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.
Confocal laser endomicroscopy technology can obtain cell-level images in real time and in situ, which can assist doctors in real-time intraoperative diagnosis, but its non-invasiveness makes it difficult to relocate the optical biopsy site. The confocal probe localization algorithm can automatically calculate the coordinates of the probe tip, that is, the coordinates of the optical biopsy site. In this paper, a confocal probe localization algorithm based on region growing and endoscope size prior was proposed. The algorithm detected the probe region by region growing on the probe edge image, then searched for tip points based on a given probe axis, and iteratively optimized it. Finally, based on the single-degree-of-freedom motion characteristics of the probe, the three-dimensional coordinates of the tip of the probe were calculated by using the prior information of the size of the endoscope, which solved the scale uncertainty problem of the monocular camera. The confocal probe localization algorithm was tested on the dataset collected in this paper. The results showed that our algorithm no longer relied on the color information of the probe, avoided the influence of uneven illumination on the gray value of the probe pixels, and had a more robust location accuracy and running speed. Within the length of the probe extending out of the endoscope from 0 to 5 cm, the pixel error could be as low as 11.76 pixels, and the average relative position error could be as low as 1.66 mm, which can achieve the real-time and accurate localization of the confocal probe.
Objective To investigate the effect of bone morphogenetic protein 2 (BMP-2) and dexamethason (DXM) on proliferation and differentiation of human dental pulp cellsin vitro. Methods Primary human dental pulp cells were cultured in vitro by tissue culture method. The 3rd generation cells were used to identify cell phenotype for vimentin and cytokeratin by immunocytochemistry staining. The 3-5 generations of human dental pulp cells were randomly divided into 4 groups: 100 ng/mL BMP-2 (group A), 1×10–8 mol/L DXM (group B), and both 100 ng/mL BMP-2 and 1×10–8 mol/L DXM (group C) were added; neither BMP-2 nor DXM was added in group D as control group. The cell growth curve was drawn at 1, 3, 5, and 7 days after culture. The expressions of osteo/dentanogenic genes including alkaline phosphatase (ALP), dentin sialophoshoprotein (DSPP), and dentin matrix protein 1 (DMP-1) were detected by RT-PCR analysis at 5 and 7 days after culture, the ratio between the positive staining area and the total area by ALP staining at 14 days, and absorbance (A) value at 562 nm by alizarin red staining at 21 days after culture. Results Human dental pulp cells were successfully isolated and cultured, which were long fusiform and showed a positive reaction for vimentin and a negative reaction for cytokeratin. The growth curve indicated that cells increased with the extending of incubation time, reached a peak at 5 days, then reduced at 7 days to the level at 3 days. At 5 days after culture, the cells were significantly more in groups A, B, and C than group D (P<0.05), in group C than group A (P<0.05), and in group A than group B (P<0.05). RT-PCR analysis showed that the mRNA expressions of ALP, DSPP, and DMP-1 at 5 days were significantly higher in groups A, B, and C than group D (P<0.05), and in group C than groups A and B (P<0.05), but no significant difference was found between groups A and B (P>0.05); the mRNA expression of DSPP in groups A, B, and C was significantly higher than that in group D (P<0.05), but there was no significant difference in mRNA expressions between other groups at 7 days (P>0.05). At 14 days, positive staining in varying degrees was observed in each group, especially in group C; the ratio between the positive staining area and the total area was significantly higher in group C than groups A, B, and D (P<0.05), and in groups A and B than group D (P<0.05), but there was no significant difference between groups A and B (P>0.05). At 21 days, there were a variety of mineralized nodules in groups A, B, and C in nonuniformly scattered or clustered distribution, but no mineralized nodules were observed in group D. TheA values of mineralized nodules showed significant difference between groups (P<0.05). Conclusion BMP-2 may be more effective in promoting proliferation of human dental pulp cells than DXM. Combined application of BMP-2 and DXM can remarkably promote the proliferation and differentiation of human dental pulp cells.