Purpose To develop an integrate model combining deep learning features from contrast-enhanced lung ultrasonography with clinical characteristics for predicting epidermal growth factor receptor mutation status in peripheral non-small cell lung cancer.Materials and Methods This retrospective study included 117 patients with pathologically confirmed non-small cell lung cancer from the First Affiliated Hospital of Guangxi Medical University(July 2021 to February 2024).Patients were randomly divided into training(n=93)and test(n=24)sets at an 8∶2 ratio.Regions of interest were delineated at the peak enhancement phase of contrast-enhanced lung ultrasonography.Various deep learning convolutional neural networks were pretrained,with ResNet18 selected as optimal for feature extraction.Deep learning,clinical,and integrated models were constructed using naive Bayesian algorithm.Performance was evaluated via receiver operating characteristic and calibration curves,while class activation mapping and Shapley additive explanation values provided model interpretability.Results In the training set,the deep learning,clinical and integrated models achieved area under the curve of 0.93(95%CI 0.88-0.98),0.86(95%CI 0.68-1.00),and 0.91(95%CI 0.85-0.97),respectively.Corresponding test set area under the curve were 0.81(95%CI 0.72-0.90),0.56(95%CI 0.33-0.80),and 0.87(95%CI 0.72-1.00).Both deep learning and integrated models significantly outperformed the clinical model in training(Z=2.380,P=0.017;Z=2.597,P=0.009)and test sets(Z=2.034,P=0.042;Z=2.577,P=0.010).The integrated model demonstrated excellent calibration and predictive performance.Conclusion The integrated model combining deep learning features from contrast-enhanced lung ultrasonography with clinical characteristics effectively predicts epidermal growth factor receptor mutation status in peripheral non-small cell lung cancer.

Purpose To develop an integrate model combining deep learning features from contrast-enhanced lung ultrasonography with clinical characteristics for predicting epidermal growth factor receptor mutation status in peripheral non-small cell lung cancer.Materials and Methods This retrospective study included 117 patients with pathologically confirmed non-small cell lung cancer from the First Affiliated Hospital of Guangxi Medical University(July 2021 to February 2024).Patients were randomly divided into training(n=93)and test(n=24)sets at an 8∶2 ratio.Regions of interest were delineated at the peak enhancement phase of contrast-enhanced lung ultrasonography.Various deep learning convolutional neural networks were pretrained,with ResNet18 selected as optimal for feature extraction.Deep learning,clinical,and integrated models were constructed using naive Bayesian algorithm.Performance was evaluated via receiver operating characteristic and calibration curves,while class activation mapping and Shapley additive explanation values provided model interpretability.Results In the training set,the deep learning,clinical and integrated models achieved area under the curve of 0.93(95%CI 0.88-0.98),0.86(95%CI 0.68-1.00),and 0.91(95%CI 0.85-0.97),respectively.Corresponding test set area under the curve were 0.81(95%CI 0.72-0.90),0.56(95%CI 0.33-0.80),and 0.87(95%CI 0.72-1.00).Both deep learning and integrated models significantly outperformed the clinical model in training(Z=2.380,P=0.017;Z=2.597,P=0.009)and test sets(Z=2.034,P=0.042;Z=2.577,P=0.010).The integrated model demonstrated excellent calibration and predictive performance.Conclusion The integrated model combining deep learning features from contrast-enhanced lung ultrasonography with clinical characteristics effectively predicts epidermal growth factor receptor mutation status in peripheral non-small cell lung cancer.

Objective:To evaluate the efficacy and safety of 532-nm picosecond laser in the treatment of early-stage facial seborrheic keratosis.Methods:A total of 95 patients with early-stage facial seborrheic keratosis were prospectively enrolled from the Department of Dermatology, General Hospital of Ningxia Medical University between December 2020 and September 2022. All the patients received a session of 532-nm picosecond laser treatment, and were followed up for 6 months. A 4-point scale was used to evaluate the overall improvement of skin lesions for assessing the clinical efficacy. A VISIA skin detector was used to quantitatively determine the characteristic counts, absolute scores, and percentiles of brown spots before and after treatment, and the paired sample t-test was used to compare the quantitative indicators of brown spots before and after treatment. The patients′ pain grades were evaluated, and adverse reactions were recorded. Results:All the 95 patients with early-stage facial seborrheic keratosis received a session of 532-nm picosecond laser treatment, and completed a 6-month follow-up. All the patients achieved over 25% regression of skin lesions in the treatment area, of whom 10 received mild improvement, 17 received favorable improvement, and 68 received marked improvement, with the response rate being 89.47% (85/95). The examination with the VISIA skin detector showed that the characteristic counts (195.19 ± 51.06) and absolute scores (28.80 ± 6.20 points) of brown spots significantly decreased, while the percentiles of brown spots (38.48% ± 10.80%) significantly increased at 6 months after treatment compared with the corresponding baseline indicators (211.48 ± 50.94, 35.16 ± 6.84 points, 30.61% ± 10.27%, t = 12.73, 16.90, -15.73, respectively, all P < 0.001). All the patients experienced varying degrees of pain during the treatment, with the pain scores being 2 - 6 (3.64 ± 1.67) points, but all of them could tolerate the pain and completed the treatment. Temporary postinflammatory hyperpigmentation and hypopigmentation occurred in 9 (9.47%) and 4 (4.21%) patients respectively, and the skin color restored to normal during the 6-month follow-up. Conclusion:The 532-nm picosecond laser was safe and effective for the treatment of early-stage facial seborrheic keratosis.

Objective To summarize experience of anti-cancer drug management for clinical trials,and to explore a more efficient and standardized management model of anti-cancer drugs used in clinical trials.Methods Based on our current work in central pharmacy,the particularity and complexity of anti-cancer drug management for clinical trials were analyzed.In the meantime,we identified high-risk parts in the drug management process.Based on those risks,feasible measures were taken and presented in detail.Results Management of anti-cancer drugs used in clinical trials has its characteristics,such as long cycle,low error-tolerant rate,closed-loop model,etc.Recognizing these representative high-risk parts during the trials and making responses,including standardization of drug management records and disposition of drugs and packaging returned by subjects,should be achieved as soon as possible.Conclusion Establishing and observing strict rules and regulations,improving the hardware and software performance of the central pharmacy as well as implementing risk-based drug management is beneficial to conduct clinical trials normatively.

Objective To observe the value of shear wave viscoelastography(SWV)for differentiating lung peripheral inflammatory masses and malignant tumors.Methods Conventional gray-scale ultrasound and SWV were prospectively performed in 70 patients with lung peripheral inflammatory mass or malignant tumor.The patients were divided into malignant group(n=42)and inflammatory group(n=28)according to pathological results.Clinical and ultrasonic data,including the maximum diameter of lesions,the mean Young's modulus(Emean),mean viscosity(Vmean),and mean dispersion slope(Dmean)were compared between groups.Receiver operating characteristic curves of ultrasonic parameters being significantly different between groups were drawn,and area under the curves(AUCs)were calculated to evaluate the efficacy of each parameter for differentiating lung peripheral inflammatory mass or malignant tumor.Results In malignant group,the maximum diameter and Emean of lesions were both higher,while Vmean and Dmean of lesions were both lower than those in inflammatory group(all P＜0.05).Vmean and Dmean of lesions had moderately/good efficacy for differentiating lung peripheral inflammatory mass or malignant tumor(AUC=0.843,0.866),both better than that of conventional ultrasound and Emean(AUC=0.673,0.685)(all P＜0.05).The combination of Emean,Vmean and Dmean had good efficacy for differentiating lung peripheral inflammatory masses and malignant tumors,with AUC of 0.874.Conclusion The viscous parameters of SWV could effectively differentiating lung peripheral inflammatory masses and malignant tumors.

Objective:To assess the clinical efficacy and safety of image-guided γ-ray stereotactic body radiation therapy(IG γ-SBRT)in treating advanced pancreatic cancer.Methods:A total of fifty-six patients with advanced pancreatic cancer admitted to Senior Department of Oncology Medicine of the Fifth Medical Center of Chinese PLA General Hospital(Department of Oncology of the Sixth Medical Center)from February 2017 to September 2020 were selected.All patients were treated with IG γ-SBRT,and the 50%-60%of isodose curve covered the planned target volume(PTV).The peripheral dose of each time was 3.0-4.5 Gy,and there were 10-11 times of treatment.The therapeutic effect was observed and was evaluated by follow-up.The visual analog scale(VAS)score was adopted to assess the situation of the pain of patients before and 3 months after treatment,and the adverse reaction of them.Results:In the 56 patients,52 cases occurred epigastric pain with VAS ranging from 3 to 10 points,among which 32 patients accompanied by symptoms such as lower back pain and abdominal distension.After 3 months of treatment,the results of reexamination and follow-up indicated that there were 48 patients whose VAS scores decreased 3 scores and above 3 scores on the basis of original scores,and the efficiency of treating pain was 92.3%.In addition,the VAS scores of 3 patients decreased 1-2 scores on the basis of original scores,which ratio was 5.85%of the total number of people.All 56 patients were reexamined at the 3rd month after treatment,and 13 cases of them obtained complete response(CR),and 37 cases obtained partial response(PR),and 1 case obtained progressive disease(PD),and 5 cases obtained stable disease(SD),and the objectively response rate(ORR)was 89.3%,and the locally control rate was 98.2%.In addition,median progression-free survival(PFS)was 6.5 months,and 1-year survival rate was 62.5%(35/56),and 2-year survival rate was 23.2%(13/56).The adverse reactions of 56 patients were the adverse reactions of digestive system and blood system,among which 47 patients occurred upper digestive tract reaction,and the incidence of adverse reactions was 83.9%(47/56).A total of 43 patients occurred myelosuppression,and the incidence of myelosuppression was 76.8%(43/56).Conclusion:IG γ-SBRT can effectively relieve the symptoms of metastatic pancreatic cancer,and improve the effectiveness of treatment,the local control rate and survival rate.The tolerance of adverse reaction of that is favorable,and the safety of that is higher.

A 44-year-old female patient was treated with norethisterone 5 mg once every 8 hours due to atypical hyperplasia of endometrium. One month later, the patient developed asthma with cyanosis, and sudden cardiac arrest later. According to the results of electrocardiogram and echocardiogram examination, acute pulmonary embolism with cardiac arrest was diagnosed. Cardiac resuscitation was immediately implemented, and thrombolysis and anticoagulation therapies were performed, accompanied by veno-arterial extracorporeal membrane oxygenation (VA-ECMO) for life support. After 5 minutes of thrombolytic therapy, the patient′s heart beat and blood pressure gradually recovered. The results of pulmonary artery CT angiography supported the diagnosis of acute pulmonary embolism and effectiveness of thrombolysis. After 31 hours of thrombolytic therapy, the patient has stabilized vital signs and VA-ECMO was removed. After 47 hours of thrombolytic therapy, the patient′s consciousness fully recovered, the tracheal tube was removed, and anticoagulant therapy was continued. After 11 days of thrombolytic therapy, the echocardiography was re-performed, showing normal pulmonary artery pressure, and the exercise tolerance was checked to be good. At 1 month of follow-up, the cardiac function and structure were normal on echocardiography, no thrombus was found on lower limb vascular ultrasound.

A 44-year-old female patient was treated with norethisterone 5 mg once every 8 hours due to atypical hyperplasia of endometrium. One month later, the patient developed asthma with cyanosis, and sudden cardiac arrest later. According to the results of electrocardiogram and echocardiogram examination, acute pulmonary embolism with cardiac arrest was diagnosed. Cardiac resuscitation was immediately implemented, and thrombolysis and anticoagulation therapies were performed, accompanied by veno-arterial extracorporeal membrane oxygenation (VA-ECMO) for life support. After 5 minutes of thrombolytic therapy, the patient′s heart beat and blood pressure gradually recovered. The results of pulmonary artery CT angiography supported the diagnosis of acute pulmonary embolism and effectiveness of thrombolysis. After 31 hours of thrombolytic therapy, the patient has stabilized vital signs and VA-ECMO was removed. After 47 hours of thrombolytic therapy, the patient′s consciousness fully recovered, the tracheal tube was removed, and anticoagulant therapy was continued. After 11 days of thrombolytic therapy, the echocardiography was re-performed, showing normal pulmonary artery pressure, and the exercise tolerance was checked to be good. At 1 month of follow-up, the cardiac function and structure were normal on echocardiography, no thrombus was found on lower limb vascular ultrasound.

Objective:To measure the morphological parameters of the fetal vertebral centrum ossification centers (COC) in the second-third trimester using MRI susceptibility weighted imaging (SWI), and to explore the growth and development trajectory of the vertebrae.Methods:Fetus in the second-third trimester with normal vertebrae development were prospectively and continuously included in Shandong Provincial Hospital Affiliated to Shandong First Medical University from December 2015 to December 2021, and the SWI scanning of fetal spine was performed. The following morphometric parameters of the C4, T6, L3, S1 vertebrae COC were measured, including sagittal diameter, transverse diameter, height, cross-sectional area and volume. The linear and nonlinear regression analysis was used to derive the best-fit curve for each parameters and gestational age.Results:A total of 112 fetuses were recruited with gestatonal age 21-39 (29.4±3.9) weeks, including 30 cases of C4, 58 cases of T6, 92 cases of L3, 62 cases of S1. Fetal spine in utero with global curvature was kyphosis, presenting two primary curves (thoracic and sacral kyphosis). The morphological parameters sagittal diameter, transverse diameter, height, cross-sectional area and volume of C4 followed the quadratic polynomial rule during 25 to 38 weeks (R 2=0.938, 0.943, 0.952, 0.957, 0.982). During 21 to 38 weeks, the sagittal diameter, transverse diameter and height of the T6 followed the exponential growth pattern (R 2=0.915, 0.923, 0.849) and the growth of the area and volume followed the quadratic polynomial growth pattern (R 2=0.943, 0.961). The L3 followed the quadratic polynomial rule during 21 to 39 weeks (R 2=0.910, 0.916, 0.914, 0.942, 0.948) The sagittal diameter, transverse diameter and height of the S1 followed the linear growth pattern (R 2=0.905, 0.911, 0.922) and the area and volume followed the quadratic polynomial growth pattern (R 2=0.930, 0.964) during 23 to 39 weeks. Conclusions:The growth and development of C4, T6, L3 and S1 COC of fetus in the second-third trimester has a good correlation with gestational age. The growth of fetal vertebral COC in the early stage is slow, but with the growth of gestational age, the growth rate of vertebral bodies accelerates.

Objective    To evaluate the effectiveness and safety of proximal aortic repair (PAR) versus total arch replacement (TAR) for treatment of acute type A aortic dissection (ATAAD). Methods     An electronic search was conducted for clinical controlled studies on PAR versus TAR for patients with ATAAD published in Medline via PubMed, EMbase, The Cochrane Library, Web of Science, Wanfang Database and CNKI since their inception up to April 30, 2022. The quality of each study included was assessed by 2 evaluators and the necessary data were extracted. STATA 16 software was used to perform statistical analysis of the available data. Results    A total of 28 cohort studies involving 7 923 patients with ATAAD were included in this meta-analysis, of whom 5 710 patients received PAR and 2 213 patients underwent TAR, and 96.43% of the studies (27/28) were rated as high quality. The meta-analysis results showed that: (1) patients who underwent PAR had lower incidences of 30 d mortality [RR=0.62, 95%CI (0.50, 0.77), P<0.001], in-hospital mortality [RR=0.64, 95%CI (0.54, 0.77), P<0.001], and neurologic deficiency after surgery [RR=0.84, 95%CI (0.72, 0.98), P=0.032] than those who received TAR; (2) the cardiopulmonary bypass time [WMD=–52.07, 95%CI (–74.19, –29.94), P<0.001], circulatory arrest time [WMD=–10.14, 95%CI (–15.02, –5.26), P<0.001], and operation time [WMD=–101.68, 95%CI (–178.63, –24.73), P<0.001] were significantly shorter in PAR than those in TAR; (3) there was no statistical difference in mortality after discharge, rate of over 5-year survival, renal failure after surgery and re-intervention, volume of red blood cells transfusion and fresh-frozen plasma transfusion, or hospital stay between two surgical procedures. Conclusion     Compared with TAR, PAR has a shorter operation time and lower early and in-hospital mortality, but there is no difference in long-term outcomes or complications between the two procedures for patients with ATAAD.