Prostate cancer (PCa) ranks as the second most prevalent malignancy among men worldwide. Early diagnosis, personalized treatment, and prognosis prediction of PCa play a crucial role in improving patients' survival rates. The advancement of artificial intelligence (AI), particularly the utilization of deep learning (DL) algorithms, has brought about substantial progress in assisting the diagnosis, treatment, and prognosis prediction of PCa. The introduction of the foundation model has revolutionized the application of AI in medical treatment and facilitated its integration into clinical practice. This review emphasizes the clinical application of AI in PCa by discussing recent advancements from both pathological and imaging perspectives. Furthermore, it explores the current challenges faced by AI in clinical applications while also considering future developments, aiming to provide a valuable point of reference for the integration of AI and clinical applications.
Humans ; Prostatic Neoplasms/diagnosis* ; Male ; Artificial Intelligence ; Deep Learning ; Prognosis

Advancements in artificial intelligence (AI) and emerging technologies are rapidly expanding the exploration of chemical space, facilitating innovative drug discovery. However, the transformation of novel compounds into safe and effective drugs remains a lengthy, high-risk, and costly process. Comprehensive early-stage evaluation is essential for reducing costs and improving the success rate of drug development. Despite this need, no comprehensive tool currently supports systematic evaluation and efficient screening. Here, we present druglikeFilter, a deep learning-based framework designed to assess drug-likeness across four critical dimensions: 1) physicochemical rule evaluated by systematic determination, 2) toxicity alert investigated from multiple perspectives, 3) binding affinity measured by dual-path analysis, and 4) compound synthesizability assessed by retro-route prediction. By enabling automated, multidimensional filtering of compound libraries, druglikeFilter not only streamlines the drug development process but also plays a crucial role in advancing research efforts towards viable drug candidates, which can be freely accessed at https://idrblab.org/drugfilter/.

Obesity and metabolic dysfunction-associated steatotic liver disease (MASLD) are linked to numerous chronic conditions, including cardiovascular disease, atherosclerosis, chronic kidney disease, and type II diabetes. Previous research identified the natural flavonoid diosmin, derived from Chrysanthemum morifolium, as a regulator of glucose metabolism. However, its effects on lipid metabolism and underlying mechanisms remained unexplored. The AMP-activated protein kinase (AMPK) pathway serves a critical function in glucose and lipid metabolism. The relationship between diosmin and the AMPK pathway has not been previously documented. This investigation examined diosmin's capacity to reduce lipid content through AMPK pathway activation in hepatoblastoma cell line G2 (HepG2) and 3T3-L1 cells. The study revealed that diosmin inhibits lipogenesis, indicating its potential as an anti-obesity agent in obese mice. Moreover, diosmin demonstrated effective MASLD alleviation in vivo. These findings suggest that diosmin may represent a promising therapeutic candidate for treating obesity and MASLD.
Diosmin/administration & dosage* ; Animals ; AMP-Activated Protein Kinases/genetics* ; Humans ; Non-alcoholic Fatty Liver Disease/enzymology* ; Mice ; Obesity/enzymology* ; Hep G2 Cells ; Male ; 3T3-L1 Cells ; Mice, Inbred C57BL ; Signal Transduction/drug effects* ; Lipid Metabolism/drug effects* ; Chrysanthemum/chemistry* ; Lipogenesis/drug effects*

Objective:To discuss the expression and clinical significance of inositol polyphosphate-4-phosphatase type Ⅱ(INPP4B)gene in hepatocellular carcinoma(HCC)based on The Cancer Genome Atlas(TCGA)database and experimental verification with clinical samples.Methods:Based on data from 424 clinical samples in the TCGA database(including 374 HCC tissues and 50 paracarcinoma tissues),Kaplan-Meier method and Cox regression analysis were used to evaluate the relationship between INPP4B gene and the clinical characteristics and survival prognosis of the HCC patients.The correlations between INPP4B gene and the number of 24 types of immune cells,matrix,immune cell infiltration and tumor purity in tumor tissue,and the expression level of the high-frequency mutant gene tumor protein 53(TP53)in HCC were analyzed.The clinicopathological data and paraffin-embedded tissue sections of 60 HCC patients treated with surgical resection from December 2022 to December 2023 were collected.According to clinical diagnosis,they were divided into poorly differentiated group(HCC-L group),moderately differentiated group(HCC-M group)and well-differentiated group(HCC-H group),with 20 cases in each group;20 patients during the same period who underwent biopsy and were pathologically diagnosed as non-tumor were selected as normal group,and their clinicopathologic data and liver tissue paraffin sections were collected.HE staining was used to observe the pathomorphology of HCC tissue and normal liver tissue of the subjects in various groups;immunohistochemistry method was used to detect the expressions of Ki-67 and INPP4B proteins in the HCC tissue and normal liver tissue of the subjects in various groups.Results:The TCGA database analysis results showed that compared with normal tissue,the expression level of INPP4B mRNA in HCC tissue was significantly increased(P<0.01).Compared with INPP4B low expression group,the overall survival(OS)of the patients in INPP4B high expression group was significantly prolonged(P<0.05).The univariate Cox regression analysis results showed that tumor stage,pathological stage,tumor status and residual tumor had impacts on OS of the HCC patients(P<0.05).The univariate regression analysis results showed that the INPP4B prognostic risk model score ratio was HR=0.781,95％confidence interval(CI):0.552-1.105,P=0.168.The AUC value for the impact of INPP4B on OS of the HCC patients was 0.558,indicating that the INPP4B gene prognostic risk model had certain predictive value in survival prognosis.The INPP4B mRNA expression level was not correlated with TNM stage,stage,patient gender,age,race or body mass index(BMI)(P>0.05).In tumor tissue with high and low INPP4B expression,22 types of immune cells showed statistically significant differences(P<0.05);the INPP4B mRNA expression level was positively correlated with the number of 23 types of immune cells except T helper(Th)17 cells(r>0),among which all Th cells except natural killer(NK)CD56+cells were statistically significant(P<0.01);INPP4B was significantly correlated with matrix(r=0.475),immune cell infiltration(r=0.641)and tumor purity(r=0.599)in tumor tissue(P<0.01).INPP4B was correlated with TP53(r=0.287,P<0.01).The HE staining results showed that clear and complete lobular structure,neatly arranged cells and slight inflammatory cell infiltration were observed in liver tissue of the subjects in normal group;completely destroyed lobular structure,significant hepatocellular steatosis,massive inflammatory cell infiltration,and lesions such as ballooning degeneration and small cell hyperplasia in some cells were observed in HCC tissue of the patients in HCC-L,HCC-M and HCC-H groups,and the lower the HCC differentiation degree,the more severe the tissue destruction;The immunohistochemistry results showed that compared with normal group,the expression levels of Ki-67 protein in HCC tissue of the patients in HCC-L,HCC-M and HCC-H groups were significantly increased(P<0.01),and the lower the differentiation degree of the HCC patients,the higher the Ki-67 positive rate.Brownish-yellow granules evenly distributed in the cells and INPP4B protein was highly expressed in liver tissue of the subjects in normal group;compared with normal group,the expression levels of INPP4B protein in HCC tissue of the patients in HCC-L,HCC-M and HCC-H groups were significantly decreased(P<0.01),and the lower the differentiation degree of the HCC tissue,the lower the INPP4B positive rate.Conclusion:INPP4B is a protective factor for the prognosis of HCC patients;as a new tumor suppressor gene,INPP4B may become a potential target for new drug screening in HCC treatment.

BACKGROUND:The basic principle of the design of the robot system used for total knee arthroplasty is to combine three-dimensional surgical planning,early warning of danger areas during surgery,real-time data feedback,robot arm assisted osteotomy and other technologies to achieve precision and personalization of total knee arthroplasty,which is exactly its biggest advantage.Therefore,it has become a hot topic in the field of joint surgery in recent years and attracted much attention. OBJECTIVE:To summarize the development status of robotic-assisted total knee arthroplasty in the field of joint surgery and the comparison of advantages and disadvantages with conventional total knee arthroplasty and to prospect the future development of robotic-assisted total knee arthroplasty. METHODS:Relevant articles were searched from PubMed,CNKI,Wanfang and VIP databases by computer.English key words were"robot OR robotic OR robotics OR robotically OR computer,total knee arthroplasty OR total knee replacement,TKA OR TKR".Chinese key words were"robotic-assisted,computer navigation,total knee arthroplasty".Finally,64 articles were included for review and analysis. RESULTS AND CONCLUSION:(1)The robot system used to assist total knee arthroplasty is divided into active,semi-active and passive according to its degree of freedom.The semi-active system,currently widely used in robotic systems,effectively enhances the accuracy and personalization of total knee arthroplasty.However,its high implementation cost and relatively steep learning curve remain key factors to be balanced when promoting its adoption in joint surgery field.(2)Robotic-assisted total knee arthroplasty can achieve precise osteotomy and correct placement of prosthesis in local three-dimensional space of the knee joint.It has been widely proven that it can provide better accuracy of prosthesis implantation,reduce imaging abnormalities,obtain good soft tissue balance during the operation,and ultimately improve the motion and functional status of the knee joint after the operation.(3)However,the current robotic-assisted system still has objective shortcomings,including the problem of learning curve between different robot devices and operators,additional installation and maintenance costs,and potential complications related to robot surgery.Therefore,whether it can truly benefit the medical system and patients still needs to be proven by long-term research,and the robotic-assisted system also needs to be further improved substantially.(4)Robotic-assisted total knee arthroplasty technique is still in the preliminary research stage in clinical practice and has not been widely applied.To better define the usage of robotic-assisted total knee arthroplasty and enhance its clinical procedural standards and safety,refining these aspects will become a focal point of future research on robotic-assisted total knee arthroplasty.

Objectives:To retrieve,evaluate and summarize the contemporary evidence of strategies for weaning from extracorporeal membrane oxygenation(ECMO)of adult patients,and to provide evidence-based reference for clinical practice. Methods:The Web of Science,Embase,Cochrane Library,PubMed,Wanfang Database,CNKI,VIP website,SinoMed,BMJ Best Practice,National Institute for Health and Care Excellence,Joanna Briggs Institute Library,UpToDate and the website of Agency for Healthcare Research and Quality,Society of Critical Care Medicine,American Association of Critical-Care Nurses,European Society of Intensive Care Medicine and Extracorporeal Life Support Organization were researched to collect the literature related to randomized controlled trials,systematic reviews,guidelines,evidence summaries,expert consensuses and clinical decisions in this field.The time limit for the retrieval is from the inception of databases until July 2023. Results:A total of 13 related literature were retrieved,including 4 guidelines,4 expert consensuses,3 clinical decisions and 2 system reviews.Totally 42 evidences were formulated based on retrieved literature,including adequately accessing the ability of gas exchange before weaning from veno-venous ECMO(V-V ECMO)and withdrawing from veno-arterial ECMO(V-A ECMO)as soon as possible when patients's heart function has recovered,involving six aspects such as team composition,anticoagulation measures,assessment before weaning,weaning implementation,cannula and wound management and quality measures. Conclusions:It is suggested to build a professional ECMO team based on the actual hospital situation,to follow the contemporary evidence to standardize the weaning process of patients from ECMO to ensure the patients'safety and improve the outcomes.

Objective:To analyze the dosimetric differences between gamma knife stereotactic body radiation therapy (SBRT) and linear accelerator-based SBRT for lung tumors by comparison to provide a theoretical basis for the selection of treatment strategies.Methods:Seven patients who underwent SBRT for lung tumors in the Cancer Center of Affiliated Zhongshan Hospital of Dalian University from January 2022 to May 2023 were enrolled. Plans of gamma knife SBRT (γ_SBRT) or linear accelerator-based SBRT plans (X_SBRT) were designed for the 13 lesions in the patients, with adjacent lesions in the same patient sharing one plan. As a result, 10 γ_SBRT plans and 10 X_SBRT plans were obtained. All lesions received 30-50 Gy of radiation in 5-10 fractions. Then, dosimetric parameters were analyzed and compared between γ_SBRT and X_SBRT plans, including the target coverage, gradient index (GI), conformity index (CI), maximum dose ( Dmax); mean dose ( Dmean), and minimum dose ( Dmin) of planning target volumes (PTVs); lung volumes receiving 20 Gy or more ( V20), 10 Gy or more ( V10), 5 Gy or more ( V5), 100% of the prescription dose ( V100%), and 50% of the prescription dose ( V50%); Dmean and the percentages of lung volume receiving doses of 20 Gy or more (Lung_ V20) and 5 Gy or more (Lung_ V5) of ipsilateral lung; Dmean and Lung_ V5 of contralateral lung; and Dmax values of the esophagus, spinal cord, and heart. Results:Compared to X_SBRT plans, γ_SBRT plans exhibited superior GI, V20, V10, V5, V50%, the Dmean, Lung_ V20, and Lung_ V5 of ipsilateral lung, the Dmean and Lung_ V5 of the contralateral lung, and the Dmax of esophageal and heart ( z = -2.81 to -1.99, P < 0.05), higher Dmax and Dmean of PTVs ( z = -2.80, -2.80, P < 0.05), and longer delivery time ( z=-2.70, P<0.05). Meanwhile, there was no significant difference in target coverage, CI, and Dmax of the spinal cord ( P > 0.05). Conclusions:Gamma knife SBRT plans can achieve sharper dose falloff outside target volumes than linear accelerator-based SBRT plans. Gamma knife radiosurgery is expected to reduce the radiation dose to low-dose areas around PTVs and normal lung tissue in SBRT for lung tumors. However, it significantly prolongs the delivery time.

Objective To study the mechanism of the treatment of metabolism associated steatohepatitis(MASH)in rats with Xiaoyao Wan.Methods Twenty-four SD male rats were randomly divided into control group(CON group,n=8)and model group(n=8).The model group was given high-fat diet,carbon tetrachloride(CCl4)subcutaneous injection,hunger and satiety disorder and tail clamping for four weeks to establish the MASH model,and the rats were randomly divided into the MOD group and the Xiaoyao Wan group(XYW group),with 8 rats in each group.The rats of the XYW group were given Xiaoyao Wan,the other two groups were given normal saline.Four weeks after administration,the serum biochemical indexes and oxidative stress indexes of rats in different groups were detected.The pathological sections of rat liver tissue were observed by hematoxylin-eosin(HE)stai-ning and oil red O staining.The expression of cytochrome P450 2E1(CYP2E1),factor-related apoptosis ligand(FasL),tumor necrosis factor-α(TNF-α)and tumor growth factor-β1(TGF-β1)in rat liver were detected by Western blot method.The relative contents of CYP2E1,FasL,TNF-α and TGF-β1 mRNA in liver tissue were de-tected by RT-qPCR.Results The general condition of rats in the XYW group was significantly improved compared with the MOD group;the level of hepatic index was significant decrease compared with the MOD group(P＜0.01)and the level of body mass index was significant increase compared with the MOD group(P＜0.01);the serum levels of triglyceride,total cholesterol,low-density lipoprotein cholesterol,aspartate aminotransferase,alanine aminotransferase,malondialdehyde,monocyte chemotactic protein-1,TNF-α,and interleukin(IL)-18 were signif-icantly reduced compared with the MOD group(all P＜0.05),and the levels of high-density lipoprotein choles-terol,superoxide dismutase,and IL-10 were significantly elevated compared with the MOD group(all P＜0.05);the content of lipid droplets in hepatocytes of rats was significantly reduced compared with the MOD group under light microscope;the protein levels of CYP2E1,FasL,TNF-α and TGF-β1 in liver tissues were significantly re-duced compared with the MOD group(all P＜0.05),and the relative contents of CYP2E1,FasL,TNF-α and TGF-β1 mRNA were significantly reduced compared with the MOD group(all P＜0.05).Conclusion Xiaoyao Wan can regulate the expression of CYP2E1,FasL,TNF-α and TGF-β1 in the liver tissue of MASH rats by reduc-ing the accumulation of fat in the liver,so as to achieve the purpose of treating MASH.

Objective To explore and validate the application value of a deep learning model based on the Huawei Cloud ModelArts platform in the diagnosis of atypical cervical cells in liquid-based cytology(LBC)and to evaluate its assistive effect for pathologists with different diagnostic experiences.Methods We retrospectively analyzed 1 044 cervical cytology specimens from Dongguan People's Hospital in 2020.The artifical intelligence(AI)-assisted diagnostic system developed on the Huawei Cloud ModelArts platform was compared with junior,intermediate,and senior pathologists for diagnosis.Sensitivity,specificity,precision,recall,and area under the receiver operating characteristic curve(AUC)were calculated to assess the diagnostic performance of the Al system and its assistive effect for pathologists with different levels of experience.The McNemar test was used to compare the differences between the Al system and manual diagnosis.P＜0.05 was considered statistically significant.Results For the 1 044 cervical exfoliated cytology specimens,the sensitivity and specificity of the AI system in detecting atypical cells was 98.96％and 89.15％,both of which were higher than those of junior doctors(81.95％and 91.81％,respectively).The overall diagnostic accuracy of the Al system was 93.68％,which was significantly higher than that of junior doctors(87.26％,P＜0.001).Al assistance could significantly improve junior doctors'ability to detect atypical cells,with the sensitivity and specificity increasing from 80.1％to 96.5％and from 85.6％to 92.3％,respectively.Conclusion The AI-assisted cervical cytology diagnostic system developed in this study demonstrated superior performance,particularly in significantly improving the diagnostic level of junior pathologists,showing promising clinical application prospects.