Objective:To develop a deep learning model based on super-resolution endorectal ultrasound（ERUS）images for the preoperative prediction of perineural invasion（PNI）in patients with rectal cancer，thereby providing a reference for risk stratification and individualized treatment planning.Methods:A retrospective analysis was conducted on 382 patients with rectal cancer who underwent total mesorectal excision at Fujian Medical University Union Hospital between June 2019 and February 2024. Patients were randomly divided into a training set（ n=305）and a test set（ n=77）at a ratio of 8∶2，and further grouped into PNI-negative group and PNI-positive group subgroups based on pathological results. Super-resolution ultrasound images were generated from original ERUS images using a generative adversarial network（GAN）. Deep convolutional neural networks were developed based on features from intratumoral and peritumoral regions to identify the optimal region of interest（ROI）. The dSR5_ResNet18 and dSR5_ResNet50 models were constructed using the super-resolution images with a 5-pixel peritumoral extension. Representative clinical features were selected for subgroup analysis based on sample size and intergroup statistical differences between PNI-positive and PNI-negative patients. Forest plots were used to evaluate model applicability and robustness across subgroups. Results:The dSR5_ResNet18 model，built using super-resolution images of the tumor combined with a 5-pixel peritumoral region，achieved the best predictive performance，with an AUC of 0.867（95% CI=0.782 - 0.952）in the test set. Decision curve analysis demonstrated that the dSR5_ResNet18 model provided the greatest net clinical benefit. Forest plot analysis indicated strong generalizability of the models across subgroups such as pathological N stage，maximum lesion length，and lymph node enlargement，though relatively weaker performance was observed in the carcinoembryonic antigen（CEA）subgroup. Among all models，dSR5_ResNet18 exhibited the most consistent performance across subgroups，with the narrowest confidence intervals and highest robustness. Conclusions:The deep learning model incorporating ERUS-based super-resolution reconstruction demonstrated excellent performance in the preoperative prediction of PNI in rectal cancer. It offers significant advantages in image quality and generalizability，and may serve as a valuable tool to assist clinicians in formulating personalized treatment strategies.

Objective:To develop a deep learning model based on super-resolution endorectal ultrasound（ERUS）images for the preoperative prediction of perineural invasion（PNI）in patients with rectal cancer，thereby providing a reference for risk stratification and individualized treatment planning.Methods:A retrospective analysis was conducted on 382 patients with rectal cancer who underwent total mesorectal excision at Fujian Medical University Union Hospital between June 2019 and February 2024. Patients were randomly divided into a training set（ n=305）and a test set（ n=77）at a ratio of 8∶2，and further grouped into PNI-negative group and PNI-positive group subgroups based on pathological results. Super-resolution ultrasound images were generated from original ERUS images using a generative adversarial network（GAN）. Deep convolutional neural networks were developed based on features from intratumoral and peritumoral regions to identify the optimal region of interest（ROI）. The dSR5_ResNet18 and dSR5_ResNet50 models were constructed using the super-resolution images with a 5-pixel peritumoral extension. Representative clinical features were selected for subgroup analysis based on sample size and intergroup statistical differences between PNI-positive and PNI-negative patients. Forest plots were used to evaluate model applicability and robustness across subgroups. Results:The dSR5_ResNet18 model，built using super-resolution images of the tumor combined with a 5-pixel peritumoral region，achieved the best predictive performance，with an AUC of 0.867（95% CI=0.782 - 0.952）in the test set. Decision curve analysis demonstrated that the dSR5_ResNet18 model provided the greatest net clinical benefit. Forest plot analysis indicated strong generalizability of the models across subgroups such as pathological N stage，maximum lesion length，and lymph node enlargement，though relatively weaker performance was observed in the carcinoembryonic antigen（CEA）subgroup. Among all models，dSR5_ResNet18 exhibited the most consistent performance across subgroups，with the narrowest confidence intervals and highest robustness. Conclusions:The deep learning model incorporating ERUS-based super-resolution reconstruction demonstrated excellent performance in the preoperative prediction of PNI in rectal cancer. It offers significant advantages in image quality and generalizability，and may serve as a valuable tool to assist clinicians in formulating personalized treatment strategies.

OBJECTIVE: To explore the effect of occupational high temperature exposure on type 2 diabetes( T2 DM) in male steel workers. METHODS: A cluster random sampling method was used to select 684 male steel workers,who exposed to occupational high temperature in a steel enterprise in Tangshan City,as the high temperature group,and 1 153 male steel workers without occupational high temperature exposure as the control group. The high temperature level of workers in these two groups was measured. The cumulative exposure( CE) of high temperature was calculated,and occupational health exam was performed. The multivariate logistic regression analysis and restricted cubic splines were used to analyze the relationship between high temperature CE and T2 DM. RESULTS: The prevalence of T2 DM in high-temperature group was higher than that in the control group( 13. 0% vs 7. 9%,P < 0. 05). The multivariate logistic regression analysis results showed that the risk of T2 DM in the high temperature group was higher than that in the control group after adjusting for age,body mass index,smoking,drinking,physical exercise and parents with diabetes( P < 0. 05). The 95% confidence interval was 1. 65( 1. 17-2. 33). Restricted cubic spline analysis showed that the high temperature CE was correlated with the prevalence of T2 DM in workers( P < 0. 01) and showed a linear correlation( nonlinearity test,P > 0. 05). CONCLUSION: Occupational high temperature exposure is associated with the occurrence of T2 DM in male steel workers. The male steel workers with high temperature CE show high prevalence of T2 DM risk.

OBJECTIVE: To investigate the behavioral and ultrastructural changes of intrathecal administration of different concentrations of ropivacaine for 12 h. METHODS: Thirty male SD rats were randomly divided into 5 groups (6 rats in each group):group N (control), group A (ropivacaine 0.25%), group B (ropivacaine 0.5%), group C (ropivacaine 0.75%),and group D (ropivacaine 1.0%). A polyurethane microcatheter was inserted into the lumbar subarachnoid space 8 cm according to Yakshos intrathecal administration. The rats in group N received saline 0.12 mL/kg for 8 times at 1.5 h interval through the catheter, and the rats in the other groups received different concentrations of ropivacaine in the same way as in group N. The poster paw withdrawal latency to heat (PWHL) and mechanical stimulation (von Fray filament) (PWML) were measured the day before the intrathecal administration and 12 hours after the first intrathecal administration of ropivacaine. Motor function (MF) was measured after the last intrathecal administration. After the behavior test, the rats were sacrificed and the lumber segments of the spinal cord were immediately removed for electron microscopic examination. RESULTS: A total hind limb paralysis was seen at 30 seconds and intramuscular strain gradually came back 10~60 minutes after the intrathecal administration of ropivacaine in group A, B, C, and D, but not in group N. The recovery time of motor block of group A was the shortest (P<0.05), that of group D was the longest,and that of group B and C was between group A and D. Intrathecal administration of different concentrations of ropivacaine did not affect the percent maximum possible effect (%MPE) of PWHL and PWML. Electron microscopic examination showed that the spinal cords were normal in group N and A, slight edema of mitochondria and endoplasmic reticulum (ER) in group B, loosened fibrous layers in medullary sheath, edema and local degeneration of neuraxis in group C,and shrinkage of nuclear membrane, serious edema of ER, vacuolus change of mitochondria and local demyelination in group D. CONCLUSION Ropivacaine (0.5%, 0.75%, and 1.0%) administered intrathecally for 12 hours causes different degrees of ultrastructural changes in the spinal cord depending on concentrations.
Amides ; administration & dosage ; toxicity ; Anesthetics, Local ; administration & dosage ; toxicity ; Animals ; Behavior, Animal ; drug effects ; Dose-Response Relationship, Drug ; Injections, Spinal ; Male ; Microscopy, Electron ; Random Allocation ; Rats ; Rats, Sprague-Dawley ; Ropivacaine ; Spinal Cord ; ultrastructure