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.

Objective:To evaluate the anti-reflux effect of digestive tract reconstruction using esophageal-tubular gastric asymmetric anastomosis after radical resection of esophageal and esophagogastric junction cancer.Methods:The main steps were as follows:(1)oblique incision of the lower esophagus;(2)curved incision of the tubular anterior gastric wall;(3)the lower end of the esophagus was anastomosed to the tubular gastric incision with a 90-degree torsion; (4)The anterior wall of the anastomosis was reinforced with a transverse-inverted suture,the posterior wall with a folded suture,and the corners of the gastric stump were buried with sutures.The anastomosis operation time,postoperative complications and postoperative hospital stay were recorded;the reconstructed structure and anti-reflux effect of the anastomosis were observed by digestive tract radiography,gastroscopy and follow-up investigation.Results:The Department of Gastrointestinal and Thoracic Surgery of Huaian First People's Hospital, affiliated to Nanjing Medical University, treated 5 patients of esophagogastric junction cancer and 20 esophageal cancer cases between August 2022 and November 2024, including 19 men and 6 women, with a mean age of (66.7±7.4) years. The mean anastomosis time was (35.4±5.9) minutes, the intraoperative blood loss was (117.6±33.4) ml and the mean postoperative hospital stay was(16.6±5.2) days, with no complications such as anastomotic leakage and bleeding. Postoperative digestive tract radiography (Trendelenburg position)showed that all the patients had no contrast reflux,gastroscopy showed no signs of reflux esophagitis and bile reflux gastritis, the anastomosis showed an inverted whiskers valve-like structure. The median follow-up time was (16.8±6.3) months, and all patients had no reflux symptoms such as acid reflux and belching,and no acid suppressive medication was needed.Conclusion:The esophageal-tubular gastric asymmetric anastomosis is a safe and effective antireflux reconstruction technique.

Objective·To investigate the effects of liraglutide on liver fibrosis in mice with non-alcoholic fatty liver disease(NAFLD)and the underlying mechanisms.Methods·Twenty 8-week-old C57BL/6J mice were randomly divided into a normal chow diet group(Chow group)and a methionine-choline-deficient(MCD)diet group(MCD group),with 10 mice per group.The MCD diet was used to induce NAFLD.Each group was further divided into two subgroups,resulting in four subgroups:Chow+saline,Chow+liraglutide,MCD+saline,and MCD+liraglutide group.After daily intraperitoneal injection of liraglutide(400 μg/kg)or an equivalent volume of saline for 4 weeks,an intraperitoneal glucose tolerance test(IPGTT)was performed.Serum levels of aspartate transaminase(AST),alanine aminotransferase(ALT),total cholesterol(TC),triglyceride(TAG),high-density lipoprotein cholesterol(HDL-C),and low-density lipoprotein cholesterol(LDL-C)were measured.Liver tissues were collected post-euthanasia to assess TAG content.Histopathological changes,lipid deposition,and fibrosis were evaluated via hematoxylin-eosin(HE)staining,Oil Red O staining,and Masson staining.Real-time quantitative PCR(qPCR)and Western blotting were used to analyze the expression of α-smooth muscle actin(α-SMA),fibronectin(FN),collagen type Ⅰ α(COL1A),matrix metalloproteinase 9(MMP9),tissue inhibitor of metalloproteinase 1(TIMP1),transforming growth factor β(TGF-β),SMAD3,and phosphorylated SMAD3(pSMAD3).Results·The IPGTT revealed that liraglutide intervention reduced blood glucose levels at 15,30,and 60 min,with a decreased area under the curve(AUC)(both P<0.05).Biochemical analysis showed that liraglutide lowered AST and ALT levels(both P<0.001),increased TC and HDL-C levels(both P<0.05),but had no significant effect on TAG or LDL-C in MCD mice.HE staining and Oil Red O staining revealed reduced lipid droplets,ballooning degeneration,and inflammatory infiltration in hepatocytes after liraglutide treatment.Masson staining indicated decreased collagen fiber deposition in the liver.qPCR and Western blotting analysis demonstrated upregulated expression of α-SMA,FN,COL1A,TIMP1,TGF-β,and pSMAD3/SMAD3,alongside downregulated MMP9 in MCD mice.Liraglutide reversed these changes,lowering α-SMA,FN,COL1A,TIMP1,TGF-β,and pSMAD3/SMAD3 expression while increasing MMP9 expression.Conclusion·Liraglutide ameliorates liver injury,lipid deposition,and fibrosis in NAFLD mice,through modulation of the TGF-β/SMAD3 pathway and regulating fibrosis-associated protein expression.

Objective This study aimed to adapt the data-driven Palliative Care Outcomes Collaboration(PCOC)model to the local context and evaluate its feasibility and preliminary effectiveness in a palliative care unit in China,with the goal of informing its broader integration into national palliative care practice.Methods Based on international experience,a localized implementation protocol for the PCOC model was developed through expert con-sultations and a pilot study.The protocol incorporated key elements including organizational and managerial sup-port,team training and capacity building,information system integration,supervision and feedback mechanisms,pro-cess optimization,and data-driven decision-making.From June to December 2023,the protocol was piloted in the palliative care unit of a tertiary cancer hospital in Changsha,China.Implementation outcomes were assessed by comparing patients' urgent care response rates,symptom stability rates,and symptom improvement rates between the first 1～3 months and 4～6 months after implementation.Results During the study period,a total of 355 inpatients were enrolled,with the PCOC assessment achieving full coverage(100％)and a completion rate of 97.78％.There was no statistically significant difference in the urgent needs response rate between the first 1～3 months and the 4～6 months after the implementation of the PCOC model(P=0.533).However,compared to the first 1～3 months af-ter implementation,patients in the 4～6 months period showed significantly higher symptom stability rates for pain,psychological/spiritual issues,and family/caregiver problems,as well as a higher improvement rate for pain(P＜0.05).Conclusion The localized PCOC implementation protocol facilitates standardized assessment and symptom manage-ment,and its application can enhance the quality of palliative care.

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 evaluate the anti-reflux effect of digestive tract reconstruction using esophageal-tubular gastric asymmetric anastomosis after radical resection of esophageal and esophagogastric junction cancer.Methods:The main steps were as follows:(1)oblique incision of the lower esophagus;(2)curved incision of the tubular anterior gastric wall;(3)the lower end of the esophagus was anastomosed to the tubular gastric incision with a 90-degree torsion; (4)The anterior wall of the anastomosis was reinforced with a transverse-inverted suture,the posterior wall with a folded suture,and the corners of the gastric stump were buried with sutures.The anastomosis operation time,postoperative complications and postoperative hospital stay were recorded;the reconstructed structure and anti-reflux effect of the anastomosis were observed by digestive tract radiography,gastroscopy and follow-up investigation.Results:The Department of Gastrointestinal and Thoracic Surgery of Huaian First People's Hospital, affiliated to Nanjing Medical University, treated 5 patients of esophagogastric junction cancer and 20 esophageal cancer cases between August 2022 and November 2024, including 19 men and 6 women, with a mean age of (66.7±7.4) years. The mean anastomosis time was (35.4±5.9) minutes, the intraoperative blood loss was (117.6±33.4) ml and the mean postoperative hospital stay was(16.6±5.2) days, with no complications such as anastomotic leakage and bleeding. Postoperative digestive tract radiography (Trendelenburg position)showed that all the patients had no contrast reflux,gastroscopy showed no signs of reflux esophagitis and bile reflux gastritis, the anastomosis showed an inverted whiskers valve-like structure. The median follow-up time was (16.8±6.3) months, and all patients had no reflux symptoms such as acid reflux and belching,and no acid suppressive medication was needed.Conclusion:The esophageal-tubular gastric asymmetric anastomosis is a safe and effective antireflux reconstruction technique.

Objective·To investigate the effects of liraglutide on liver fibrosis in mice with non-alcoholic fatty liver disease(NAFLD)and the underlying mechanisms.Methods·Twenty 8-week-old C57BL/6J mice were randomly divided into a normal chow diet group(Chow group)and a methionine-choline-deficient(MCD)diet group(MCD group),with 10 mice per group.The MCD diet was used to induce NAFLD.Each group was further divided into two subgroups,resulting in four subgroups:Chow+saline,Chow+liraglutide,MCD+saline,and MCD+liraglutide group.After daily intraperitoneal injection of liraglutide(400 μg/kg)or an equivalent volume of saline for 4 weeks,an intraperitoneal glucose tolerance test(IPGTT)was performed.Serum levels of aspartate transaminase(AST),alanine aminotransferase(ALT),total cholesterol(TC),triglyceride(TAG),high-density lipoprotein cholesterol(HDL-C),and low-density lipoprotein cholesterol(LDL-C)were measured.Liver tissues were collected post-euthanasia to assess TAG content.Histopathological changes,lipid deposition,and fibrosis were evaluated via hematoxylin-eosin(HE)staining,Oil Red O staining,and Masson staining.Real-time quantitative PCR(qPCR)and Western blotting were used to analyze the expression of α-smooth muscle actin(α-SMA),fibronectin(FN),collagen type Ⅰ α(COL1A),matrix metalloproteinase 9(MMP9),tissue inhibitor of metalloproteinase 1(TIMP1),transforming growth factor β(TGF-β),SMAD3,and phosphorylated SMAD3(pSMAD3).Results·The IPGTT revealed that liraglutide intervention reduced blood glucose levels at 15,30,and 60 min,with a decreased area under the curve(AUC)(both P<0.05).Biochemical analysis showed that liraglutide lowered AST and ALT levels(both P<0.001),increased TC and HDL-C levels(both P<0.05),but had no significant effect on TAG or LDL-C in MCD mice.HE staining and Oil Red O staining revealed reduced lipid droplets,ballooning degeneration,and inflammatory infiltration in hepatocytes after liraglutide treatment.Masson staining indicated decreased collagen fiber deposition in the liver.qPCR and Western blotting analysis demonstrated upregulated expression of α-SMA,FN,COL1A,TIMP1,TGF-β,and pSMAD3/SMAD3,alongside downregulated MMP9 in MCD mice.Liraglutide reversed these changes,lowering α-SMA,FN,COL1A,TIMP1,TGF-β,and pSMAD3/SMAD3 expression while increasing MMP9 expression.Conclusion·Liraglutide ameliorates liver injury,lipid deposition,and fibrosis in NAFLD mice,through modulation of the TGF-β/SMAD3 pathway and regulating fibrosis-associated protein expression.

Objective:To review the literature on surrogate decision making in stroke patients, and to clarify the application status of proxy decision making in stroke patients.Methods:Using the scope review guide as the methodological framework, studies on the application of surrogate decision in stroke patients, PubMed, Medline, CINAHL, Web of Science, Cochrane Library, CNKI, Wanfang, China Biology Medicine databases were searched from the database inception to January 12, 2024.Results:A total of 20 articles were included, including 12 cross-sectional studies, 6 qualitative studies, 1 cohort study, and 1 case report. At present, surrogate decision was mainly used in brain surgery, tube placement and comfort care. The agent had a complicated mood when making a decision and self-doubt after making a decision. Agency decision making was susceptible to demographic factors, disease-related factors, cultural factors, emotional and psychological factors and other factors. Although the outcomes of most proxy decisions were in line with patient preferences, there was a difference in the estimates of prognosis between agents and medical staff.Conclusions:Proxy decision making is widely used in the field of stroke, but the psychological burden of agents is heavy. Developing advance care planning for stroke patients and developing decision aids may help agents make the best decision.