubiquitin-proteasome degradation of podocalyxin (PC) and ezrin in podocytes was associated with the stability of the PC/ezrin complex.

Podocyte damage is commonly accompanied by destabilization of the podocalyxin (PC)/ezrin complex. Serum- and glucocorticoid-inducible kinase 3 (SGK3) plays a role in the maintenance of podocyte function, but the details of this role are poorly understood. Herein we demonstrated that SGK3 and its downstream target protein neural precursor cell expressed developmentally downregulated protein 4 subtype 2 (Nedd4-2) triggered PC and ezrin interaction. In adriamycin (ADR)-induced nephritic mice, and after puromycin aminonucleoside (PAN)-induced podocyte damage in vitro, PC and ezrin protein expression levels decreased significantly, while Nedd4-2 activity increased. Moreover, PAN treatment increased PC and ezrin ubiquitination and decreased PC/ezrin interaction in cultured mouse podocytes. The downregulation of SGK3 activity in mouse podocytes resulted in decreased PC and ezrin protein expression and increased the ubiquitin-proteasome degradation of PC and ezrin. Furthermore, upregulation of SGK3 activity mostly reversed the PAN-induced decrease in PC and ezrin protein expression. Overexpression of Nedd4-2 led to decreased ezrin protein expression via the upregulation of ezrin ubiquitination. In contrast, Nedd4-2 knockdown resulted in increased ezrin protein expression but decreased ezrin ubiquitination. In PC-transfected human embryonic kidney (HEK293T) cells, SGK3 activity downregulation and Nedd4-2 overexpression resulted in decreased PC/ezrin interaction. These results suggested that SGK3 triggers the ubiquitin-proteasome degradation of PC and ezrin, while the SGK3/Nedd4-2 signaling pathway regulates ezrin, but not PC, ubiquitination. Thus SGK3 helps to regulate podocyte function by maintaining the stability of the PC/ezrin complex.

Lack of serum- and glucocorticoid-inducible kinase 3 leads to podocyte dysfunction.

Serum- and glucocorticoid-inducible kinase 3 (SGK3) is a downstream mediator of PI3K, which is essential for maintaining the functional integrity of podocytes. However, little is known about the role of SGK3 in podocyte function. Herein, we demonstrated that SGK3 contributes to the maintenance of podocyte integrity. Conditionally immortalized mouse podocyte cells (MPCs) were treated with puromycin aminonucleoside (PAN). PAN treatment inhibited the activity of SGK3 and the expression of podocin. Short hairpin RNA (shRNA)-mediated knockdown of SGK3 also reduced podocin expression in the absence of PAN. Adriamycin (ADR)-treated mice developed proteinuria and had decreased renal glomerular SGK3 expression in comparison to control mice. Consistent with a role for SGK3 in the ADR effect, SGK3 knockout (KO) mice had markedly reduced kidney podocin expression and significantly elevated proteinuria compared with wild-type mice. Electron microscopy revealed that SGK3 KO mice displayed partial effacement of podocyte foot processes. Further, a SGK3 target protein, glycogen synthase kinase-3 (GSK3), was discovered to be dramatically activated in PAN and SGK3 shRNA-treated MPCs and in SGK3 KO mice. Taken together, these data strongly suggest that SGK3 plays a significant role in regulating podocyte function, likely by controlling the expression and activity of GSK3.-Peng, L.-Q., Zhao, H., Liu, S., Yuan, Y.-P., Yuan, C.-Y., Mwamunyi, M.-J., Pearce, D., Yao, L.-J. Lack of serum- and glucocorticoid-inducible kinase 3 leads to podocyte dysfunction.

Glycogen Synthase Kinase-3 Modulates Hyperosmotic-Induced Urea Transporter A1 Relocation in the Inner Medullary Collecting Duct Cells.

AIM: Glycogen synthase kinase 3 (GSK3) regulates urine concentration by mediating the vasopressin-induced aquaporin 2 expression and water permeability, although it is unknown whether GSK3 also mediates the accumulation of the urea transporter A1 (UT-A1). The aim of this study is to investigate the effect of GSK3 on UT-A1 distribution. METHODS: Mouse inner medullary collecting duct 3 cells were transfected with UT-A1-GFP construct. The stable transfected cells were cultured under hypertonic conditions, treated with GSK3 inhibitor lithium chloride, GSK3 activator, lysosome or proteasome inhibitor. The expression levels of UT-A1, GSK3, and phospho-GSK3 were analyzed using western blot. The interaction between UT-A1 and the Golgi apparatus was examined using confocal immunofluorescence microscope. The UT-A1 trafficking was examined using the biotinylation of surface membranes. RESULTS: UT-A1 dissociated away from the Golgi apparatus and translocated to the plasma membrane under hypertonic-NaCl and NaCl plus urea stimulation. This movement was accompanied by the increased phosphorylation of GSK3 and its localization on the cellular membrane. Moreover, these results were duplicated by treating the cells with the GSK3 inhibitor, and by contrast, were partially reversed by the GSK3 activator. Treating cells with a lysosome or proteasome inhibitor failed to attenuate the effects of hypertonic stimulus, indicating that the loss of UT-A1 from the Golgi was not due to degradation. CONCLUSION: Our results suggest that GSK3 may in part modulate the hypertonic-induced intracellular UT-A1 redistribution and its accumulation on the plasma membrane, which may constitute another mechanism by which GSK3 modulates urine concentration.