With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.

Objective To construct and evaluate a prognostic model for clear cell renal cell carcinoma(ccRCC)based on preoperative lipid ratios, cM0(i+)staging, and other clinical characteristics, so as to provide a precise tool for clinical prognosis assessment. Methods A retrospective analysis was conducted on the clinical data of 215 ccRCC patients treated in our hospital during May 2014 and May 2023. Lipid ratios were calculated using preoperative lipid data, and patients were divided into cM0(i+)stage or cM0 stage according to postoperative circulating tumor cells(CTCs)test results. The optimal lipid ratio and cutoff value were selected using receiver operating characteristic(ROC)curves and the X-tile method. Patients were subdivided into three groups based on the level of the low-density lipoprotein cholesterol to non-low-density lipoprotein cholesterol ratio(LNLR)and cM0(i+)staging:Group A [LNLR＞1.68 and diagnosed with cM0(i+)], Group B [LNLR＞1.68 or diagnosed with cM0(i+)], and Group C(LNLR ≤1.68 and diagnosed with cM0). Kaplan-Meier survival analysis was used to plot survival curves for patients in different groups. The log-rank test was employed to compare differences in recurrence-free survival(RFS)among the subgroups. Multivariate Cox regression analysis was conducted to identify the independent risk factors influencing RFS, and a nomogram prediction model was constructed based on these results. The predictive performance of the model was validated using ROC curves, calibration curves, and decision curves. Results ROC curves were plotted for lipid markers, and LNLR was identified as the most predictive for RFS. Its optimal cutoff point was 1. 68. Patients in Group A experienced a significantly shorter postoperative RFS. Multivariate Cox regression analysis identified preoperative LNLR, cM0(i+)staging, pathological grade, and stage as independent risk factors for RFS. A nomogram model was constructed based on these risk factors. The area under the ROC curve(AUC)for 1-, 3-, and 5-year RFS was 0.896(95% CI:0.8121-0.9627), 0.890(95%CI:0.7879-0.9641), and 0.870(95%CI:0.7697-0.9526), indicating good discriminatory ability and predictive performance. Calibration plots demonstrated good agreement between predicted and actual outcomes. Clinical decision curve analysis showed high clinical net benefit. Conclusion Preoperative LNLR level is an independent risk factor for RFS in ccRCC patients. The prognostic prediction model based on LNLR, cM0(i+)staging, patient pathological grade, and staging demonstrates good predictive performance for RFS and holds potential clinical application value.

Malignant tumors are a class of diseases that pose a serious threat to human health, and radiotherapy (RT) is one of the essential treatment modalities. Virtual reality (VR) technology, with its unique characteristics of immersion, interactivity, and imagination, demonstrates tremendous application potential in radiotherapy. Several randomized controlled trials have confirmed that VR, as a non-pharmacological intervention, can effectively alleviate anxiety in patients, especially children, and improve treatment adherence. In medical education and professional training, VR provides safe training platforms for radiation oncologists, medical physicists, and radiation therapists through the construction of high-fidelity virtual environments. These platforms can be used for training skills in target volume delineation, treatment plan evaluation, and equipment quality control, thereby significantly improving training efficiency and quality. Furthermore, VR technology enables three-dimensional visualization and intuitive evaluation of treatment plans, facilitates multidisciplinary team (MDT) collaboration, and provides new paradigms for the development of real-time guidance technologies that integrate with augmented reality. This article systematically reviews the current applications of VR technology in the clinical practice, medical education, radiation protection, and scientific research of radiotherapy. It also discusses future prospects for integrating VR with artificial intelligence (AI), augmented reality (AR), and haptic feedback technologies. This review provides a valuable reference for the standardized application of VR technology in radiotherapy and radiation protection in China.

Malignant tumors are a class of diseases that pose a serious threat to human health, and radiotherapy (RT) is one of the essential treatment modalities. Virtual reality (VR) technology, with its unique characteristics of immersion, interactivity, and imagination, demonstrates tremendous application potential in radiotherapy. Several randomized controlled trials have confirmed that VR, as a non-pharmacological intervention, can effectively alleviate anxiety in patients, especially children, and improve treatment adherence. In medical education and professional training, VR provides safe training platforms for radiation oncologists, medical physicists, and radiation therapists through the construction of high-fidelity virtual environments. These platforms can be used for training skills in target volume delineation, treatment plan evaluation, and equipment quality control, thereby significantly improving training efficiency and quality. Furthermore, VR technology enables three-dimensional visualization and intuitive evaluation of treatment plans, facilitates multidisciplinary team (MDT) collaboration, and provides new paradigms for the development of real-time guidance technologies that integrate with augmented reality. This article systematically reviews the current applications of VR technology in the clinical practice, medical education, radiation protection, and scientific research of radiotherapy. It also discusses future prospects for integrating VR with artificial intelligence (AI), augmented reality (AR), and haptic feedback technologies. This review provides a valuable reference for the standardized application of VR technology in radiotherapy and radiation protection in China.

Malignant tumors are a class of diseases that pose a serious threat to human health, and radiotherapy (RT) is one of the essential treatment modalities. Virtual reality (VR) technology, with its unique characteristics of immersion, interactivity, and imagination, demonstrates tremendous application potential in radiotherapy. Several randomized controlled trials have confirmed that VR, as a non-pharmacological intervention, can effectively alleviate anxiety in patients, especially children, and improve treatment adherence. In medical education and professional training, VR provides safe training platforms for radiation oncologists, medical physicists, and radiation therapists through the construction of high-fidelity virtual environments. These platforms can be used for training skills in target volume delineation, treatment plan evaluation, and equipment quality control, thereby significantly improving training efficiency and quality. Furthermore, VR technology enables three-dimensional visualization and intuitive evaluation of treatment plans, facilitates multidisciplinary team (MDT) collaboration, and provides new paradigms for the development of real-time guidance technologies that integrate with augmented reality. This article systematically reviews the current applications of VR technology in the clinical practice, medical education, radiation protection, and scientific research of radiotherapy. It also discusses future prospects for integrating VR with artificial intelligence (AI), augmented reality (AR), and haptic feedback technologies. This review provides a valuable reference for the standardized application of VR technology in radiotherapy and radiation protection in China.

[Objective] To compare the diagnostic accuracy of three imaging modalities, inlducing CT urography (CTU), contrast-enhanced MRI (CE-MRI), and contrast-enhanced ultrasound (CEUS) in the qualitative diagnosis of renal space-occupying lesions. [Methods] A retrospective analysis was performed on 542 patients with renal lesions confirmed by surgical pathology in our hospital during Jan.2019 and May 2024.The diagnostic results of CTU, CE-MRI and CEUS were compared and analyzed based on the patients' clinical and pathological data. [Results] The diagnostic accuracy rate of CTU, CE-MRI and CEUS were 84.50%, 83.14% and 86.14%, respectively.For the 161 patients who underwent all three examinations, CEUS was significantly more accurate than CTU (84.16% vs. 77.02%, P=0.018), while there was no significant difference between CTU or CEUS and CE-MRI (79.81%) (P>0.05). Further analysis found that for lesions ≤4 cm, the accuracy of the three examinations was as follows: CEUS=CTU 79.55%, CE-MRI 76.14%, with no significant difference (P>0.05). However, for lesions >4 cm, CEUS ranked the first, followed by CE-MRI and CTU (89.73% vs. 84.25% vs. 73.97%), and CEUS and CE-MRI were better than CTU (P<0.05). Additionally, for the diagnosis of clear cell renal carcinoma and benign renal space-occupying lesions, there was no statistically significant difference among the three imaging modalities (P>0.05), while for the qualitative diagnosis of non-clear cell renal carcinoma, CEUS ranked the first, followed by CE-MRI and CTU (83.87% vs. 74.19% vs. 56.45%), and CE-MRI and CEUS were better than CTU (P<0.05). [Conclusion] All of them have important diagnostic value, and the appropriate selection should be based on patients' specifc conditions.CEUS and CE-MRI are more accurate in the qualitative diagnosis of renal space-occupying lesions than CTU, especially for large lesions and non-clear cell carcinoma.

Objective:To summarize the surgical strategies and to evaluate the clinical outcomes of up-per urinary tract reconstruction in patients with stone-related ureteral strictures.Methods:This retro-spective study included 71 patients diagnosed with ureteral strictures secondary to urinary stones who un-derwent upper urinary tract reconstructive surgery at Peking University First Hospital between March 2014 and November 2023.Patient data were collected,including demographic characteristics,clinical presen-tation,laboratory results,imaging findings,surgical procedures,and follow-up outcomes.Ureteral stric-tures were classified according to anatomical location into upper,middle,lower,or multiple segments.Surgical procedures were carried out depending on the stricture characteristics.Surgical success was de-fined as resolution or improvement of clinical symptoms,radiographic improvement or stabilization of hy-dronephrosis,and maintenance of normal and stable renal function.Results:Among the 71 patients,36(50.7％)had strictures in the upper ureter,9(12.7％)in the middle ureter,15(21.1％)in the lower ureter,and 11(15.5％)had multifocal ureteral strictures.The median stricture length was 5.0 cm(interquartile range:3.0-15.0 cm).Surgical approach selection was individualized based on the location and extent of the stricture.For upper ureteral strictures,the most frequently employed techniques were oral mucosal graft ureteroplasty(13/36,36.1％)and appendiceal flap ureteroplasty(8/36,22.2％).Other options included ureteroureterostomy and ileal ureter replacement for longer or more complex strictures.In middle ureteral strictures,treatment was stratified by length:balloon dilation(1/9,11.1％)and ureteroureterostomy(1/9,11.1％)were applied in shorter strictures,while oral mucosal graft ureteroplasty(3/9,33.3％)and ileal ureter replacement(4/9,44.4％)were reserved for longer segments.For lower ureteral strictures,ureteral reimplantation into the bladder was the most common approach(10/15,66.7％),often combined with a psoas hitch or Boari flap when necessary.All the patients with multiple segmental strictures underwent ileal ureter replacement due to the extensive nature of the disease.The median follow-up period was 14.2 months(range:6.1-107.1 months).During follow-up,69 of 71 patients(97.2％)achieved surgical success.Conclusion:Stone-related ure-teral strictures present with considerable heterogeneity in terms of anatomical location,length,and com-plexity.Careful preoperative evaluation and individualized surgical planning are critical to successful re-construction.With appropriate selection of surgical methods,favorable long-term clinical outcomes can be achieved in the majority of patients.

Objective To investigate the abnormal changes characteristics of the degree centrality(DC)of the brain functional network in patients with benign paroxysmal positional vertigo(BPPV)in the classical frequency band(0.010-0.080 Hz),the slow-4 frequency band(0.027-0.073 Hz),and the slow-5 frequency band(0.010-0.027 Hz).Methods Twenty patients with BPPV(BPPV group)and 14 healthy controls(HC)(HC group)were selected.Resting-state functional magnetic resonance imaging(rs-fMRI)scans were performed,and the clinical data were analyzed.The DC method was used to analyze the changes of centrality of resting state network in patients with BPPV.Results Compared with the HC group,the BPPV group showed an increase in DC in the left caudate nucleus in the classical frequency band(P＜0.05),and a decrease in DC in the right auxiliary motor region in the classical frequency band(P＜0.05);within the slow-4 frequency band,no significant differences were observed in brain regions(P＞0.05);within the slow-5 frequency band,the BPPV group showed an increase in DC in the left thalamus(P＜0.05),while the left anterior cingulate and paracingulate gyrus showed a decrease in DC(P＜0.05).Conclusion Patients with BPPV have spontaneous activity disorders in multiple brain regions at resting states,and these changes show frequency band specificity.

Objective:To explore the correlation between triglyceride-glucose (TyG) index-body mass index (BMI) product (TyG-BMI) and hypertension.Methods:Based on the cross-sectional survey data of adult hypertension prevalence in Hunan Province from June 2013 to May 2014, 4 012 subjects aged ≥18 years with complete key data were included. Binary logistic regression analysis was used to analyze the correlation between TyG-BMI and hypertension, and receiver operating characteristic (ROC) curve was used to compare the ability of TyG index and TyG-BMI to identify hypertension.Results:A total of 4 012 subjects were included in this study, with an average age of (54.6±12.6)years, and males accounted for 40.98%(1 644/4 012). The prevalence of hypertension was 38.33%(1 538/4 012). Logistic regression analysis showed that elevated TyG-BMI was an independent risk factor for hypertension ( P<0.05). In the fully adjusted model, each 1/4 increase in TyG-BMI was associated with a 1.017-fold increase in the risk of hypertension ( OR=1.017, 95% CI: 1.014-1.019). Compared with the lowest quartile group (Q 1), the higher quartile groups (Q 2, Q 3, Q 4) of TyG-BMI had a higher risk of hypertension, with OR values of 1.841, 2.265, and 4.386, respectively. Restricted cubic spline plot showed a linear dose-response relationship between TyG-BMI and the risk of hypertension (overall trend P<0.001). In subgroup analyses stratified by age, gender, smoking and drinking status, TyG-BMI was positively correlated with hypertension. In addition, ROC curve analysis showed that TyG-BMI had better diagnostic value for hypertension compared with TyG index. Conclusions:TyG-BMI is an independent risk factor for hypertension. Excessively high TyG-BMI or gradual increase of TyG-BMI will increase the risk of hypertension, and TyG-BMI has higher value in identifying hypertension compared with TyG index.

Objective To observe the difference of iron deposition in brain deep nuclei of systemic lupus erythematosus(SLE)patients with different disease activity levels using quantitative susceptibility mapping(QSM).Methods Fifty-four SLE patients were retrospectively enrolled and divided into moderate to severe activity group(score＞9,n=25)and mild activity group(score≤9,n=29)according to SLE disease activity index(SLEDAI)score.Patients' general clinical data,as well as the mean QSM of bilateral head of caudate nuclei,putamina,globi pallidi,red nuclei,substantiae nigrae,dentate nuclei and thalami were compared between groups.Pearson or Spearman coefficients were performed to analyze correlations of the mean QSM of nuclei being significant different between groups and conventional clinical indicators.Then receiver operating characteristic(ROC)curve was drawn,and the area under the curve(AUC)was calculated to evaluate the efficacy of the mean QSM for distinguishing moderate to severe and mild activity SLE.Results Compared with mild activity group,moderate to severe activity group had higher serum ferritin,erythrocyte sedimentation rate(ESR),C reactive protein(CRP),anti-double stranded DNA(anti-dsDNA)antibody levels,also higher proportion of positive anti-ribosomal P protein(anti-P)antibodies,but lower complement C3 and C4 levels(all P＜0.05).The mean QSM of bilateral putamina and thalami were significantly higher in moderate to severe activity group than in mild activity group(both P＜0.05).The mean QSM of bilateral putamina was positively correlated with SLEDAI scores,ferritin levels and positivity of anti-P antibodies in SLE patients(with r or rs of 0.447,0.526 and 0.473,respectively,and all P＜0.05).The AUC for distinguishing moderate to severe SLE and mild activity SLE based on the mean bilateral putamina QSM was 0.810.Conclusion There were significant differences of iron deposition in deep brain nuclei of SLE patients with moderate to severe and mild activity.The mean QSM of bilateral putamina could be used to distinguish SLE with moderate to severe activity and mild activity.