Objective To explore the efficiency improvement in segmenting neural network with the application of Transformer + U-Net artificial intelligence (AI) and modeling with the application of Python scripts in three-dimensional (3D) printing brachytherapy. Methods A Transformer + U-Net AI neural network model was constructed, and Adam optimizer was used to ensure rapid gradient descent. Computed tomography or magnetic resonance imaging data of patients were standardized and processed as self-made data sets. The training set was used to train AI and the optimal result weight parameters were saved. The test set was used to evaluate the AI ability. Python programming language was used to write an automated script to obtain the output segmentation image and convert it to the STL file for import. The source applicator and needle could be automatically modeled. The time of automatic segmentation and modeling and the time of manual segmentation and modeling were entered by two people, and the difference was verified by paired t-test. Results Dice similarity coefficient (DSC), mean intersection over union (MIOU), and Hausdorff distance (HD95) were used for evaluation. DSC was 0.9341, MIOU was 0.8762, and mean HD95 was 2.516. The mean time of manual segmentation was 1187 s, and the mean time of AI segmentation was 145 s (P < 0.01). The mean time of manual modeling was 321 s, and the mean time of modeling with Python automated scripts was 18 s (P < 0.01). Conclusion The application of Transformer + U-Net automatic segmentation and Python automated scripts can effectively improve work efficiency in the 3D printing brachytherapy for cervical cancer.

Diabetic retinopathy(DR), a major microvascular complication of diabetes, is driven by hyperglycemia-induced oxidative stress, chronic inflammation, and neurodegeneration. Post-translational modifications(PTM)play pivotal roles in DR progression by dynamically regulating protein functions. Key PTMs, including phosphorylation, acetylation, ubiquitination, and O-glcNAcylation, collectively exacerbate vascular dysfunction, inflammatory responses, metabolic dysregulation, and neuronal damage. The intricate crosstalk among PTM underscores the multifaceted pathology of DR. Future research should focus on elucidating PTM interaction networks, developing targeted modulators, and leveraging advanced technologies to uncover their roles in retinal cellular heterogeneity, thereby advancing precision therapeutic strategies for DR.

Objective:To investigate the diagnostic value and influencing factors of endoscopic ultrasonography (EUS) for detecting rectal neuroendocrine neoplasms (R-NENs).Methods:A retrospective case-control study was performed on data of patients with suspected R-NENs by white light endoscopy who underwent endoscopic diagnosis and treatment or surgical operation and obtained pathological diagnosis at the Affiliated Hospital of Qingdao University from March 2016 to June 2023. Clinical data, EUS characteristics and pathological results were statistically analyzed, and the diagnostic accuracy of EUS for R-NENs were obtained by comparing the EUS results with the pathological results. Influencing factors affecting accuracy were analyzed by using the binary logistic regression model.Results:A total of 317 patients were included. The sensitivity, the specificity, the positive predictive value and the negative predictive value of EUS in diagnosing R-NENs were 98.03% (249/254), 34.92% (22/63), 85.86% (249/290) and 81.48% (22/27) respectively. The accuracy was 85.49% (271/317) and the Jorden index was 0.33. Tumor size ≤5 mm ( P=0.002, OR=2.892, 95% CI: 1.464-5.713), absence of surface vascular dilation ( P=0.019, OR=2.613, 95% CI: 1.170-5.837), normal tumor coloration ( P=0.001, OR=3.460, 95% CI: 1.645-7.279) and erythematous surface appearance ( P=0.048, OR=7.242, 95% CI: 1.015-51.680) were independent risk factors affecting the accuracy of R-NENs diagnosis by EUS. Depth assessment accuracy of EUS was 76.77% (195/254), with echo heterogeneity ( P<0.001, OR=4.008, 95% CI: 1.980-8.113) and surface depression ( P=0.035, OR=2.664, 95% CI: 1.073-6.615) emerging as significant factors affecting invasion depth evaluation. Conclusion:EUS demonstrates substantial clinical utility for R-NENs assessment, with diagnostic performance being significantly associated with tumor morphology and sonographic features. Macroscopic characteristics including tumor size, vascular patterns, and chromatic features influence diagnostic accuracy, while echo-textural heterogeneity and surface depression affect invasion depth precision. These findings underscore the clinical relevance of comprehensive EUS evaluation in R-NENs management.

Objective To investigate the effects and underlying mechanisms of down-regulating m6A demethylase fat mass and obesity-associated protein(FTO)on proplatelet formation in the MEG-01 megakaryocytic cells.Methods ①MEG-01 cells were treated with 1 nmol/L phorbol myristate acetate(PMA)(treatment group)or DMSO(control group)for 72 h.FTO expression was measured by Western blotting and RT-qPCR.② MEG-01 cells were infected with targeted FTO shRNA(knockdown group,sh-FTO)or negative control shRNA(negative control group,sh-NC)viruses.FTO knockdown group and negative control group MEG-1 cells were treated with 1 nmol/L PMA for 72 h,and the protein and mRNA expression levels of FTO were detected by Western blotting and RT-qPCR.Cell cycle,viability and apoptosis were assessed by propidium iodide(PI)DNA staining,CCK-8 assay and Annexin V-FITC/PI double staining and TUNEL staining.The expression of cleaved Caspase-3 protein was determine by Western blotting.Megakaryocyte maturation was assessed by CD41/CD61 staining.Proplatelet formation was observed under bright field and detected by CD61 immunofluorescence assay.The expression of apoptosis-related molecules(Caspase3,BAD,BAK1,BCL2 and MCL1)was detected by RT-qPCR,and the protein change of BCL2 was further verified by Western blotting.The dataset was screened out from the gene expression omnibus(GEO)database,and then analyzed with University of California,Santa Cruz(UCSC)genome browser to compare the methylation sequencing peaks on BCL2 mRNA,and m6A methylated RNA immunoprecipitation(m6A-RIP)was used to assess the m6A methylation levels of BCL2 target gene mRNAs in MEG-01 megakaryocytes.Then,the changes in the m6A methylation enrichment level of BCL2 mRNA were observed between the sh-NC group and the sh-FTO group.mRNA stability and ribosome profiling assays were performed to assess translational efficiency of target genes.Results ①PMA treatment upregulated the expression of FTO at protein(P＜0.05)and mRNA(P＜0.01)levels.② FTO shRNA resulted in reduced FTO expression at both mRNA and protein levels(P＜0.01).Compared to the negative control group,the FTO knockdown group showed more cells arrested at the G1/S phase[(60.80±1.29)%vs(72.13±1.18)%,P＜0.01],significantly reduced cell viability[(1.17±0.03)%vs(0.69±0.05)%,P＜0.01],increased Annexin V-FITC/PI positive cells[(12.87±0.83)%vs(17.45±1.58)%,P＜0.01],more TUNEL positive cells[(1.03±0.27)%vs(17.49±9.91)%,P＜0.01],enhanced protein level of cleaved Caspase-3(P＜0.01),decreased proportion of CD41/CD61 positive cells[(51.63±1.13)%vs(34.08±0.53)%,P＜0.01],and less proplatelet formation in MEG-01 megakaryocytes[(26.49±6.73)%vs(13.31±5.97)%,P＜0.01].③Compared to sh-NC group,the FTO knockdown group had significantly decreased protein and mRNA expression of anti-apoptotic molecule BCL2(P＜0.01).UCSC GEO sequencing data revealed there were m6A methylation modification sites on BCL2 mRNA,which was verified through m6A-RIP experiment in MEG-01 megakaryocytes.Compared with GAPDH mRNA,BCL2 mRNA exhibited a significantly enriched m6A signal(P＜0.01).Compared to sh-NC group,a significant increase in m6A methylation modification was observed on BCL2 mRNA.BCL2 mRNA stability was significantly decreased,and its translation efficiency significantly was decreased(P＜0.01).Conclusion m6 A demethylase FTO rgulates BCL2 mRNA stability and translation efficiency,thereby promoting proplatelet formation in MEG-01 megakaryocytes.

Objective : To explore the utility of a nomogram integrating contrast-enhanced CT radiomics with clinical features in the preoperative prediction of WHO/ISUP grade for clear cell renal cell carcinoma(ccRCC). Methods: A total of 214 patients with pathologically proven ccRCC who underwent enhanced CT scan before surgery were retrospectively included. According to the WHO/ISUP grade system, the cases were classified into low-grade(grades Ⅰ-Ⅱ) and high-grade(grades Ⅲ-Ⅳ), and then randomly divided into training and test set with a ratio of 4 ∶1. Regions of interest were segmented from both unenhanced and three-phase enhanced images, and radiomic features were extracted. Feature selection and dimensionality reduction were performed using Spearman rank correlation coefficients and LASSO regression, followed by the construction of the radiomic model with the KNN algorithm. Clinical and semantic imaging features were selected through univariate and multivariate analyses, and a clinical model was developed using the KNN algorithm. The clinical and radiomics signatures were used to construct a combined model and a nomogram was developed. The ROC curve and delong test were used to evaluate the diagnostic performance of the model, while calibration and decision curve analyses assessed its accuracy and clinical applicability. Results: 8 clinical features and 11 radiomic features were selected. The combined model, integrating these clinical and radiomics signatures, exhibited robust predictive performance with AUC values of 0.887 in the training set and 0.800 in the test set. The calibration curve demonstrated good consistency between the nomogram model and actual outcomes, while decision curve analysis indicated a favorable net benefit for the nomogram. Conclusion The nomogram constructed by combining radiomics and clinical signatures can provide evidence for preoperative prediction of ccRCC grade and guide clinical decision-making.

Objective:To investigate the interaction of workplace noise, body mass index (BMI) and systemic inflammatory response on hypertension.Methods:In January 2019, 1124 male workers from an automobile factory in Wuhan were selected by cluster random sampling method. The study population was divided into normal body weight group (BMI<24 kg/m 2) and overweight group (BMI≥24 kg/m 2) according to BMI, and were followed up for 3 years. The occupational health examination of the workers was carried out every year, blood routine and blood biochemical indexes were collected, and the information of the workers' age, BMI, type of work and age of exposure to injury were collected through field questionnaires. The noise intensity of the workplace of the enterprise was measured for 3 consecutive years, and the equivalent sound level was calculated according to the working time. Normal and skewness measurements were described by Mean±SD and [ M ( Q1, Q3) ], respectively. t-test or Wilcoxon rank sum test was used for inter-group comparisons. Categorical variables were expressed by frequency and percentage (%), and Chi-square test was used for inter-group comparisons. Mixed effects models and generalized estimation equations were fitted to analyze the relationship between occupational noise, systemic inflammation, and their interaction terms with blood pressure and hypertension risk. Results:Univariate analysis revealed that the white blood cell counts, neutrophil counts, lymphocyte counts and eosinophil counts were positively associated with systolic blood pressure and diastolic blood pressure in overweight group ( n=467), respectively ( P<0.05). The participants with white blood cell counts≥5.94×10 9/L, neutrophil counts≥3.31×10 9/L, lymphocyte counts ≥2.03×10 9/L, and eosinophil counts ≥0.12×10 9/L had increased risk of hypertension by 52% ( RR=1.52, 95% CI: 1.11-2.05), 37% ( RR=1.37, 95% CI: 1.01-1.83), 58% ( RR=1.58, 95% CI: 1.18-2.09), and 52% ( RR=1.52, 95% CI: 1.12-2.06), respectively (all P<0.05). Multivariate analysis found a positive association between BMI and the risk of hypertension in the overweight group ( P<0.05), the participants with lymphocyte counts≥2.03×10 9/L and eosinophil counts≥0.12×10 9/L had increased risk of hypertension by 39% ( RR=1.39, 95% CI: 1.01-1.89) and 46% ( RR=1.46, 95% CI: 1.06-1.98), respectively (all P<0.05). There was no correlation between BMI and the risk of hypertension in normal weight group ( P>0.05). The multiplicative interaction of occupational noise (≥80 dB) with white blood cell counts (≥5.94×10 9/L) and lymphocyte counts (≥2.03×10 9/L) increased the risk of hypertension by 100% ( RR=2.00, 95% CI: 1.06-3.55) and 89% ( RR=1.89, 95% CI: 1.01-3.32) (all P<0.05) in overweight group, respectively. Additionally, a significant additive interaction was observed between noise exposure (≥80 dB) and basophil counts (≥0.03×10 9/L) on hypertension risk in the overweight group (RERI=0.49, 95% CI: 0.02-0.96, P<0.05) . Conclusion:The combined exposure of occupational noise and systemic inflammation may increase the risk of hypertension in overweight workers in automobile manufacturing plants, and the two have additive and multiplicative interactions.

Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective:To investigate the diagnostic value and influencing factors of endoscopic ultrasonography (EUS) for detecting rectal neuroendocrine neoplasms (R-NENs).Methods:A retrospective case-control study was performed on data of patients with suspected R-NENs by white light endoscopy who underwent endoscopic diagnosis and treatment or surgical operation and obtained pathological diagnosis at the Affiliated Hospital of Qingdao University from March 2016 to June 2023. Clinical data, EUS characteristics and pathological results were statistically analyzed, and the diagnostic accuracy of EUS for R-NENs were obtained by comparing the EUS results with the pathological results. Influencing factors affecting accuracy were analyzed by using the binary logistic regression model.Results:A total of 317 patients were included. The sensitivity, the specificity, the positive predictive value and the negative predictive value of EUS in diagnosing R-NENs were 98.03% (249/254), 34.92% (22/63), 85.86% (249/290) and 81.48% (22/27) respectively. The accuracy was 85.49% (271/317) and the Jorden index was 0.33. Tumor size ≤5 mm ( P=0.002, OR=2.892, 95% CI: 1.464-5.713), absence of surface vascular dilation ( P=0.019, OR=2.613, 95% CI: 1.170-5.837), normal tumor coloration ( P=0.001, OR=3.460, 95% CI: 1.645-7.279) and erythematous surface appearance ( P=0.048, OR=7.242, 95% CI: 1.015-51.680) were independent risk factors affecting the accuracy of R-NENs diagnosis by EUS. Depth assessment accuracy of EUS was 76.77% (195/254), with echo heterogeneity ( P<0.001, OR=4.008, 95% CI: 1.980-8.113) and surface depression ( P=0.035, OR=2.664, 95% CI: 1.073-6.615) emerging as significant factors affecting invasion depth evaluation. Conclusion:EUS demonstrates substantial clinical utility for R-NENs assessment, with diagnostic performance being significantly associated with tumor morphology and sonographic features. Macroscopic characteristics including tumor size, vascular patterns, and chromatic features influence diagnostic accuracy, while echo-textural heterogeneity and surface depression affect invasion depth precision. These findings underscore the clinical relevance of comprehensive EUS evaluation in R-NENs management.

Objective:To investigate the interaction of workplace noise, body mass index (BMI) and systemic inflammatory response on hypertension.Methods:In January 2019, 1124 male workers from an automobile factory in Wuhan were selected by cluster random sampling method. The study population was divided into normal body weight group (BMI<24 kg/m 2) and overweight group (BMI≥24 kg/m 2) according to BMI, and were followed up for 3 years. The occupational health examination of the workers was carried out every year, blood routine and blood biochemical indexes were collected, and the information of the workers' age, BMI, type of work and age of exposure to injury were collected through field questionnaires. The noise intensity of the workplace of the enterprise was measured for 3 consecutive years, and the equivalent sound level was calculated according to the working time. Normal and skewness measurements were described by Mean±SD and [ M ( Q1, Q3) ], respectively. t-test or Wilcoxon rank sum test was used for inter-group comparisons. Categorical variables were expressed by frequency and percentage (%), and Chi-square test was used for inter-group comparisons. Mixed effects models and generalized estimation equations were fitted to analyze the relationship between occupational noise, systemic inflammation, and their interaction terms with blood pressure and hypertension risk. Results:Univariate analysis revealed that the white blood cell counts, neutrophil counts, lymphocyte counts and eosinophil counts were positively associated with systolic blood pressure and diastolic blood pressure in overweight group ( n=467), respectively ( P<0.05). The participants with white blood cell counts≥5.94×10 9/L, neutrophil counts≥3.31×10 9/L, lymphocyte counts ≥2.03×10 9/L, and eosinophil counts ≥0.12×10 9/L had increased risk of hypertension by 52% ( RR=1.52, 95% CI: 1.11-2.05), 37% ( RR=1.37, 95% CI: 1.01-1.83), 58% ( RR=1.58, 95% CI: 1.18-2.09), and 52% ( RR=1.52, 95% CI: 1.12-2.06), respectively (all P<0.05). Multivariate analysis found a positive association between BMI and the risk of hypertension in the overweight group ( P<0.05), the participants with lymphocyte counts≥2.03×10 9/L and eosinophil counts≥0.12×10 9/L had increased risk of hypertension by 39% ( RR=1.39, 95% CI: 1.01-1.89) and 46% ( RR=1.46, 95% CI: 1.06-1.98), respectively (all P<0.05). There was no correlation between BMI and the risk of hypertension in normal weight group ( P>0.05). The multiplicative interaction of occupational noise (≥80 dB) with white blood cell counts (≥5.94×10 9/L) and lymphocyte counts (≥2.03×10 9/L) increased the risk of hypertension by 100% ( RR=2.00, 95% CI: 1.06-3.55) and 89% ( RR=1.89, 95% CI: 1.01-3.32) (all P<0.05) in overweight group, respectively. Additionally, a significant additive interaction was observed between noise exposure (≥80 dB) and basophil counts (≥0.03×10 9/L) on hypertension risk in the overweight group (RERI=0.49, 95% CI: 0.02-0.96, P<0.05) . Conclusion:The combined exposure of occupational noise and systemic inflammation may increase the risk of hypertension in overweight workers in automobile manufacturing plants, and the two have additive and multiplicative interactions.