Objective To observe the value of deep learning model for automatically segmenting prostate on large-field T2WI based on integrated 68Ga-prostate specific membrane antigen(PSMA)PET/MRI.Methods Ninety male patients with prostate tumors who underwent 68Ga-PSMA PET/MRI were retrospectively enrolled and divided into training set(n=72)and validation set(n=18)at the ratio of 4∶1.Models were established based on 3D SegResNet and 3D Unet deep learning neural networks,respectively.Taken physicians'manual segmentation results as reference standards,the performances of models for segmenting the peripheral zone(PZ)and central zone(CZ)+transition zone(TZ)of prostate on large-field T2WI were evaluated.Results In both training and validation sets,the Dice similarity coefficient(DSC)of 3D SegResNet deep learning model for segmenting prostate on T 2WI were both higher than that of 3D Unet model(both P＜0.05),the 95％Hausdorff distance(HD95)of SegR esNet deep learning model for segmenting prostate CZ+TZ was lower than that of 3D Unet model(both P＜0.05),while DSC and HD95 of these 2 models for segmenting prostate CZ+TZ were superior to PZ(all P＜0.05).Conclusion 3D SegResNet deep learning model could be used to automatically segment prostate on large-field T2WI based on integrated 68Ga-PSMA PET/MRI.

Objective:To investigate the role of Pink1/Parkin-induced mitophagy in acute lung injury of exertional heat stroke rats.Methods:Sixty SD rats were randomly divided into four groups, including normal group (CON group), normal Parkin overexpression group (CON+Parkin group), heat stroke group (EHS group) and heat stroke Parkin overexpression group (EHS+Parkin group), with fifteen rats in each group. The rat model of exertional heat stroke was established and the survival curve was drawn. Pulmonary coefficient and pulmonary capillary permeability were detected. HE staining was used to observe the pathological changes of lung tissue. ELISA was used to detect the contents of IL-6, IL-1β, TNF-α and ROS in lung tissue; immunohistochemistry was used to observe apoptosis in lung tissue; Western blot was used to determine the expression of Pink1, Parkin, P62 and LC3 in rat lung tissue, and the LC3II/LC3I ratio was calculated. Single factor multi-level group comparison was performed by single factor analysis of variance, SNK-q method was used to further pairwise comparison between groups.Results:Compared with the normal group, the survival rate of EHS group was decreased ( P<0.001), lung coefficient and pulmonary vascular permeability were increased [(4.39±0.42), (33.38±8.29) μg/g, P<0.05)], lung tissue was exudative and solid, the levels of inflammatory factors IL-6, IL-1β, TNF-α and ROS were significantly increased[(34.31±5.34) pg/mL, (34.03±4.78) pg/mL, (91.64±8.16) pg/mL, (259.01±89.17) U/mg, P<0.05)], and apoptosis was increased. Western and immunohistochemistry results showed that the expressions of Pink1 and Parkin were decreased, co-location of Pink1and Parkin was attenuated, LC3II/LC3I were decreased, and P62 expression was increased. Compared with the EHS group, the survival rate of EHS+Parkin group was significantly increased ( P<0.05), lung coefficient and pulmonary vascular permeability were decreased [(3.83±0.62), (22.49±7.90) μg/g, P<0.05)], exudation and consolidation and other pathological changes were significantly reduced, and the levels of the above inflammatory factors and ROS were significantly decreased [(14.09±3.24) pg/mL, (26.94±2.11) pg/mL、(63.35±11.62) pg/mL, (161.13±26.31) U/mg, P<0.05]. Lung tissue apoptosis was reduced. The co-location of Pink1and Parkin、Parkin expression and LC3II/LC3I ratio were increased ( P<0.05), P62 expression was decreased( P<0.05), while Pink1 expression was not significant different (q=0.75). There was no difference between normal group and normal Parkin overexpression group (q=0.95). Conclusion:Activation of Pink1/Parkin-induced mitophagy can alleviate the acute lung injury in exertional heat stroke rats.