Fully Automatic Deep Learning Model for Spine Refracture in Patients with OVCF: A Multi-Center Study.

BACKGROUND: The reaserch of artificial intelligence (AI) model for predicting spinal refracture is limited to bone mineral density, X-ray and some conventional laboratory indicators, which has its own limitations. Besides, it lacks specific indicators related to osteoporosis and imaging factors that can better reflect bone quality, such as computed tomography (CT). OBJECTIVE: To construct a novel predicting model based on bone turn-over markers and CT to identify patients who were more inclined to suffer spine refracture. METHODS: CT images and clinical information of 383 patients (training set = 240 cases of osteoporotic vertebral compression fractures (OVCF), validation set = 63, test set = 80) were retrospectively collected from January 2015 to October 2022 at three medical centers. The U-net model was adopted to automatically segment ROI. Three-dimensional (3D) cropping of all spine regions was used to achieve the final ROI regions including 3D_Full and 3D_RoiOnly. We used the Densenet 121-3D model to model the cropped region and simultaneously build a T-NIPT prediction model. Diagnostics of deep learning models were assessed by constructing ROC curves. We generated calibration curves to assess the calibration performance. Additionally, decision curve analysis (DCA) was used to assess the clinical utility of the predictive models. RESULTS: The performance of the test model is comparable to its performance on the training set (dice coefficients of 0.798, an mIOU of 0.755, an SA of 0.767, and an OS of 0.017). Univariable and multivariable analysis indicate that T_P1NT was an independent risk factor for refracture. The performance of predicting refractures in different ROI regions showed that 3D_Full model exhibits the highest calibration performance, with a Hosmer-Lemeshow goodness-of-fit (HL) test statistic exceeding 0.05. The analysis of the training and test sets showed that the 3D_Full model, which integrates clinical and deep learning results, demonstrated superior performance with significant improvement (p-value < 0.05) compared to using clinical features independently or using only 3D_RoiOnly. CONCLUSION: T_P1NT was an independent risk factor of refracture. Our 3D-FULL model showed better performance in predicting high-risk population of spine refracture than other models and junior doctors do. This model can be applicable to real-world translation due to its automatic segmentation and detection.

The ROS-associated programmed cell death causes the decline of pollen viability recovered from cryopreservation in Paeonia lactiflora.

KEY MESSAGE: After cryopreservation, the occurrence of apoptosis-like programmed cell death events induced by the accumulation of ROS reduces pollen viability. Cryopreservation, as a biotechnological means for long-term preservation of pollen, has been applied to many species. However, after cryopreservation, the viability of pollen significantly decreases via a mechanism that is not completely clear. In this study, the pollen of Paeonia lactiflora 'Zi Feng Chao Yang', which exhibits significantly reduced viability after liquid nitrogen (LN2) storage, was used to study the relationship among pollen viability, programmed cell death (PCD) and reactive oxygen species (ROS). The apoptosis rate was increased significantly in pollen with decreased viability after cryopreservation, and the changes in ROS generation and hydrogen peroxide (H2O2) were consistent with the apoptosis rate. Correlation analysis results showed that the apoptosis rate is positively correlated with ROS generation and H2O2 content. In addition, ascorbic acid (AsA), glutathione (GSH) and ascorbic acid reductase (APX) levels were significantly correlated with ROS and H2O2. After LN2 preservation for 8 months, the exogenous antioxidants AsA and GSH at appropriate concentrations significantly decreased H2O2 content, inhibited PCD indicator levels, and increased cryopreserved pollen viability. These observations suggest that PCD occurred in pollen during LN2 preservation for 1-8 months and was induced by the accumulation of ROS in pollen after cryopreservation, thus explaining the main reasons for the reduction in pollen viability after cryopreservation in LN2.

Changes of pollen viability of ornamental plants after long-term preservation in a cryopreservation pollen bank.

This study determined the changes in pollen viability of 102 species/cultivars of ornamental plants (affiliated to 32 genera of 14 families) following long-term liquid nitrogen storage in a cryopreservation pollen bank. The goal was to provide information on the safety and stability of pollen cryopreservation technology. Fresh pollen at the time of storage was used as the control, and the study examined the pollen viability of ornamental plants cryopreserved for 8, 9, or 10 years. The results show that pollen of the 102 species/cultivars in the cryopreservation pollen bank retained viability ranging from 1% to 58%, After long-term storage there were changes in viability: 11.76% (12 species/cultivars) had increased viability, 16.67% (17 species/cultivars) had stable viability, and the viability of 71.57% (73 species/cultivars) showed a decreasing trend.