VR technology can generate virtual,immersive,and interactive environments,allowing users to immerse themselves in these environments and interact with objects within them.AR technology,on the other hand,can accurately overlay virtual information onto real-world scenes,achieving a seamless integration of the virtual and the real.These two emerging technologies each possess unique advantages and exhibit broad development prospects.They have already begun to be applied in various aspects of medical education,such as basic theoretical teaching and skills training,with promising results.They can compensate for the shortcomings of traditional medical education,enhance students'learning enthusiasm and safety,and improve teaching effectiveness.However,limitations remain,such as the need for improved hardware infrastructure and a scarcity of teaching resources.Based on this,this paper systematically introduces the concepts of AR and VR technologies,reviews their application prospects,current status,advantages,and limitations in medical education,aiming to provide evidence-based support and feasible approaches for medical schools to develop digital teaching plans,promote educational reform,and drive research innovation.

Objective:To develop and evaluate a medical visual question answering (VQA) model for neonatal lung ultrasound (LUS) images to enhance intelligent auxiliary diagnosis of neonatal pulmonary diseases.Methods:Using data from neonates admitted to Beijing Obstetrics and Gynecology Hospital, Capital Medical University (January 2023 to December 2024), an image-question-answer dataset comprising 251 LUS images was constructed [43 pneumonia (17.1%), 42 neonatal respiratory distress syndrome (16.7%), 83 transient tachypnea (33.1%), and 83 normal (33.1%) images] with a four-tier medical question-answer framework. Building upon the Qwen2.5-VL-7B base model and integrating LoRA fine-tuning with chain-of-thought prompting, we developed the NLUS-VQA model to enhance visual-language semantic alignment and enable stepwise clinical reasoning, achieving efficient small-sample adaptation. Model performance was comprehensively assessed through natural language generation metrics (BLEU-4, ROUGE-1/2/L), qualitative evaluation of characteristic recognition, and clinical consistency analysis.Results:(1) Quantitative evaluation demonstrated that NLUS-VQA achieved scores of 22.38 (BLEU-4), 48.26 (ROUGE-1), 22.40 (ROUGE-2), and 37.20 (ROUGE-L), representing significant improvements over baseline models. (2) Qualitatively, the model exhibited strong performance in identifying lung consolidation, coalescent B-lines, and snowflake signs, with its chain-of-thought strategy enhancing clinical interpretability and answer accuracy. (3) Clinically, NLUS-VQA achieved a Cohen's Kappa coefficient of 0.78 and diagnostic accuracy of 80.8% (21/26), indicating substantial agreement with clinical experts.Conclusion:The NLUS-VQA model demonstrates robust interpretability in recognizing key sonographic patterns (e.g. lung consolidation, confluent B-lines, and snowflake signs), providing a scalable framework for small-sample medical image analysis, though diagnostic performance on complex conditions remains limited by dataset scale and minority class representation.

VR technology can generate virtual,immersive,and interactive environments,allowing users to immerse themselves in these environments and interact with objects within them.AR technology,on the other hand,can accurately overlay virtual information onto real-world scenes,achieving a seamless integration of the virtual and the real.These two emerging technologies each possess unique advantages and exhibit broad development prospects.They have already begun to be applied in various aspects of medical education,such as basic theoretical teaching and skills training,with promising results.They can compensate for the shortcomings of traditional medical education,enhance students'learning enthusiasm and safety,and improve teaching effectiveness.However,limitations remain,such as the need for improved hardware infrastructure and a scarcity of teaching resources.Based on this,this paper systematically introduces the concepts of AR and VR technologies,reviews their application prospects,current status,advantages,and limitations in medical education,aiming to provide evidence-based support and feasible approaches for medical schools to develop digital teaching plans,promote educational reform,and drive research innovation.

Objective:To develop and evaluate a medical visual question answering (VQA) model for neonatal lung ultrasound (LUS) images to enhance intelligent auxiliary diagnosis of neonatal pulmonary diseases.Methods:Using data from neonates admitted to Beijing Obstetrics and Gynecology Hospital, Capital Medical University (January 2023 to December 2024), an image-question-answer dataset comprising 251 LUS images was constructed [43 pneumonia (17.1%), 42 neonatal respiratory distress syndrome (16.7%), 83 transient tachypnea (33.1%), and 83 normal (33.1%) images] with a four-tier medical question-answer framework. Building upon the Qwen2.5-VL-7B base model and integrating LoRA fine-tuning with chain-of-thought prompting, we developed the NLUS-VQA model to enhance visual-language semantic alignment and enable stepwise clinical reasoning, achieving efficient small-sample adaptation. Model performance was comprehensively assessed through natural language generation metrics (BLEU-4, ROUGE-1/2/L), qualitative evaluation of characteristic recognition, and clinical consistency analysis.Results:(1) Quantitative evaluation demonstrated that NLUS-VQA achieved scores of 22.38 (BLEU-4), 48.26 (ROUGE-1), 22.40 (ROUGE-2), and 37.20 (ROUGE-L), representing significant improvements over baseline models. (2) Qualitatively, the model exhibited strong performance in identifying lung consolidation, coalescent B-lines, and snowflake signs, with its chain-of-thought strategy enhancing clinical interpretability and answer accuracy. (3) Clinically, NLUS-VQA achieved a Cohen's Kappa coefficient of 0.78 and diagnostic accuracy of 80.8% (21/26), indicating substantial agreement with clinical experts.Conclusion:The NLUS-VQA model demonstrates robust interpretability in recognizing key sonographic patterns (e.g. lung consolidation, confluent B-lines, and snowflake signs), providing a scalable framework for small-sample medical image analysis, though diagnostic performance on complex conditions remains limited by dataset scale and minority class representation.

BACKGROUND: Breast cancer patients who are positive for hormone receptor typically exhibit a favorable prognosis. It is controversial whether chemotherapy is necessary for them after surgery. Our study aimed to establish a multigene model to predict the relapse of hormone receptor-positive early-stage Chinese breast cancer after surgery and direct individualized application of chemotherapy in breast cancer patients after surgery. METHODS: In this study, differentially expressed genes (DEGs) were identified between relapse and nonrelapse breast cancer groups based on RNA sequencing. Gene set enrichment analysis (GSEA) was performed to identify potential relapse-relevant pathways. CIBERSORT and Microenvironment Cell Populations-counter algorithms were used to analyze immune infiltration. The least absolute shrinkage and selection operator (LASSO) regression, log-rank tests, and multiple Cox regression were performed to identify prognostic signatures. A predictive model was developed and validated based on Kaplan-Meier analysis, receiver operating characteristic curve (ROC). RESULTS: A total of 234 out of 487 patients were enrolled in this study, and 1588 DEGs were identified between the relapse and nonrelapse groups. GSEA results showed that immune-related pathways were enriched in the nonrelapse group, whereas cell cycle- and metabolism-relevant pathways were enriched in the relapse group. A predictive model was developed using three genes ( CKMT1B , SMR3B , and OR11M1P ) generated from the LASSO regression. The model stratified breast cancer patients into high- and low-risk subgroups with significantly different prognostic statuses, and our model was independent of other clinical factors. Time-dependent ROC showed high predictive performance of the model. CONCLUSIONS A multigene model was established from RNA-sequencing data to direct risk classification and predict relapse of hormone receptor-positive breast cancer in Chinese patients. Utilization of the model could provide individualized evaluation of chemotherapy after surgery for breast cancer patients.
Humans ; Female ; Breast Neoplasms/genetics* ; East Asian People ; Neoplasm Recurrence, Local/genetics* ; Breast ; Algorithms ; Chronic Disease ; Prognosis ; Tumor Microenvironment

Objective:To explore the influencing factors of postoperative infection in patients undergoing thoracoscopic lung cancer resection, and provide the basis for formulating nursing strategies and reducing the infection rate.Method:Using the convenient sampling method, a total of 83 patients who underwent thoracoscopic lung cancer resection in Henan Provincial People's Hospital from March 2017 to March 2021 were selected as the research objects. A self-made questionnaire was used to investigate the influencing factors. Patients were divided into the infection group ( n=7) and the non-infection group ( n=76) according to whether postoperative infection occurred. Univariate analysis was used to investigate influencing factors of postoperative infection in patients undergoing thoracoscopic lung cancer resection. And targeted nursing interventions were proposed. Results:The incidence of postoperative infection in 83 patients with thoracoscopic lung cancer resection was 8.43% (7/83) . There were statistically significant differences in age, smoking, diabetes, postoperative bed rest time between the infected group and the non-infected group ( P<0.05) . Conclusions:Age, smoking, diabetes, postoperative bed rest time are the influencing factors of postoperative infection in patients undergoing thoracoscopic lung cancer resection. Nursing staff should formulate targeted nursing interventions according to the influencing factors of infection.

Objective:To analyze the clinical and pathological features of asymptomatic primary hyperparathyroidism (PHPT) .Methods:A retrospective analysis was carried out in terms of the clinical characteristics and pathological data in 30 patients with asymptomatic PHPT and 86 patients with typical PHPT hospitalized in the Department of Endocrinology and General Surgery of Beijing Jishuitan Hospital from Jan. 2013 to Dec. 2018. There were 7 males (23.3%) and 23 females (76.7%) , with a male to female ratio of 1:3.3. The average age was 56.9±13.3 years. In typical PHPT group, there were 32 males (37.2%) and 54 females (62.8%) , with the average age of 46.4±17.0 years. Bone metabolism indicators included bone density and bone biochemical markers (parathyroid hormone, 25-hydroxyvitamin D and alkaline phosphatase) . The t test was used to compare normally distributed variables, the Mann-Whitney rank sum test was used to compare skewed distributed variables, and the χ 2 test was used to compare enumeration data. Results:The median serum parathyroid hormone and alkaline phosphatase were 144.2 (108.1, 207.0) pg/ml and 80.0 (53.7, 105.5) IU/L respectively, the average serum concentration of calcium was 2.80±0.20 mmol/L, which were significantly lower than those of the classic group ( P<0.05) . The median serum 25-hydroxyvitamin D was 12.14 (7.87, 14.38) ng/ml, which was higher than that of the classic group ( P<0.001) . Ten patients (33.3%) developed osteoporosis, and the incidence was lower than that of the classic group ( P< 0.001) . The median tumor weight was 0.80 (0.25, 1.98) g, significantly smaller than that in the classical group ( P=0.003) . There were 26 cases (86.7%, including 2 atypical parathyroid adenomas) of parathyroid adenomas and 4 cases (13.3%) of hyperplasia. Conclusions:The asymptomatic PHPT has the same sex ratio as the classic type, mainly female, but the average age is significantly higher than that in the classic type. Although asymptomatic PHPT in this study are all benign lesions, abnormal bone biochemical indicators, especially vitamin D deficiency, are common, which also lead to osteoporosis.

Objective:To investigate the value of serum miR-143 level combined with MRI in predicting the early response to concurrent chemoradiotherapy (CCRT) in cervical cancer.Methods:A total of 85 patients with pathologically confirmed cervical cancer underwent conventional MRI, intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI), and dynamic contrast-enhanced MRI (DCE-MRI) before CCRT. The biopsy tissues and serum samples were collected. The differential expression of miRNA in the biopsy tissues was determined by microarray chip. The expression level of miR-143 in the serum samples was analyzed by qRT-PCR. All patients were divided into the non-residual and residual tumor groups according to post-treatment MRI. Pre-treatment clinical factors, MRI parameters and miR-143 between two groups were statistically analyzed by the univariate and multivariate analyses. The optimal thresholds and predictive performance for post-treatment incidence of residual tumors were estimated by drawing the ROC curve.Results:At one month after CCRT, there were 52 patients in the non-residual tumor group and 33 patients in the residual tumor group. In the residual tumor group, pre-treatment FIGO staging, apparent diffusion coefficient (ADC), D and V e were significantly higher (all P<0.05), whereas K trans value was significantly lower ( P<0.001) when compared to those in the non-residual tumor group. The miRNA array analysis showed that there were 16 miRNAs with differential expression levels between two groups (all P<0.05). Among them, the increase of miR-143 was the most significant in the residual tumor group. Compared with the residual tumor group, the expression level of serum miR-143 was significantly down-regulated in the non-residual tumor group ( P=0.002). Compared with the SiHa cells, the expression level of miR-143 in the SiHa-R cells was significantly up-regulated ( P<0.05). Multivariate analysis showed that only miR-143, D, K trans and V e were the independent prognostic factors. The combination of multi-parametric MRI and miR-143 exhibited the highest predictive performance (AUC=0.975), with a sensitivity of 84.8% and a specificity of 96.2%. Conclusion:The combination of multi-parametric MRI with miR-143 further improves the predictive performance for residual tumors after CCRT, which contributes to the personalized treatment of cervical cancer.

Objective:To explore the diagnostic value of 68Ga-fibroblast activation protein inhibitor (FAPI) PET for the restaging of patients with colorectal cancer and its impact on treatment strategy. Methods:Patients with colorectal cancer who underwent 68Ga-FAPI PET imaging in the PET Center of Union Hospital, Tongji Medical College, Huazhong University of Science and Technology from June 2020 to June 2021 were retrospectively analyzed. PET images were evaluated by 3 experienced imaging physicians. Biopsy or postoperative pathology, clinical and imaging follow-up results were as the gold standard. The diagnostic value of PET was compared with conventional imaging (CT/MR), and the impact of 68Ga-FAPI PET on guiding treatment was evaluated. χ2 test and Fisher exact test were used to compare the differences between groups. Results:A total of 33 patients were included (17 males, 16 females, age (52.8±12.3) years), of which 24 were finally diagnosed as recurrence/metastases/progression. The accuracy, sensitivity, specificity, positive predictive value and negative predictive value of 68Ga-FAPI PET in detecting recurrence/metastases/progression of colorectal cancer were 93.9%(31/33), 100%(24/24), 7/9, 92.3%(24/26) and 7/7, respectively. Its accuracy, sensitivity and negative predictive value were significantly higher than those of conventional imaging (64.5%(20/31), 56.5%(13/23) and 7/17; χ2 values: 8.549 and 10.786, all P<0.05). Compared with the clinical or pathological stage before examination, 68Ga-FAPI PET led upstaging to stage Ⅳ in 12 patients (50.0%, 12/24). Of the 31 patients who were correctly diagnosed by 68Ga-FAPI PET, the treatment regimen of 22 patients (71.0%) was changed because of 68Ga-FAPI PET imaging. Conclusion:68Ga-FAPI PET has good diagnostic performance in the restaging of colorectal cancer, which is helpful to further guide clinical treatment strategy.

Objective:To explore the feasibility of statistical parametric mapping (SPM) aided semi-quantitative analysis in 11C-Pittsburgh compound B (PIB) β-amyloid (Aβ) PET imaging acquired by hybrid PET/MR, and evaluate its possibility in assisting the diagnosis or differential diagnosis for cognitive impairment. Methods:From January 2018 to September 2019, 13 Alzheimer′s disease (AD) patients (4 males, 9 females; age (59.2±5.8) years) and 10 vascular cognitive disorders (VCD) patients (9 males, 1 female; age (59.5±11.5) years) who underwent 11C-PIB PET/MR in PET center of Union Hospital, Tongji Medical College, Huazhong University of Science and Technology were retrospectively analyzed. The standardized uptake value ratio (SUVR) of eight key brain regions (cerebral white matter, striatum, thalamus, posterior cingulate gyrus, frontal cortex, posterior parietal cortex, lateral temporal cortex and occipital cortex) to cerebellum cortex were obtained by manual delineation and SPM-aided semi-automatic segmentation with the help of synchronous three-dimensional T 1 weighted imaging (3D T 1WI). Pearson correlation analysis was carried out on the SUVR obtained by the two methods. Independent-sample t test and paired t test were used to analyze the data. Results:There was no significant difference between AD group and VCD group in age and Mini-Mental State Examination (MMSE) score (19.7±4.7 vs 21.7±3.8; t values: 0.095 and 1.098, both P>0.05). Except thalamus( r=0.179, P=0.413), there were good correlations between SUVR obtained by segmentation and delineation in the other 7 key regions ( r values: 0.678-0.893, all P<0.05). The SUVR of 8 key regions obtained by the two methods in AD group was significantly higher than that in VCD group (1.519-2.055 vs 1.105-1.618; t values: 2.799-11.582, all P<0.01). The SUVR of striatum (1.942±0.205), posterior cingulate gyrus (1.915±0.249), frontal lobe (1.983±0.264), parietal lobe (2.008±0.296) and temporal cortex (1.931±0.254) in AD group was significantly higher than that of cerebral white matter (1.746±0.192; t values: 3.793-6.992, all P<0.01). But in VCD group, there was no region with the SUVR higher than that of cerebral white matter. Conclusions:Hybrid PET/MR can acquire the PET and MRI images synchronously, which can realize the accurate brain segmentation and obtain the semi-quantitative data of key brain regions aided by SPM. The method can analyze the characteristics and differences of amyloid imaging in AD and VCD, which is expected to provide an accurate imaging analysis method for the diagnosis and differential diagnosis of cognitive disorders.