This paper presents a novelmulticlass systemdesigned to detect pleural effusion and pulmonary edema on chest Xray images,addressing the critical need for early detection in healthcare.A new comprehensive dataset was f...This paper presents a novelmulticlass systemdesigned to detect pleural effusion and pulmonary edema on chest Xray images,addressing the critical need for early detection in healthcare.A new comprehensive dataset was formed by combining 28,309 samples from the ChestX-ray14,PadChest,and CheXpert databases,with 10,287,6022,and 12,000 samples representing Pleural Effusion,Pulmonary Edema,and Normal cases,respectively.Consequently,the preprocessing step involves applying the Contrast Limited Adaptive Histogram Equalization(CLAHE)method to boost the local contrast of the X-ray samples,then resizing the images to 380×380 dimensions,followed by using the data augmentation technique.The classification task employs a deep learning model based on the EfficientNet-V1-B4 architecture and is trained using the AdamW optimizer.The proposed multiclass system achieved an accuracy(ACC)of 98.3%,recall of 98.3%,precision of 98.7%,and F1-score of 98.7%.Moreover,the robustness of the model was revealed by the Receiver Operating Characteristic(ROC)analysis,which demonstrated an Area Under the Curve(AUC)of 1.00 for edema and normal cases and 0.99 for effusion.The experimental results demonstrate the superiority of the proposedmulti-class system,which has the potential to assist clinicians in timely and accurate diagnosis,leading to improved patient outcomes.Notably,ablation-CAM visualization at the last convolutional layer portrayed further enhanced diagnostic capabilities with heat maps on X-ray images,which will aid clinicians in interpreting and localizing abnormalities more effectively.展开更多
Introduction: The diagnosis of pneumonia is usually made based on clinical manifestations and chest X-ray. The use of ultrasound in detecting pulmonary diseases in general, and especially consolidation syndrome has be...Introduction: The diagnosis of pneumonia is usually made based on clinical manifestations and chest X-ray. The use of ultrasound in detecting pulmonary diseases in general, and especially consolidation syndrome has been demonstrated. The objective of this study was to determine the accuracy of thoracic ultrasound compared to chest X-ray in the diagnosis of infectious pneumonia in children. Methods: Children between 0 to 15 years were included in our study. The lung ultrasound results obtained were compared with those of the chest X-ray used as the reference. Our data were introduced into the EpiInfo 3.5.4 software and analyzed with the EpiInfo 3.5.4 and IBMSPSS Statistics version 20.0 softwares. Microsoft Office Excel 2016 was used to produce Charts. Continuous quantitative variables were presented. Cohen’s Kappa concordance test was applied with confidence interval of 95%. Results: 52 children were enrolled in the study. In imaging, the dominant sign was consolidation syndrome (75.0%) of cases by chest radiography, and in 78.8% of cases by lung ultrasound (p Conclusion: Our study demonstrated that lung echography is a non-ionizing and reliable tool in the diagnosis of childhood’s pneumonia.展开更多
Tuberculosis(TB)is a severe infection that mostly affects the lungs and kills millions of people’s lives every year.Tuberculosis can be diagnosed using chest X-rays(CXR)and data-driven deep learning(DL)approaches.Bec...Tuberculosis(TB)is a severe infection that mostly affects the lungs and kills millions of people’s lives every year.Tuberculosis can be diagnosed using chest X-rays(CXR)and data-driven deep learning(DL)approaches.Because of its better automated feature extraction capability,convolutional neural net-works(CNNs)trained on natural images are particularly effective in image cate-gorization.A combination of 3001 normal and 3001 TB CXR images was gathered for this study from different accessible public datasets.Ten different deep CNNs(Resnet50,Resnet101,Resnet152,InceptionV3,VGG16,VGG19,DenseNet121,DenseNet169,DenseNet201,MobileNet)are trained and tested for identifying TB and normal cases.This study presents a deep CNN approach based on histogram matched CXR images that does not require object segmenta-tion of interest,and this coupled methodology of histogram matching with the CXRs improves the accuracy and detection performance of CNN models for TB detection.Furthermore,this research contains two separate experiments that used CXR images with and without histogram matching to classify TB and non-TB CXRs using deep CNNs.It was able to accurately detect TB from CXR images using pre-processing,data augmentation,and deep CNN models.Without histogram matching the best accuracy,sensitivity,specificity,precision and F1-score in the detection of TB using CXR images among ten models are 99.25%,99.48%,99.52%,99.48%and 99.22%respectively.With histogram matching the best accuracy,sensitivity,specificity,precision and F1-score are 99.58%,99.82%,99.67%,99.65%and 99.56%respectively.The proposed meth-odology,which has cutting-edge performance,will be useful in computer-assisted TB diagnosis and aids in minimizing irregularities in TB detection in developing countries.展开更多
BACKGROUND:The appropriate sequence of different imagings and indications of thoracic computed tomography(TCT)in evaluating chest trauma have not yet been clarified at present.The current study was undertaken to deter...BACKGROUND:The appropriate sequence of different imagings and indications of thoracic computed tomography(TCT)in evaluating chest trauma have not yet been clarified at present.The current study was undertaken to determine the value of chest X-ray(CXR)in detecting chest injuries in patients with blunt trauma.METHODS:A total of 447 patients with blunt thoracic trauma who had been admitted to the emergency department(ED)in the period of 2009–2013 were retrospectively reviewed.The patients met inclusion criteria(age>8 years,blunt injury to the chest,hemodynamically stable,and neurologically intact)and underwent both TCT and upright CXR in the ED.Radiological imagings were re-interpreted after they were collected from the hospital database by two skilled radiologists.RESULTS:Of the 447 patients,309(69.1%)were male.The mean age of the 447 patients was 39.5±19.2(range 9 and 87 years).158(35.3%)patients were injured in motor vehicle accidents(MVA).CXR showed the highest sensitivity in detecting clavicle fractures[95%CI 78.3(63.6–89)]but the lowest in pneuomediastinum[95%CI 11.8(1.5–36.4)].The specificity of CXR was close to 100%in detecting a wide array of entities.CONCLUSION:CXR remains to be the first choice in hemodynamically unstable patients with blunt chest trauma.Moreover,stable patients with normal CXR are candidates who should undergo TCT if significant injury has not been ruled out.展开更多
Objective:To investigate the quantitative assessment efficacy of chest CT combined with serum Vanin-1 and SPP1 in determining the progression stage of chronic obstructive pulmonary disease(COPD).Methods:A total of 100...Objective:To investigate the quantitative assessment efficacy of chest CT combined with serum Vanin-1 and SPP1 in determining the progression stage of chronic obstructive pulmonary disease(COPD).Methods:A total of 100 COPD subjects from our hospital from January 2020 to December 2023 were included and randomly divided into a healthy control group and an experimental group(50 cases each).The healthy control group underwent slow vital capacity measurement using a spirometer,while the experimental group underwent high-resolution thin-slice CT scans and serum Vanin-1 and SPP1 concentration measurements.Pulmonary function parameters,symptom burden,biomarker concentrations,and imaging characteristics were compared between the two groups.Results:The FEV1/FVC ratio in the experimental group(58.3±7.2)was lower than that in the healthy control group(92.1±4.8);the total CAT score(22.4±3.5)was higher than that in the healthy control group(3.1±1.2);both Vanin-1(18.7±2.3μg/L)and SPP1(25.6±4.1μg/L)levels were higher than those in the healthy control group;LAA%-950(38.7±6.2%)and WA%(68.5±5.3%)were significantly higher than those in the healthy control group(all p<0.001).Conclusion:Chest CT combined with serum Vanin-1 and SPP1 can accurately quantify the pathological progression of COPD,providing a dual basis for clinical staging and individualized intervention.展开更多
This study presents an advanced method for post-mortem person identification using the segmentation of skeletal structures from chest X-ray images.The proposed approach employs the Attention U-Net architecture,enhance...This study presents an advanced method for post-mortem person identification using the segmentation of skeletal structures from chest X-ray images.The proposed approach employs the Attention U-Net architecture,enhanced with gated attention mechanisms,to refine segmentation by emphasizing spatially relevant anatomical features while suppressing irrelevant details.By isolating skeletal structures which remain stable over time compared to soft tissues,this method leverages bones as reliable biometric markers for identity verification.The model integrates custom-designed encoder and decoder blocks with attention gates,achieving high segmentation precision.To evaluate the impact of architectural choices,we conducted an ablation study comparing Attention U-Net with and without attentionmechanisms,alongside an analysis of data augmentation effects.Training and evaluation were performed on a curated chest X-ray dataset,with segmentation performance measured using Dice score,precision,and loss functions,achieving over 98% precision and 94% Dice score.The extracted bone structures were further processed to derive unique biometric patterns,enabling robust and privacy-preserving person identification.Our findings highlight the effectiveness of attentionmechanisms in improving segmentation accuracy and underscore the potential of chest bonebased biometrics in forensic and medical imaging.This work paves the way for integrating artificial intelligence into real-world forensic workflows,offering a non-invasive and reliable solution for post-mortem identification.展开更多
BACKGROUND In pediatric age group patients(<18 years old)treated operatively for distal radius/both bone fractures extending imaging beyond the initial postoperative period-particularly in uncomplicated cases-appea...BACKGROUND In pediatric age group patients(<18 years old)treated operatively for distal radius/both bone fractures extending imaging beyond the initial postoperative period-particularly in uncomplicated cases-appears to provide limited additional benefit.AIM To determine the necessary number of follow-up X-rays to use resources efficiently.METHODS Participants included in this study are pediatric age group patients who were treated operatively for distal radius/both bone fractures and were identified from a prospected collected data from the operating room database between the years 2009 and 2017.The data in the study included patients who had distal radius fractures and underwent fixation surgery(n=88).RESULTS When assessing the difference in the odds of conducting 1 or less X-ray compared to 2 or more X-rays in regard to the type of fixation,the only significant difference is the closed reduction fixation method.Patients who underwent closed reduction method procedure have significantly lower odds of having 2 more X-rays compared to those who didn’t have closed reduction method.Open reduction,internal fixation,and other fixation methods(close reduction and internal fixation,debridement,or epiphysiodesis)have higher odds of having two or more X-rays compared to patients who did not receive these methods;however,these odds are not statistically significant.CONCLUSION The findings of this study reveal notable absence of a statistically significant association between the frequency of postoperative X-rays and the outcome of children with distal radius fractures.展开更多
Objective: This study aims to investigate the drainage effect and clinical outcomes of negative pressure chest drainage in patients after two-port thoracoscopic valve surgery, comparing the differences in postoperativ...Objective: This study aims to investigate the drainage effect and clinical outcomes of negative pressure chest drainage in patients after two-port thoracoscopic valve surgery, comparing the differences in postoperative pain, hospital stay, and other factors between the negative pressure group and the control group. Methods: This study is a prospective controlled trial that selected patients undergoing two-port thoracoscopic valve surgery at a certain hospital from January 2019 to December 2024. Patients were randomly assigned to the control group and the negative pressure group using a random number table method. The control group consisted of 30 patients (20 males, 10 females, mean age 42.03 ± 12.89 years), and the negative pressure group consisted of 35 patients (26 males, 9 females, mean age 41.84 ± 11.83 years). The control group received traditional chest drainage, while the negative pressure group received negative pressure chest drainage. Postoperative pain scores, hospital stay, drainage time, number of tube blockages, and incidences of pneumothorax or subcutaneous emphysema were recorded and statistically analyzed. Results: The negative pressure group had a significantly shorter postoperative drainage time compared to the control group (49.09 ± 11.99 hours vs. 79.10 ± 7.32 hours, P < 0.001). The postoperative pain score was lower in the negative pressure group (4.49 ± 1.27 vs. 7.03 ± 0.85, P < 0.001), and the hospital stay was significantly shorter (9.83 ± 1.69 days vs. 14.73 ± 2.32 days, P < 0.001). The incidence of pneumothorax or subcutaneous emphysema was significantly lower in the negative pressure group than in the control group (14.29% vs. 56.67%, P = 0.0003). Conclusion: The application of negative pressure chest drainage in patients after two-port thoracoscopic valve surgery can effectively reduce postoperative pain, shorten hospital stay, and lower the incidence of tube blockage and pneumothorax, demonstrating good clinical outcomes.展开更多
This study aimed to analyze the early high-resolution CT(HRCT)manifestations and dynamic imaging changes of coronavirus disease 2019(COVID-19)in Qinghai Province.A total of 24 nucleic acid-positive COVID-19 patients a...This study aimed to analyze the early high-resolution CT(HRCT)manifestations and dynamic imaging changes of coronavirus disease 2019(COVID-19)in Qinghai Province.A total of 24 nucleic acid-positive COVID-19 patients admitted to our hospital between January 2020 and November 2021 were included.All patients underwent HRCT examinations,and lesion characteristics—including number,distribution,morphology,and surrounding involvement were analyzed.Among the 24 patients,systemic and respiratory circulatory symptoms were more common than other symptoms(P<0.05).There were no significant differences in the lung lobes,relative positions,quantity,size,and density of lesions across different stages of the disease course(P>0.05).Within the same disease stage,lesions were primarily located in the lower lobes of both lungs,the peripheral lung fields,and a combination of peripheral and central regions,with single and multiple lesions being the most common.Lesion morphology varied significantly across disease stages(P<0.05),including differences between patchy and striped lesions,striped and massive lesions(P<0.05),and patchy and massive lesions(P<0.05).The incidence of striped lesions was higher in the progressive and recovery stages than in the early stage,showing an upward trend.There were no significant differences in pleural thickening,pleural effusion,mediastinal lymph node enlargement,or pericardial effusion across different disease stages(P>0.05).Common HRCT signs observed at all stages included air bronchograms,paving stone patterns,halo signs,subpleural lines,and grid-like patterns.The main patterns of lesion progression were an increase in lesion size(16/24,66.67%),an increase in the number of lesions(17/24,70.83%),changes in lesion density(20/24,80.33%),and localized lesion increase and partial absorption(6/24,25.00%).In conclusion,the HRCT manifestations and evolution of lung lesions in COVID-19 patients are complex and varied,with a progressive increase in striped lesions potentially serving as a characteristic imaging feature of the disease.展开更多
Basic life support for cardiac arrest associates cardiopulmonary resuscitation(CPR)and defibrillation.CPR relies on chest compressions(CC)and ventilation.Current guidelines on CPR recommend a depth of 5-6 cm at a rhyt...Basic life support for cardiac arrest associates cardiopulmonary resuscitation(CPR)and defibrillation.CPR relies on chest compressions(CC)and ventilation.Current guidelines on CPR recommend a depth of 5-6 cm at a rhythm of 100-120 times/min for CC.[1,2]Interruptions of the CC must be as short as possible and are related to ventilation,defibrillation and turnover of the rescuers.Most of the automated external defibrillators(AEDs)require interruptions of the CC to perform rhythm analysis.Among the numerous marketed models of AEDs,some provide real-time feedback about the quality of the CC.展开更多
Objective:To explore a simple method for improving the diagnostic accuracy of malignant lung nodules based on imaging features of lung nodules.Methods:A retrospective analysis was conducted on the imaging data of 114 ...Objective:To explore a simple method for improving the diagnostic accuracy of malignant lung nodules based on imaging features of lung nodules.Methods:A retrospective analysis was conducted on the imaging data of 114 patients who underwent lung nodule surgery in the Thoracic Surgery Department of the First People’s Hospital of Huzhou from June to September 2024.Imaging features of lung nodules were summarized and trained using a BP neural network.Results:Training with the BP neural network increased the diagnostic accuracy for distinguishing between benign and malignant lung nodules based on imaging features from 84.2%(manual assessment)to 94.1%.Conclusion:Training with the BP neural network significantly improves the diagnostic accuracy of lung nodule malignancy based solely on imaging features.展开更多
BACKGROUND Cryptococcus is a systemic opportunistic pathogenic fungus that can cause infections in both immunocompromised and immunocompetent hosts,with diverse clinical manifestations,ranging from asymptomatic pulmon...BACKGROUND Cryptococcus is a systemic opportunistic pathogenic fungus that can cause infections in both immunocompromised and immunocompetent hosts,with diverse clinical manifestations,ranging from asymptomatic pulmonary lesions to disseminated central nervous system infections.The incidence of pulmonary cryptococcosis(PC)has rapidly increased in recent years,with an increasing proportion of non-human immunodeficiency virus-infected and immunocompetent patients making its diagnosis challenging.If not properly recognized,PC can lead to systemic dissemination and high mortality rates.Early diagnosis and treatment can improve the prognosis.This study summarizes the clinical features of three immunocompetent children with PC who presented with chest pain to raise clinicians'awareness of the disease and reduce mortality.CASE SUMMARY Three male pediatric patients in good health were hospitalized because of chest pain without cough or fever.Chest computed tomography(CT)revealed pleuralbased nodules and consolidation with cavitation.A lung biopsy was performed in one case,and Cryptococcus was cultured from the pathological tissues.Cryptococcus was detected in the alveolar lavage fluid,and serum Cryptococcus capsular(C.capsular)polysaccharide antigen was positive in one case,and the other case was positive for serum C.capsular polysaccharide.All patients received oral fluconazole treatment.Follow-up chest CT scans after six months showed significant resolution of the lesions.CONCLUSION PC can also occur in immunocompetent children.When encountering children with chest pain only in the clinic,one should be vigilant about PC,promptly complete the relevant examinations,and avoid misdiagnosis.展开更多
With the rapid development of computed tomography(CT)technology,the widespread use of CT examinations in the evaluation of chest diseases in pediatrics has raised extensive concerns about radiation issues.This review ...With the rapid development of computed tomography(CT)technology,the widespread use of CT examinations in the evaluation of chest diseases in pediatrics has raised extensive concerns about radiation issues.This review first systematically summarizes the factors influencing radiation dose(detector,tube voltage,tube current-time product,field of view,and reconstruction algorithms)in pediatric chest computed tomography examinations.Methods to reduce radia-tion dose are also discussed,including the utilization of filters,automatic tube current modulation,automatic tube voltage selection,and organ dose modulation.Finally,the methods for individualized radiation dose calculation in pediatric chest CT examinations:effective dose,CT dosimetry software,Size-Specific Dose Estimate,and the Monte Carlo method are reviewed.Radiation exposure re-duction is a multifaceted issue.This review aims to provide an optimal scanning scheme for pediatric chest CT from different perspectives.展开更多
BACKGROUND:Previous studies have reported that early computed tomography(CT)findings significantly contribute to the outcomes of cardiac arrest(CA)patients.This study aims to evaluate the association between chest CT ...BACKGROUND:Previous studies have reported that early computed tomography(CT)findings significantly contribute to the outcomes of cardiac arrest(CA)patients.This study aims to evaluate the association between chest CT features and prognosis in CA patients treated with extracorporeal cardiopulmonary resuscitation(ECPR).METHODS:A retrospective observational study was conducted on adult CA patients treated with ECPR in a tertiary hospital between March 2015 and June 2023.All the patients underwent a wholebody CT scan within 1 h of ECPR.Data regarding demographic and clinical characteristics were collected from electronic medical records.The presence of gravity-dependent distribution and CT scores based on chest CT scans were determined for each patient.The primary outcome was 28-day survival.Receiver operating characteristic(ROC)curves were used to evaluate the ability of chest CT features(gravitydependent distribution and CT scores)to predict poor outcomes.The cut-off value of the CT score was determined.Kaplan-Meier curves were used to compare 28-day survival between the low-and high-CT score groups,which were classified using the estimated cut-off value.RESULTS:Among the 100 patients included,74 were non-survivors.The non-survivor patients showed a higher presence of gravity-dependent distribution and higher CT scores than survivors(P<0.05).Patients with gravity-dependent distribution had significantly higher CT scores than those with non-gravity-dependent distribution(P<0.05).The combination of CT score and gravity-dependent distribution predicted poor outcomes better than considering the features individually,demonstrating moderate performance(AUC:0.693,95%CI:0.568-0.801).According to the survival analysis,the risk of death increased as the CT score rose,with an estimated cut-off value of≥11(P=0.016).CONCLUSION:Chest CT features were associated with poor outcomes in CA patients following ECPR.展开更多
Thoracic reconstructions are essential surgical techniques used to replace severely damaged tissues and restore protection to internal organs.In recent years,advancements in additive manufacturing have enabled the pro...Thoracic reconstructions are essential surgical techniques used to replace severely damaged tissues and restore protection to internal organs.In recent years,advancements in additive manufacturing have enabled the production of thoracic implants with complex geometries,offering more versatile performance.In this study,we investigated a design based on a spring-like geometry manufactured by laser powder bed fusion(LPBF),as proposed in earlier research.The biomechanical behavior of this design was analyzed using various isolated semi-ring-rib models at different levels of the rib cage.This approach enabled a comprehensive examination,leading to the proposal of several implant configurations that were incorporated into a 3D rib cage model with chest wall defects,to simulate different chest wall reconstruction scenarios.The results revealed that the implant design was too rigid for the second rib level,which therefore was excluded from the proposed implant configurations.In chest wall reconstruction simulations,the maximum stresses observed in all prostheses did not exceed 38%of the implant material's yield stress in the most unfavorable case.Additionally,all the implants showed flexibility compatible with the physiological movements of the human thorax.展开更多
Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),...Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),comprising an initialization followed by subsequent learning,selects a small subset of informative data points for labeling.Recent advancements in pretrained models by supervised or self-supervised learning tailored to chest radiograph have shown broad applicability to diverse downstream tasks.However,their potential in cold-start AL remains unexplored.Methods:To validate the efficacy of domain-specific pretraining,we compared two foundation models:supervised TXRV and self-supervised REMEDIS with their general domain counterparts pretrained on ImageNet.Model performance was evaluated at both initialization and subsequent learning stages on two diagnostic tasks:psychiatric pneumonia and COVID-19.For initialization,we assessed their integration with three strategies:diversity,uncertainty,and hybrid sampling.For subsequent learning,we focused on uncertainty sampling powered by different pretrained models.We also conducted statistical tests to compare the foundation models with ImageNet counterparts,investigate the relationship between initialization and subsequent learning,examine the performance of one-shot initialization against the full AL process,and investigate the influence of class balance in initialization samples on initialization and subsequent learning.Results:First,domain-specific foundation models failed to outperform ImageNet counterparts in six out of eight experiments on informative sample selection.Both domain-specific and general pretrained models were unable to generate representations that could substitute for the original images as model inputs in seven of the eight scenarios.However,pretrained model-based initialization surpassed random sampling,the default approach in cold-start AL.Second,initialization performance was positively correlated with subsequent learning performance,highlighting the importance of initialization strategies.Third,one-shot initialization performed comparably to the full AL process,demonstrating the potential of reducing experts'repeated waiting during AL iterations.Last,a U-shaped correlation was observed between the class balance of initialization samples and model performance,suggesting that the class balance is more strongly associated with performance at middle budget levels than at low or high budgets.Conclusions:In this study,we highlighted the limitations of medical pretraining compared to general pretraining in the context of cold-start AL.We also identified promising outcomes related to cold-start AL,including initialization based on pretrained models,the positive influence of initialization on subsequent learning,the potential for one-shot initialization,and the influence of class balance on middle-budget AL.Researchers are encouraged to improve medical pretraining for versatile DL foundations and explore novel AL methods.展开更多
BACKGROUND Primary ciliary dyskinesia(PCD)is a rare condition characterised by dysmotile,immotile,or absent cilia.As a result of the impairment in respiratory mucociliary clearance,patients with PCD typically develop ...BACKGROUND Primary ciliary dyskinesia(PCD)is a rare condition characterised by dysmotile,immotile,or absent cilia.As a result of the impairment in respiratory mucociliary clearance,patients with PCD typically develop neonatal respiratory distress,nasal congestion,otitis media and recurrent respiratory infections leading to bronchiectasis and structural lung changes.These changes have been shown by chest computed tomography(CT)to develop in infancy and early childhood.Recent development and refinement of radiation-reducing CT techniques have allowed significant radiation dose reductions,with chest CT doses now in the range of chest radiography(CR).AIM To evaluate the efficacy of ultra-low dose CT(ULDCT)chest in identifying pulmonary changes within a PCD paediatric patient cohort.METHODS Paediatric patients with PCD who presented for routine clinical outpatient follow-up within the study period,were eligible for inclusion in the study.ULDCT and CR were performed on these patients and the results compared.Comparison metrics included radiation dose,subjective and objective image quality and disease severity.RESULTS Six paediatric patients(mean age 9 years)underwent clinically indicated ULDCT chest examinations and CR for surveillance of their PCD.The mean effective dose was 0.08±0.02 mSv,a dose that approximates that of a frontal and lateral chest radiograph.The average Brody II score across the entire cohort was 12.92,with excellent interrater reliability and intra-class correlation coefficient(ICC)of 0.98.The average Chrispin-Norman score on CR was 1 with excellent inter-rater reliability and ICC of 0.92.CONCLUSION ULDCT demonstrates superior diagnostic capabilities,minimal radiation dose penalty,and high interobserver reliability in comparison to CR.Thus,we advocate for ULDCT to be the preferred modality for surveillance imaging in paediatric PCD.展开更多
Background:The National Chest Pain Center Program(NCPCP)is a nationwide,quality enhancement program aimed at raising the standard of care for patients experiencing acute chest pain in China.The benefits of chest pain ...Background:The National Chest Pain Center Program(NCPCP)is a nationwide,quality enhancement program aimed at raising the standard of care for patients experiencing acute chest pain in China.The benefits of chest pain center(CPC)accreditation on acute coronary syndrome have been demonstrated.However,there is no evidence to indicate whether CPC accreditation improves outcomes for patients with acute aortic dissection(AAD).Methods:We conducted a retrospective observational study of patients with AAD from 1671 hospitals in China,using data from the NCPCP spanning the period from January 1,2016 to December 31,2022.The patients were divided into 2 groups:pre-accreditation and post-accreditation admissions.The outcomes examined included in-hospital mortality,misdiagnosis,and Stanford type A AAD surgery.Multivariate logistic regression was employed to explore the relationship between CPC accreditation and in-hospital outcomes.Furthermore,we stratified the hospitals based on their geographical location(Eastern/Central/Western regions)or administrative status(provincial/non-provincial capital areas)to assess the impact of CPC accreditation on AAD patients across various regions.Results:The analysis encompassed a total of 40,848 patients diagnosed with AAD.The post-accreditation group exhibited significantly lower rates of in-hospital mortality and misdiagnosis(12.1%vs.16.3%,P<0.001 and 2.9%vs.5.4%,P<0.001,respectively)as well as a notably higher rate of Stanford type A AAD surgery(61.1%vs.42.1%,P<0.001)compared with the pre-accreditation group.After adjusting for potential covariates,CPC accreditation was associated with substantially reduced risks of in-hospital mortality(adjusted OR=0.644,95%CI 0.599-0.693)and misdiagnosis(adjusted OR=0.554,95%CI 0.493-0.624),along with an increase in the proportion of patients undergoing Stanford type A AAD surgery(adjusted OR=1.973,95%CI 1.797-2.165).Following CPC accreditation,there were significant reductions in in-hospital mortality across various regions,particularly in Western regions(from 21.5%to 14.1%).Moreover,CPC accreditation demonstrated a more pronounced impact on in-hospital mortality in non-provincial cities compared to provincial cities(adjusted OR:0.607 vs.0.713).Conclusion:CPC accreditation is correlated with improved management and in-hospital outcomes for patients with AAD.展开更多
Objective: To analyze the clinical significance of the emergency green channel in the treatment of patients with acute chest pain. Methods: Sixty patients with acute chest pain treated between September 2022 and July ...Objective: To analyze the clinical significance of the emergency green channel in the treatment of patients with acute chest pain. Methods: Sixty patients with acute chest pain treated between September 2022 and July 2024 were selected as the subjects of this study. They were divided into groups based on the order of treatment: the first 30 patients were included in the Green Channel group, where the emergency green channel was employed, while the remaining 30 patients were placed in the Regular Emergency group, receiving standard emergency treatment. The rescue time, hospitalization time, pain scores, incidence of adverse reactions, and quality of life between the Green Channel group and the Regular Emergency group were compared. Results: The rescue time and hospitalization time of the Green Channel group were shorter than those of the Regular Emergency group, with statistical significance (P < 0.05). The pain scores at 30, 60, 120, and 240 minutes after rescue in the Green Channel group were lower than those in the Regular Emergency group, with statistical significance (P < 0.05). The incidence of adverse reactions such as recurrent acute attacks, arrhythmia, heart failure, stroke, and shock in the Green Channel group was lower than that in the Regular Emergency group, with statistical significance (P < 0.05). The treatment satisfaction rate and success rate in the Green Channel group were 93.33% and 93.33%, respectively, while those in the Regular Emergency group were 73.33% and 73.33%. Both the satisfaction and success rates in the Green Channel group were higher than those in the Regular Emergency group, with statistical significance (P < 0.05). The quality of life in the Green Channel group was also higher than that in the Regular Emergency group, with statistical significance (P < 0.05). Conclusion: The emergency green channel plays a significant role in the treatment of patients with acute chest pain and is worthy of widespread clinical application.展开更多
Our understanding of grain-level bursts of plasticity in polycrystals remains limited by current techniques.By employing a modified Synchrotron transmission X-ray Laue diffraction method(beam size larger than the grai...Our understanding of grain-level bursts of plasticity in polycrystals remains limited by current techniques.By employing a modified Synchrotron transmission X-ray Laue diffraction method(beam size larger than the grain size),we tracked grain rotations for the first 1%of tensile strain,in 4400 time steps.We indexed 33 grains and quantified the magnitude and frequency of intermittent bursts of grain rotation.We interpret these events in terms of bursts of plastic deformation.The events are highly coordinated amongst nearby grains,and their frequency and magnitude,as well as the number of grains participating,peaked at around the onset of full plasticity.At this point,7 out of the 10 indexed grains with orientations favorable for twinning showed significant drops in diffracted intensity(a mean value of 8%),due to twin induced re-orientation.For other orientations,20 out of 23 grains displayed bursts attributable to lattice dislocation glide(interpreted in terms of basal and prismatic <α> slip).The mean value of the magnitude of these bursts is∼0.08°,implying accumulated shear strains of the order of 3×10^(-3).These bursts,in many cases,were due to the activation of more than a single slip/twin system within the grain,and co-ordination amongst neighboring grains also involved collaboration between slip and twinning events.展开更多
文摘This paper presents a novelmulticlass systemdesigned to detect pleural effusion and pulmonary edema on chest Xray images,addressing the critical need for early detection in healthcare.A new comprehensive dataset was formed by combining 28,309 samples from the ChestX-ray14,PadChest,and CheXpert databases,with 10,287,6022,and 12,000 samples representing Pleural Effusion,Pulmonary Edema,and Normal cases,respectively.Consequently,the preprocessing step involves applying the Contrast Limited Adaptive Histogram Equalization(CLAHE)method to boost the local contrast of the X-ray samples,then resizing the images to 380×380 dimensions,followed by using the data augmentation technique.The classification task employs a deep learning model based on the EfficientNet-V1-B4 architecture and is trained using the AdamW optimizer.The proposed multiclass system achieved an accuracy(ACC)of 98.3%,recall of 98.3%,precision of 98.7%,and F1-score of 98.7%.Moreover,the robustness of the model was revealed by the Receiver Operating Characteristic(ROC)analysis,which demonstrated an Area Under the Curve(AUC)of 1.00 for edema and normal cases and 0.99 for effusion.The experimental results demonstrate the superiority of the proposedmulti-class system,which has the potential to assist clinicians in timely and accurate diagnosis,leading to improved patient outcomes.Notably,ablation-CAM visualization at the last convolutional layer portrayed further enhanced diagnostic capabilities with heat maps on X-ray images,which will aid clinicians in interpreting and localizing abnormalities more effectively.
文摘Introduction: The diagnosis of pneumonia is usually made based on clinical manifestations and chest X-ray. The use of ultrasound in detecting pulmonary diseases in general, and especially consolidation syndrome has been demonstrated. The objective of this study was to determine the accuracy of thoracic ultrasound compared to chest X-ray in the diagnosis of infectious pneumonia in children. Methods: Children between 0 to 15 years were included in our study. The lung ultrasound results obtained were compared with those of the chest X-ray used as the reference. Our data were introduced into the EpiInfo 3.5.4 software and analyzed with the EpiInfo 3.5.4 and IBMSPSS Statistics version 20.0 softwares. Microsoft Office Excel 2016 was used to produce Charts. Continuous quantitative variables were presented. Cohen’s Kappa concordance test was applied with confidence interval of 95%. Results: 52 children were enrolled in the study. In imaging, the dominant sign was consolidation syndrome (75.0%) of cases by chest radiography, and in 78.8% of cases by lung ultrasound (p Conclusion: Our study demonstrated that lung echography is a non-ionizing and reliable tool in the diagnosis of childhood’s pneumonia.
文摘Tuberculosis(TB)is a severe infection that mostly affects the lungs and kills millions of people’s lives every year.Tuberculosis can be diagnosed using chest X-rays(CXR)and data-driven deep learning(DL)approaches.Because of its better automated feature extraction capability,convolutional neural net-works(CNNs)trained on natural images are particularly effective in image cate-gorization.A combination of 3001 normal and 3001 TB CXR images was gathered for this study from different accessible public datasets.Ten different deep CNNs(Resnet50,Resnet101,Resnet152,InceptionV3,VGG16,VGG19,DenseNet121,DenseNet169,DenseNet201,MobileNet)are trained and tested for identifying TB and normal cases.This study presents a deep CNN approach based on histogram matched CXR images that does not require object segmenta-tion of interest,and this coupled methodology of histogram matching with the CXRs improves the accuracy and detection performance of CNN models for TB detection.Furthermore,this research contains two separate experiments that used CXR images with and without histogram matching to classify TB and non-TB CXRs using deep CNNs.It was able to accurately detect TB from CXR images using pre-processing,data augmentation,and deep CNN models.Without histogram matching the best accuracy,sensitivity,specificity,precision and F1-score in the detection of TB using CXR images among ten models are 99.25%,99.48%,99.52%,99.48%and 99.22%respectively.With histogram matching the best accuracy,sensitivity,specificity,precision and F1-score are 99.58%,99.82%,99.67%,99.65%and 99.56%respectively.The proposed meth-odology,which has cutting-edge performance,will be useful in computer-assisted TB diagnosis and aids in minimizing irregularities in TB detection in developing countries.
文摘BACKGROUND:The appropriate sequence of different imagings and indications of thoracic computed tomography(TCT)in evaluating chest trauma have not yet been clarified at present.The current study was undertaken to determine the value of chest X-ray(CXR)in detecting chest injuries in patients with blunt trauma.METHODS:A total of 447 patients with blunt thoracic trauma who had been admitted to the emergency department(ED)in the period of 2009–2013 were retrospectively reviewed.The patients met inclusion criteria(age>8 years,blunt injury to the chest,hemodynamically stable,and neurologically intact)and underwent both TCT and upright CXR in the ED.Radiological imagings were re-interpreted after they were collected from the hospital database by two skilled radiologists.RESULTS:Of the 447 patients,309(69.1%)were male.The mean age of the 447 patients was 39.5±19.2(range 9 and 87 years).158(35.3%)patients were injured in motor vehicle accidents(MVA).CXR showed the highest sensitivity in detecting clavicle fractures[95%CI 78.3(63.6–89)]but the lowest in pneuomediastinum[95%CI 11.8(1.5–36.4)].The specificity of CXR was close to 100%in detecting a wide array of entities.CONCLUSION:CXR remains to be the first choice in hemodynamically unstable patients with blunt chest trauma.Moreover,stable patients with normal CXR are candidates who should undergo TCT if significant injury has not been ruled out.
基金Baoding Science and Technology Plan Project(Project No.:2341ZF214)。
文摘Objective:To investigate the quantitative assessment efficacy of chest CT combined with serum Vanin-1 and SPP1 in determining the progression stage of chronic obstructive pulmonary disease(COPD).Methods:A total of 100 COPD subjects from our hospital from January 2020 to December 2023 were included and randomly divided into a healthy control group and an experimental group(50 cases each).The healthy control group underwent slow vital capacity measurement using a spirometer,while the experimental group underwent high-resolution thin-slice CT scans and serum Vanin-1 and SPP1 concentration measurements.Pulmonary function parameters,symptom burden,biomarker concentrations,and imaging characteristics were compared between the two groups.Results:The FEV1/FVC ratio in the experimental group(58.3±7.2)was lower than that in the healthy control group(92.1±4.8);the total CAT score(22.4±3.5)was higher than that in the healthy control group(3.1±1.2);both Vanin-1(18.7±2.3μg/L)and SPP1(25.6±4.1μg/L)levels were higher than those in the healthy control group;LAA%-950(38.7±6.2%)and WA%(68.5±5.3%)were significantly higher than those in the healthy control group(all p<0.001).Conclusion:Chest CT combined with serum Vanin-1 and SPP1 can accurately quantify the pathological progression of COPD,providing a dual basis for clinical staging and individualized intervention.
基金funded by Umm Al-Qura University,Saudi Arabia under grant number:25UQU4300346GSSR08.
文摘This study presents an advanced method for post-mortem person identification using the segmentation of skeletal structures from chest X-ray images.The proposed approach employs the Attention U-Net architecture,enhanced with gated attention mechanisms,to refine segmentation by emphasizing spatially relevant anatomical features while suppressing irrelevant details.By isolating skeletal structures which remain stable over time compared to soft tissues,this method leverages bones as reliable biometric markers for identity verification.The model integrates custom-designed encoder and decoder blocks with attention gates,achieving high segmentation precision.To evaluate the impact of architectural choices,we conducted an ablation study comparing Attention U-Net with and without attentionmechanisms,alongside an analysis of data augmentation effects.Training and evaluation were performed on a curated chest X-ray dataset,with segmentation performance measured using Dice score,precision,and loss functions,achieving over 98% precision and 94% Dice score.The extracted bone structures were further processed to derive unique biometric patterns,enabling robust and privacy-preserving person identification.Our findings highlight the effectiveness of attentionmechanisms in improving segmentation accuracy and underscore the potential of chest bonebased biometrics in forensic and medical imaging.This work paves the way for integrating artificial intelligence into real-world forensic workflows,offering a non-invasive and reliable solution for post-mortem identification.
文摘BACKGROUND In pediatric age group patients(<18 years old)treated operatively for distal radius/both bone fractures extending imaging beyond the initial postoperative period-particularly in uncomplicated cases-appears to provide limited additional benefit.AIM To determine the necessary number of follow-up X-rays to use resources efficiently.METHODS Participants included in this study are pediatric age group patients who were treated operatively for distal radius/both bone fractures and were identified from a prospected collected data from the operating room database between the years 2009 and 2017.The data in the study included patients who had distal radius fractures and underwent fixation surgery(n=88).RESULTS When assessing the difference in the odds of conducting 1 or less X-ray compared to 2 or more X-rays in regard to the type of fixation,the only significant difference is the closed reduction fixation method.Patients who underwent closed reduction method procedure have significantly lower odds of having 2 more X-rays compared to those who didn’t have closed reduction method.Open reduction,internal fixation,and other fixation methods(close reduction and internal fixation,debridement,or epiphysiodesis)have higher odds of having two or more X-rays compared to patients who did not receive these methods;however,these odds are not statistically significant.CONCLUSION The findings of this study reveal notable absence of a statistically significant association between the frequency of postoperative X-rays and the outcome of children with distal radius fractures.
文摘Objective: This study aims to investigate the drainage effect and clinical outcomes of negative pressure chest drainage in patients after two-port thoracoscopic valve surgery, comparing the differences in postoperative pain, hospital stay, and other factors between the negative pressure group and the control group. Methods: This study is a prospective controlled trial that selected patients undergoing two-port thoracoscopic valve surgery at a certain hospital from January 2019 to December 2024. Patients were randomly assigned to the control group and the negative pressure group using a random number table method. The control group consisted of 30 patients (20 males, 10 females, mean age 42.03 ± 12.89 years), and the negative pressure group consisted of 35 patients (26 males, 9 females, mean age 41.84 ± 11.83 years). The control group received traditional chest drainage, while the negative pressure group received negative pressure chest drainage. Postoperative pain scores, hospital stay, drainage time, number of tube blockages, and incidences of pneumothorax or subcutaneous emphysema were recorded and statistically analyzed. Results: The negative pressure group had a significantly shorter postoperative drainage time compared to the control group (49.09 ± 11.99 hours vs. 79.10 ± 7.32 hours, P < 0.001). The postoperative pain score was lower in the negative pressure group (4.49 ± 1.27 vs. 7.03 ± 0.85, P < 0.001), and the hospital stay was significantly shorter (9.83 ± 1.69 days vs. 14.73 ± 2.32 days, P < 0.001). The incidence of pneumothorax or subcutaneous emphysema was significantly lower in the negative pressure group than in the control group (14.29% vs. 56.67%, P = 0.0003). Conclusion: The application of negative pressure chest drainage in patients after two-port thoracoscopic valve surgery can effectively reduce postoperative pain, shorten hospital stay, and lower the incidence of tube blockage and pneumothorax, demonstrating good clinical outcomes.
基金Qinghai Provincial Health Commission Medical and Health Science and Technology(Project No.:2022-wjzdx-63)。
文摘This study aimed to analyze the early high-resolution CT(HRCT)manifestations and dynamic imaging changes of coronavirus disease 2019(COVID-19)in Qinghai Province.A total of 24 nucleic acid-positive COVID-19 patients admitted to our hospital between January 2020 and November 2021 were included.All patients underwent HRCT examinations,and lesion characteristics—including number,distribution,morphology,and surrounding involvement were analyzed.Among the 24 patients,systemic and respiratory circulatory symptoms were more common than other symptoms(P<0.05).There were no significant differences in the lung lobes,relative positions,quantity,size,and density of lesions across different stages of the disease course(P>0.05).Within the same disease stage,lesions were primarily located in the lower lobes of both lungs,the peripheral lung fields,and a combination of peripheral and central regions,with single and multiple lesions being the most common.Lesion morphology varied significantly across disease stages(P<0.05),including differences between patchy and striped lesions,striped and massive lesions(P<0.05),and patchy and massive lesions(P<0.05).The incidence of striped lesions was higher in the progressive and recovery stages than in the early stage,showing an upward trend.There were no significant differences in pleural thickening,pleural effusion,mediastinal lymph node enlargement,or pericardial effusion across different disease stages(P>0.05).Common HRCT signs observed at all stages included air bronchograms,paving stone patterns,halo signs,subpleural lines,and grid-like patterns.The main patterns of lesion progression were an increase in lesion size(16/24,66.67%),an increase in the number of lesions(17/24,70.83%),changes in lesion density(20/24,80.33%),and localized lesion increase and partial absorption(6/24,25.00%).In conclusion,the HRCT manifestations and evolution of lung lesions in COVID-19 patients are complex and varied,with a progressive increase in striped lesions potentially serving as a characteristic imaging feature of the disease.
文摘Basic life support for cardiac arrest associates cardiopulmonary resuscitation(CPR)and defibrillation.CPR relies on chest compressions(CC)and ventilation.Current guidelines on CPR recommend a depth of 5-6 cm at a rhythm of 100-120 times/min for CC.[1,2]Interruptions of the CC must be as short as possible and are related to ventilation,defibrillation and turnover of the rescuers.Most of the automated external defibrillators(AEDs)require interruptions of the CC to perform rhythm analysis.Among the numerous marketed models of AEDs,some provide real-time feedback about the quality of the CC.
基金Zhejiang Medical and Health Technology Project(Project No.2020PY072)。
文摘Objective:To explore a simple method for improving the diagnostic accuracy of malignant lung nodules based on imaging features of lung nodules.Methods:A retrospective analysis was conducted on the imaging data of 114 patients who underwent lung nodule surgery in the Thoracic Surgery Department of the First People’s Hospital of Huzhou from June to September 2024.Imaging features of lung nodules were summarized and trained using a BP neural network.Results:Training with the BP neural network increased the diagnostic accuracy for distinguishing between benign and malignant lung nodules based on imaging features from 84.2%(manual assessment)to 94.1%.Conclusion:Training with the BP neural network significantly improves the diagnostic accuracy of lung nodule malignancy based solely on imaging features.
基金Supported by Shenzhen Fund for Guangdong Provincial High-Level Clinical Key Specialties,No.SZGSP012Shenzhen Key Medical Discipline Construction Fund,No.SZXK032。
文摘BACKGROUND Cryptococcus is a systemic opportunistic pathogenic fungus that can cause infections in both immunocompromised and immunocompetent hosts,with diverse clinical manifestations,ranging from asymptomatic pulmonary lesions to disseminated central nervous system infections.The incidence of pulmonary cryptococcosis(PC)has rapidly increased in recent years,with an increasing proportion of non-human immunodeficiency virus-infected and immunocompetent patients making its diagnosis challenging.If not properly recognized,PC can lead to systemic dissemination and high mortality rates.Early diagnosis and treatment can improve the prognosis.This study summarizes the clinical features of three immunocompetent children with PC who presented with chest pain to raise clinicians'awareness of the disease and reduce mortality.CASE SUMMARY Three male pediatric patients in good health were hospitalized because of chest pain without cough or fever.Chest computed tomography(CT)revealed pleuralbased nodules and consolidation with cavitation.A lung biopsy was performed in one case,and Cryptococcus was cultured from the pathological tissues.Cryptococcus was detected in the alveolar lavage fluid,and serum Cryptococcus capsular(C.capsular)polysaccharide antigen was positive in one case,and the other case was positive for serum C.capsular polysaccharide.All patients received oral fluconazole treatment.Follow-up chest CT scans after six months showed significant resolution of the lesions.CONCLUSION PC can also occur in immunocompetent children.When encountering children with chest pain only in the clinic,one should be vigilant about PC,promptly complete the relevant examinations,and avoid misdiagnosis.
基金Supported by the Key Natural Science Project of the Anhui Provincial Education Department Under,No.KJ2021A0746.
文摘With the rapid development of computed tomography(CT)technology,the widespread use of CT examinations in the evaluation of chest diseases in pediatrics has raised extensive concerns about radiation issues.This review first systematically summarizes the factors influencing radiation dose(detector,tube voltage,tube current-time product,field of view,and reconstruction algorithms)in pediatric chest computed tomography examinations.Methods to reduce radia-tion dose are also discussed,including the utilization of filters,automatic tube current modulation,automatic tube voltage selection,and organ dose modulation.Finally,the methods for individualized radiation dose calculation in pediatric chest CT examinations:effective dose,CT dosimetry software,Size-Specific Dose Estimate,and the Monte Carlo method are reviewed.Radiation exposure re-duction is a multifaceted issue.This review aims to provide an optimal scanning scheme for pediatric chest CT from different perspectives.
基金approved by the Ethics Committee of the First Affiliated Hospital of Nanjing Medical University(2020-SR-226).
文摘BACKGROUND:Previous studies have reported that early computed tomography(CT)findings significantly contribute to the outcomes of cardiac arrest(CA)patients.This study aims to evaluate the association between chest CT features and prognosis in CA patients treated with extracorporeal cardiopulmonary resuscitation(ECPR).METHODS:A retrospective observational study was conducted on adult CA patients treated with ECPR in a tertiary hospital between March 2015 and June 2023.All the patients underwent a wholebody CT scan within 1 h of ECPR.Data regarding demographic and clinical characteristics were collected from electronic medical records.The presence of gravity-dependent distribution and CT scores based on chest CT scans were determined for each patient.The primary outcome was 28-day survival.Receiver operating characteristic(ROC)curves were used to evaluate the ability of chest CT features(gravitydependent distribution and CT scores)to predict poor outcomes.The cut-off value of the CT score was determined.Kaplan-Meier curves were used to compare 28-day survival between the low-and high-CT score groups,which were classified using the estimated cut-off value.RESULTS:Among the 100 patients included,74 were non-survivors.The non-survivor patients showed a higher presence of gravity-dependent distribution and higher CT scores than survivors(P<0.05).Patients with gravity-dependent distribution had significantly higher CT scores than those with non-gravity-dependent distribution(P<0.05).The combination of CT score and gravity-dependent distribution predicted poor outcomes better than considering the features individually,demonstrating moderate performance(AUC:0.693,95%CI:0.568-0.801).According to the survival analysis,the risk of death increased as the CT score rose,with an estimated cut-off value of≥11(P=0.016).CONCLUSION:Chest CT features were associated with poor outcomes in CA patients following ECPR.
文摘Thoracic reconstructions are essential surgical techniques used to replace severely damaged tissues and restore protection to internal organs.In recent years,advancements in additive manufacturing have enabled the production of thoracic implants with complex geometries,offering more versatile performance.In this study,we investigated a design based on a spring-like geometry manufactured by laser powder bed fusion(LPBF),as proposed in earlier research.The biomechanical behavior of this design was analyzed using various isolated semi-ring-rib models at different levels of the rib cage.This approach enabled a comprehensive examination,leading to the proposal of several implant configurations that were incorporated into a 3D rib cage model with chest wall defects,to simulate different chest wall reconstruction scenarios.The results revealed that the implant design was too rigid for the second rib level,which therefore was excluded from the proposed implant configurations.In chest wall reconstruction simulations,the maximum stresses observed in all prostheses did not exceed 38%of the implant material's yield stress in the most unfavorable case.Additionally,all the implants showed flexibility compatible with the physiological movements of the human thorax.
文摘Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),comprising an initialization followed by subsequent learning,selects a small subset of informative data points for labeling.Recent advancements in pretrained models by supervised or self-supervised learning tailored to chest radiograph have shown broad applicability to diverse downstream tasks.However,their potential in cold-start AL remains unexplored.Methods:To validate the efficacy of domain-specific pretraining,we compared two foundation models:supervised TXRV and self-supervised REMEDIS with their general domain counterparts pretrained on ImageNet.Model performance was evaluated at both initialization and subsequent learning stages on two diagnostic tasks:psychiatric pneumonia and COVID-19.For initialization,we assessed their integration with three strategies:diversity,uncertainty,and hybrid sampling.For subsequent learning,we focused on uncertainty sampling powered by different pretrained models.We also conducted statistical tests to compare the foundation models with ImageNet counterparts,investigate the relationship between initialization and subsequent learning,examine the performance of one-shot initialization against the full AL process,and investigate the influence of class balance in initialization samples on initialization and subsequent learning.Results:First,domain-specific foundation models failed to outperform ImageNet counterparts in six out of eight experiments on informative sample selection.Both domain-specific and general pretrained models were unable to generate representations that could substitute for the original images as model inputs in seven of the eight scenarios.However,pretrained model-based initialization surpassed random sampling,the default approach in cold-start AL.Second,initialization performance was positively correlated with subsequent learning performance,highlighting the importance of initialization strategies.Third,one-shot initialization performed comparably to the full AL process,demonstrating the potential of reducing experts'repeated waiting during AL iterations.Last,a U-shaped correlation was observed between the class balance of initialization samples and model performance,suggesting that the class balance is more strongly associated with performance at middle budget levels than at low or high budgets.Conclusions:In this study,we highlighted the limitations of medical pretraining compared to general pretraining in the context of cold-start AL.We also identified promising outcomes related to cold-start AL,including initialization based on pretrained models,the positive influence of initialization on subsequent learning,the potential for one-shot initialization,and the influence of class balance on middle-budget AL.Researchers are encouraged to improve medical pretraining for versatile DL foundations and explore novel AL methods.
文摘BACKGROUND Primary ciliary dyskinesia(PCD)is a rare condition characterised by dysmotile,immotile,or absent cilia.As a result of the impairment in respiratory mucociliary clearance,patients with PCD typically develop neonatal respiratory distress,nasal congestion,otitis media and recurrent respiratory infections leading to bronchiectasis and structural lung changes.These changes have been shown by chest computed tomography(CT)to develop in infancy and early childhood.Recent development and refinement of radiation-reducing CT techniques have allowed significant radiation dose reductions,with chest CT doses now in the range of chest radiography(CR).AIM To evaluate the efficacy of ultra-low dose CT(ULDCT)chest in identifying pulmonary changes within a PCD paediatric patient cohort.METHODS Paediatric patients with PCD who presented for routine clinical outpatient follow-up within the study period,were eligible for inclusion in the study.ULDCT and CR were performed on these patients and the results compared.Comparison metrics included radiation dose,subjective and objective image quality and disease severity.RESULTS Six paediatric patients(mean age 9 years)underwent clinically indicated ULDCT chest examinations and CR for surveillance of their PCD.The mean effective dose was 0.08±0.02 mSv,a dose that approximates that of a frontal and lateral chest radiograph.The average Brody II score across the entire cohort was 12.92,with excellent interrater reliability and intra-class correlation coefficient(ICC)of 0.98.The average Chrispin-Norman score on CR was 1 with excellent inter-rater reliability and ICC of 0.92.CONCLUSION ULDCT demonstrates superior diagnostic capabilities,minimal radiation dose penalty,and high interobserver reliability in comparison to CR.Thus,we advocate for ULDCT to be the preferred modality for surveillance imaging in paediatric PCD.
基金supported by the National Key Research and Development Program of China(2023YFC2506500,2021YFC2500500)the Program of Shanghai Academic Research Leader(22XD1423300)the National Natural Science Foundation of China(T2288101,82370357,82100470)。
文摘Background:The National Chest Pain Center Program(NCPCP)is a nationwide,quality enhancement program aimed at raising the standard of care for patients experiencing acute chest pain in China.The benefits of chest pain center(CPC)accreditation on acute coronary syndrome have been demonstrated.However,there is no evidence to indicate whether CPC accreditation improves outcomes for patients with acute aortic dissection(AAD).Methods:We conducted a retrospective observational study of patients with AAD from 1671 hospitals in China,using data from the NCPCP spanning the period from January 1,2016 to December 31,2022.The patients were divided into 2 groups:pre-accreditation and post-accreditation admissions.The outcomes examined included in-hospital mortality,misdiagnosis,and Stanford type A AAD surgery.Multivariate logistic regression was employed to explore the relationship between CPC accreditation and in-hospital outcomes.Furthermore,we stratified the hospitals based on their geographical location(Eastern/Central/Western regions)or administrative status(provincial/non-provincial capital areas)to assess the impact of CPC accreditation on AAD patients across various regions.Results:The analysis encompassed a total of 40,848 patients diagnosed with AAD.The post-accreditation group exhibited significantly lower rates of in-hospital mortality and misdiagnosis(12.1%vs.16.3%,P<0.001 and 2.9%vs.5.4%,P<0.001,respectively)as well as a notably higher rate of Stanford type A AAD surgery(61.1%vs.42.1%,P<0.001)compared with the pre-accreditation group.After adjusting for potential covariates,CPC accreditation was associated with substantially reduced risks of in-hospital mortality(adjusted OR=0.644,95%CI 0.599-0.693)and misdiagnosis(adjusted OR=0.554,95%CI 0.493-0.624),along with an increase in the proportion of patients undergoing Stanford type A AAD surgery(adjusted OR=1.973,95%CI 1.797-2.165).Following CPC accreditation,there were significant reductions in in-hospital mortality across various regions,particularly in Western regions(from 21.5%to 14.1%).Moreover,CPC accreditation demonstrated a more pronounced impact on in-hospital mortality in non-provincial cities compared to provincial cities(adjusted OR:0.607 vs.0.713).Conclusion:CPC accreditation is correlated with improved management and in-hospital outcomes for patients with AAD.
基金Baoding Science and Technology Plan Funded Project“The Value of Emergency Green Channel in the Treatment Rate of Acute Chest Pain Patients”(Project No.2441ZF291)。
文摘Objective: To analyze the clinical significance of the emergency green channel in the treatment of patients with acute chest pain. Methods: Sixty patients with acute chest pain treated between September 2022 and July 2024 were selected as the subjects of this study. They were divided into groups based on the order of treatment: the first 30 patients were included in the Green Channel group, where the emergency green channel was employed, while the remaining 30 patients were placed in the Regular Emergency group, receiving standard emergency treatment. The rescue time, hospitalization time, pain scores, incidence of adverse reactions, and quality of life between the Green Channel group and the Regular Emergency group were compared. Results: The rescue time and hospitalization time of the Green Channel group were shorter than those of the Regular Emergency group, with statistical significance (P < 0.05). The pain scores at 30, 60, 120, and 240 minutes after rescue in the Green Channel group were lower than those in the Regular Emergency group, with statistical significance (P < 0.05). The incidence of adverse reactions such as recurrent acute attacks, arrhythmia, heart failure, stroke, and shock in the Green Channel group was lower than that in the Regular Emergency group, with statistical significance (P < 0.05). The treatment satisfaction rate and success rate in the Green Channel group were 93.33% and 93.33%, respectively, while those in the Regular Emergency group were 73.33% and 73.33%. Both the satisfaction and success rates in the Green Channel group were higher than those in the Regular Emergency group, with statistical significance (P < 0.05). The quality of life in the Green Channel group was also higher than that in the Regular Emergency group, with statistical significance (P < 0.05). Conclusion: The emergency green channel plays a significant role in the treatment of patients with acute chest pain and is worthy of widespread clinical application.
基金the Australian Research Council through the Discovery Grant DP200100727 and Laureate Fellowship FL210100147。
文摘Our understanding of grain-level bursts of plasticity in polycrystals remains limited by current techniques.By employing a modified Synchrotron transmission X-ray Laue diffraction method(beam size larger than the grain size),we tracked grain rotations for the first 1%of tensile strain,in 4400 time steps.We indexed 33 grains and quantified the magnitude and frequency of intermittent bursts of grain rotation.We interpret these events in terms of bursts of plastic deformation.The events are highly coordinated amongst nearby grains,and their frequency and magnitude,as well as the number of grains participating,peaked at around the onset of full plasticity.At this point,7 out of the 10 indexed grains with orientations favorable for twinning showed significant drops in diffracted intensity(a mean value of 8%),due to twin induced re-orientation.For other orientations,20 out of 23 grains displayed bursts attributable to lattice dislocation glide(interpreted in terms of basal and prismatic <α> slip).The mean value of the magnitude of these bursts is∼0.08°,implying accumulated shear strains of the order of 3×10^(-3).These bursts,in many cases,were due to the activation of more than a single slip/twin system within the grain,and co-ordination amongst neighboring grains also involved collaboration between slip and twinning events.
