Objective:To explore the influencing factors of absorption effect postoperative ablation area after microwave ablation(MWA)for papillary thyroid microcarcinoma(PTMC).Methods:The clinical and ultrasound data of 101 patients with single PTMC who underwent microwave ablation in Beijing Friendship Hospital between April 2019 and July 2023 were collected.According to the endpoint event of whether the ablation area disappeared one year after MWA,they were divided into disappearance group(52 cases)and non-disappearance group(49 cases).Univariate and multivariate logistic regression were used to analyze the factors of affecting the absorption effect of ablation area,and a regression model was constructed.Receiver operating characteristic(ROC)curve was drawn to test the predictive efficacy of the model.Results:There were significant differences in the age,coarse calcification in the nodule,ablation time,Hashimoto's thyroiditis between two groups(x2=4.708,12.180,19.497,8.457,P<0.05),respectively.There were also significant differences in maximum diameter of nodule,nodule volume,ablation energy between two groups(Z=-3.929,-3.969,-3.677,P<0.05).Multivariate logistic regression analysis showed that age≥50 years old,coarse calcification in the nodule,ablation time≥50s,and Hashimoto's thyroiditis were independent influencing factors for the non-disappearance of ablation area one year after MWA for PTMC(OR=4.464,3.733,10.063,4.173,P<0.05).The ROC curve analysis showed that the area under curve(AUC)of the regression model in predicting non-disappearance of ablation area after MWA for PTMC was 0.853(95%CI:0.777-0.929),and the diagnostic sensitivity and specificity of that were respectively 75.5%and 82.7%.Conclusion:The logistic regression model,that is constructed on the basis of clinical information,preoperative ultrasound features,and thermal ablation parameters,has high clinical application value in predicting the postoperative absorption of the ablation area in patients who undergo MWA for PTMC.

Objective:To explore the assessment value of ultrasound scoring system combined with shear wave elastography(SWE)on curative effect of IgG4-related submandibular and lacrimal gland inflammation.Methods:This study was a prospective cohort study.A total of 103 patients with IgG4-related submandibular and/or lacrimal gland inflammation who admitted to the Department of Rheumatology and Immunology of Beijing Friendship Hospital,Capital Medical University from September 2022 to December 2024 were consecutively included.They were divided into an effective group(45 cases)and a non-effective group(58 cases)based on the curative effect.All patients were assessed by conventional ultrasound and SWE before and after treatment.Logistic regression analysis was used to determine the independent influencing factors of assessing the curative effect,and then,a receiver operating characteristic(ROC)curve and nomograms were drawn.Results:There were no statistically significant differences in gender and age between the effective group and the non-effective group(P>0.05).The difference between the submandibular and lacrimal gland score,change rate of score,difference of mean Young's modulus(Emean),Emean change rate,difference of maximum value of Young's modulus(Emax),and Emax change rate in the effective group were all higher than those in the non-effective group,and the differences were statistically significant(Z=-7.916,-7.680,-6.767,-6.722,-6.360,-5.957,P<0.05),respectively.The difference between the submandibular and lacrimal gland score(OR=2.90,P<0.001)and the Emax difference(OR=1.18,P<0.05)had diagnostic value for assessing the curative effectiveness.The area under curve(AUC)value,sensitivity,specificity and accuracy of the difference between submandibular and lacrimal gland score were respectively 0.945,88.9%,94.8%and 87.4%in assessing the curative effectiveness.The above indicators of Emax difference were respectively 0.866,86.7%,70.7%and 77.7%in assessing the curative effectiveness.The above indicators of the combination of them were respectively 0.976,93.3%,94.8%and 94.2%.Conclusion:The combination of the conventional ultrasound scoring system and SWE has higher diagnostic value in assessing the curative effect of IgG4-related submandibular and lacrimal gland inflammation.The combined application can significantly improve the accuracy and provide reliable imaging reference for clinical practice.

Objective:To propose a processing method of medical image segmentation based on U-Net network with residual connection under single source domain environment,so as to improve the limited diversity of data samples of medical image in the single-source domain environment.Methods:The medical image data under the single-source domain environment were amplified through image transformation,contrast adjustment,and noise addition.The U-Net network was used as the basic structure,and multiple residual connection modules were introduced to achieve reuse of feature.And then,the features at shallow layer were directly transmitted to deep layer,and features at different levels were utilized for segmentation.The input features were added to the features that were processed by partial network layers,thus better learned the features in the data,and constructed medical image segmentation model based on the U-Net network with residual connection.The segmentation model was trained by using the gradient descent method,and the combination of that and the Generalized Dice Loss(GDL)function.Results:The processing method of medical image segmentation based on the U-Net network can effectively achieve segmentation of medical image.Even under low signal-to-noise ratio conditions and facing to different types of segmentation tasks of medical image,the DSC value was greater than 0.90.Conclusion:The processing method of medical image segmentation based on the U-Net network in this study can effectively enhance recognition ability for the features of complex lesions,and increase the segmentation precise of medical images,and improve the accuracy of clinical diagnosis and the effectiveness of treatment.

Objective:To explore the clinical application value of a combined model based on the radiomics features of magnetic resonance imaging(MRI)and MRI signs in predicting recurrence after radical resection for hepatocellular carcinoma(HCC).Methods:A retrospective analysis was conducted on the imaging data of 100 patients with radical resection for HCC who admitted to Zibo 148 Hospital from May 2016 to May 2020.All patients underwent abdominal enhanced MRI examination before surgery,and they were followed up for at least 2 years after the surgery.They were randomly divided into training group(70 cases)and verification group(30 cases)as a ratio of 7:3.According to the postoperative follow-up results,the training group existed 12 cases of recurrence and 58 cases without recurrence,and the verification group existed 5 cases of recurrence and 25 cases without recurrence.The 3D-slicer software was used to extract radiomics features of preoperative MRI images of each HCC patient.The intra-group correlation coefficient(ICC)of the extracted imaging features of the observers was calculated.The maximum related minimum redundancy(mRMR)algorithm and LASSO regression were selected to analyze the established radiomics labels after dimensionality reduction and screening.Univariate and multivariate logistic regression analysis were used to screen the independent risk factors of predicting recurrence in MRI signs,and they were used respectively to construct radiomics models with the radiomics labels of plain scan,arterial phase,portal phase and hepatobiliary phase.The receiver operating characteristic(ROC)curve was used to assess the diagnostic efficacy of each radiomics model in predicting recurrence.Results:The ICC range of two physicians in selecting radiomics features from the MRI images of all patients were between 0.903 and 0.957,which consistency was favorable(ICC≥0.9).Compared with other predictive models,the highest area under curve(AUC)values of ROC curve of the radiomics model of plain scan of training group[0.951(95%CI:0.901-1.000)]and verification group[0.968(95%CI:0.917-1.000)]were respectively 0.951 and 0.968 in predicting recurrence after radical resection for liver cancer.Conclusion:The combined model that is constructed on the basis of MRI radiomics features has favorable predictive value for the recurrence of patients after radical resection for HCC.Among of them,the radiomics model of plain scan has a certain guiding role in the clinical implementation of personalized treatment plans under the absence of enhancement,and in underdeveloped areas.

Objective:To construct an evaluation system for the operation quality of the equipment of the urological department based on the pressure-state-response(PSR)model,so as to explore it's application effect in the evaluation for the operation quality of the equipment of urological department.Methods:Based on the PSR model,the analytic hierarchy process was used to determine the weights of index,and the fuzzy evaluation method was adopted to evaluate the management efficiency for equipment.A total of 160 devices of clinical use in the Urological Department of The First Affiliated Hospital of Xi'an Jiaotong University from January 2022 to January 2024 were selected.According to different management modes,the random number table was adopted to equally distribute these devices into conventional management mode(80 devices)and management mode with evaluation system(model evaluation)for operation quality of the equipment of the urological department(80 devices).A self-made questionnaire was used to investigate the satisfaction of the usage managers in the urological department and operation room,department of medical equipment,and department of managing infection for the clinical services of the two kinds of management modes.The infection situations,management quality of equipment operation,and the score of operation quality in using equipment between two kinds of management modes were compared.Results:The average repair rate of equipment failure,risk rate of infection,inefficiency rate of cleaning,and problem rate of quality inspection in the management mode with model evaluation were respectively(1.58±0.69)%,(1.98±0.69)%,(1.10±0.78)%and(1.01±0.70)%,all of which were lower than those in the conventional management mode,and the differences of them were statistically significant(t=7.879,6.663,7.863,14.601,P<0.05).In the 120 patients who adopted the management mode with model evaluation,the infection rates of using equipment in laparoscopic minimally invasive surgery,endoscopic surgery for stone,resectoscopic surgery and flexible ureteroscope were respectively 2.50%,3.33%,4.17%and 3.33%,all of which were lower than those in the conventional management mode,and the differences between the two kinds of modes were statistically significant(x2=6.696,6.916,5.154,7.101,P<0.05).The scores of the standardization of using equipment,effectiveness of cleaning and disinfection,recognition of emergency management,and qualification of controlling infection in the management mode with model evaluation were significantly higher than those in the conventional management mode,and the differences were statistically significant(t=22.198,11.806,9.385,18.071,P<0.05).The satisfaction scores of the managers involved in using equipment in the operation room of urology,department of medical equipment and department of managing infection for the management mode with model evaluation were all higher than those of the conventional management mode,and the differences were statistically significant(t=14.426,14.916,14.707,P<0.05).Conclusion:The quality evaluation system of equipment operation of the urological department based on the PSR model can reduce the failure rate of equipment,and improve the usage efficiency of equipment,and ensure the medical safety of patients.

Objective:To formulate refined management strategies to improve the operation quality and protective effect of medical X-ray diagnosis equipment based on the risk analysis of the correlation of medical X-ray diagnostic equipment.Methods:The used 41 medical X-ray diagnosis equipment in Fuwai Hospital,Chinese Academy of Medical Sciences from January 2022 to December 2023 were selected.According to different management modes for equipment,they were managed respectively by the conventional management mode(20 units)and the management mode with risk analysis of the correlation(21 units).The risk grades of correlation of management mode with risk analysis of the correlation were classified on the basis of the probability of risk and the degree of harm in medical X-ray diagnosis equipment.The protection management of equipment was conducted from three aspects included the location of equipment,the staffs and subjects.A self-made questionnaire was used to investigate the satisfactions of engineers of using management for equipment,operators,and staffs of operating and maintaining equipment for the two kinds of management modes.The protection quality,failure rate of equipment,and qualification rate of protection of medical X-ray diagnosis equipment under different management modes were compared.Results:The quality scores of operation safety,regular inspection,maintenance and repair,and shielding protection for radiation of medical X-ray diagnosis equipment that adopted the management mode with risk analysis of the correlation were respectively(92.14±3.36),(91.47±2.41),(92.54±3.32)and(91.69±3.57)points,all of which were higher than those of the conventional management mode,and the differences of them were statistically significant(t=16.396,17.368,19.688,14.401,P<0.05).The failure rate of the 21 medical X-ray diagnosis equipment that adopted the management mode with risk analysis of correlation was 0,which was lower than 20.00%of the conventional management mode.The qualified rate of protection was 95.23%,which was higher than 70.00%of the conventional management mode,and the differences of them were statistically significant(x2=4.654,4.608,P<0.05).The satisfaction scores of engineers of using equipment,operators and staffs of operating and maintaining equipment for the protective effect of adopting the management mode with risk analysis of correlation were respectively(94.69±4.02),(93.21±4.36)and(92.54±3.47)points,all of which were higher than those of the conventional management mode,and the differences were statistically significant(t=16.902,11.291,12.020,P<0.05).Conclusion:The process-based protection management strategy on the basis of risk analysis of correlation for medical X-ray diagnosis equipment can prevent risks of medical X-ray diagnostic equipment,and improve the operation quality of the equipment,and reduce the operation risks of the equipment,and maximize the enhancement for management quality of medical X-ray diagnosis equipment.

Objective:To explore clinical validation standard for intelligent ventilation mode of ventilator and promote ventilator's clinical application.Methods:By real-time quantification of physiological parameters related to patient's ventilation and oxygenation,the change of respiratory function was analyzed,and the settings of ventilator's parameters were adjusted synchronously by using feedback signals to realize personalized support of ventilation.Combining with artificial intelligence(AI)technique,the clinical validation standard for intelligent ventilation mode was investigated from three aspects:requirements of clinical application and function of intelligent ventilation mode of ventilator,validation for platform of simulation experiment,and early clinical evaluation and interventional trials.Results:The clinical validation standards for intelligent ventilation mode of ventilator should meet the requirements of clinical application and function,and should complete preclinical evaluation of intelligent ventilation mode of ventilator,and assess safety and usability of that by the platform of simulation trials,and should conduct early clinical evaluations and interventional clinical trials so as to further assess safety and effectiveness of that before it was used formally in clinical application.Conclusion:The clinical validation standard of intelligent ventilation mode of ventilator can form standard validation process for intelligent ventilation mode,and promote the construction of standard validation platform,and facilitate clinical application and iterative optimization of intelligent ventilation mode,and improve medical quality.

Stroke is one of the common cerebrovascular diseases,which can be classified into acute(0-24 h),subacute(24 h-2 weeks)and chronic stage(>2 weeks).High-resolution T1-weighted imaging(T1WI)is one kind of magnetic resonance imaging(MRI)technique,which is main imaging mode of assessing the change of cerebral structure after stroke at chronic stage,and it can accurately judge the location and size of lesion.The precise segmentation for lesion is we accurately analyze dataset of neuroimaging in stroke with large scale,and is the key of predicting rehabilitation outcomes.The automatic segmentation algorithm is one kind of technique that can automatically segment data into many independent regions or object by specific regulation or model,which does not need manual intervention.Compared with manual segmentation,it has repeatable and scalable advantages,which does not need manual setting parameter.With the development of artificial intelligence technology,its application is gradually widespread in the field of medical imaging analysis.Adopting automatic segmentation algorithm to conduct reliable and repeatable segmentation for the lesions in T1WI,which can effectively assist clinical diagnosis and rehabilitation treatment for stroke.This review summarized the advance research of automatic segmentation algorithm based on T1WI for the lesion of chronic stroke from two aspects included conventional machine learning and deep learning,and the optimization approach of three kinds of algorithm structures,which can provide reference and inspiration for researching small lesion with higher difficulty in the field of automatic segmentation.

Objective:To research access management method of evaluating medical consumables based on Kano performance classification model,so as to improve the quality of access management of medical consumables and clinical service level.Methods:The Better-Worse coefficient analysis method was adopted to analyze quantitative data,and a comprehensive performance evaluation was conducted on the basis of Kano model.And then,a classification management mode included access allocation of priority,evaluation dimensions of priority,standardization of access process and strengthening of dynamic supervision were formulated.A total of 120 kinds of medical consumables in clinical use of Jiangsu Province Hospital from January 2021 to December 2023 were selected.The expert performance evaluation model(expert performance evaluation)was adopted to conduct access management for medical consumables that were used during January 2021 and June 2022,and the Kano performance evaluation model(Kano performance evaluation)was adopted to conduct that for medical consumables that were used during July 2022 and December 2023.The performances of clinical service and operation quality of the two evaluation modes for the access of medical consumables were compared.Results:The Better coefficients of the consumables in outpatient department,emergency department and inpatient department,and consumables that were used in medical technique that adopted Kano performance evaluation mode were respectively 0.25±0.06,0.32±0.07,0.28±0.06 and 0.27±0.05,which were higher than those of that adopted expert performance evaluation mode,and the difference were statistically significant(t=4.791,4.241,5.667,5.996,P<0.05),respectively.The Worse coefficients of Kano performance evaluation mode were respectively 0.08±0.03,0.10±0.01,0.09±0.05 and 0.09±0.04,which were significantly lower than those of expert performance evaluation mode,and the differences of them were significant(t=3.431,3.049,3.324,2.979,P<0.05).The Better coefficients of operation quality performance of warehouse management,operating cost and supply of outside hospital of using Kano performance evaluation mode were respectively 0.44±0.08,0.40±0.09 and 0.22±0.06,which were higher than that of expert performance evaluation mode,and the differences were significant(t=4.052,3.563,4.792,P<0.05).The Worse coefficients of them of using Kano performance evaluation mode were respectively 0.18±0.05,0.16±0.06 and 0.10±0.04,which were lower than those of expert performance evaluation mode,and the differences were significant(t=3.347,3.438,4.092,P<0.05).Conclusion:The access management of evaluating medical consumables on the basis of Kano performance classification mode can improve the comprehensiveness and scientific nature of assessing the access of medical consumables,and enhance the level of clinical service of medical consumables,and improve the operation quality of supply management for medical consumables.

Objective:To construct a management model of data mining for medical imaging equipment,so as to improve the quality of managing equipment.Methods:A management model of mining data was constructed to manage medical imaging equipment.A total of twenty imaging equipment that were using at Hainan Hospital of the General Hospital of the People's Liberation Army of China from April 2022 to March 2024 were selected.According to different management methods,the conventional management was adopted to manage them during April 2022 to March 2023,and the management model of mining data(model management)was adopted to manage them during April 2023 to March 2024.A self-developed questionnaire was used to conduct a satisfaction survey for imaging physicians,staffs of operating and maintaining equipment,and technicians who using and managing equipment,and patients who received diagnosis and treatment by using equipment.The failure rate and the imaging effect of equipment,the satisfaction scores of the relative staffs who used equipment,and the growth amplitude of operational benefits of equipment between two management methods were compared.Results:A total of 20 failures occurred in imaging equipment that adopted model management.In them,the failure rates of the self-equipment,improper operation and insufficient professional level were respectively 15%,5%and 5%,all of which were lower than those of the conventional management method.The predicted failure rate of model management was 75%,which was higher than that of the conventional management method,and the differences of the above indicators between two methods were statistically significant(x2=6.547,4.392,5.124,6.701,P<0.05).The scores of image clarity,qualification rate,excellent rate,qualification rate of body position,and the total score of imaging effect of adopting model management method were respectively(22.36±2.01),(23.21±1.54),(22.65±1.87),(23.21±1.52)and(91.43±6.77)points,all of which were higher than those of the conventional management method,and the differences were statistically significant(t=10.662,12.727,15.324,16.333,13.742,P<0.05).The satisfaction scores of imaging physicians,staffs of operation and maintenance,technicians and patients who uses management for adopting the model management method were all higher than those of the conventional management method,and the differences were statistically significant(t=13.586,14.249,17.021,11.006,P<0.05).The average values of growth amplitude of cost and benefit of equipment operation of adopting model management method were higher than those of the conventional management method,and the average value of the growth amplitude of the cost of the troubleshooting of model management method was lower than that of the conventional management method,and the differences of them were statistically significant(t=15.057,19.310,18.336,P<0.05).Conclusion:The application of the management model of data mining for medical imaging equipment can provide warning of equipment failures in advance,and reduce the failure rate of equipment,and improve the quality of management and operation of equipment,and enhance the service level of equipment.