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 effect of donor age on short-term survival of patients with idiopathic pulmonary fibrosis (IPF) after lung transplantation. Methods Clinical data of 235 IPF donors and recipients of lung transplantation were retrospectively analyzed. Univariate and multivariate Cox proportional hazard regression models were employed to analyze the correlation between donor age and short-term mortality rate of IPF patients after lung transplantation. Kaplan-Meier was used to draw the survival curve. Results Univariate Cox regression analysis showed that donor age was correlated with the 1-year fatality of IPF patients after lung transplantation. The 1-year fatality of recipients after lung transplantation was increased by 0.020 times if donor age was increased by 1 year (P=0.009). Oxygenation index of the donors, preoperative oxygenation index, preoperative lung allocation score, preoperative N-terminal pro brain natriuretic peptide, pattern of transplantation, pattern of intraoperative extracorporeal membrane oxygenation and intraoperative blood transfusion volume of the recipients were correlated with 1-year fatality after lung transplantation (all P < 0.1). Multivariate Cox regression analysis demonstrated that there was no correlation between donor age and 30-, 90-, 180-d and 1-year fatality of IPF patients after lung transplantation (all P > 0.05). Sensitivity analysis showed that there was no significant difference in 30-, 90-, 180-d and 1-year fatality after lung transplantation among donors aged < 18, 18-33, 34-49 and ≥50 years (all P > 0.05). Conclusions Donor age exerts no effect upon short-term survival of IPF patients after lung transplantation. Considering the mechanical ventilation time, oxygenation index, infection and other factors of donors, the age range of lung transplant donors may be expanded.

Objective:To investigate the risk factors of early death after lung transplantation in patients with idiopathic pulmonary fibrosis (IPF) complicated with pulmonary arterial hypertension (PAH).Methods:A retrospective cohort study was conducted. The clinical data of 134 patients with IPF and PAH who underwent lung transplantation at Wuxi People's Hospital Affiliated to Nanjing Medical University from January 2017 to December 2020 were collected. The donor's gender, age, duration of mechanical ventilation, and cold ischemia time, the recipient's gender, age, body mass index (BMI), smoking, history of hypertension and diabetes, preoperative usage of hormones, mean pulmonary arterial pressure (mPAP), cardiac echocardiography and cardiac function, serum creatinine (SCr), N-terminal pro-brain natriuretic peptide (NT-proBNP) as well as surgical type, extracorporeal membrane oxygenation (ECMO) treatment, duration of operation, and plasma and red blood cell infusion ratio were collected. The cumulative survival rates of patients at 30, 60, and 180 days after lung transplantation were calculated by Kaplan-Meier method. The univariate and multivariate Cox proportional hazards regression models were used to analyze the effects of donor, recipient, and surgical factors on early survival in donors after lung transplantation.Results:The majority of donors were male (80.6%). There was 63.4% of the donors older than 35 years old, 80.6% of the donors had mechanical ventilation duration less than 10 days, and the median cold ischemia time was 465.00 (369.25, 556.25) minutes. The recipients were mainly males (83.6%). Most of the patients were younger than 65 years old (70.9%). Most of them had no hypertension (75.4%) or diabetes (67.9%). The median mPAP of recipients was 36 (30, 43) mmHg (1 mmHg≈0.133 kPa). There were 73 patients with single lung transplantation (54.5%), and 61 with double lung transplantation (45.5%). The survival rates of 134 IPF patients with PAH at 30, 60, 180 days after lung transplantation were 81.3%, 76.9%, and 67.4%, respectively. Univariate Cox proportional risk regression analysis showed that recipient preoperative use of hormone [hazard ratio ( HR) = 2.079, 95% confidence interval (95% CI) was 1.048-4.128], mPAP ≥ 35 mmHg ( HR = 2.136, 95% CI was 1.129-4.044), NT-proBNP ≥ 300 ng/L ( HR = 2.411, 95% CI was 1.323-4.392), New York Heart Association (NYHA) cardiac function classification Ⅲ-Ⅳ ( HR = 3.021, 95% CI was 1.652-5.523) were the risk factors of early postoperative death in patients with IPF complicated with PAH (all P < 0.05). In the multivariable Cox proportional risk regression analysis, recipient preoperative hormone usage (model 1: HR = 2.072, 95% CI was 1.044-4.114, P = 0.037; model 2: HR = 2.098, 95% CI was 1.057-4.165, P = 0.034), NT-proBNP ≥ 300 ng/L ( HR = 2.246, 95% CI was 1.225-4.116, P = 0.009) and NYHA cardiac function classification Ⅲ-Ⅳ ( HR = 2.771, 95% CI was 1.495-5.134, P = 0.001) were independent risk factors of early postoperative death in patients with IPF. Conclusions:Preoperative hormone usage, NT-proBNP ≥ 300 ng/L, NYHA cardiac function classification Ⅲ-Ⅳ are independent risk factors for early death in patients with IPF and PAH after lung transplantation. For these patients, attention should be paid to optimize their functional status before operation. Preoperative reduction of receptor hormone usage and improvement of cardiac function can improve the early survival rate of such patients after lung transplantation.

Objective:To explore the effect of acute kidney injury(AKI)on near-term survival after lung transplantation(LT)in patients with idiopathic pulmonary fibrosis(IPF).Methods:Through consulting electronic medical records, anesthetic modes and Chinese Lung Transplant Registration System, clinical data are retrospectively reviewed for 275 IPF patients undergoing LT at Affiliated Wuxi People's Hospital of Nanjing Medical University from January 2017 to April 2021.According to the diagnostic criteria of Kidney Disease: Improving Global Outcomes(KDIGO), they are divided into two groups of AKI(169 cases)and non-AKI(106 cases).Perioperative findings of two groups are recorded.Then univariate and multivariate Cox regression models are employed for determining whether or not inter-group differences existed in survival rates post-LT.Also AKI is staged according to the KDIGO.And the effect of stage 1/2/3 AKI on near-term postoperative prognosis is examined.Results:The differences are significantly different in recipient gender, creatinine, 6-minute walking test, forced vital capacity(FVC), lung allocation score, oxygenation index, N-terminal pro-brain natriuretic peptide(NT-Pro BNP), preoperative hormone use and volume of crystal infusion( P<0.05).After multivariate Cox regression correcting for covariates, no statistical significance exists in effect of AKI stage 1 on near-term postoperative survival rate( P<0.05).AKI stage 2/3 still has statistical significance in risk of mortality at Day 30/90/180/365 post-operation( P>0.05). Conclusions:As a common complication post-LT, AKI significantly affects near-term postoperative prognosis of transplant IPF patients.Stage 2/3 AKI impacts near-term postoperative survival while stage 1 AKI is not associated with higher mortality.

Objective To evaluate the impact of customized rehabilitation exercise plans based on the results of cardiopulmonary exercise test(CPET)on cardiac function and prognosis in patients with chronic heart failure(CHF).Methods A total of 52 CHF patients admitted to Chengde Central Hospital from February 2020 to September 2021 were selected as the study subjects,and the patients were divided into observation group and control group according to the principle of randomized controlled study,with 26 cases in each group.The control group received rehabilitation treatment excluding exercise.The observation group was given routine rehabilitation treatment and high-intensity rehabilitation exercise plans based on CPET guidance.Above anaerobic threshold Δ50%power was exercise intensity,exercise time was 30 minutes/day,4 days/week,and intervention period was 12 weeks.Before and 12 weeks after intervention,CPET functional indicators,serum brain natriuretic peptide(BNP),left ventricular ejection fraction(LVEF),left ventricular end-diastolic diameter(LVEDD),and 6-minute walking distance(6MWD)were measured.The Minnesota CHF quality of life questionnaire(LiHFe)was used to evaluate patient's quality of life,readmission rate and cardiogenic mortality within 1 year of follow-up,and univariate and multivariate Logistic regression analysis was used to analyze factors affecting readmission of CHF patients.Results ① Cardiopulmonary function indicators:there was no statistically significant difference in the anaerobic threshold,peak oxygen uptake,and peak oxygen pulse of CPET functional indicators before and after intervention in the control group,after intervention,the CPET functional indicators in the observation group were significantly higher than those before intervention,and the above indexes in the observation group were significantly higher than those of the control group[anaerobic threshold(mL·min-1·kg-1):10.77±1.40 vs.9.59±1.11,anaerobic threshold(%ped):78.95±11.39 vs.70.09±6.48,peak oxygen uptake(mL·min-1·kg-1):15.63±1.36 vs.14.27±1.72,peak oxygen uptake(%ped):72.42±6.91 vs.63.41±7.31,peak oxygen pulse(mL/order):11.38±1.29 vs.9.05±1.64,peak oxygen pulse(%ped):90.23±10.16 vs.80.53±6.73,all P＜0.05].②Serum indicators,cardiac function indicators,exercise ability indicators,and quality of life evaluation:there was no statistically significant difference in serum indicators BNP,cardiac function indicators LVEDD,LVEF,exercise ability indicators 6MWD,and quality of life LiHFe scores between the two groups before intervention.After intervention,BNP and LiHFe scores were significantly reduced compared with before intervention,while LVEF and 6MWD were both increased compared with before intervention,and the changes of the above indexes in the observation group were more significant than those in the control group[BNP(ng/L):313.25±77.91 vs.445.89±110.67,LVEF:0.41±0.08 vs.0.37±0.06,6MWD(m):495.62±91.35 vs.416.04±65.29,LiHFe score:23.27±6.02 vs.29.50±4.61,all P＜0.05].③ Prognostic follow-up:the readmission rate within 1 year in the observation group was significantly lower than that in the control group(23.08%vs.53.85%),and there was no statistically significant difference in the mortality rate of cardiogenic diseases between the two groups.④Logistic univariate analysis showed that hyperlipidemia,New York Heart Association(NYHA)grading,BNP,and rehabilitation exercise were factors that affect the prognosis of CHF patients[odds ratio(OR)and 95%confidence interval(95%CI)were 0.098(0.019-0.494),0.069(0.016-0.294),1.018(1.007-1.029),and 3.889(1.178-12.841),respectively,all P＜0.05].Multivariate analysis showed that after adjusting for other factors,hyperlipidemia,NYHA grading,and BNP were risk factors affecting the prognosis of CHF patients(OR and 95%CI were 0.068(0.007-0.687),0.048(0.005-0.415),1.016(1.002-1.030),respectively,with P＜0.05],the use of rehabilitation exercise therapy was a protective factor affecting the prognosis of CHF patients[OR and 95%CI were 11.179(1.135-10.124),P＜0.05].Receiver operator characteristic curve(ROC curve)analysis showed that hyperlipidemia,NYHA grading,BNP,rehabilitation exercise therapy,and combined testing all had predictive value for the patient's prognosis(all P＜0.05),and the prediction value of joint detection was the highest,with the area under the ROC curve(AUC)=0.984 and P = 0.000.Conclusion Developing a high-intensity individualized cardiac exercise rehabilitation plan under the guidance of CPET can help improve the cardiopulmonary function,cardiac function,and quality of life of CHF patients,which is of great benefit for improving the long-term prognosis of CHF patients and has high safety.

Objective To explore the diagnostic value of artificial intelligence (AI) cytology combined with DNA-image cytometry (DNA-ICM) auxiliary diagnostic system for the identification of benign and malignant pleural effusion and ascites. Methods Liquid-based cytology technology (LCT), DNA-ICM, AI, and AI combined with DNA-ICM were used to identify benign and malignant pleural effusion and ascites specimens in 360 cases, and their sensitivity, specificity, accuracy, Kappa value, Youden index and AUC were statistically analyzed. Results The sensitivity, specificity, and accuracy of AI combined with DNA-ICM in detecting benign and malignant pleural effusion and ascites were 95.23%, 94.12%, and 94.44%, respectively, which were higher than those of the three other separate detection methods (all P < 0.05). The kappa values of LCT, DNA-ICM, and AI were 0.646, 0.642, and 0.586; their Youden index values were 0.693, 0.687, and 0.676, and their AUC values were 0.846, 0.843, and 0.838, respectively. The Kappa value of AI combined with DNA-ICM was 0.869, the Youden index was 0.893, and AUC was 0.947, which were all higher than those of the three detection methods alone. Conclusion Among the three separate detection methods, LCT has the highest reliability, authenticity, and diagnostic value, and it can be used as a common method for the clinical identification of benign and malignant pleural effusion and ascites. The diagnostic performance of AI combined with DNA-ICM auxiliary diagnosis system in identifying benign and malignant pleural effusion and ascites is better than those of the three separate detection methods and can be used as a reliable method for the clinical identification of benign and malignant pleural effusion and ascites.

Objective:To explore the early prognosis on patient of idiopathic pulmonary fibrosis (IPF) combined with different degrees of pulmonary arterial hypertension (PAH) undertake lung transplantation (LTx).Methods:From January 2017 to December 2020, the clinical data of 134 patients with IPF who underwent LTx in Wuxi People's Hospital were analyzed retrospectively. According to the average pulmonary artery pressure detected by right cardiac catheter before operation, the patients were divided into mild PAH group (63 cases), moderate PAH group (47 cases) and severe PAH group (24 cases). The donor data and the recipient's preoperative, intraoperative and postoperative data were collected; the postoperative survival curve to analyze early survival among the three patient groups.Results:With the increase of pulmonary artery pressure, the rate of abnormal right ventricular function increased, the end diastolic diameter of left ventricle decreased before operation, and the rate of using veno-arterial extracorporeal membrane oxygenation (V-A ECMO) increased during the surgery ( P<0.05). Multivariate analysis found that combined severe PAH had significant effects on primary graft dysfunction (Primary graft dysfunction, PGD), retracheal intubation or tracheotomy, hypovolemic shock within 72 h, and 6-month survival after LTx. The survival surve showed that 30-day survival rates of patients with IPF complicated with mild, moderate and severe PAH were 85.7%, 80.8% and 66.7% respectively, and the 6-month survival rates were 80.9%, 74.0% and 62.2%, respectively. Conclusion:Patient of IPF combined with different degrees of PAH had a significant impact on cardiac function and intraoperative ECMO selection of LTx, and severe PAH could significantly reduce the early survival rate after LTx.

Objective:To compare the effect of extracorporeal membrane oxygenation(ECMO)on pulmonary transplantation(LTx)in patients with idiopathic pulmonary fibrosis(IPF)complicated with pulmonary hypertension(PH).Methods:From January 2017 to December 2020, clinical data were retrospectively reviewed for 112 IPF patients complicated with PH undergoing LTx assisted by venous ECMO(VV-ECMO group, n=68)or venous arterial ECMO(VA-ECMO group, n=44). Gender, age, mechanical ventilation time, oxygenation index, cold ischemic time, preoperative gender, age, smoking history, PO 2, PCO 2, PH degree, NYHA cardiac function grade, right cardiac function, ejection fraction(EF)and complications(hypertension & diabetes)of two groups were compared. Intraoperative approach, operative duration, ECMO transfer time, blood loss, blood transfusion, urine volume, postoperative blood transfusion, mechanical ventilation time, ICU stay time, re-thoracotomy, pulmonary infection, primary graft dysfunction(PGD)and renal insufficiency were recorded. And the effects of two different diversion modes on early postoperative complications and short-term outcomes of LTx were further analyzed by multiple factors. Cox proportional risk model was employed for comparing VV-ECMO and VA-ECMO flow patterns with factors related to recipient survival after transplantation. Results:The preoperative PO 2 of 58.3(51.3, 72.0)mmHg was significantly lower in VV-ECMO bypass group than that of 73.2(63.3, 96.8)mmHg in VA-ECMO group and the difference was statistically significant( P<0.006). Compared with VV-ECMO group, 24(54.5%), 15(34.1%)and 22(50.0%)had NYHA class Ⅲ, severe PH and preoperative right heart enlargement in VA-ECMO group respectively and the differences were statistically significant compared with 17(25.0%), 6(8.8%)and 16(23.5%)in VV-ECMO group( P<0.05 for all). No significant inter-group differences existed in postoperative PGD, postoperative mechanical ventilation time(≥3 d), pulmonary infection, postoperative thoracotomy ratio, postoperative renal insufficiency, ICU stay, hospital stay and other aspects( P>0.05). And 6-month postoperative survival rates of VV-ECMO and VA-ECMO groups were 80.9% and 61.4%, respectively and no significant inter-group difference existed in short-term survival rate(6 months)after adjustment by multivariate Cox regression model( P>0.05). Multivariate statistics indicated that the risk of delayed postoperative withdrawal was 14.452-fold higher in VV-ECMO group than in VA-ECMO group and the inter-group difference was statistically significant(95% CI: 2.448-85.323, P=0.03). Conclusions:No differences exist in postoperative complications or short-term survival rate between IPF recipients with mild PH on VV-ECMO mode and IPF recipients with severe PH on VA-ECMO mode. VV-ECMO flow reversal can delay the transplant back-off time.