1.Role of artificial intelligence in medical image analysis.
Lu WANG ; Shimin ZHANG ; Nan XU ; Qianqian HE ; Yuming ZHU ; Zhihui CHANG ; Yanan WU ; Huihan WANG ; Shouliang QI ; Lina ZHANG ; Yu SHI ; Xiujuan QU ; Xin ZHOU ; Jiangdian SONG
Chinese Medical Journal 2025;138(22):2879-2894
With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence
;
Humans
;
Image Processing, Computer-Assisted/methods*
;
Neural Networks, Computer
;
Deep Learning
;
Diagnostic Imaging/methods*
2.Protection of morusin against lipopolysaccharide-induced acute liver injury through gut microbiota modulation and anti-inflammatory effects in mice
Yan LI ; Qi LIU ; Lin WANG ; Yayun LI ; Xinping LI ; Qianqian JIANG ; Zhengzhi WU
Digital Chinese Medicine 2025;8(4):478-490
Objective:
To investigate the protective effects of morusin on lipopolysaccharide (LPS)-induced acute liver injury in mice and its underlying mechanisms.
Methods:
Thirty-two male specific pathogen-free (SPF) C57BL/6J mice were randomly divided into four groups (n = 8 per group): control, LPS, low-dose morusin (morusin-L, 10 mg/kg), and high-dose morusin (morusin-H, 20 mg/kg) groups. The mice in each group were administered the corresponding drugs or normal saline via continuous gavage daily for 16 consecutive days. Except for control group, which received an equal volume of normal saline, other groups were intraperitoneally injected with LPS (5 mg/kg) 2 h after the last gavage to establish the acute liver injury model. Serum and liver tissues were collected for subsequent analysis 6 h after LPS injection. The activities of alanine aminotransferase (ALT) and aspartate aminotransferase (AST) in serum were detected with biochemical methods. The levels of tumor necrosis factor (TNF)-α, interleukin (IL)-6, and IL-1β in serum were measured by enzyme-linked immunosorbent assay (ELISA). Hepatic pathological changes were evaluated by hematoxylin-eosin (HE) staining. The 16S ribosomal RNA (16S rRNA) sequencing was performed to assess the composition of intestinal flora, linear discriminant analysis effect size (LEfSe) was applied for multi-level species discrimination, and Spearman’s correlation analysis was performed. The liver tissues of mice with acute liver injury were analyzed by RNA sequencing (RNA-seq) technology to identify differentially expressed genes (DEGs), and then enrichment analysis of the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway was conducted. The expression levels of selected genes was validated by quantitative reverse transcription polymerase chain reaction (qRT-PCR), while immunohistochemistry (IHC) was performed to examine the expression levels of IL-6, myeloid differentiation primary response 88 (MYD88), and toll-like receptor 2 (TLR2).
Results:
Morusin significantly reduced the serum levels of ALT, AST, and inflammatory factors (TNF-α, IL-6, and IL-1β) (P < 0.05, P < 0.01, or P < 0.001), while alleviating the hepatic pathological damage in mice. Based on efficacy comparisons, morusin-H group was selected for subsequent microbiome and transcriptome analyses. Microbiome analysis revealed that morusin-H effectively mitigated LPS-induced gut dysbiosis and restored the Firmicutes/Bacteroidota balance (P < 0.01). At the genus level, morusin-H significantly reduced the abundances of norank_f_Muribaculaceae, Desulfovibrio, Parabacteroides, and Muribaculum (P < 0.05, P < 0.01, or P < 0.001). At the phylum, family, and genus levels, our findings indicated that morusin-H treatment caused a significant decrease in the abundance of Desulfobacterota, Desulfovibrionaceae, and Desulfovibrio (P < 0.01). Importantly, the abundance of Desulfovibrio was positively correlated with the levels of ALT, AST, TNF-α, IL-1β, and IL-6. Transcriptomic and molecular analyses showed that the therapeutic mechanism of morusin-H involved suppression of the IL-17/TNF signaling pathways and downregulating the mRNA levels of Tlr2, Tlr3, Myd88, Il6, and Cxcl10 (P < 0.05 or P < 0.001), as well as the protein levels of key inflammatory mediators (IL-6, MYD88, and TLR2) (P < 0.001).
Conclusion
Morusin demonstrates protective effects against LPS-induced acute liver injury, likely through modulation of gut microbiota and suppression of pro-inflammatory factor expression. These findings indicate that morusin exerts its effects through the "microbiota-inflammation-liver" axis, providing a theoretical basis for its use as a multi-target plant-based drug in the treatment of metabolic inflammation-related liver diseases.
3.Analysis on Components Absorbed into Blood and Cerebrospinal Fluid of Schisandrae Chinensis Fructus Based on Sequential Metabolism
Shuang YU ; Yanli PAN ; Huining LIU ; Xueyan LI ; Xinyu WANG ; Dongying QI ; Fulu PAN ; Qianqian WANG ; Xiaoyu CHAI ; Guopeng WANG ; Tao MA ; Yang LIU
Chinese Journal of Experimental Traditional Medical Formulae 2024;30(3):114-123
ObjectiveTo identify the prototypical components and metabolites absorbed into blood and cerebrospinal fluid of Schisandrae Chinensis Fructus(SCF) based on sequential metabolism combined with liquid chromatography-mass spectrometry. MethodBlood and cerebrospinal fluid samples of integrated metabolism, intestinal metabolism and hepatic metabolism were collected from male SD rats after gavage and in situ intestinal perfusion administration, and ultra-performance liquid chromatography-quadrupole/electrostatic field orbitrap high-resolution mass spectrometry(UPLC Q-Exactive Orbitrap MS) was used to analyze and compare the differences in the spectra of SCF extract, blank plasma, administered plasma, blank cerebrospinal fluid and administered cerebrospinal fluid with ACQUITY UPLC BEH Shield RP18 column(2.1 mm×100 mm, 1.7 µm), the mobile phase was acetonitrile(A)-0.1% formic acid aqueous solution(B) for gradient elution(0-7 min, 95%B; 7-12 min, 95%-35%B; 12-17 min, 35%-15%B; 17-20 min, 15%-12%B; 20-22 min, 12%-5%B; 22-23 min, 5%B; 23-25 min, 5%-95%B; 25-28 min, 95%B). And heated electrospray ionization(HESI) was used with positive and negative ion modes, the scanning range was m/z 100-1 500. The prototypical constituents and their metabolites absorbed into blood and cerebrospinal fluid of SCF were identified according to the retention time, characteristic fragments, molecular formulae and the information of reference substances. ResultA total of 42 chemical components were identified in the extract of SCF, including lignans, flavonoids, amino acids, tannins, and others, of which lignans were the main ones. A total of 27 prototypical components and 14 metabolites were identified in plasma samples from different sites. A total of 15 prototypical components and 9 metabolites were identified in cerebrospinal fluid. The main metabolic reactions involved in the formation of metabolites were mainly demethylation, methylation, demethoxylation and hydroxylation. ConclusionThrough the systematic identification of the prototypical components and metabolites of SCF in rats, it provides data support for further better exploring the material basis of SCF in the treatment of central nervous system diseases.
4.Quantitative research on China's disability rehabilitation policy using policy modeling consistency index model
Tongtong GUO ; Xinyi ZHANG ; Lihong JI ; Zhiwei DONG ; Zongrun LI ; Liduan WANG ; Weiqin CAI ; Qianqian GAO ; Qi JING ; Wengui ZHENG
Chinese Journal of Rehabilitation Theory and Practice 2024;30(6):621-629
Objective To quantitatively analyze and evaluate the content of rehabilitation policy for people with disabilities in China. Methods This study focused on ten national policies of disability rehabilitation issued from 2021 to 2023.It employed text mining techniques to process policy texts and constructed a policy modeling consistency index model for dis-ability rehabilitation policies in China.The relevant policies were evaluated and analyzed quantitatively. Results The disability rehabilitation policies in China were relatively comprehensive in terms of policy transparency,op-erational mechanisms and policy nature.However,there was still a need for optimization in terms of policy per-spectives,target groups,incentive mechanisms,and other aspects. Conclusion The overall quality of disability rehabilitation policy texts at the national level in China is relatively good.There is a need to further enhance the predictability of policy objectives,clarify the responsibilities and division of labor among various departments,and improve policy incentive mechanisms in future policy formulation,which will further refine China's disability rehabilitation policy system and contribute to high-quality develop-ment of the disability cause.
5.Analysis of framework and strategies of community-based health-related rehabilitation service for older adults based on ICF
Qi JING ; Weiqin CAI ; Qianqian GAO ; Lihong JI ; Zhiwei DONG ; Yang XING ; Wei LI ; Jianhua ZHANG
Chinese Journal of Rehabilitation Theory and Practice 2024;30(7):804-810
Objective To assess the elderly health-related rehabilitation services(HRRS)needs from a community and population perspective and construct a community-based elderly HRRS framework. Methods The limitation of the elderly HRRS was analyzed,a community-based elderly rehabilitation service framework based on the International Classification of Functioning,Disability,and Health(ICF)was guided,and the imple-mentation path was proposed. Results This paper analyzed the evaluation,provision and models of existing community rehabilitation services both do-mestically and internationally.It combined the background and practical requirements of China's new era to eluci-date the connotation of HRRS for the elderly in the community.It proposed constructing a community-based el-derly HRRS framework guided by ICF.The paper also offered implementation strategies for promoting communi-ty-based elderly HRRS,focusing on enhancing leadership and policy,financing,human resources,service provi-sion,technology,and digital intelligence empowerment.It provided reference and insights for advancing the na-tional strategy of population aging and implementing the Healthy China strategy. Conclusion It is suggested to continue to accelerate the development of rehabilitation capacity,and increase the supply of HRRS,to meet the diverse needs of the masses of HRRS.
6.Study on the variation characteristics of serum lymphocyte subsets, immunoglobulins, and complement levels in patients with cheilitis
Qi ZHANG ; Ming CHENG ; Rui ZHAO ; Qianqian MA
Chinese Journal of Stomatology 2024;59(10):1027-1036
Objective:To analyze the variations of serum lymphocyte subsets, immunoglobulins, and complement levels in patients with cheilitis, and to explore the associations between the changes in serum immune levels and the onset of cheilitis.Methods:A retrospective analysis was conducted on 153 patients with cheilitis who visited the Department of Stomatology, The First Affiliated Hospital of Zhengzhou University from January 2017 to December 2023. They were compared with 50 healthy individuals who visited the physical examination department during the same period. The changes of serum lymphocyte subsets, immunoglobulins, and complement levels in patients with cheilitis were analyzed. Main detection indicators as the percentage of total T lymphocytes (T%), helper/inducer T lymphocytes (CD4 +T%), absolute numbers of total T lymphocytes (T#), absolute numbers of helper/inducer T lymphocytes (CD4 +T#), percentage of natural killer cells (NK%), absolute numbers of B lymphocytes (B#), immunoglobulins IgG, IgM and complement C3, C4 were included. Multivariate logistic regression was used to explore the relationship between serum lymphocyte subsets, immunoglobulins, complement levels and cheilitis. Subgroup analysis was further conducted on patients with cheilitis based on gender, age, cheilitis type and severity. Results:The levels of T% [69.54% (64.41%, 75.14%)], CD4 +T% [(35.09±7.10)%], T# [1 328.00 (1 054.00, 1 560.50)], and CD4 +T# [653.00 (505.00, 831.50)] in the cheilitis group were significantly lower than those in the control group respectively [72.33% (69.41%, 75.47%), (39.07±5.84)%, 1 483.50 (1 245.75, 1 805.25), 769.00 (687.25, 933.00), with the corresponding statistical test results of Z=-2.64, P=0.008; t=3.58, P<0.001; Z=-2.80, P=0.005; Z=-3.80, P<0.001]. The level of NK% [16.21% (12.16%, 21.29%)] was significantly higher in the cheilitis group compared to the control group [14.61% (10.97%, 17.87%)] ( Z=-2.28, P=0.023). IgG [12.29 (10.77, 13.73) g/L] and IgM levels [1.18 (0.86, 1.58) g/L] were significantly higher in the cheilitis group than in the control group respectively [11.52 (10.16, 12.91) g/L, 0.99 (0.77, 1.26) g/L] ( Z=-2.24, P=0.025; Z=-2.10, P=0.036), while complement C3 [(1.09±0.17) g/L] and C4 levels [0.23 (0.19, 0.28) g/L] were significantly lower in the cheilitis group compared to the control [(1.18±0.17) g/L, 0.31(0.24, 0.35) g/L] ( t=3.10, P=0.002; Z=-4.79, P<0.001). Logistic regression analysis showed that elevated IgG ( P=0.021), decreased C4 ( P<0.001), decreased CD4 +T% ( P=0.003), and decreased T# ( P=0.035) were independent influencing factors for the occurrence of cheilitis. The rate of abnormal lymphocyte immune analysis in the cheilitis group [68.0% (104/153)] was significantly higher than that in the control group [24.0% (12/50)] (χ 2=29.76, P<0.001). The rate of abnormal immunoglobulin and complement detection in the cheilitis group [41.8% (64/153)] was significantly higher than that in the control group [4.0% (2/50)] (χ 2=24.58, P<0.001). The rate of detection abnormalities in female patients with cheilitis [51.5% (53/103)] was significantly higher than in male ones [22.0% (11/50)] (χ 2=12.00, P=0.001). Patients with granulomatous cheilitis had significantly lower levels of T# [1 136.50 (663.75, 1 310.50)] and B# [162.50 (104.00, 225.50)] compared to those with chronic cheilitis [1 366.00 (1 063.03, 1 602.00), 202.48 (148.00, 298.00)] ( Z=-2.35, P=0.019; Z=-2.16, P=0.031). Conclusions:Patients with cheilitis exhibit a certain degree of imbalance on cellular immunity, humoral immunity, and innate immunity, which may be related to the onset of cheilitis.
7.Imaging Features of Patients With Isolated Left Ventricular Apical Hypoplasia
Yaoyao CAI ; Qianqian LIU ; Linyuan WAN ; Hongxia QI ; Muzi LI ; Hong MENG
Chinese Circulation Journal 2024;39(7):682-687
Objectives:To explore the imaging features of patients with isolated left ventricular apical hypoplasia(ILVAH). Methods:Twelve patients diagnosed with ILVAH(ILVAH group)in our hospital from April 2018 to August 2023 were enrolled,and all of them received transthoracic echocardiography(TTE)examination;9 patients underwent CMR examination;and 1 patient underwent CT examination.Clinical data and imaging characteristics of the patients were analyzed.At the same time,twelve healthy age and sex matched participants who underwent physical examination in the same period were selected as the control group. Results:TTE showed that:compared with the control group,the left ventricular transverse diameter([46.3±5.7]mm vs.[57.8±12.6]mm)and right ventricular long diameter([62.0±4.2]mm vs.[73.6±6.4]mm)were larger in the ILVAH group(P<0.05),the left ventricular long diameter([63.0±3.5]mm vs.[53.4±8.2]mm)was smaller(P<0.05).There was no significant difference in right ventricular transverse diameter between the two groups(P>0.05).The interventricular septum was convex to the right ventricle,and the thickness at the apex was(5.2±2.0)mm in the ILVAH group.The papillary muscles were all attached to the flat left ventricular apex.Among the 9 patients who underwent CMR examination,adipose tissue replacement was found in the left ventricular apex in 7 out of the 9 patients,and endocardial fibrosis was found in 2 out of the 9 patients. Conclusions:The clinical presentation of ILVAH is non-specific,but there are specific imaging manifestations that may help improve the understanding of the disease.
8.Adenosine monophosphate-activated protein kinase and vascular cognitive impairment
Qianqian QI ; Zhenjie TENG ; Xiaohua XIE ; Yanhong DONG ; Peiyuan LYU
Chinese Journal of Behavioral Medicine and Brain Science 2024;33(6):567-571
Adenosine monophosphate-activated protein kinase(AMPK) is a highly conserved serine/ threonine protein kinase which plays an important role in regulating energy metabolism of the systemic cells. Under stress conditions, such as ischemia and hypoxia, AMPK can be activated.Then it plays a neuroprotective role in regulating mechanisms such as oxidative stress, autophagy, apoptosis and neuroinflammation and so on. Researches have found that chronic cerebral hypoperfusion may be a major cause of vascular cognitive impairment(VCI).AMPK can exert neuroprotective effects on VCI by regulating the aforementioned pathological processes.Therefore, this article reviews the molecular biological characteristics of AMPK and its role and mechanism in VCI, with the aim of promoting further research on AMPK and making it a new target for VCI treatment.
9.Application of NNN-linked early care intervention in children with autism spectrum disorders
Caixiao SHI ; Yuyan SUN ; Qianqian QI ; Minghui SHI ; Mengyao LI ; Linqi ZHANG
Chinese Journal of Modern Nursing 2024;30(34):4739-4744
Objective:To explore the application effect of early nursing intervention based on NNN-link in social disorders of children with autism spectrum disorders (ASD) .Methods:A total of 126 hospitalized children with ASD in the Rehabilitation Center of Henan Children's Hospital from January to May 2023 were selected as research subjects by convenience sampling. They were randomly divided into an intervention group ( n=63) and a control group ( n=63) using a random number table. The control group received routine care, while the intervention group received early nursing intervention based on NNN-link in addition to routine care. The Social Disorder-related Nursing Diagnosis Outcome Scales and the Childhood Autism Rating Scale (CARS) scores were compared between the two groups before and after intervention. Results:After the early nursing intervention, the scores for family atmosphere, participation in leisure activities, participation in play, social skills, and social participation were higher in the intervention group compared to the control group, the differences were statistically significant ( P<0.05). The CARS scores of the intervention group were also lower than those of the control group, the differences were statistically significant ( P<0.05) . Conclusions:Early nursing intervention based on NNN-link can effectively improve the social disorder conditions of children with ASD, reduce their autism symptoms, and promote recovery.
10.Comparison of Risk Prediction Models for Atherosclerosis in Type 2 Diabetes Mellitus
Yifan WANG ; Chaojun SHI ; Xiaojie MA ; Wenjia FENG ; Hongqing AN ; Qianqian GAO ; Qi JING ; Weiqin CAI ; Anning MA
Journal of Medical Informatics 2024;45(7):74-80
Purpose/Significance To explore the application and predictive accuracy of various models in predicting the risk of ather-osclerosis in diabetic patients.Method/Process Based on the biochemical data table from the"Diabetes Complications Warning Dataset"provided by the National Population Health Science Data Center,MATLAB software is used to construct risk prediction models for diabe-tes-induced atherosclerosis.The models are built by using k-nearest neighbors(KNN),decision trees,backpropagation(BP)neural networks,and Naive Bayes algorithms,and which are subjected to comparative analysis.Result/Conclusion In terms of effectiveness,the predictive accuracy of Naive Bayes algorithm is the highest(61.6%),followed by the decision tree model(58.2%),the KNN mod-el(57.7%),and the BP neural network model(55.9%).The results of the confusion matrix and the receiver operating characteristic(ROC)curve indicate that the Naive Bayes model performs best.When comparing the models in terms of effectiveness,performance and stability,the Naive Bayes model is superior.

Result Analysis
Print
Save
E-mail