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 investigate the therapeutic efficacy of autologous hematopoietic stem cell transplantation (auto-HSCT) for treatment of diffuse large B-cell lymphoma (DLBCL) and the factors affecting the prognosis.Methods:A retrospective case series study was conducted. The clinical data of 51 patients with DLBCL who underwent auto-HSCT in the First Affiliated Hospital of Xinjiang Medical University from March 2019 to January 2024 were retrospectively analyzed. Patients were divided into high-risk group (19 cases) and non-high-risk group (low-risk, low-moderate-risk and moderate-high-risk groups, 32 cases) based on different risk stratifications; patients were divided into the germinal center B-cell (GCB) group (29 cases) and non-GCB group (22 cases) based on different cellular origins; patients were divided into BEAM group (39 cases) and BeEAM group (12 cases) based on different conditioning regimens before auto-HSCT; patients were divided into auto-HSCT consolidation therapy group (41 cases) and auto-HSCT after relapsed/refractory group (10 cases) based on different transplantation timings. The Kaplan-Meier method was used for survival analysis and log-rank was used for subgroup comparison.Results:All 51 patients achieved the hematopoietic reconstitution with no transplantation-related death within 100 d. Before auto-HSCT, 39 cases achieved complete remission and 12 cases (23.5%) achieved partial remission. After auto-HSCT, all cases achieved complete remission. Follow-up was until May 31, 2024, and the median follow-up time [ M ( Q1, Q3)] of 51 DLBCL patients was 33 (8, 43) months. After 51 DLBCL patients receiving auto-HSCT, 7 patients relapsed and 6 cases died including 3 cases with relapse-related death and 3 cases with non relapse-related death. The 3-year progression-free survival (PFS) and overall survival (OS) rates were 78.5% (95% CI: 64.4%-92.6%) and 85.5% (95% CI: 73.2%-97.8%), respectively. The 3-year PFS rate was 94.7% (95% CI: 84.7%-104.7%) in the high-risk group, 82.2% (95% CI: 67.9%-96.5%) in the non-high-risk group, and the difference in the PFS was not statistically significant between the high-risk group and the non-high-risk group ( P = 0.158). The 3-year PFS rate was 80.1% (95% CI: 64.4%-95.8%) in the GCB group, 88.1% (95% CI: 72.3%-104.2%) in the non-GCB group, and the difference in PFS was not statistically significant between the 2 groups ( P = 0.803). The 3-year PFS rate was 84.9% (95% CI: 72.6%-97.2%) in BEAM group, 61.1% (95% CI: 25.0%-97.2%) in the BeEAM group, and the difference in PFS was not statistically significant between the 2 groups ( P = 0.106). The 3-year PFS rate was 85.4% (95% CI: 73.4%-97.4%) in the auto-HSCT consolidation therapy group, 64.3% (95% CI: 31.4%-96.4%) in the auto-HSCT after relapsed/refractory group, and the difference in PFS was not statistically significant between the 2 groups ( P = 0.171). Conclusions:auto-HSCT is an effective therapy method for DLBCL.

Objective:To investigate the efficacy and safety of venetoclax and azacitidine combined with GHA (human granulocyte colony stimulating factor, homoharringtonine and low-dose cytarabine) priming regimen in treatment of patients with relapsed/refractory acute myeloid leukemia.Methods:A retrospective case series study was conducted. Twenty-three patients with relapsed/refractory acute myeloid leukemia (non-acute promyelocytic leukemia) who received treatment with the combination of venetoclax and azacitidine with GHA priming regimen at the Second Affiliated Hospital of Xi'an Jiaotong University from October 2020 to July 2024 were selected, and the treatment efficacy, minimal residual disease (MRD)-negative rate in patients with comprehensive complete remission (cCR) (including complete remission, complete remission with partial hematologic recovery and complete remission with incomplete hematologic recovery) and the adverse reactions were analyzed; patients were followed-up, and their overall survival (OS) was analyzed by using Kaplan-Meier method.Results:The median age of the 23 patients was 60 years (range: 21-79 years), including 10 males and 13 females. The cCR rate for 1 course of treatment was 52.2% (12/23), with 4 cases of MRD negative among cCR patients; 5 cases received 2 courses of treatment, with 3 cases achieving cCR, of which 2 cases were MRD negative; 2 cases received 3 courses of treatment, with 1 case achieving complete remission with incomplete hematologic recovery. Six patients underwent allogeneic hematopoietic stem cell transplantation. The patients were followed up until July 31, 2024, and the median follow-up period was 5.3 months (range: 1.1-41.7 months). Ten cases survived, 12 cases died, 1 case was lost to follow-up, and the median OS time of 23 patients was 7.9 months. The 6-month OS rate was 60.2% (95% CI: 42.7%-84.8%), and the 12-month OS rate was 44.6% (95% CI: 26.8%-74.3%). Common adverse reactions during treatment included infection [69.6% (16/23)], nausea [56.5% (13/23)], febrile neutropenia [52.2% (12/23)], bleeding [52.2% (12/23)], vomiting [34.8% (8/23)], and pneumonia [34.8% (8/23)]. Conclusions:The combination of vinaclotide and azacitidine with GHA priming regimen has certain efficacy and good safety in the treatment of relapsed/refractory acute myeloid leukemia.

Objective:To evaluate the effectiveness of opioid-free anesthesia on postoperative outcomes in elderly patients following laparoscopic cholecystectomy.Methods:In this randomized controlled trial, 90 patients of either sex, aged 65-75 yr, with a body mass index of 18.5-23.9 kg/m 2, of American Society of Anesthesiologists Physical Status classification Ⅱ or Ⅲ, scheduled for elective laparoscopic cholecystectomy, were divided into 2 groups ( n=45 each) using a table of random numbers: conventional general anesthesia group (GA group) and opioid-free anesthesia group (OFA group). Anesthesia was induced with intravenous etomidate, sufentanil and cisatracurium besylate and maintained with infusion of propofol and remifentanil combined with inhalation of sevoflurane in GA group. In OFA group, bilateral ultrasound-guided transversus abdominis plane block was performed via the posterior gluteal approach (injection of 0.25% ropivacaine 20 ml respectively) before anesthesia induction, anesthesia was induced with intravenous dexmedetomidine, esketamine, etomidate and cisatracurium besylate and maintained with infusion of dexmedetomidine, esketamine and propofol combined with inhalation of sevoflurane. In both groups, mechanical ventilation was performed with a laryngeal mask airway after anesthesia induction, and ketorolac tromethamine 30 mg (for postoperative analgesia) and metoclopramide 10 mg (to prevent postoperative nausea and vomiting) were intravenously injected at the end of surgery. The intraoperative adverse cardiovascular events, emergence time, laryngeal mask airway removal time, time of postanesthesia care unit stay, and postoperative rescue analgesia, nausea and vomiting and delirium were recorded. Results:No gallbladder cardiac reflex was found during operation in either group. Compared with GA group, the incidence of intraoperative bradycardia (11% versus 22%) was significantly increased ( P<0.05), the incidence of intraoperative hypotension and postoperative nausea, vomiting and delirium (17% versus 8%, 29% versus 16%, 16% versus 4% and 18% versus 4%), and requirements for rescue analgesia and antiemetics (31% versus 7% and 13% versus 4%) were decreased ( P<0.05), the postoperative emergence time, time of laryngeal mask airway removal and time of postanesthesia care unit stay were prolonged ( P<0.05), and no statistically significant difference was found in discharge time in OFA group ( P>0.05). Conclusions:The results of this study, as a single-center, small-sample randomized controlled trial, indicate that referenced to conventional general anesthesia, opioid-free anesthesia (esketamine-dexmedetomidine based anesthesia combined with bilateral transversus abdominis plan block) can improve the short-term postoperative outcomes to a certain extent in elderly patients following laparoscopic cholecystectomy.

Objective:To investigate the impact of olanzapine and risperidone on the cognitive function, sensory gating function and clinical symptoms of patients with first-episode schizophrenia(FES).Additionally, to analyze the correlation between sensory gating inhibitory deficits and cognitive impairment in FES patients.Methods:A total of 71 FES patients were selected in the Third People's Hospital of Zhongshan City from March 2023 to March 2024, and 60 healthy controls were recruited during the same period.The FES patients were divided into olanzapine group and risperidone group by random number table.Olanzapine group was treated with variable doses of olanzapine(10-20 mg/d), and risperidone group was treated with variable doses of risperidone(3-6 mg/d).The MATRICS consensus cognitive battery(MCCB) was used to evaluate the cognitive function of the patients, P50 index was measured by auditory paired condition-stimulus paradigm, and the efficacy was evaluated by positive and negative syndrome scale(PANSS) score reduction rate before and after 6 weeks of treatment.Healthy controls were assessed cognitive function only once with P50.SPSS 25.0 software was used for data processing. Perform statistical analysis using paired sample t-test, Wilcoxon signed rank test, independent sample t-test, Mann Whitney U test, χ2 test and generalized linear model. Results:Before treatment, the S2 amplitude of FES (1.74 (0.91, 2.79) μV) was higher than that of healthy controls (1.70 (1.04, 2.71) μV) (Wald χ2=4.483, P=0.034), the S2/S1 ratio of FES (0.58 (0.43, 0.78)) was higher than that of healthy controls (0.41 (0.31, 0.57)) (Wald χ2=10.909, P=0.001), and the difference of FES amplitude of S1-S2 was (1.22 (0.43, 1.92) μV) was lower than that of healthy controls (2.23 (1.54, 3.07) μV) (Wald χ2=17.679, P<0.001). There was no significant difference in PANSS, MCCB and P50 between olanzapine group and risperidone group before treatment (all P>0.05). After treatment, there was no significant difference in response rate between the two groups ( χ2=0.059, P=0.808), the PANSS scores were lower than those before treatment, the MCCB test results were higher than those before treatment (both P<0.05), and the P50 results were not statistically significant different compared with those before treatment (both P>0.05). The generalized linear model showed that the S1, S2 amplitude of the P50 had positive impact on the connection test score in the MCCB test ( β=0.466, P=0.020; β=0.879, P=0.009), other indicators were not found to have an impact on the test scores of the MCCB test (all P>0.05). Conclusion:Olanzapine and risperidone can significantly improve the cognitive function of FES, but the improvement of sensory gating deficits is limited. The pathogenic mechanism of sensory gating inhibitory deficits in FES may be different from that of cognitive dysfunction.

Objective:To evaluate the effectiveness of opioid-free anesthesia on postoperative outcomes in elderly patients following laparoscopic cholecystectomy.Methods:In this randomized controlled trial, 90 patients of either sex, aged 65-75 yr, with a body mass index of 18.5-23.9 kg/m 2, of American Society of Anesthesiologists Physical Status classification Ⅱ or Ⅲ, scheduled for elective laparoscopic cholecystectomy, were divided into 2 groups ( n=45 each) using a table of random numbers: conventional general anesthesia group (GA group) and opioid-free anesthesia group (OFA group). Anesthesia was induced with intravenous etomidate, sufentanil and cisatracurium besylate and maintained with infusion of propofol and remifentanil combined with inhalation of sevoflurane in GA group. In OFA group, bilateral ultrasound-guided transversus abdominis plane block was performed via the posterior gluteal approach (injection of 0.25% ropivacaine 20 ml respectively) before anesthesia induction, anesthesia was induced with intravenous dexmedetomidine, esketamine, etomidate and cisatracurium besylate and maintained with infusion of dexmedetomidine, esketamine and propofol combined with inhalation of sevoflurane. In both groups, mechanical ventilation was performed with a laryngeal mask airway after anesthesia induction, and ketorolac tromethamine 30 mg (for postoperative analgesia) and metoclopramide 10 mg (to prevent postoperative nausea and vomiting) were intravenously injected at the end of surgery. The intraoperative adverse cardiovascular events, emergence time, laryngeal mask airway removal time, time of postanesthesia care unit stay, and postoperative rescue analgesia, nausea and vomiting and delirium were recorded. Results:No gallbladder cardiac reflex was found during operation in either group. Compared with GA group, the incidence of intraoperative bradycardia (11% versus 22%) was significantly increased ( P<0.05), the incidence of intraoperative hypotension and postoperative nausea, vomiting and delirium (17% versus 8%, 29% versus 16%, 16% versus 4% and 18% versus 4%), and requirements for rescue analgesia and antiemetics (31% versus 7% and 13% versus 4%) were decreased ( P<0.05), the postoperative emergence time, time of laryngeal mask airway removal and time of postanesthesia care unit stay were prolonged ( P<0.05), and no statistically significant difference was found in discharge time in OFA group ( P>0.05). Conclusions:The results of this study, as a single-center, small-sample randomized controlled trial, indicate that referenced to conventional general anesthesia, opioid-free anesthesia (esketamine-dexmedetomidine based anesthesia combined with bilateral transversus abdominis plan block) can improve the short-term postoperative outcomes to a certain extent in elderly patients following laparoscopic cholecystectomy.

Objective:To construct an evaluation system for the risk factors of PICC catheter malposition in patients with hematological diseases, providing a reference for the prevention of central venous access malposition in these patients.Methods:From July 2022, a literature review was conducted to retrieve literature published in database and website such as PubMed, Web of Science domestically and internationally related to the risk assessment system of PICC catheter malposition in hematology patients. After full-text screening and extraction, the articles were included in the system′s item pool. Through further discussions among the research group′s experts, in conjunction with evidence-based findings, the system′s consultation items were formulated. Using the Delphi expert consultation method, a standard for PICC catheter malposition risk assessment system applicable to hematology patients was ultimately formulated.Results:In this study, 25 experts were invited for consultation: 24 females and 1 male, with an average age of (48.36 ± 6.82) years. After two rounds of expert consultations and revisions, the risk factors for PICC catheter malposition in hematology patients were identified to include 4 first-level indicators: patient factors, treatment factors, catheter-related factors, and operational factors, along with 11 second-level indicators and 25 third-level indicators. The positive coefficients of the experts in the two rounds of consultations were 84% and 100%, respectively; the Kendall coordination coefficients were 0.22 and 0.55 (both P<0.05); and the expert authority coefficient was 0.93. Conclusions:The risk assessment scale for PICC catheter malposition in patients with hematological diseases has high expert recognition and good consistency, and has clinical practice and guiding value.

Objective:To analyze the characteristics and influential factors of ischemic stroke in young adults.Methods:This study used a retrospective research design. From May 2021 to April 2022, a total of 80 patients aged 18 to 45 years with acute ischemic stroke, who were hospitalized in the Department of Neurology of Yuncheng Central Hospital, were selected for the patient group. Additionally, 80 healthy individuals in the same age range who underwent outpatient examinations during this period were selected as the control group. The risk factors, imaging characteristics, pathological causes, severity, progression, and prognosis of ischemic stroke were analyzed.Results:The average age of the 80 patients with ischemic stroke was (39.6 ± 5.1) years. These patients included 56 male patients (70.0%) and 24 female patients (30.0%). Univariate analysis revealed statistically significant differences in the prevalence of hypertension ( χ2 = 70.45, P < 0.001), hyperlipidemia ( χ2 = 92.35, P < 0.001), hyperglycemia ( χ2 = 8.73, P < 0.001), smoking ( χ2 = 14.82, P < 0.001), alcohol consumption ( χ2 = 4.81, P < 0.001), and familial inheritance ( χ2 = 3.79, P < 0.001) between the patient and control groups. Multivariate logistic regression analysis indicated that hyperlipidemia ( OR = 6.75, 95% CI: 4.21-10.04, P < 0.001), hypertension ( OR = 5.83, 95% CI: 3.75-9.34, P < 0.001), smoking ( OR = 7.36, 95% CI: 1.37-3.04, P < 0.001), alcohol consumption ( OR = 1.57, 95% CI: 1.03-2.42, P < 0.001), familial inheritance ( OR = 1.66, 95% CI: 1.01-2.49, P < 0.001), and hyperglycemia ( OR = 2.16, 95% CI: 1.22-3.56, P < 0.001) are independent risk factors for ischemic stroke in young adults. Conclusions:Hyperlipidemia, hypertension, smoking, alcohol consumption, family history, and hyperglycemia are risk factors for ischemic stroke in young adults. It is essential to enhance the promotion of healthy living practices and to monitor patients' blood pressure and lipid levels regularly, as this can help reduce the likelihood of stroke occurrence.