Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Objective To evaluate the application value of artificial intelligence (AI) in the quality control of mammographic images and explore its feasibility for improving image quality. Methods A retrospective analysis was conducted on 500 mammographic images from 125 female patients. These images were acquired in December 2024 at the Department of Radiology, Obstetrics and Gynecology Hospital of Tongji University by two junior technologists with qualification certificate for junior radiologic technologists and ≤ 2 months of independent operation. The reference standard was the evaluation by a panel of senior experts comprising one associate chief radiologist and two intermediate radiologic technologists with over 10 years of experience in mammography. The evaluation was based on nine criteria within an AI quality control system. The correlation and consistency (Kappa test) of the assessment outcomes were compared among the junior technologist group, the AI quality control group, and the panel group. Additionally, the differences in the proportions of high-, medium-, and low-quality images rated by the three groups were analyzed. After one month of AI assistance, 200 images from 50 additional patients acquired by the same two junior technologists in January 2025 were collected. The area under the receiver operating characteristic curve and 95% confidence interval (95%CI) were calculated for the assessment performance of the junior technologist group before and after AI assistance. Differences were compared using the DeLong test. Changes in the disqualification rates for the nine criteria were analyzed. Results In consistency analysis, the AI quality control group showed high consistency with the panel group across multiple key criteria, with Kappa values ranging from 0.41 to 1.00. In contrast, the consistency between the junior technologist group and the panel group was generally low, with Kappa values ranging from 0.13 to 0.49. In comparison of image quality classification, no significant differences were observed in image quality classification between the AI group and the panel group (P>0.05). However, the proportion of images rated as high quality by the junior technologist group was significantly higher, while the proportions rated as medium and low quality were significantly lower, compared to those rated by the panel group (P<0.05). After AI assistance, the area under the receiver operating characteristic curve for the assessment performance of junior technologist group increased significantly from 0.56 (95%CI: 0.51-0.61) to 0.91 (95%CI: 0.87-0.94) (P<0.001). The disqualification rates for skin folds, incomplete inclusion of the pectoralis major muscle, and nipple not in profile decreased significantly. Conclusion AI demonstrates assessment capability comparable to the panel group in mammographic quality control. AI effectively enhances the quality of images acquired by junior technologists through real-time, objective feedback.

Biomaterials provide a reliable and safe treatment for the repair of ear defects,especially microtia.With the continuous promotion of interdisciplinary research,the types and properties of materials used in auricle reconstruction have been greatly expanded and improved.In this paper,the latest research progress of polymer materials and tissue engineering scaffolds in the field of auricle reconstruction was reviewed,and the physical and chemical properties and clinical application effects of these scaffolds in vitro and in vivo were discussed.However,despite significant progress in ear stent research,there are still some challenges and limitations in the application of current polymer materials,such as the hydrophobicity of high-density polyethylene and the uncontrolled differen-tiation of stem cells in tissue engineering.Therefore,this paper discusses the research and clinical application of new modified materials,especially emphasizing the importance of surface modification technology and innovative synthesis strategies,so that the properties of modified materials are infinitely close to the characteristics of human ear cartilage.In addition,this paper also summarizes the control methods of stem cell differentiation in ear carti-lage tissue engineering.The application performance and biocompatibility of different ear scaffolds were reviewed in order to provide guidance for auricle reconstruction.

The integration of artificial intelligence(AI)into medical practice has significantly impacted the field of cerebrovascular disease.AI algorithms are increasingly being employed to enhance the diagnosis and management of cerebrovascular conditions.However,the clinical application and accuracy of these AI tools require further rigorous evaluation.This review probes into the current applications of AI in diagnosis and decision-making in cerebrovascular disease,and explores the potential and challenges associated with their implementation.

Objective To investigate the compliance of hormone receptor-positive breast cancer patients with prolonged endocrine therapy and analyze its influencing factors.Methods This study was a retrospective cohort study.A total of 347 patients with breast cancer who received prolonged endocrine therapy in our hospital from June 2017 to March 2023 were selected.Relevant data of the patients were collected and they were divided into two groups according to whether they adhered to prolonged endocrine therapy:the compliance group and the non-compliance group.Using the x2 test to analyze the impact of patients'disease-related data on prolonging compliance with endocrine therapy.Use Logistic regression to analyze its influencing factors.Results Among 347 breast cancer patients who received extended endocrine therapy,during the median follow-up of 28 months(ranging from 12 to 60 months),319 patients(91.9％)adhered to extended endocrine therapy(compliance group),and their treatment compliance was acceptable.Twenty-eight cases(8.1％)of patients did not adhere to prolonged endocrine therapy(non-compliance group).Multivariate analysis showed that the independent factors Influencing the compliance of breast cancer patients with prolonged endocrine therapy were comorbidities and radiotherapy(P＜0.05).Conclusion Based on the characteristics of influencing factors,behavioral interventions such as increasing follow-up frequency and strengthening health education content can be implemented for some patients without comorbidities and those who have not received radiation therapy,and to improve treatment compliance.

Objective:To separate and purify the polysaccharides from Polygonatum filipes,characterize their primary structure and investigate the immunomodulatory effects on RAW264.7 macrophages.Methods:Crude polysaccharides from Polygonatum filipes were extracted by ultrasound assisted method,then Polygonatum filipes polysaccharides(CSPFPs)were obtained after elimination of the proteins with combined papain-Sevag method.The total sugar content was determined by phenol-sulfuric acid method.Structures of CSPFPs were analyzed by fourier transform infrared spectroscopy(FT-IR),high performance gel permeation chromatography(HPGPC)and high performance liquid chromatography(HPLC).Effects of CSPFPs on cell viability,pinocytic activity,TNF-α secretion,MAPK and NF-κB signaling pathways of RAW264.7 cells were explored by MTT,Neutral red,ELISA and Western blot,respectively.Results:Extraction rate of CSPFPs by ultrasound-assisted method was 41.61%,which contained total sugar content of 94.00%.CSPFPs with Mw of 3 125 Da was composed of arabinose(1.85%),galactose(6.14%),glucose(56.41%)and mannose(35.60%).The in vitro experiments showed that CSPFPs were non-cytotoxic and enhanced the pinocytic activity,TNF-α secretion and phosphorylation levels of p38,ERK,JNK,p65,IκB and IKK,indicating the activation of MAPK and NF-κB signaling pathways under the concentra-tion of 2.5～200 μg/ml.Conclusion:The ultrasound-assisted method can efficiently isolate CSPFPs with immunomodulatory activity,which provides basic data for the development and application of CSPFPs as an immunostimulant.

Objective To investigate the compliance of hormone receptor-positive breast cancer patients with prolonged endocrine therapy and analyze its influencing factors.Methods This study was a retrospective cohort study.A total of 347 patients with breast cancer who received prolonged endocrine therapy in our hospital from June 2017 to March 2023 were selected.Relevant data of the patients were collected and they were divided into two groups according to whether they adhered to prolonged endocrine therapy:the compliance group and the non-compliance group.Using the x2 test to analyze the impact of patients'disease-related data on prolonging compliance with endocrine therapy.Use Logistic regression to analyze its influencing factors.Results Among 347 breast cancer patients who received extended endocrine therapy,during the median follow-up of 28 months(ranging from 12 to 60 months),319 patients(91.9％)adhered to extended endocrine therapy(compliance group),and their treatment compliance was acceptable.Twenty-eight cases(8.1％)of patients did not adhere to prolonged endocrine therapy(non-compliance group).Multivariate analysis showed that the independent factors Influencing the compliance of breast cancer patients with prolonged endocrine therapy were comorbidities and radiotherapy(P＜0.05).Conclusion Based on the characteristics of influencing factors,behavioral interventions such as increasing follow-up frequency and strengthening health education content can be implemented for some patients without comorbidities and those who have not received radiation therapy,and to improve treatment compliance.

Cleidocranial dysplasia(CCD)is a rare autosomal dominant disorder mainly characterized by skeletal and dental abnormali-ties.It is caused by the runt-related transcription factor-2(Runx2)mutations.In this paper,a case of CCD syndrome is reported.The proband and his family were examined by the proband's verification method for general condition,oral specialty and genetic examination.A new nonsense mutation exon7 c.1078C＞T,p.Gln360*heterozygous variant(Q360X)was verified,the relationship between Runx2 mutation and CCD phenotype was analyzed.

AIM:To elucidate the intervention and mechanism of 4'-hydroxychalcone(4-HC)in colitis mice through the regulation of Th17/Treg homeostasis.METHODS:Using a dextran sodium sulfate(DSS)-induced colitis model in mice,we meticulously observed the pathological characteristics of colon tissue via HE staining.Additionally,we employed immunohistochemical analysis and Western blot techniques to assess the expression levels of proteins associated with the JAK/STAT signaling pathway,as well as the specific content of tight junction proteins such as ZO-1 and occludin.The differentiation of Th17 and Treg cells was analyzed through flow cytometry.RESULTS:Compared to the normal group,the DSS group exhibited a consistent decline in body weight,coupled with symptoms of diarrhea and hematochezia,an increase in the DAI score,and a notable reduction in colon length.In contrast,the body weight of the 4-HC group dis-played an upward trend following an initial decrease,with improvements in diarrhea and hematochezia symptoms,a reduc-tion in the DAI score,and a restoration of colon length relative to the model group.The integrity of colon tissue in the 4-HC group was significantly better than that in the DSS group,evidenced by a marked increase in the number of goblet cells and an enhancement in crypt integrity,while the average histology score showed a decrease.Western blot analysis re-vealed substantial increase in ZO-1 and occludin expression after 4-HC treatment.Flow cytometry results indicated a dra-matic decrease in the differentiation rate of Th17 cells in spleen lymphocytes and mesenteric lymph nodes,while the dif-ferentiation rate of Treg cells was significantly elevated.Immunohistochemical and Western blot analyses demonstrated that 4-HC markedly reduced the phosphorylation of STAT1 and STAT3,while up-regulating the phosphorylation of STAT6,suggesting that 4-HC modulates CD4+T cell activity through the JAK-STAT pathway.CONCLUSION:The 4-HC may enhance the course of DSS-induced colitis in mice,alleviate colonic tissue damage,and modulate the balance be-tween Th17 and Treg cells,potentially involving the JAK/STAT signaling pathway.