Medical imaging foundation models, as an important direction in the intelligent analysis of medical images, are driving a paradigm shift in this field—from task-specific modeling for individual tasks toward a new paradigm grounded in large-scale pre-training and general-purpose representation learning. These models have demonstrated considerable potential in multimodal information integration, cross-task transfer, multi-scenario adaptation, and generative interaction. However, most current studies remain based on benchmark datasets, retrospective cohorts, or controlled experimental conditions, and still face challenges such as insufficient data representativeness, task settings that deviate from real-world clinical workflows, inadequate validation of generalizability and robustness, and ambiguous boundaries of ethical oversight and accountability. This article reviews the research background, key technologies, and advances in the applications of medical imaging foundation models, and further discusses practical challenges including data governance, workflow integration, and ethical regulation, with the aim of providing guidance for related research and clinical translation.

Abstract Non-small cell lung cancer(NSCLC), the most prevalent type of lung cancer, has a poor prognosis in patients with advanced disease. In recent years, immune checkpoint inhibitors(ICIs) have demonstrated promising efficacy in this disease, while bringing a unique set of immune-related adverse events(irAEs). This article comprehensively explores the multi-systemic irAEs of programmed death protein-1(PD-1)/programmed death protein ligand-1(PD-L1) inhibitors in the treatment of NSCLC, including but not limited to dermatotoxicity, endocrine toxicity,hepatic toxicity and gastrointestinal toxicity. The occurrence of these adverse reactions not only poses a challenge for clinical treatment,but also correlates with treatment efficacy. In addition,the paper discusses biomarkers for predicting the risk of ir AEs,such as gut microbiota,blood biomarkers,etc.,with the aim of providing a potential risk assessment tool for the clinic.

Recent advances in large models demonstrate significant prospects for transforming the field of medical imaging. These models, including large language models, large visual models, and multimodal large models, offer unprecedented capabilities in processing and interpreting complex medical data across various imaging modalities. By leveraging self-supervised pretraining on vast unlabeled datasets, cross-modal representation learning, and domain-specific medical knowledge adaptation through fine-tuning, large models can achieve higher diagnostic accuracy and more efficient workflows for key clinical tasks. This review summarizes the concepts, methods, and progress of large models in medical imaging, highlighting their potential in precision medicine. The article first outlines the integration of multimodal data under large model technologies, approaches for training large models with medical datasets, and the need for robust evaluation metrics. It then explores how large models can revolutionize applications in critical tasks such as image segmentation, disease diagnosis, personalized treatment strategies, and real-time interactive systems, thus pushing the boundaries of traditional imaging analysis. Despite their potential, the practical implementation of large models in medical imaging faces notable challenges, including the scarcity of high-quality medical data, the need for optimized perception of imaging phenotypes, safety considerations, and seamless integration with existing clinical workflows and equipment. As research progresses, the development of more efficient, interpretable, and generalizable models will be critical to ensuring their reliable deployment across diverse clinical environments. This review aims to provide insights into the current state of the field and provide directions for future research to facilitate the broader adoption of large models in clinical practice.
Humans ; Diagnostic Imaging/methods* ; Precision Medicine/methods* ; Image Processing, Computer-Assisted/methods*

Objective:To investigate the prospective association between lifestyle and the risk for all-cause mortality in middle-aged and elderly residents in China.Methods:The data from China Health and Retirement Longitudinal Study were used. Baseline information about the lifestyle were collected through questionnaire survey and physical measurements, and the mortality data were obtained through surveys conducted at 2-3 year intervals. A total of 5 436 study participants were included. A comprehensive lifestyle including smoking, alcohol consumption, sleep, BMI and physical activity was constructed, and a multivariate-adjusted Cox proportional hazards regression model was used to estimate the association between lifestyle and the risk for all-cause mortality.Results:During the follow-up of average 8.2 years, 695 deaths were recorded. The comprehensive lifestyle score was linearly associated with the risk for all-cause mortality. Compared with the study participants with comprehensive lifestyle score of 0-1, those with score of 2-5 all had lower risk for all-cause mortality, with HRs of 0.78 (95% CI: 0.62-0.98), 0.56 (95% CI: 0.44-0.72), 0.36 (95% CI:0.27-0.48), and 0.33 (95% CI: 0.21-0.52), respectively. The results of Cox proportional hazards regression model analysis of single lifestyle showed that compared with those with unhealthy lifestyles, the HRs of all-cause mortality for study participants who never smoked, had moderate alcohol consumption, had appropriate night sleep, maintained healthy body weight and kept active physical activity were 0.70 (95% CI: 0.57-0.84), 0.76 (95% CI: 0.64-0.90), 0.79 (95% CI: 0.67-0.94), 0.73 (95% CI: 0.62-0.87), and 0.68 (95% CI: 0.58-0.80), respectively. Conclusions:Keeping healthy lifestyles can significantly reduce the risk for all-cause mortality in middle-aged and elderly residents China. The higher the healthy lifestyle level, the lower the risk for all-cause mortality.

Objective:To deeply analyze the epidemiological characteristics and changing trends of intestinal infectious diseases in China, and provide scientific evidence for the prevention and control of intestinal infectious diseases.Methods:The incidence data of notifiable intestinal infectious diseases in China from 2013 to 2022 were collected from China Disease Prevention and Control Information System. Descriptive statistical method was used to analyze the distributions of intestinal infectious diseases in China, and the annual change rate and seasonal index were calculated.Results:During 2013-2022, intestinal infectious diseases were reported nationwide, with the cases accounting for 43.50% of all notifiable infectious disease cases. The average reported incidence rate was 224.50/100 000, showing a decreasing trend year by year (average annual percent change=-6.45%, t=-2.76, P=0.025). The top 5 intestinal infectious diseases were hand foot and mouth disease (HFMD) (130.40/100 000), other infectious diarrhea (80.18/100 000), dysentery (7.45/100 000), acute hemorrhagic conjunctivitis (2.49/100 000) and viral hepatitis E (1.92/100 000). The incidences of dysentery, HFMD, typhoid fever/paratyphoid fever, viral hepatitis A and acute hemorrhagic conjunctivitis all showed decreasing trends year by year (all P<0.05), while the incidences of hepatitis E and other infectious diarrhea showed no significant changes with year (both P>0.05). The incidence of intestinal infectious diseases was high during May to October, with the peak in June. The incidence rate of intestinal infectious diseases was significantly higher in men than in women (all P<0.05). The HFMD, other infectious diarrhea and dysentery cases were mainly children aged 0-5 years, while the cholera, hepatitis A, hepatitis E, typhoid fever/paratyphoid fever and acute hemorrhagic conjunctivitis cases were mainly farmers aged ≥20 years. The annual reported incidence rate of intestinal infectious diseases was higher in southern provinces (283.66/100 000) than in northern provinces (142.63/100 000), and the annual reported incidence rate of intestinal infectious diseases was higher in coastal provinces (279.52/100 000) than in inland provinces (181.78/100 000), the differences were all significant (both P<0.001). Conclusions:During 2013-2022, the incidence of intestinal infectious diseases decreased significantly in China, with HFMD and other infectious diarrhea as the main diseases. Strengthened surveillance for intestinal infectious diseases should be carried out in key groups, such as children living scatteredly and farmers, and targeted prevention and control measures should be taken according to the epidemiological characteristics of different diseases to effectively reduce the incidence of intestinal infectious diseases.

Objective:To investigate the prospective association between lifestyle and the risk for all-cause mortality in middle-aged and elderly residents in China.Methods:The data from China Health and Retirement Longitudinal Study were used. Baseline information about the lifestyle were collected through questionnaire survey and physical measurements, and the mortality data were obtained through surveys conducted at 2-3 year intervals. A total of 5 436 study participants were included. A comprehensive lifestyle including smoking, alcohol consumption, sleep, BMI and physical activity was constructed, and a multivariate-adjusted Cox proportional hazards regression model was used to estimate the association between lifestyle and the risk for all-cause mortality.Results:During the follow-up of average 8.2 years, 695 deaths were recorded. The comprehensive lifestyle score was linearly associated with the risk for all-cause mortality. Compared with the study participants with comprehensive lifestyle score of 0-1, those with score of 2-5 all had lower risk for all-cause mortality, with HRs of 0.78 (95% CI: 0.62-0.98), 0.56 (95% CI: 0.44-0.72), 0.36 (95% CI:0.27-0.48), and 0.33 (95% CI: 0.21-0.52), respectively. The results of Cox proportional hazards regression model analysis of single lifestyle showed that compared with those with unhealthy lifestyles, the HRs of all-cause mortality for study participants who never smoked, had moderate alcohol consumption, had appropriate night sleep, maintained healthy body weight and kept active physical activity were 0.70 (95% CI: 0.57-0.84), 0.76 (95% CI: 0.64-0.90), 0.79 (95% CI: 0.67-0.94), 0.73 (95% CI: 0.62-0.87), and 0.68 (95% CI: 0.58-0.80), respectively. Conclusions:Keeping healthy lifestyles can significantly reduce the risk for all-cause mortality in middle-aged and elderly residents China. The higher the healthy lifestyle level, the lower the risk for all-cause mortality.

Objective:To deeply analyze the epidemiological characteristics and changing trends of intestinal infectious diseases in China, and provide scientific evidence for the prevention and control of intestinal infectious diseases.Methods:The incidence data of notifiable intestinal infectious diseases in China from 2013 to 2022 were collected from China Disease Prevention and Control Information System. Descriptive statistical method was used to analyze the distributions of intestinal infectious diseases in China, and the annual change rate and seasonal index were calculated.Results:During 2013-2022, intestinal infectious diseases were reported nationwide, with the cases accounting for 43.50% of all notifiable infectious disease cases. The average reported incidence rate was 224.50/100 000, showing a decreasing trend year by year (average annual percent change=-6.45%, t=-2.76, P=0.025). The top 5 intestinal infectious diseases were hand foot and mouth disease (HFMD) (130.40/100 000), other infectious diarrhea (80.18/100 000), dysentery (7.45/100 000), acute hemorrhagic conjunctivitis (2.49/100 000) and viral hepatitis E (1.92/100 000). The incidences of dysentery, HFMD, typhoid fever/paratyphoid fever, viral hepatitis A and acute hemorrhagic conjunctivitis all showed decreasing trends year by year (all P<0.05), while the incidences of hepatitis E and other infectious diarrhea showed no significant changes with year (both P>0.05). The incidence of intestinal infectious diseases was high during May to October, with the peak in June. The incidence rate of intestinal infectious diseases was significantly higher in men than in women (all P<0.05). The HFMD, other infectious diarrhea and dysentery cases were mainly children aged 0-5 years, while the cholera, hepatitis A, hepatitis E, typhoid fever/paratyphoid fever and acute hemorrhagic conjunctivitis cases were mainly farmers aged ≥20 years. The annual reported incidence rate of intestinal infectious diseases was higher in southern provinces (283.66/100 000) than in northern provinces (142.63/100 000), and the annual reported incidence rate of intestinal infectious diseases was higher in coastal provinces (279.52/100 000) than in inland provinces (181.78/100 000), the differences were all significant (both P<0.001). Conclusions:During 2013-2022, the incidence of intestinal infectious diseases decreased significantly in China, with HFMD and other infectious diarrhea as the main diseases. Strengthened surveillance for intestinal infectious diseases should be carried out in key groups, such as children living scatteredly and farmers, and targeted prevention and control measures should be taken according to the epidemiological characteristics of different diseases to effectively reduce the incidence of intestinal infectious diseases.

Diseases caused by animal virus infection seriously restricts the healthy development of animal husbandry.In-depth study of the molecular mechanism of viral replication and pathogenesis will provide theoretical basis for screening vaccine and drug targets.N6-methyladenosine(m6 A)modification occurs extensively in viral and host transcriptomes and affects viral replication and pathogenicity by regulating gene expression,which acts as a novel regulator of gene expression in addition to DNA and protein modifications.Insight into the regulatory molecular mechanism of m6 A modification in virus infection is the research hotspots and frontiers.In recent years,there are re-ports of alternation of the m6 A modification-associated epitranscriptomes and related function a-nalysis during virus infection.Here,we summarize the alternation of the epitranscriptomes induced by African swine fever virus(ASFV),porcine reproductive and respiratory syndrome virus(PRRSV),porcine epidemic diarrhoea virus(PEDV),cestode virus(CSFV),porcine pseudorabies virus(PRV),Marek's disease virus(MDV),Newcastle disease virus(NDV),avian leukaemia virus(ALV)and duck hepatitis A virus(DHAV)infection,and the subsequent effects on viral replica-tion and pathogenicity.We also discuss the potential role and molecular mechanism of m6 A modification in animal virus replication and pathogenesis,which will contributes to the prevention and control for animal disease.

Peritoneal metastasis is a key factor in the poor prognosis of advanced gastrointestinal cancer patients. Traditional radiological diagnostic faces challenges such as insufficient sensitivity. Through technologies like radiomics and deep learning, artificial intelligence can deeply analyze the tumor heterogeneity and microenvironment features in medical images, revealing markers of peritoneal metastasis and constructing high-precision predictive models. These technologies have demonstrated advantages in tasks such as predicting peritoneal metastasis, assessing the risk of peritoneal recurrence, and identifying small metastatic foci during surgery. This paper summarizes the representative progress and application prospects of medical imaging artificial intelligence in the diagnosis and treatment of peritoneal metastasis, and discusses potential development directions such as multimodal data fusion and large model. The integration of medical imaging artificial intelligence with clinical practice is expected to advance personalized and precision medicine in the diagnosis and treatment of peritoneal metastasis in gastrointestinal cancers.

Objective:To investigate the effect and mechanism of Jianpi Qinghua granule in improving skeletal muscle insulin resistance induced by long-term low-dose cadmium exposure in rats.Methods:A total of 24 SPF-grade healthy 2-month-old Sprague-Dawley rats were assigned to normal control(NC) group, cadmium exposure(Cd) group, and Jianpi Qinghua granule protection(Cd+ JPQHG) group. After 24 weeks, fasting blood glucose and insulin levels were measured, and HOMA-IR was calculated. The intraperitoneal glucose tolerance test and insulin tolerance test were conducted to assess insulin sensitivity. Skeletal muscle tissues were extracted for Western blot analysis to detect levels of insulin signaling pathway-related proteins. Immunofluorescence was used to assess the translocation of glucose transporter 4(GLUT4), and oxidative stress markers were measured.Results:Compared to the NC group, the Cd group showed significant increases in fasting plasma glucose, fasting insulin levels, and HOMA-IR after 24-week exposure. Abnormal glucose and insulin tolerance were also observed in the Cd group. The 12-week intervention with Jianpi Qinghua granule significantly improved glucose metabolism and alleviated the abnormalities in glucose and insulin tolerance. Western blot results indicated that the phosphorylation levels of PI3K and Akt in the skeletal muscle of the Cd group were significantly reduced compared to the NC group, while these levels were significantly elevated in the Cd+ JPQHG group, along with increased translocation of GLUT4 to the cell membrane. Additionally, cadmium exposure significantly increased H 2O 2 and malondialdehyde levels while decreased antioxidant enzyme activity. These oxidative stress indicators improved significantly after Jianpi Qinghua granule intervention( P<0.05). Conclusion:Jianpi Qinghua granule may improve skeletal muscle insulin resistance and glucose metabolism disorders due to long-term low-dose cadmium exposure by reducing oxidative stress, regulating the phosphorylation levels of key proteins in the insulin signaling pathway, and promoting GLUT4 translocation to the cell membrane.