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

ObjectiveTo investigate the effects and mechanism of Zuogui Jiangtang Tongmai prescription （ZJTP） on human umbilical vein endothelial cells （HUVECs） damaged by high glucose combined with lipopolysaccharide （LPS）. MethodThe survival rate of cells was determined by cell counting kit-8 （CCK-8）， and the level of tumor necrosis factor-α （TNF-α） was determined by enzyme-linked immunosorbent assay （ELISA） to determine the optimal injury concentration and action time of LPS， as well as the optimal action concentration of ZJTP drug-containing serum. HUVECs were divided into a blank control group， a model group， a ZJTP drug-containing serum group， and an SCFA mixed liquid group. ELISA was used to detect the level of endothelin-1 （ET-1）， nitric oxide （NO）， interleukin-1β （IL-1β）， interleukin-6 （IL-6）， and TNF-α. Western blot was performed to detect the protein expression of G protein-coupled receptor43 （GPR43）， β-suppressor protein-2 （β-arrestin-2）， nuclear factor-κB suppressor α （IκBα）， and nuclear factor κB p65 （NF-κB p65）. The nucleation of NF-κB p65 was observed by immunofluorescence staining （IF）. The role of GPR43 in the regulation of inflammatory injury was observed by means of small interfering ribonucleic acid （siRNA）. The cells after intervention were divided into an empty carrier group， a ZJTP drug-containing serum group， a Si-GPR43 group， and a Si-GPR43 + ZJTP drug-containing serum group. The content of IL-1β， IL-6， and TNF-α was detected by ELISA. The protein expression of pathways was detected by Western blot. IF was used to observe the nucleation of NF-κB p65. ResultThe optimal molding condition was 1 mg·L^-1 LPS for 24 h. The optimal drug intervention condition was 5% ZJTP drug-containing serum for 24 h. Compared with the blank control group， the content of ET-1 in the model group was significantly increased， and the content of NO was significantly decreased （P<0.01）. The levels of inflammatory factors were significantly increased （P<0.01）. The expressions of GPR43 and IκBα were significantly decreased， while the protein expressions of β-arrestin-2 and NF-κB p65 were significantly increased （P<0.01）. NF-κB p65 protein was transferred from the extranuclear to the intranuclear （P<0.01）. Compared with the model group， the content of ET-1 in the ZJTP drug-containing serum group was decreased， and the content of NO was increased （P<0.05）. The levels of inflammatory factors decreased （P<0.05）. The protein expressions of GPR43 and IκBα were increased， while the expressions of β-arrestin-2 and NF-κB p65 were decreased （P<0.05）. The amount of NF-κB p65 transferred from the intranuclear to the extranuclear decreased （P<0.01）. The mechanism study showed that compared with the Si-GPR43 group， the content of IL-1β， IL-6， and TNF-α were significantly decreased after treatment with ZJTP drug-containing serum （P<0.01）. The protein expressions of GPR43 and IκBα were significantly increased （P<0.01）， while the protein expressions of β-arrestin-2 and NF-κB p65 were significantly decreased （P<0.01）. The amount of NF-κB p65 transferred from the extranuclear to the intranuclear decreased （P<0.01）. ConclusionZJTP has a protective effect on HUVECs with high glucose and LPS-induced inflammatory injury， which may be related to the regulation of GPR43/β-arrestin-2/IκBα/NF-κB pathway.

Oral diseases concern almost every individual and are a serious health risk to the popula-tion.The restorative treatment of tooth and jaw defects is an important means to achieve oral function and support the appearance of the contour.Based on the principle of"learning from the nature",Deng Xu-liang's group of Peking University School and Hospital of Stomatology has proposed a new concept of"microstructural biomimetic design and tissue adaptation of tooth/jaw materials"to address the worldwide problems of difficulty in treating dentine hypersensitivity,poor prognosis of restoration of tooth defects,and vertical bone augmentation of alveolar bone after tooth loss.The group has broken through the bottle-neck of multi-stage biomimetic technology from the design of microscopic features to the enhancement of macroscopic effects,and invented key technologies such as crystalline/amorphous multi-level assembly,ion-transportation blocking,and multi-physical properties of the micro-environment reconstruction,etc.The group also pioneered the cationic-hydrogel desensitizer,digital stump and core integrated restora-tions,and developed new crown and bridge restorative materials,gradient functionalisation guided tissue regeneration membrane,and electrically responsive alveolar bone augmentation restorative membranes,etc.These products have established new clinical strategies for tooth/jaw defect repair and achieved inno-vative results.In conclusion,the research results of our group have strongly supported the theoretical im-provement of stomatology,developed the technical system of oral hard tissue restoration,innovated the clinical treatment strategy,and led the progress of the stomatology industry.

BackgroundMental illness during pregnancy has become a major public health problem in China over the recent years， and depression is the most common psychological symptom during pregnancy. Current research efforts are directed towards the therapy on prenatal depression， whereas the construction of prediction model for prenatal depression risk has been little studied. ObjectiveTo construct a simple model for predicting the risk of prenatal depression， thus providing a valuable reference for the prevention of maternal depression during pregnancy. MethodsA total of 803 pregnant women attending three hospitals in Nanchong city were consecutively recruited from May 2021 to February 2022. A self-administered questionnaire was developed for the assessment of social demographic variables， obstetrical and general medical indexes and psychological status of all participants， and Self-rating Depression Scale （SDS） was utilized to screen for the presence of maternal depression. Subjects were randomly assigned into modelling group （n=635） and validation group （n=168） at the ratio of 8∶2 under simple random sampling with replacement. The candidate risk factors of maternal depression during pregnancy were screened using binary Logistic regression analysis， and the predictive model was constructed. Then the performance of the predictive model was validated using receiver operating characteristics （ROC） curve. Results① Lack of companionship （β=-0.692， OR=0.501， 95% CI： 0.289~0.868）， low mood during the last menstrual period （β=-1.510， OR=0.221， 95% CI： 0.074~0.656）， emotional stress during the last menstrual period （β=-1.082， OR=0.339， 95% CI： 0.135~0.853）， unsatisfactory relationship between mother-in-law and daughter-in-law （β=-1.228， OR=0.293， 95% CI： 0.141~0.609）， and indifferent generally relationship between mother-in-law and daughter-in-law （β=-0.831， OR=0.436， 95% CI： 0.260~0.730） were risk factors for prenatal depression in pregnant women （P<0.05 or 0.01）. ② Model for predicting the prenatal depression risk yielded an area under curve （AUC） of 0.698 （95% CI： 0.646~0.749）， the maximum Youden index was 0.357 in modelling group with the sensitivity and specificity was 0.606 and 0.751， and an AUC of 0.672 （95% CI： 0.576~0.767） and maximum Youden index of 0.263 in validation group with the sensitivity and specificity of 0.556 and 0.707. ConclusionThe simple model constructed in this study has good discriminant validity in predicting of the risk of prenatal depression. ［Funded by Nanchong Social Science Research Project of the 14th Five-Year Plan （number， NC21B165）］

Ischemic stroke， also known as cerebral infarction， is the most common type of stroke. Ischemic stroke is extremely harmful with high rates of morbidity， incidence， disability， and mortality， bringing a huge burden on society and families. As a result， finding new and effective prevention and treatment methods is critical. The pathological mechanism of ischemic stroke is very complex and superimposed， with inflammatory response serving as a critical pathological link in the ischemic stroke cascade injury process. NOD-like receptor 3 （NLRP3） is an intracellular sensor， and the inflammatory cascade mediated by the activated NLRP3 inflammasome can exacerbate ischemic stroke injury through the release of inflammatory factors. Taking the NLRP3 inflammasome as the entry point， a large number of experimental studies on the intervention of traditional Chinese medicine （TCM） in the assembly and activation of NLRP3 inflammasome have been carried out， which proved that Chinese medicinal monomers or prescriptions with the main functions of tonifying deficiency， clearing heat and removing toxin， eliminating phlegm， promoting circulation and resolving stasis can interfere with the assembly and activation of NLRP3 inflammasome， reduce the inflammatory response， and relieve ischemic stroke. This study reviewed the assembly and activation of NLRP3 inflammasome， the mechanism of NLRP3 inflammasome in ischemic stroke， and the prevention and treatment of ischemic stroke by TCM through regulation of the NLRP3 inflammasome， which provides a new entry point for the pathological mechanism of ischemic stroke and a direction for the development of new treatments for ischemic stroke.

ObjectiveTo explore the effect and mechanism of Zuogui Jiangtang Tongmai prescription （ZGJTTMP） on astrocytes （ASs） injured by advanced glycation end products（AGEs） combined with oxygen-glucose deprivation （OGD）. MethodCell counting kit-8 （CCK-8） was used to determine the optimal concentration of AGEs and the action time of OGD， and the optimal blood concentration of ZGJTTMP was selected for follow-up experiments. ASs were divided into normal group， model group （AGEs + OGD）， ZGJTTMP group， an adenosine 5'-monophosphate-activated protein kinase （AMPK） inhibitor （Compound C） group， AMPK activator （AICAR） group， and combination group （ZGJTTMP + AICAR）. The morphological changes in ASs in each group were observed under an inverted microscope. The cell survival rate in each group was detected by CCK-8. The content of interleukin-1β（IL-1β）， interleukin-6（IL-6）， and tumor necrosis factor-α（TNF-α） was detected by enzyme-linked immunosorbent assay （ELISA）. The number of autophagosomes in each group was counted under an electron microscope. The expression of microtubule-associated protein light chain 3 （LC3） was observed by immunofluorescence. The protein expression of LC3， p62， p-AMPK， AMPK， p-mammalian target of rapamycin （mTOR）， mTOR， p-UNC-51 like kinase 1 （ULK1）， and ULK1 was detected by Western blot. ResultAccording to the results of cell survival rate， 200 mg·L^-1 AGEs and OGD for 6 h were selected as the optimal modeling conditions for the model group， and 5% was selected as the optimal blood concentration of ZGJTTMP. Under the inverted microscope， the cells were severely damaged after modeling， but the cell injury in the ZGJTTMP group and the Compound C group was significantly improved. As revealed by ELISA results， the content of IL-1β， IL-6， and TNF-α in the model group increased （P<0.01）， and the content of inflammatory factors in the ZGJTTMP group and the Compound C group decreased （P<0.01）. Under the electron microscope， the number of autophagosomes in the model group increased significantly. The immunofluorescence results showed that the expression area of LC3 increased in the model group （P<0.01）， and the ZGJTTMP group and the Compound C group showed decreased number of autophagosomes and reduced expression area of LC3 （P<0.01）. As demonstrated by the results of Western blot， compared with the normal group， the model group showed increased expression of LC3Ⅱ/LC3Ⅰ and p-AMPK/AMPK （P<0.01） and decreased p62， p-mTOR/mTOR， and p-ULK1/ULK1 （P<0.01）. Compared with the model group， the ZGJTTMP group and the Compound C group showed decreased expression of LC3Ⅱ/LC3Ⅰ and p-AMPK/AMPK （P<0.01） and increased p62， p-mTOR/mTOR， and p-ULK1/ULK1 （P<0.01）. ConclusionZGJTTMP possesses a protective effect on ASs with inflammatory injury by AGEs combined with OGD， which may be achieved by inhibiting the activation of the AMPK/mTOR/ULK1 pathway related to autophagy， thus inhibiting the overexpression of autophagy.

Objective:To explore the relationship between Th17 immunoregulatory system and depression and reveal the mechanism of depression from the perspective of neuroimmunity, as well to look for biomarkers that can be used to diagnose, evaluate and predict recurrence of depression.Methods:A total of 91 patients with depression including 45 first-episode patients (FED group) and 46 recurrent episodes patients (RMDD group) were collected who were admitted to Psychiatry Department of the First Affiliated Hospital of Zhengzhou University from March 2019 to May 2020. And 40 healthy controls matched with depression patients in age, gender and education level were collected as control group (HC group). The levels of eight inflammatory cytokines in Th17 immunoregulatory system (five pro-inflammatory cytokines: IL-1β, IL-6, IL-17A, IL-21, IL-23; three anti-inflammatory cytokines: TGF-β1, IL-10, and IL-27) were measured by enzyme-linked immunosorbent assay (ELISA). Hamilton depression scale-24 (HAMD-24) was used to evaluate the severity of depressive symptoms. Data analyses were performed with SPSS 23.0.Two independent samples t-test, one-way ANOVA, Mann Whitney U test and Kruskal Wallis H test were used for comparison between groups. Results:(1) Comparison of FED group, RMDD group and HC group showed that the levels of pro-inflammatory cytokines IL-1β (5.321(1.317, 21.287)ng/L, 11.277(4.315, 26.167) ng/L, 8.126(1.179, 9.287) ng/L), IL-6(7.787(2.077, 16.778) ng/L, 5.290(2.364.14.475) ng/L, 4.389(1.453, 4.491) ng/L), IL-21 (6.777(6.293, 9.198) ng/L, 7.261(6.293, 25.058)ng/L, 5.097(3.033, 6.507) ng/L) and anti-inflammatory cytokines TGF-β1 (59.098(13.491, 125.368) ng/L, 46.230(18.852, 122.559) ng/L, 25.292(2.716, 31.874) ng/L), IL-10 (226.930(105.117, 449.444) ng/L, 193.929(109.014, 468.269) ng/L, 131.429(77.587, 157.497) ng/L) and IL-27 (0.968(0.651, 1.879)ng/L, 1.859(0.690, 6.221) ng/L, 0.865(0.679, 1.287)ng/L) in plasma were statistically different( H=7.219, 9.482, 18.989, 16.166, 11.511, 6.262, all P<0.05), while the levels of pro-inflammatory cytokines IL-17A (2.175(1.031, 7.975)ng/L, 3.576(1.896, 11.611)ng/L, 3.807(1.301, 4.710)ng/L)and IL-23 (15.708(2.898, 114.175) ng/L, 26.893(9.282, 58.592) ng/L, 17.041(5.027, 23.613)ng/L) were not statistically significant ( H=2.179, 4.305, both P>0.05). Further pairwise comparisons showed that the levels of pro-inflammatory cytokines IL-6, IL-21 and anti-inflammatory cytokines TGF-β1 and IL-10 in plasma of FED group were higher than those of HC group, and the differences were statistically significant (all P<0.05). The levels of pro-inflammatory cytokines IL-1β, IL-6, IL-21 and anti-inflammatory cytokines TGF-β1, IL-10, IL-27 in RMDD group were higher than those in HC group, and the differences were statistically significant (all P<0.05). There were no significant differences in the eight inflammatory cytokines between FED group and RMDD group (all P>0.05). (2) Spearman correlation analysis showed that IL-1β was positively correlated with total score of HAMD-24 ( r=0.286, P<0.05). IL-6 was positively correlated with total score of HAMD-24 and factor score of anxiety or somatization ( r=0.390, 0.291, both P<0.05). TGF-β1 was negatively correlated with total score of HAMD-24 and factor scores of anxiety or somatization and cognitive impairment ( r=-4.200, -0.321, - 0.361, all P<0.05). IL-21 was positively correlated with factor score of sleep ( r=0.319, P<0.05); IL-10 was negatively correlated with total score of HAMD-24 and factor score of cognitive impairment ( r=-0.306, - 0.270, both P<0.05). There was no significant correlation between other inflammatory cytokines and total score of HAMD-24 and seven factor scores (all P>0.05). Conclusion:There is an imbalance in pro-and anti-inflammatory cytokines of Th17 immunoregulatory system in patients with depression, which is more obvious in recurrent episodes patients.The level of immune activation of Th17 immunoregulatory system may be associated with the severity of clinical symptoms, in which the inflammatory cytokine IL-6 may be a biomarker of major depressive disorder; TGF-β1 and IL-21 may be associated with depressive cognitive impairment and sleep.

Objective:To study preoperative MRI imaging and its enhanced mode on tumor features in predicting microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC).Methods:The clinical data of patients with a solitary HCC who underwent MRI examination followed by surgical resection at the General Hospital of Ningxia Medical University from January 2017 to June 2019 were studied. The patients were divided into the MVI (+ ) and MVI (-) groups according to the findings on postoperative pathological diagnosis. The relationship between the rates of MVI and MRI tumor features including diffusion weighted imaging (DWI) signal, enhancement mode, enhancement type and other imaging characteristics were analysed.Results:Of 84 patients with HCC enrolled into this study, there were 65 males and 19 females. Their age (Mean±SD) was (54.94±11.51) years. MVI (+ ) was found in 46 patients and MVI (-) in 38 patients. The maximum tumor diameters (Mean±SD) of the two groups were (7.08±3.45) cm and (4.28±2.47) cm ( P<0.01). Single-factor analysis and comparison of imaging characteristics of the two groups of patients showed tumor DWI signal, tumor encapsulation, enhancement mode, tumor edge smoothness, abnormal enhancement around tumors, and intratumoral arteries were significantly different ( P<0.05); There were no significant differences in T 1WI signals, T 2WI signals, tumor periphery, and enhancement types between groups. After inputting MVI(+ ) as a risk factor into the logistic regression model, tumor maximum diameters >6.33 cm, type 3/4 enhancement mode, and unsmoothness of tumor edge were independent risk factors (all P<0.05). Through combined diagnosis using ROC curve analysis with a cut-off value of 0.53, the area under the curve was 0.881, the sensitivity 0.870, specificity 0.789, and the Youden index 0.659. Conclusion:The multivariate logistic regression model and combined diagnosis using ROC curve analysis improved the diagnostic efficacy of MVI in its prediction of HCC on imaging studies. The risk predictors were easy to use and to promote in clinical practice.

Objective:To explore the value of clinical data and MRI image features in predicting and analyzing the degree of differentiation of hepatocellular carcinoma (HCC).Methods:The clinical and imaging data of 180 patients with surgical outcomes of HCC from March 2015 to June 2019 in the General Hospital of Ningxia Medical University were retrospectively analyzed. Alpha-fetoprotein (AFP)、aspartate aminotransferase (AST)、D-dimer、clinical stage、tumor length、apparent diffusion coefficient(ADC)、enhancement types and so on the clinical and imaging data of the poorly differentiated and non-differentiated HCC were compared and analyzed. Multivariate logistic regression was used to predict independent risk factors for poorly differentiated HCC.Results:Of the 180 HCC patients, 121 were moderately and highly differentiated, and 59 were poorly differentiated. Univariate analysis showed that the patient’s age, gender, AFP, AST, D-dimer level, clinical stage, Child-Pugh score, tumor length, whether the capsule was complete, tumor apparent diffusion coefficient, the maximum level ADC value, enhancement type with HCC differentiation degree were correlated(all P<0.05). Multivariate logistic regression analysis showed that the patients' gender ( OR=4.524, P<0.05), clinical stage ( OR=5.598, P<0.05), D-dimer ( OR=8.576, P<0.05), HCC diameter ( OR=0.498, P<0.05), enhancement types ( OR=2.988, P<0.05), tumour ADC value ( OR=0.059, P<0.05) were independent of poorly differentiated HCC risk factor. Conclusion:MRI image features can be used as an effective indicator to predict the degree of HCC differentiation before surgery. It is more valuable to accurately predict the degree of HCC combined with D-dimer and AFP value.

Objective:To evaluate the radiation doses from head and chest CT examinations of children in Ningxia, and provide basic data for the optimization of CT radiation doses to children of different ages.Methods:By using stratified cluster sampling method , the dose parameters on head and chest CT scanning, CTDI vol and DLP for the children under 15 years old were sampled within 1-2 weeks from hospitals at different levels in different regions of Ningxia for the calculation of effective doses. The 75th percentile (P75) of CTDI vol and DLP was compared with those recommended by other countries. All children included four age groups: up to 1 year old, 1 to 5 years, 6 to 10 years, 11 to 15 years. Results:There were 39 hospitals and 47 CT scanners in this survey, and 1 134 head scanning and 636 chest scanning were investigating. The 75th percentile (P75) of CTDI vol and DLP for head scanning were 44.2 mGy and 456.2 mGy·cm for those up to 1 year old; 57.2 mGy and 659.6 mGy·cm for 1 to 5 years old, 61.1 mGy and 668.7 mGy·cm for 6-10 years old, and 63.6 mGy and 849.3 mGy·cm for 11-15 years old, respectively. The 75th percentile (P75) of CTDI vol and DLP for chest scanning were 5.0 mGy and 89.2 mGy·cm for those up to 1 year old, 5.9 mGy and 124.8 mGy·cm for 1 to 5 years old, 6.0 mGy and 167.9 mGy·cm for 6 to 10 years, and 7.1 mGy and 235.0 mGy·cm for 11 to 15 years old, respectively. Conclusions:The chest CT radiation dose to children in Ningxia is close to the reported values, but the head CT radiation dose is relatively high in all age groups, especially in infants. The optimization and regulation of head CT radiation doses to children in Ningxia should be strengthened. It is high time to increase dose awareness for pediatricians and radiologists and raise awareness of radiation-related risks.