Application value of a deep learning method based on a 3D V-Net convolutional neural network in the recognition and segmentation of the auditory ossicles.

Objective: To explore the feasibility of a deep learning three-dimensional (3D) V-Net convolutional neural network to construct high-resolution computed tomography (HRCT)-based auditory ossicle structure recognition and segmentation models. Methods: The temporal bone HRCT images of 158 patients were collected retrospectively, and the malleus, incus, and stapes were manually segmented. The 3D V-Net and U-Net convolutional neural networks were selected as the deep learning methods for segmenting the auditory ossicles. The temporal bone images were randomized into a training set (126 cases), a test set (16 cases), and a validation set (16 cases). Taking the results of manual segmentation as a control, the segmentation results of each model were compared. Results: The Dice similarity coefficients (DSCs) of the malleus, incus, and stapes, which were automatically segmented with a 3D V-Net convolutional neural network and manually segmented from the HRCT images, were 0.920 ± 0.014, 0.925 ± 0.014, and 0.835 ± 0.035, respectively. The average surface distance (ASD) was 0.257 ± 0.054, 0.236 ± 0.047, and 0.258 ± 0.077, respectively. The Hausdorff distance (HD) 95 was 1.016 ± 0.080, 1.000 ± 0.000, and 1.027 ± 0.102, respectively. The DSCs of the malleus, incus, and stapes, which were automatically segmented using the 3D U-Net convolutional neural network and manually segmented from the HRCT images, were 0.876 ± 0.025, 0.889 ± 0.023, and 0.758 ± 0.044, respectively. The ASD was 0.439 ± 0.208, 0.361 ± 0.077, and 0.433 ± 0.108, respectively. The HD 95 was 1.361 ± 0.872, 1.174 ± 0.350, and 1.455 ± 0.618, respectively. As these results demonstrated, there was a statistically significant difference between the two groups (P < 0.001). Conclusion: The 3D V-Net convolutional neural network yielded automatic recognition and segmentation of the auditory ossicles and produced similar accuracy to manual segmentation results.

[Effects of human cytomegalovirus on the cell cycle of duct epithelial cell cultures of human salivary gland in vitro and relative mechanism].

OBJECTIVE: To investigate the effects of human cytomegalovirus (HCMV) on the cell cycle of duct epithelial cell cultures of human salivary gland (HSG) in vitro and relative mechanism. METHODS: HSG was cultured in vitro. Reverse transcriptase polymerase chain reaction (RT-PCR) and nest-RT-PCR were used respectively to investigate ie1/ie2 transcription in HSG infected by human cytomegalovirus(HCMV). The effects of HCMV on the cell cycle of HSG were studied by flow cytometry in vitro. The expression of cyclin D1 in HSG infected by HCMV was detected by Western blotting. RESULTS: HCMV iel/ie2 transcription could be detected in HSG infected by HCMV. HCMV arrested productively infected cells in G1 stage. And cyclin D1 was down-regulated in HCMV infected HSG. CONCLUSION: HCMV inhibits proliferation of HSG by affecting G1/S check point and down-regulating cyclin D1 in vitro.

[Expression of Toll-like receptors in human bone marrow mesenchymal stem cells].

The aim of this study was to explore the characteristics of Toll-like receptor expression in mesenchymal stem cells derived from bone marrow of healthy donor (BM-MSCs). BM-MSCs were isolated from bone marrow of healthy donor by Ficoll method. Expressions of CD34, CD45, HLA-DR, CD44 and CD71 in BM-MSCs were detected by flow cytometry. CD71 in BM-MSCs was assayed by immunocytochemistry. The adipocyte and osteoblast induction of BM-MSCs were detected by alizarin red stain and oil red stain respectively. TLR 1 - 10 mRNA levels in BM-MSCs were evaluated by semiquantitative RT-PCR. The results showed that expressions of CD34, CD45 and HLA-DR in BM-MSC were negative while the expressions of CD44 and CD71 were positive. CD71 in BM-MSCs was positive. After induced by osteoblast and adipocyte inductor, BM-MSCs were positive for alizarin red staining and oil red staining respectively. All of TLR 1 - 10 mRNA were found in BM-MSCs with high expression levels of TLR2, TLR3, TLR4, TLR7, TLR8, TLR9 and low expression levels of TLR1, TLR5, TLR6, TLR10. In conclusion, different levels of TLR 1 - 10 mRNA were expressed in BM-MSCs of healthy donor.