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 analyze the results of national external quality assessment (EQA) for transfusion compatibility test from 2018 to 2023, with the aim of providing references for improving laboratory testing quality and ensuring the safety of clinical blood transfusion. Methods: Three EQA programs were conducted annually, each distributing 22 quality assessment samples. Participating transfusion laboratories were required to complete testing within specified deadlines and to submit results along with documentation of testing methodologies, reagents, and equipment used. National Center for Clinical Laboratories (NCCL) conducted statistical analysis of laboratory results, evaluated testing outcomes and related circumstances, and provided feedback to participating laboratories. EQA data from transfusion laboratories across China from 2018 to 2023 were collected and systematically analyzed. Results: From 2018 to 2023, the qualification rates for all five items (ABO forward typing, ABO reverse typing, Rh blood group typing, antibody screening, and cross-matching) were 67.59%, 77.11%, 77.38%, 72.78%, 79.96%, and 85.16%, respectively. The mean qualification rates for ABO forward typing, ABO reverse typing, RhD blood group typing, antibody screening, and cross-matching over the past six years were 96.25%±0.59%, 90.45%±4.52%, 96.05%±0.71%, 90.88%±2.86%, and 88.34%±3.48%, respectively. The qualification rates in 2019, 2020, 2022, and 2023 all showed a stable trend of "blood stations>tertiary hospitals>secondary hospitals". The mean qualification rate of laboratories in secondary hospitals from 2018 to 2023 was significantly lower than those of laboratories in tertiary hospitals and blood stations (P<0.05), while no significant difference was observed between laboratories in tertiary hospitals and blood stations (P>0.05). The micro column agglutination method was the most widely used in all five tests. In the four test items, namely ABO forward typing, ABO reverse typing, antibody screening, and cross-matching, there was a statistically significant difference in the qualification rate of micro column agglutination method compared to other methods (P<0.05). There was a statistical difference in the qualification rate between manual and automated detection using micro column agglutination method in the cross-matching tests (P<0.05), whereas no significant difference was noted for the other test items (P>0.05). Conclusion: From 2018 to 2023, the number of laboratories participating in EQA activities has been increasing year by year, and the qualification rate has shown an overall upward trend. The type of laboratory is a key factor affecting the qualification rate, and the testing capabilities of some laboratories still need to be improved. The micro column agglutination method is widely used in transfusion compatibility tests. The established EQA program effectively monitors quality issues in laboratories, drives continuous improvement, and ensures sustained enhancement of testing standards to safeguard clinical blood safety.

Objective To investigate the effect of left bundle branch area pacing(LBBaP)on new-onset atrial fibrillation(NOAF)and atrial high rate episodes(AHREs)in patients with atrioventricular block(AVB).Methods Eighty-four patients with Ⅲ°AVB for pacemaker implantaion were divided into the LBBaP group(n=42)and the RVSP group(n=42)based on the site of the ventricular leads.The two groupswere compared in terms of the pre-and post-operative QRSd,ventricular pacing parameters,complications,incidence of stroke,NOAF and AHREs.Results(1)The incidence of postoperative NOAF and AHREs in the LBBaP group was significantly lower compared with RVSP group(P<0.05).(2)The p-QRSd in the LBBaP group was significantly shorter compared with RVSP group(P<0.05).(3)The two groups showed no significant differences in ventricular pacing parameters,incidence of complications and stroke events(P>0.05).Conclusion LBBaP is superior to right ventricular pacing in reducing the incidence of postoperative AHREs and NOAF in patients after implantation and improving the prognosis of patients.

Objective To investigate the effect of Kunxian capsule combined with candesartan axetil on blood pressure, renal function, blood lipids and inflammatory factors in patients with chronic glomerulonephritis complicated with hypertension. Methods 101 patients with chronic glomerulonephritis who were admitted to our hospital from November 2017 to December 2019 were selected and randomly divided into observation group (51 cases) and control group (50 cases). The control group was treated with candesartan cilexetil on the basis of conventional treatment, and the observation group was treated with Kunxian capsule on the basis of the control group. The clinical efficacy and adverse reactions of the two groups were compared. Results The total effective rate of the observation group was significantly higher than that of the control group (P<0.05). After treatment, the blood pressure, renal function indexes (24 h Upro, BUN, Scr), blood lipid indexes (TG, TC, LDL-C), and inflammatory factors of the two groups (IL-6, hs-CRP) significantly decreased, and the observation group was significantly lower than the control group (P<0.05). After treatment, the blood lipid index HDL-C of the two groups increased significantly, and the blood lipid index HDL-C of the observation group was significantly higher than that of the control group (P<0.05). Conclusion Kunxian capsule combined with candesartan axetil can enhance the clinical efficacy, improve renal function, regulate blood lipids and reduce inflammation in patients with chronic glomerulonephritis complicated with hypertension.

The massive loss of oligodendrocytes caused by various pathological factors is a basic feature of many demyelinating diseases of the central nervous system (CNS). Based on a variety of studies, it is now well established that impairment of oligodendrocyte precursor cells (OPCs) to differentiate and remyelinate axons is a vital event in the failed treatment of demyelinating diseases. Recent evidence suggests that Foxg1 is essential for the proliferation of certain precursors and inhibits premature neurogenesis during brain development. To date, very little attention has been paid to the role of Foxg1 in the proliferation and differentiation of OPCs in demyelinating diseases of the CNS. Here, for the first time, we examined the effects of Foxg1 on demyelination and remyelination in the brain using a cuprizone (CPZ)-induced mouse model. In this work, 7-week-old Foxg1 conditional knockout and wild-type (WT) mice were fed a diet containing 0.2% CPZ w/w for 5 weeks, after which CPZ was withdrawn to enable remyelination. Our results demonstrated that, compared with WT mice, Foxg1-knockout mice exhibited not only alleviated demyelination but also accelerated remyelination of the demyelinated corpus callosum. Furthermore, we found that Foxg1 knockout decreased the proliferation of OPCs and accelerated their differentiation into mature oligodendrocytes both in vivo and in vitro. Wnt signaling plays a critical role in development and in a variety of diseases. GSK-3β, a key regulatory kinase in the Wnt pathway, regulates the ability of β-catenin to enter nuclei, where it activates the expression of Wnt target genes. We then used SB216763, a selective inhibitor of GSK-3β activity, to further demonstrate the regulatory mechanism by which Foxg1 affects OPCs in vitro. The results showed that SB216763 clearly inhibited the expression of GSK-3β, which abolished the effect of the proliferation and differentiation of OPCs caused by the knockdown of Foxg1. These results suggest that Foxg1 is involved in the proliferation and differentiation of OPCs through the Wnt signaling pathway. The present experimental results are some of the first to suggest that Foxg1 is a new therapeutic target for the treatment of demyelinating diseases of the CNS.

Objective:In order to accurately evaluate the postoperative rehabilitation of gynecological robotic surgery, a prediction model for evaluating postanesthesia care unit (PACU) extubation time and hospital stay in gynecological robotic surgery was established.Methods:The clinical data of gynecological patients who underwent robotic surgery in Xiangya Third Hospital of Central South University from October 2015 to May 2017 were retrospectively analyzed, and the data were screened to evaluate the postoperative recovery of patients from two aspects: PACU extubation time and postoperative hospital stay. Binary logistic regression was used to screen out the factors affecting PACU extubation time and postoperative hospital stay, and the prediction model was preliminarily established and verified.Results:Finally, there were 456 patients and 30 variables analyzed in the binary logistics regression. According to these variables, the prediction model of the postoperative recovery evaluation after gynecological robotic surgical procedures was established. Among them, age, intraoperative amount of atracurium and midazolam were independent risk factors affecting PACU extubation time (all P<0.05). American Society of Anesthesiologists (ASA) grade, intraoperative amount of midazolam, intraoperative bleeding and operation time were independent risk factors affecting postoperative hospital stay (all P<0.05). All models passed Hosmer lemeshow test (all P>0.05); The areas under the receiver operating characteristic curve (ROC) were 0.647 and 0.806, respectively. Conclusions:The prediction model of PACU extubation time and the postoperative hospitalization time has been established.

Objective:To study the distribution of FC γ receptor ⅢB gene polymorphism in the Han population in the Yellow River Delta, and to explore the correlation between the gene polymorphism of multiple loci and the susceptibility and clinical phenotypes of systemic lupus erythematosus (SLE).Methods:From January 2017 to December 2017, 144 SLE patients in the Affiliated Hospital of Binzhou Medical College of Shandong Province were selected as the experimental group and 150 healthy people as the control group. Whole blood samples, clinical data and laboratory examination test data were collected. Genomic DNA was extracted by single base extension polymerase chain reaction (PCR) technology and single nucleoside was extracted by mass spectrometry. The relationship between the polymorphism of each point of FC γ receptor ⅢB gene and the susceptibility and clinical phenotypes of SLE was analyzed by χ2 test with SPSS 25.0 software. Results:① The frequencies of CT and TT genotype at rs115878669 were 50.7%, 64.0%, 23.6% and 10.0% respectively in the test group and the control group, the difference was statistically significant ( χ2=5.3, P=0.021; χ2=9.8, P=0.002); The frequencies of TT genotype at rs147574249 were 17.4% and 8.0% respectively in the test group and the control group, the difference was statistically significant ( χ2=5.9, P=0.016); The frequencies of GG and GA genotype at rs199705513 were 20.8%, 10.0%, 59.0%, 70.0%, the difference was statistically significant ( χ2=6.7, P=0.010; χ2=3.9, P=0.049); The frequency of CA genotype at rs77717968 was 30.6% and 46.0% in the test group and the control group, respectively, the difference was statistically significant ( χ2=7.4, P=0.007). ② In the experimental group, the frequencies of heterozygous CT genotypes at rs115878669 were 37.2% and 56.4% in the blood system affected group and the unaffected group, respectively, the difference was statistically significant ( χ2=4.5, P=0.035). In the thrombocytopenia group and the normal platelet normal count group, the frequencies of AG genotypes at rs114531649 were 79.2% and 50.0%, respectively, the difference was statistically significant ( χ2=6.8, P=0.009) and GG genotypes were 4.2% and 25.8%. The difference was statistically significant ( χ2=4.3, P=0.039). The frequency of CC genotype at rs147574249 was 4.2%, 25.8% respectively. The difference was statistically significant ( χ2=5.4, P=0.020). The frequency of CT genotype was 79.2%, 56.7% respectively. The difference was statistically significant ( χ2=4.2, P=0.040). The frequency of CT geno-type at rs115878669 was 70.8%, 46.7%, respectively. The difference was statistically significant ( χ2=4.7, P=0.031). The frequency of AA genotype at rs199705513 was 4.2%, and 23.3%, the difference was statistically significant ( χ2=4.6, P=0.033), the frequency of AA genotype at rs77717968 was 4.2%, 26.7%, and the difference was statistically significant ( χ2= 4.5, P=0.033), the frequency of TT genotype was 25.0%, 9.2%, the difference was statistically significant ( χ2=4.8, P=0.028). There was no statistical significance difference in other comparisons ( P>0.05). The GG genotype frequencies of rs114531649 and the CC genotype frequencies of rs147574249 were 31.2% and 15.7%, respectively. The differences were statistically significant ( χ2=4.9, P=0.027). The AA geno- type frequencies of rs199705513 were 29.5% and 13.2%, the difference was statistically significant ( χ2=5.8, P=0.016), the CC genotype frequency of homozygote at rs61803007 was 32.8%, 16.9%, the difference was statistically significant ( χ2=4.9, P=0.026), the TC genotype frequency of heterozygote was 67.2%, 83.1%, the difference was statistically significant ( χ2=4.9, P=0.026), the AA genotype frequency of homozygote at rs77717968 was 31.2%, 16.9%, respectively, the difference was statistically significant ( χ2=4.1, P=0.044), and there was no significant difference in other comparisons ( P>0.05). The frequency of TC genotype in rs146653557 was 39.4% in serositis group and 75.0% in non serositis group, the difference was statistically significant ( χ2=4.3, P=0.037), the other differences were not statistically significant ( P>0.05). The frequency of CG genotype in rs428194 group and rs61803004 group was 53.8% and 22.9% respectively, the difference was statistically significant ( χ2=12.7, P=0.000 4). The frequency of GG genotype in rs428194 group was 46.2% and 77.1%, 46.2% and 78.1% in rs61803004 group respectively, the difference was statistically significant ( χ2=12.7, P=0.000 4; χ2=13.7, P=0.000 2). The frequencies of GT genotype were 46.2% and 21.0%. The differences were statistically significant ( χ2=9.0, P=0.002 7). The frequency of TT genotypes was 7.7% and 1.0%, the difference was statistically significant ( χ2=4.8, P=0.029). The frequencies of CT genotypes at rs61803008 were 46.2% and 23.8% respectively, the difference was statistically significant ( χ2=6.8, P=0.009 2). The frequencies of TT genotypes were 46.2% and 74.3%. The difference was statistically significant ( χ2=10.1, P=0.001 5). Conclusion:There is a significant correlation between Fc gamma receptor ⅢB gene related loci and SLE susceptibility and clinical phenotypes.

Objective To explore the level of serum hypoxia-inducible factor (HIF)-1α and the effect of pantoprazole on HIF-1α in patients with gouty arthritis.Methods Subjects were divided into acute gouty arthritis (group A),intermittent gouty arthritis (group B) and healthy controls (group C).Patients in group A were divided into mild (A1) and severe (A2) subgroups according to the severity of inflammation.Levels of serum HIF-1α in the three groups,and the levels of interleukin (IL)-1β and tumor necrosis factor (TNF)-α in group A1 and group A2 were detected by enzyme-linked immunosorbent assay (ELISA).Patients in group A2 were randomly divided into three groups,saline 100 ml/twice a day,20％ pantoprazole 100 ml,twice a day and 40％ panto-prazole 100 ml,twice a day were administered respectively.After 7 days,the levels of serum HIF-1α were measured by ELISA.One-way analysis of variance (ANOVA) and two independent sample t test were conducted in this study.Results ① Levels of serum HIF-1α in group A [(48±13) ng/L] were significantly higher than those in group B [(40±12) ng/L,P＜0.01] and group C [(28±12) ng/L,F=29.838,P＜0.01].② Levels of serum HIF-1α [(56±10) ng/L],IL-1β [(51 ±13) ng/L] and TNF-α [(161 ±45) ng/L] in the experimental group A2 were higher than those in the experimental group A1 [HIF-1α:(42±11) ng/L,t=4.600,P＜0.01;IL-1β:(42±12) ng/L,t=2.552,P＜0.05;TNF-α:(122±34) ng/L,t=3.432,P＜0.01].③ Levels of HIF-1α [(26±6) ng/L],IL-1β [(23±4) ng/L],TNF-α [(92±6) ng/L] in the 40％ pantoprazole group were lower than those in 20％ pantoprazole 100 ml,twice a day group [HIF-1α:(33±4) ng/L];IL-1β:(30±5) ng/L;TNF-α:(102±7) ng/ L] and saline group [HIF-1α:(37±5) ng/L];IL-1β:(38±5) ng/L];TNF-α:(108±9) ng/L](all P＜0.05);Levels of HIF-1α,IL-1β and TNF-αin the 20％ pantoprazole group were lower than those in saline group (all P＜0.05).Conclusion ① HIF-1α may be one of the indicators of acute inflammation,which may reflect the degree of inflammation in patients with gout.② Pantoprazole can reduce the level of serum HIF-1α,IL-1β and TNF-α in patients with gouty arthritis,with a concentration dependent characterisit.

Objective To study the incidence rate of prostate cancer detected in the specimen of radial cystoprostatectomy for bladder cancer and to evaluate its effect on the prognosis.Methods From June 2012 to June 2017,the clinical data of 132 patients with bladder cancer undergoing radical cystectomy (RCP) were analyzed retrospectively.The average age of 132 patients with bladder cancer was 61.2 years (37-89 years old).The serum of PSA of 89 cases out of 132 patients was examined before operation,21 cases 4 ng/ml ＜ tPSA ＜ 10 ng/ml,1 case tPSA 17 ng/ml and 67 cases tPSA ＜ 4 ng/ml.The pathology of bladder and prostate,the location and range of prostate cancer and Gleason score and the prognostic effect of prostate cancer was evaluated.Results The 132 patients with bladder cancer,116 cases (87.9％) were high grade urothelial carcinoma,8 cases (6.0％) were bladder carcinoma in situ,6 cases (4.5％) were low grade urothelial carcinoma,1 case was neuroendocrine bladder carcinoma and 1 case was signet ring cell carcinoma.The 21 cases of prostate cancer were combined with Gleason score,among which 3 + 2 score in 1 cases,3 +3 score in 17 cases,4 +3 and 3 +4 in 1 cases,and 4 +5 score in 1 cases.The lesions were unilateral in 14 cases and bilateral in 7 cases.The lesions were ＜0.5 ml in 3 cases,0.5-0.7 ml in 14 cases and 0.7-1.0 ml in 4 cases.The average age of 21 cases with prostate cancer was 67.5 years old (41-89 years).Of the 21 cases of prostate cancer,the serum tPSA was abnormal in 4 cases with an average of 8.8 ng/ml (4.2-17.0 ng/ml),the serum tPSA was normal in 12 cases with an average of 2.5 ng/ml (1.3-3.7 ng/ml),and the serum PSA in 5 cases was not detected before operation.Three cases of prostate cancer aged less than 60 years old with the detection rate of 9.6％ (3/31);18 cases were equal or older than 60 years old with the detection rate of 17.8％ (18/101).Multi parameter analysis showed that the incidence of prostate cancer increased with the age of the patients (OR =1.36,P =0.048).Followed up for 5 to 51 months,no PSA relapse was found and no patient receiving related treatment.Conclusions The detection rate of prostate cancer is very high in the specimen of radial cystoprostatectomy for bladder cancer.The clinical manifestation of the prostatic involvement is concealed.Radical resection of the prostate is necessary in radical resection of bladder cancer.

Objective To evaluate the efficacy and safety of DA-EPOCH-R protocol for patients with B-cell non-hodgkin lymphoma (NHL). Methods 43 patients with B-cell NHL received DA-EPOCH-R protocol, and their efficacy and adverse reactions were analyzed. Results 43 patients received a total of 203 cycles of chemotherapy and the median chemotherapy cycle was 6 (2ˉ8 cycles). 32 patients (74.4%) achieved complete remission (CR) after 2ˉ4 cycles of chemotherapy. A further analysis found that age ≤60 years and>60 years, stageⅠ/Ⅱand stageⅢ/Ⅳ, germinal center B-cell (GCB), non-GCB, double expression lymphoma (DEL) and non-DEL patients had no significant differences (P> 0.05). With a median follow-up of 40 months (9ˉ62 mouths), the overall survival (OS) rate of 1-year and 3-year was 97.6 % and 92.8 % respectively. The major toxicity of DA-EPOCH-R protocol was hematologic toxicity. Other toxicities were mild, and no treatment-related deaths occurred. At the end of follow-up, no secondary tumors were found. Conclusions DA-EPOCH-R protocol is an effective and safe protocol for patients with NHL. The result shows that the curative effect of patients in stageⅢandⅣis similar to the patients in stageⅠandⅡ.