The application of minimally invasive surgical tool detection and tracking technology based on deep learning in minimally invasive surgery is currently a research hotspot. This paper firstly expounds the relevant technical content of the minimally invasive surgery tool detection and tracking, which mainly introduces the advantages based on deep learning algorithm. Then, this paper summarizes the algorithm for detection and tracking surgical tools based on fully supervised deep neural network and the emerging algorithm for detection and tracking surgical tools based on weakly supervised deep neural network. Several typical algorithm frameworks and their flow charts based on deep convolutional and recurrent neural networks are summarized emphatically, so as to enable researchers in relevant fields to understand the current research progress more systematically and provide reference for minimally invasive surgeons to select navigation technology. In the end, this paper provides a general direction for the further research of minimally invasive surgical tool detection and tracking technology based on deep learning.
Brain image segmentation algorithm based on deep learning is a research hotspot at present. In this paper, firstly, the significance of brain image segmentation and the content of related brain image segmentation algorithm are systematically described, highlighting the advantages of brain image segmentation algorithms based on deep learning. Then, this paper introduces current brain image segmentation algorithms based on deep learning from three aspects: the brain image segmentation algorithms based on problems existent to brain image, the brain image segmentation algorithms based on prior knowledge guidance and the application of general deep learning models in brain image segmentation, so as to enable researchers in relevant fields to understand current research progress more systematically. Finally, this paper provides a general direction for the further research of brain image segmentation algorithm based on deep learning.
Objective To investigate the preventive therapeutic effects of CPD1, a novel phosphodiesterase 5 inhibitor, on lung pathological phenotype and interstitial fibrosis of lung in pulmonary fibrosis model rats caused by bleomycin (BLM). Methods Rats were randomly divided into a sham surgery group (n=10), a model group (n=14), a CPD1 treatment group (n=13), and a nintedanib positive control drug treatment group (n=13). Pulmonary fibrosis model was constructed by slowly instilling BLM (3 mg/kg) into the left bronchus in the model group and two treatment groups. Two hours after BLM infusion, the rats were treated with CPD1 (20 mg·kg–1·d–1), or positive control drug nintedanib (50 mg·kg–1·d–1) by intragastric administration, respectively, for 2 weeks. To observe the effect of CPD1 treatment on pathological structural damage, collagen deposition, and the expression of fibronectin (Fn), α-smooth muscle actin (α-SMA), Collagen Ⅰ, and E-cadherin (E-Cad) in the affected lung tissues of unilateral pulmonary fibrosis rats. Moreover, to further observed the effects of CPD1 intervention on the expression of transforming growth factor β1 (TGF-β1) and Smad3 in the cell model of human alveolar basal epithelial A549 cells. Results Compared with the control group, the lung tissue structure was seriously damaged in the BLM group, and with expansion of the alveolar space, collapse of the alveolar lumen. Significant widening of the alveolar septum and thickening of the alveolar wall were observed in the BLM group. There was a marked increase in collagen deposition in the thickened walls of the BLM group. Moreover, the expressions of Fn, α-SMA, Collagen Ⅰ, TGF-β and Smad3 were increased, while the expression of E-Cad significantly decreased in the BLM group (all P<0.05). Compared with the BLM group, the lung tissue damage was significantly improved in the CPD1 group rats. Furthermore, CPD1 inhibit the expression of Fn, α-SMA, Collagen Ⅰ, TGF-β and Smad3, and upregulate the expression of E-Cad (all P<0.05). Conclusions Prophylactic treatment with phosphodiesterase 5 inhibitor CPD1 strongly attenuates BLM-induced pulmonary fibrosis by inhibiting the lung injury and inflammation response via targeting TGF-β/Smad pathway, reducing the deposition of extracellular matrix.