BACKGROUND:Rapid and accurate segmentation of brain tissue in medical images is of great significance for three-dimensional biomechanical modeling and diagnosis of craniocerebral injuries.Currently,artificial intelligence(AI)-based baseline models exhibit excellent generalization capabilities on large-scale datasets.However,due to the specificity and complexity of craniocerebral tissues,these models have certain limitations in their application to craniocerebral tissue segmentation.Additionally,the scarcity of craniocerebral tissue samples makes it difficult for baseline models to achieve precise segmentation results through fine-tuning.OBJECTIVE:To construct a craniocerebral tissue segmentation model based on texture feature retrieval enhancement to improve segmentation accuracy under a small number of samples.METHODS:Segment Anything in Medical Images(MedSAM)model was selected as the basic framework,and texture features were combined with deep learning to build a brain tissue segmentation model based on texture feature retrieval enhancement(DP-MedSAM).Dice Coefficient and mean intersection over union(MIoU)were selected to evaluate the efficiency of image segmentation results.In comparison with the original MedSAM model,the ablation experiment systematically evaluated the influence of key components on the model performance.The sensitivities of MedSAM,the Segment Anything Model(SAM)for medical image segmentation(SAM-Med2D)and DP-MedSAM in the mandible,left optic nerve,and left parotid gland were compared.RESULTS AND CONCLUSION:(1)By verifying the impact of the number of point prompts on segmentation results on the HaN-Seg dataset,the experimental results indicated that the optimal Dice score was achieved with the addition of three points.(2)DP-MedSAM demonstrated performance improvements compared with MedSAM and SAM-Med2D on two datasets(HaN and Public Domain Database for Computational Anatomy).Especially on the Public Domain Database for Computational Anatomy dataset,in terms of the MIoU metric,DP-MedSAM outperformed MedSAM by 6.59％and SAM-Med2D by 37.35％;in terms of the Dice metric,DP-MedSAM outperformed MedSAM and SAM-Med2D by 4.34％and 25.32％,respectively.(3)The ablation experiment results showed that removing the texture feature extraction module in the DP-MedSAM model,relying solely on original image features,led to a significant decrease in results on the test set.Furthermore,removing the vector cache database and its retrieval enhancement function from the model,which deprived the ability of the model to perform similarity retrieval using an external knowledge base,further reduced model performance.(4)Under conditions of limited data resources,the DP-MedSAM model outperformed the other two models in all evaluation metrics.The DP-MedSAM model performed excellently when processing simple and moderately difficult samples,demonstrating a clear advantage over the other two models and indicating good generalization ability.Processing the fine structures of difficult samples placed higher demands on the model's segmentation capabilities.Although the performance of the DP-MedSAM model declined slightly,it still outperformed the other two models.(5)This study proposes an innovative craniocerebral tissue segmentation model,DP-MedSAM,which improves the baseline model's performance in capturing local details and global structural information in medical images by introducing target region texture feature extraction.Through vector similarity retrieval technology,DP-MedSAM can retrieve the feature vector most similar to the current target region from a pre-constructed vector database,providing more precise guiding information for the segmentation process.

BACKGROUND:Rapid and accurate segmentation of brain tissue in medical images is of great significance for three-dimensional biomechanical modeling and diagnosis of craniocerebral injuries.Currently,artificial intelligence(AI)-based baseline models exhibit excellent generalization capabilities on large-scale datasets.However,due to the specificity and complexity of craniocerebral tissues,these models have certain limitations in their application to craniocerebral tissue segmentation.Additionally,the scarcity of craniocerebral tissue samples makes it difficult for baseline models to achieve precise segmentation results through fine-tuning.OBJECTIVE:To construct a craniocerebral tissue segmentation model based on texture feature retrieval enhancement to improve segmentation accuracy under a small number of samples.METHODS:Segment Anything in Medical Images(MedSAM)model was selected as the basic framework,and texture features were combined with deep learning to build a brain tissue segmentation model based on texture feature retrieval enhancement(DP-MedSAM).Dice Coefficient and mean intersection over union(MIoU)were selected to evaluate the efficiency of image segmentation results.In comparison with the original MedSAM model,the ablation experiment systematically evaluated the influence of key components on the model performance.The sensitivities of MedSAM,the Segment Anything Model(SAM)for medical image segmentation(SAM-Med2D)and DP-MedSAM in the mandible,left optic nerve,and left parotid gland were compared.RESULTS AND CONCLUSION:(1)By verifying the impact of the number of point prompts on segmentation results on the HaN-Seg dataset,the experimental results indicated that the optimal Dice score was achieved with the addition of three points.(2)DP-MedSAM demonstrated performance improvements compared with MedSAM and SAM-Med2D on two datasets(HaN and Public Domain Database for Computational Anatomy).Especially on the Public Domain Database for Computational Anatomy dataset,in terms of the MIoU metric,DP-MedSAM outperformed MedSAM by 6.59％and SAM-Med2D by 37.35％;in terms of the Dice metric,DP-MedSAM outperformed MedSAM and SAM-Med2D by 4.34％and 25.32％,respectively.(3)The ablation experiment results showed that removing the texture feature extraction module in the DP-MedSAM model,relying solely on original image features,led to a significant decrease in results on the test set.Furthermore,removing the vector cache database and its retrieval enhancement function from the model,which deprived the ability of the model to perform similarity retrieval using an external knowledge base,further reduced model performance.(4)Under conditions of limited data resources,the DP-MedSAM model outperformed the other two models in all evaluation metrics.The DP-MedSAM model performed excellently when processing simple and moderately difficult samples,demonstrating a clear advantage over the other two models and indicating good generalization ability.Processing the fine structures of difficult samples placed higher demands on the model's segmentation capabilities.Although the performance of the DP-MedSAM model declined slightly,it still outperformed the other two models.(5)This study proposes an innovative craniocerebral tissue segmentation model,DP-MedSAM,which improves the baseline model's performance in capturing local details and global structural information in medical images by introducing target region texture feature extraction.Through vector similarity retrieval technology,DP-MedSAM can retrieve the feature vector most similar to the current target region from a pre-constructed vector database,providing more precise guiding information for the segmentation process.

Objective:To explore the application effectiveness of the large language model DeepSeek in the cultivation of clinical thinking skills for medical laboratory technology students.Methods:A non-randomized controlled study was conducted. In the 2024-2025 academic year, two classes of second-year medical laboratory technology students from Hubei University of Chinese Medicine were selected and divided into a DeepSeek-assisted teaching group (Class A, n=53) and a traditional teaching control group (Class B, n=53), totaling 106 students. Both groups followed a 20-week problem-based learning (PBL) framework with identical teaching content, instructors, and class hours. Class A utilized DeepSeek via the"Learning Pass AI"platform for case diagnosis reasoning, prompt construction training, test plan formulation, and result analysis, while Class B received traditional PBL instruction. Paired t-tests were used to compare pre-and post-teaching scores in clinical thinking skills, AI interaction literacy, and prompt construction in Class A. Independent samples t-tests and chi-square ( χ2) tests were used to evaluate differences in case reasoning scores, etiology analysis accuracy, and teaching satisfaction between groups. Structured questionnaires supplemented the evaluation of model-assisted teaching processes. Results:The comparison of pre-and post-teaching scores in Class A showed that post-teaching scores significantly improved in clinical thinking skills[(4.02±0.45) points vs. (3.09±0.50) points, t=2.23)] and AI interaction literacy [(4.62±0.41) points vs. (3.27±0.54) points, t=2.18]. Compared to Class B, Class A demonstrated superior performance in case reasoning scores [(81.1±3.8) points vs.(74.3±4.2) points, t=8.97], etiology analysis accuracy [94.3% (50/53) vs. 81.1% (43/53), χ2=4.29], and teaching satisfaction [(95.6±3.2)points vs. (82.6±4.8) points, t=11.86] ( P<0.05). The results of questionnaires indicated that during model application, the prompt construction improved in logic [(2.85±0.58) points to (4.25±0.50) points, t=14.23, P<0.01] and innovation [(2.60±0.53) points to (4.05±0.46) points, t=11.57, P<0.05], but question clarity (77.4%, 41/53) and medical terminology accuracy (43.4%, 23/53) remained primary shortcomings. Conclusion:Integrating large language models into AI-teacher collaborative learning pathways can effectively promote students′ autonomous inquiry and clinical reasoning skills, thereby enhancing medical laboratory technology students′ clinical thinking skills.

ObjectiveTo investigate the triglyceride-glucose (TyG) index and the level of serum homocysteine (Hcy) in association with the incidence of stroke in type 2 diabetes mellitus (T2DM) patients. MethodsBased on the chronic disease risk factor surveillance cohort in Pudong New Area, Shanghai, excluding those with stroke in baseline survey, T2DM patients who joined the cohort from January 2016 to October 2020 were selected as the research subjects. During the follow-up period, a total of 318 new-onset ischemic stroke patients were selected as the case group, and a total of 318 individuals matched by gender without stroke were selected as the control group. The Cox proportional hazards regression model was used to adjust for confounding factors and explore the serum TyG index and the Hcy biochemical indicator in association with the risk of stroke. ResultsThe Cox proportional hazards regression results showed that after adjusting for confounding factors, the risk of stroke in T2DM patients with 10 μmol·L⁻¹-¹ and Hcy>15 μmol·L⁻¹ was 1.532 times (95%CI: 1.017‒2.309 times, P=0.041) and 1.738 times (95%CI: 1.119‒2.699 times, P=0.014) higher respectively, compared to T2DM patients with Hcy≤10 μmol·L⁻¹. T2DM patients with TyG>9.074 had 1.396 times higher risk of stroke (95%CI: 1.091‒1.787, P=0.008) compared to those with TyG≤9.074. The study found that urea and α1-antitrypsin (α1-AT) were independent risk factors for the incidence of stroke in T2DM patients. For every unit increase in urea andα1-AT, the risk of stroke in T2DM patients increased by 233.6% (HR=3.336, 95%CI: 1.588‒7.009, P=0.001) and 11.3% (HR=1.113, 95%CI: 1.028‒1.205, P=0.008), respectively. Cumulative risk curves showed that Hcy>10 μmol·L⁻¹ and TyG>9.074 accelerated the time to stroke occurrence in T2DM patients. ConclusionElevated levels of Hcy>10 μmol·L⁻¹ and a higher TyG index are risk factors for stroke in T2DM patients. Effective interventions for Hcy and TyG should be conducted for diabetic patients to reduce the incidence of stroke.

Japanese spotted fever(JSF)is an infectious disease caused by Rickettsia japonica,with nonspecific clinical symptoms and a high risk of misdiagnosis.We reported a case of JSF,in which Rickettsia japonica was detected in blood cells by metagenomic next-generation sequencing.The patient recovered after treatment with doxycycline.This report provides a reference for the clinical diagnosis and treatment of JSF.
Humans ; High-Throughput Nucleotide Sequencing ; Metagenomics ; Rickettsia/isolation & purification* ; Spotted Fever Group Rickettsiosis/microbiology*

Objective To explore the diagnostic value of mediastinal lymph nodes CT image features in pulmonary sarcoidosis.Methods The imageologic data of the patients with pulmonary sarcoidosis(pulmonary sarcoidosis group)and lung cancer complicating mediastinal lymph node metastasis(lung cancer group)con-firmed by EBUS-TBNA in this hospital from June 2015 to November 2023 were analyzed retrospectively.The chest plain scan CT and enhanced scan CT were performed in all cases,and the imaging characteristics were compared between the two groups.The receiver operating characteristic(ROC)curve was drawn and the area under the curve(AUC)was calculated.The diagnostic value of CT imaging characteristics in pulmonary sar-coidosis was analyzed.Results The proportion of female patients in the lung sarcoidosis group was signifi-cantly higher than that in the lung cancer group,while the age was smaller than that in the lung cancer group,and the differences were statistically significant(P＜0.05).The number of mediastinal lymph nodes,location,short diameter and CT enhancement value in the pulmonary sarcoidosis group had statistical difference(P＜0.05).The ROC curve analysis showed that AUC of lymph node short diameter reciprocal,CT enhancement value and position in detection alone were 0.586,0.785 and 0.505 respectively,and AUC of the three combined reciprocal was the highest(0.789).Conclusion The lymph node short diameter,CT enhancement value and po-sition have certain value in clinical diagnosis of pulmonary sarcoidosis and the 3-indicator combination could increase the diagnostic efficiency of pulmonary sarcoidosis.

OBJECTIVES: To assess the preliminary efficacy and safety of a dose-intensified C5VD regimen (cisplatin, 5-fluorouracil, vincristine, and doxorubicin) in children with locally advanced hepatoblastoma. METHODS: This prospective study enrolled 24 children with newly diagnosed, locally advanced hepatoblastoma who received the dose-intensified C5VD regimen at Shanghai Children's Medical Center, Shanghai Jiao Tong University School of Medicine, and Shanghai Children's Hospital between January 2020 and December 2023. Clinical characteristics, treatment outcomes, and chemotherapy-related toxicities were analyzed. RESULTS: Of the 24 patients, 13 were male and 11 were female, with a median age at diagnosis of 18.7 months (range: 3.5-79.4 months). All patients achieved complete macroscopic resection of hepatic lesions without liver transplantation. Serum alpha-fetoprotein levels decreased significantly after two chemotherapy cycles. During a median follow-up of 38.4 months (range: 15.8-50.7 months), all patients maintained continuous complete remission, with 3-year event-free survival and overall survival rates of 100%. Across 144 chemotherapy cycles, the incidence rates of grade 3-4 neutropenia, thrombocytopenia, and infections were 97%, 77%, and 71%, respectively; no treatment-related deaths occurred. Notably, 5 patients (21%) developed Brock grade ≥3 hearing loss, of whom 1 required a hearing aid. CONCLUSIONS The dose-intensified C5VD regimen demonstrates significant efficacy with an overall favorable safety profile in the treatment of newly diagnosed, locally advanced pediatric hepatoblastoma. Grade 3-4 myelosuppression and infection are the predominant toxicities. However, high‑dose cisplatin-induced ototoxicity remains a concern, highlighting the need for improved otoprotective strategies.
Humans ; Hepatoblastoma/pathology* ; Male ; Female ; Infant ; Liver Neoplasms/pathology* ; Antineoplastic Combined Chemotherapy Protocols/therapeutic use* ; Child, Preschool ; Prospective Studies ; Doxorubicin/adverse effects* ; Child ; Cisplatin/adverse effects* ; Vincristine/adverse effects* ; Fluorouracil/adverse effects*

Ovarian tissue cryopreservation and transplantation is currently the only feasible method for preserving both fertility and ovarian endocrine function in prepubertal female patients. It is indicated for those requiring gonadotoxic therapies such as chemo-therapy, radiotherapy, or bone marrow transplantation for malignant diseases, as well as for non-malignant diseases, including immunologic, metabolic, and hematologic benign diseases requiring bone marrow transplantation, and other populations at high risk of premature ovarian insufficiency. The procedure involves laparoscopic retrieval of ovarian tissue, typically via unilateral oophorectomy in young patients, followed by slow-programmed cryopreservation. When the primary disease is cured and fertility or hormonal function restoration is desired, the tissue is thawed and transplanted, most commonly to an orthotopic site. For patients at high risk of ovarian malignancy involvement, pre-transplantation assessment of minimal residual disease in the ovarian cortex is performed using histo-pathology and molecular biology techniques. Globally, while ovarian tissue cryopreservation and transplantation has led to over 300 live births, the majority result from tissue cryopreserved after puberty. Successful restoration of puberty and subsequent live births following transplantation of tissue frozen before puberty, although demonstrated in reported cases, remain less common. Therefore, this review systematically summarizes recent advances in the indications, current application status, timing and strategies of ovarian tissue cryopreservation and transplantation, risk assessment of tumor cell reintroduction, and clinical outcomes in prepubertal patients. It also discusses the potential value and current challenges of combining this approach with invitro oocyte maturation techniques, ainming to provide practical references for clinical practice.

Objective: To understand the relationship between working hours and occupational stress among front-line employees in manufacturing enterprises, so as to provide a basis for the prevention and control of occupational stress. Methods: Front-line employees from 5 manufacturing enterprises in Hangzhou City were selected from June to November 2024 using random cluster sampling. Demographic information and occupational information such as daily average working hours and weekly working hours, were collected through questionnaires. The effort-reward imbalance questionnaire was used to investigate occupational stress. The association between working hours and occupational stress was analyzed using a multivariable logistic regression model. Results: A total of 926 people were surveyed, among whom 572 were male, accounting for 61.77%, and 354 were female, accounting for 38.23%. The average age was (32.98±8.28) years. There were 515 people (55.62%) who had a monthly personal income of more than 5 000 yuan but less than 9 000 yuan. There were 353 people (38.12%) who had a working seniority of less than 5 years. There were 784 people (84.67%) who had an average daily working hours of >8 hours and 645 people (69.65%) who had a weekly working day of more than 5 days. There were 338 people (36.50%) on the shift work system, and 331 people (35.75%) worked night shifts. A total of 707 people were detected with occupational stress, with a detection rate of 76.35%. Multivariable logistic regression analysis showed that after adjusting for gender, age, educational level, marital status, number of children, only-child status, monthly personal income, working seniority, weekly working hours, assembly-line work, shift work system and night shift, compared with employees with an average daily working hours of ≤8 hours, the risk of occupational stress increased by 118.7% for those with an average daily working hours of >8-<10 hours (OR=2.187, 95%CI: 1.434-3.336) and by 248.4% for those with an average daily working hours of ≥10 hours (OR=3.484, 95%CI: 2.034-5.966). Conclusions The detection rate of occupational stress among front-line employees in manufacturing enterprises in Hangzhou City is high. Long average daily working hours can increase the risk of occupational stress among employees in manufacturing enterprises. It is recommended to reasonably arrange work intensity and working hours.

The gut microbiota regulates intestinal nutrient absorption, participates in modulating host glucolipid metabolism, and contributes to ameliorating glucolipid metabolism disorder. Dysbiosis of the gut microbiota can compromise the integrity of the intestinal mucosal barrier, induce inflammatory responses, and exacerbate insulin resistance and abnormal lipid metabolism in the host. Dangua Humai Oral Liquid, a hospital-developed formulation for regulating glucolipid metabolism, has been granted a national invention patent and demonstrates significant clinical efficacy. This study aimed to investigate the effects of Dangua Humai Oral Liquid on gut microbiota and the intestinal mucosal barrier in a mouse model with glucolipid metabolism disorder. A glucolipid metabolism disorder model was established by feeding mice a high-glucose and high-fat diet. The mice were divided into a normal group, a model group, and a treatment group, with eight mice in each group. The treatment group received a daily gavage of Dangua Humai Oral Liquid(20 g·kg~(-1)), while the normal group and model group were given an equivalent volume of sterile water. After 15 weeks of intervention, glucolipid metabolism, intestinal mucosal barrier function, and inflammatory responses were evaluated. Metagenomics and untargeted metabolomics were employed to analyze changes in gut microbiota and associated metabolic pathways. Significant differences were observed between the indicators of the normal group and the model group. Compared with the model group, the treatment group exhibited marked improvements in glucolipid metabolism disorder, alleviated pathological damage in the liver and small intestine tissue, elevated expression of recombinant claudin 1(CLDN1), occluding(OCLN), and zonula occludens 1(ZO-1) in the small intestine tissue, and reduced serum levels of inflammatory factors lipopolysaccharides(LPS), lipopolysaccharide-binding protein(LBP), interleukin-6(IL-6), and tumor necrosis factor-α(TNF-α). At the phylum level, the relative abundance of Bacteroidota decreased, while that of Firmicutes increased. Lipid-related metabolic pathways were significantly altered. In conclusion, based on the successful establishment of the mouse model of glucolipid metabolism disorder, this study confirmed that Dangua Humai Oral Liquid effectively modulates gut microbiota and mucosal barrier function, reduces serum inflammatory factor levels, and regulates lipid-related metabolic pathways, thereby ameliorating glucolipid metabolism disorder.
Animals ; Gastrointestinal Microbiome/drug effects* ; Mice ; Intestinal Mucosa/microbiology* ; Male ; Drugs, Chinese Herbal/administration & dosage* ; Mice, Inbred C57BL ; Humans ; Glycolipids/metabolism* ; Lipid Metabolism/drug effects* ; Administration, Oral ; Disease Models, Animal