Objective:To explore the role of lung ultrasound combined with multi-organ evaluation in assessing the risk of weaning from mechanical ventilation(MV)in severe patients.Methods:A retrospective analysis was conducted o...Objective:To explore the role of lung ultrasound combined with multi-organ evaluation in assessing the risk of weaning from mechanical ventilation(MV)in severe patients.Methods:A retrospective analysis was conducted on 60 severe patients admitted to the hospital from December 2022 to December 2024,all of whom underwent MV treatment.Based on weaning status,thirty-eight patients were successfully weaned(success group),and 22 patients failed weaning(failure group).All patients underwent lung ultrasound and multi-organ evaluation.The parameter differences between the two groups were compared,risk factors for weaning risk were evaluated,and a receiver operating characteristic curve(ROC)was drawn to assess the predictive value of lung ultrasound combined with multi-organ evaluation for weaning risk.Results:The lung ultrasound score(LUS)of the success group was lower than that of the failure group,the left ventricular ejection fraction(LVEF)was higher than that of the failure group,and the diaphragmatic excursion(DE)and diaphragmatic thickening fraction(DTF)were higher than those of the failure group(P<0.05).Multifactor analysis showed that LUS was a risk factor for weaning risk,while LVEF,DE,and DTF were protective factors(P<0.05).The ROC showed that the area under the curve(AUC)of a single parameter for weaning risk was smaller than that of the combined parameters(P<0.05).Conclusion:Lung ultrasound combined with multi-organ evaluation can predict the weaning risk of severe patients undergoing MV treatment,and the diagnostic efficiency of multiple parameters combined evaluation is higher.展开更多
Fairness is an emerging consideration when assessing the segmentation per-formance of machine learning models across various demographic groups.During clinical decision-making,an unfair segmentation model exhibits ris...Fairness is an emerging consideration when assessing the segmentation per-formance of machine learning models across various demographic groups.During clinical decision-making,an unfair segmentation model exhibits risks in that it can pose inappropriate diagnoses and unsuitable treatment plans for underrepresented demographic groups,resulting in severe consequences for patients and society.In medical artificial intelligence(AI),the fairness of multi-organ segmentation is imperative to augment the integration of models into clinical practice.As the use of multi-organ segmentation in medical image analysis expands,it is crucial to systematically examine fairness to ensure equitable segmentation performance across diverse patient populations and ensure health equity.However,comprehensive studies assessing the problem of fairness in multi-organ segmentation remain lacking.This study aimed to provide an overview of the fairness problem in multi-organ segmentation.We first define fairness and discuss the factors that lead to fairness problems such as individual fairness,group fairness,counterfactual fairness,and max–min fairness in multi-organ segmentation,focusing mainly on datasets and models.We then present strategies to potentially improve fairness in multi-organ segmentation.Additionally,we highlight the challenges and limita-tions of existing approaches and discuss future directions for improving the fairness of AI models for clinically oriented multi-organ segmentation.展开更多
Bacillus Calmette-Guerin(BCG) intravesical instillation has been adopted in the treatment of patients with superficial bladder cancer.BCG-induced disseminated infection,though rare,has been associated with the histolo...Bacillus Calmette-Guerin(BCG) intravesical instillation has been adopted in the treatment of patients with superficial bladder cancer.BCG-induced disseminated infection,though rare,has been associated with the histological finding of epithelioid granulomas in different organs,including the liver.We report the case of an adult patient with multi-organ failure,who developed sepsis,acute respiratory failure and acute hepatic failure with encephalopathy whose liver biopsy confirmed the presence of atypical,granulomatous-like lesions.Recovery was observed only after empirical therapy for Mycobacterium bovis with isoniazid,rifampicin,ethambutol and steroids was introduced.This case highlights the importance of a thorough patient assessment in order to exclude other more common causes of hepatic granulomas and to confirm diagnosis.Histological findings may be non-specific when the liver is involved in BCGinduced disseminated infection.展开更多
Pantoe agglomerans (P. agglomerans) is an unusual cause for sepsis in immunocompetent individuals, especially in the absence of characteristic risk factors. We report one such case occurring in a farmer, manifesting w...Pantoe agglomerans (P. agglomerans) is an unusual cause for sepsis in immunocompetent individuals, especially in the absence of characteristic risk factors. We report one such case occurring in a farmer, manifesting with severe illness. The severe nature of illness and the apparently spontaneous origin of septicemia underline the pathogenic potential of this organism. When coupled with the ubiquity of the organism, there is a definite possibility that this disease may become increasingly frequent in the near future, especially in agronomic countries like India. Further studies on the epidemiology and natural history of this disease are required.展开更多
Unnecessary exposure to ionizing radiation(IR)often causes acute and chronic oxidative damages to normal cells and organs,leading to serious physiological and even life-threatening consequences.Amifostine(AMF)is a val...Unnecessary exposure to ionizing radiation(IR)often causes acute and chronic oxidative damages to normal cells and organs,leading to serious physiological and even life-threatening consequences.Amifostine(AMF)is a validated radioprotectant extensively applied in radiation and chemotherapy medicine,but the short half-life limits its bioavailability and clinical applications,remaining as a great challenge to be addressed.DNAassembled nanostructures especially the tetrahedral framework nucleic acids(tFNAs)are promising nanocarriers with preeminent biosafety,low biotoxicity,and high transport efficiency.The tFNAs also have a relative long-term maintenance for structural stability and excellent endocytosis capacity.We therefore synthesized a tFNA-based delivery system of AMF for multi-organ radioprotection(tFNAs@AMF,also termed nanosuit).By establishing the mice models of accidental total body irradiation(TBI)and radiotherapy model of Lewis lung cancer,we demonstrated that the nanosuit could shield normal cells from IR-induced DNA damage by regulating the molecular biomarkers of anti-apoptosis and anti-oxidative stress.In the accidental total body irradiation(TBI)mice model,the nanosuit pretreated mice exhibited satisfactory alteration of superoxide dismutase(SOD)activities and malondialdehyde(MDA)contents,and functional recovery of hematopoietic system,reducing IRinduced pathological damages of multi-organ and safeguarding mice from lethal radiation.More importantly,the nanosuit showed a selective radioprotection of the normal organs without interferences of tumor control in the radiotherapy model of Lewis lung cancer.Based on a conveniently available DNA tetrahedron-based nanocarrier,this work presents a high-efficiency delivery system of AMF with the prolonged half-life and enhanced radioprotection for multi-organs.Such nanosuit pioneers a promising strategy with great clinical translation potential for radioactivity protection.展开更多
Accurate plant species classification is essential for many applications,such as biodiversity conservation,ecological research,and sustainable agricultural practices.Traditional morphological classification methods ar...Accurate plant species classification is essential for many applications,such as biodiversity conservation,ecological research,and sustainable agricultural practices.Traditional morphological classification methods are inherently slow,labour-intensive,and prone to inaccuracies,especiallywhen distinguishing between species exhibiting visual similarities or high intra-species variability.To address these limitations and to overcome the constraints of imageonly approaches,we introduce a novel Artificial Intelligence-driven framework.This approach integrates robust Vision Transformer(ViT)models for advanced visual analysis with a multi-modal data fusion strategy,incorporating contextual metadata such as precise environmental conditions,geographic location,and phenological traits.This combination of visual and ecological cues significantly enhances classification accuracy and robustness,proving especially vital in complex,heterogeneous real-world environments.The proposedmodel achieves an impressive 97.27%of test accuracy,andMean Reciprocal Rank(MRR)of 0.9842 that demonstrates strong generalization capabilities.Furthermore,efficient utilization of high-performance GPU resources(RTX 3090,18 GB memory)ensures scalable processing of highdimensional data.Comparative analysis consistently confirms that ourmetadata fusion approach substantially improves classification performance,particularly formorphologically similar species,and through principled self-supervised and transfer learning from ImageNet,the model adapts efficiently to new species,ensuring enhanced generalization.This comprehensive approach holds profound practical implications for precise conservation initiatives,rigorous ecological monitoring,and advanced agricultural management.展开更多
BACKGROUND Single-ventricle congenital heart disease often requires the Fontan procedure,which can lead to Fontan-associated liver disease(FALD)and multi-organ failure.Combined heart-liver transplantation(CHLT)is a po...BACKGROUND Single-ventricle congenital heart disease often requires the Fontan procedure,which can lead to Fontan-associated liver disease(FALD)and multi-organ failure.Combined heart-liver transplantation(CHLT)is a potential lifesaving option for these patients.AIMTo investigate the outcomes and complications of CHLT in patients with failing Fontan physiology.METHODSSeven retrospective studies of 121 patients undergoing CHLT were systematically reviewed. Quality was assessedwith the Newcastle-Ottawa Scale. A meta-analysis using random-effects models to calculate odds ratios (ORs) ormean differences (MDs) with 95% confidence intervals.RESULTSThe pooled 30-day, 1-year, 5-year, and 10-year survival rates after CHLT were 92.6%, 86.78%, 81.17%, and 77.8%,respectively. The mean intensive care unit and total hospital lengths of stay were 8.46 and 28.16 days. Meanischemic time was 267.29 minutes, while cardiopulmonary bypass time was 260.27 minutes. Infections (30%), renalreplacement therapy (36.84%), and graft rejection (12.34%) were notable complications. Compared to orthotopicheart transplantation (OHT), CHLT significantly reduced mortality (OR: 0.30, P = 0.009) and ischemic time (MD:–65.93 minutes), with no major differences in perioperative morbidity.CONCLUSIONCHLT offers a survival advantage over OHT for patients with FALD and failing Fontan physiology. Futureprospective studies are warranted to refine eligibility and improve long-term survival.展开更多
The application of transformer networks and feature fusion models in medical image segmentation has aroused considerable attention within the academic circle.Nevertheless,two main obstacles persist:(1)the restrictions...The application of transformer networks and feature fusion models in medical image segmentation has aroused considerable attention within the academic circle.Nevertheless,two main obstacles persist:(1)the restrictions of the Transformer network in dealing with locally detailed features,and(2)the considerable loss of feature information in current feature fusion modules.To solve these issues,this study initially presents a refined feature extraction approach,employing a double-branch feature extraction network to capture complex multi-scale local and global information from images.Subsequently,we proposed a low-loss feature fusion method-Multi-branch Feature Fusion Enhancement Module(MFFEM),which realizes effective feature fusion with minimal loss.Simultaneously,the cross-layer cross-attention fusion module(CLCA)is adopted to further achieve adequate feature fusion by enhancing the interaction between encoders and decoders of various scales.Finally,the feasibility of our method was verified using the Synapse and ACDC datasets,demonstrating its competitiveness.The average DSC(%)was 83.62 and 91.99 respectively,and the average HD95(mm)was reduced to 19.55 and 1.15 respectively.展开更多
基金Sichuan Provincial Medical Scientific Research Project(Project No.:s19085)。
文摘Objective:To explore the role of lung ultrasound combined with multi-organ evaluation in assessing the risk of weaning from mechanical ventilation(MV)in severe patients.Methods:A retrospective analysis was conducted on 60 severe patients admitted to the hospital from December 2022 to December 2024,all of whom underwent MV treatment.Based on weaning status,thirty-eight patients were successfully weaned(success group),and 22 patients failed weaning(failure group).All patients underwent lung ultrasound and multi-organ evaluation.The parameter differences between the two groups were compared,risk factors for weaning risk were evaluated,and a receiver operating characteristic curve(ROC)was drawn to assess the predictive value of lung ultrasound combined with multi-organ evaluation for weaning risk.Results:The lung ultrasound score(LUS)of the success group was lower than that of the failure group,the left ventricular ejection fraction(LVEF)was higher than that of the failure group,and the diaphragmatic excursion(DE)and diaphragmatic thickening fraction(DTF)were higher than those of the failure group(P<0.05).Multifactor analysis showed that LUS was a risk factor for weaning risk,while LVEF,DE,and DTF were protective factors(P<0.05).The ROC showed that the area under the curve(AUC)of a single parameter for weaning risk was smaller than that of the combined parameters(P<0.05).Conclusion:Lung ultrasound combined with multi-organ evaluation can predict the weaning risk of severe patients undergoing MV treatment,and the diagnostic efficiency of multiple parameters combined evaluation is higher.
基金Shanghai Municipal Science and Technology Major Project,Grant/Award Number:2023SHZD2X02A05National Natural Science Foundation of China,Grant/Award Number:62331021Shanghai Sailing Program,Grant/Award Numbers:20YF1402400,22YF1409300。
文摘Fairness is an emerging consideration when assessing the segmentation per-formance of machine learning models across various demographic groups.During clinical decision-making,an unfair segmentation model exhibits risks in that it can pose inappropriate diagnoses and unsuitable treatment plans for underrepresented demographic groups,resulting in severe consequences for patients and society.In medical artificial intelligence(AI),the fairness of multi-organ segmentation is imperative to augment the integration of models into clinical practice.As the use of multi-organ segmentation in medical image analysis expands,it is crucial to systematically examine fairness to ensure equitable segmentation performance across diverse patient populations and ensure health equity.However,comprehensive studies assessing the problem of fairness in multi-organ segmentation remain lacking.This study aimed to provide an overview of the fairness problem in multi-organ segmentation.We first define fairness and discuss the factors that lead to fairness problems such as individual fairness,group fairness,counterfactual fairness,and max–min fairness in multi-organ segmentation,focusing mainly on datasets and models.We then present strategies to potentially improve fairness in multi-organ segmentation.Additionally,we highlight the challenges and limita-tions of existing approaches and discuss future directions for improving the fairness of AI models for clinically oriented multi-organ segmentation.
文摘Bacillus Calmette-Guerin(BCG) intravesical instillation has been adopted in the treatment of patients with superficial bladder cancer.BCG-induced disseminated infection,though rare,has been associated with the histological finding of epithelioid granulomas in different organs,including the liver.We report the case of an adult patient with multi-organ failure,who developed sepsis,acute respiratory failure and acute hepatic failure with encephalopathy whose liver biopsy confirmed the presence of atypical,granulomatous-like lesions.Recovery was observed only after empirical therapy for Mycobacterium bovis with isoniazid,rifampicin,ethambutol and steroids was introduced.This case highlights the importance of a thorough patient assessment in order to exclude other more common causes of hepatic granulomas and to confirm diagnosis.Histological findings may be non-specific when the liver is involved in BCGinduced disseminated infection.
文摘Pantoe agglomerans (P. agglomerans) is an unusual cause for sepsis in immunocompetent individuals, especially in the absence of characteristic risk factors. We report one such case occurring in a farmer, manifesting with severe illness. The severe nature of illness and the apparently spontaneous origin of septicemia underline the pathogenic potential of this organism. When coupled with the ubiquity of the organism, there is a definite possibility that this disease may become increasingly frequent in the near future, especially in agronomic countries like India. Further studies on the epidemiology and natural history of this disease are required.
基金supported by National Natural Science Foundation of China(82370929)Sichuan Science and Technology Program(2022NSFSC0002 and 2024NSFSC3508)+4 种基金Sichuan Province Youth Science and Technology Innovation Team(2022JDTD0021)Research and Develop Program,West China Hospital of Stomatology Sichuan University(RD03202302,RCDWJS2024-1)China Postdoctoral Science Foundation(GZB2023470)Sichuan Province Innovative Talent Funding Project for Postdoctoral Fellows(BX202317)The authors would like to thank Dr.Chenghui Li(Analytical&Testing Center,Sichuan University)for technical assistance in assisting with the particle size analysis.
文摘Unnecessary exposure to ionizing radiation(IR)often causes acute and chronic oxidative damages to normal cells and organs,leading to serious physiological and even life-threatening consequences.Amifostine(AMF)is a validated radioprotectant extensively applied in radiation and chemotherapy medicine,but the short half-life limits its bioavailability and clinical applications,remaining as a great challenge to be addressed.DNAassembled nanostructures especially the tetrahedral framework nucleic acids(tFNAs)are promising nanocarriers with preeminent biosafety,low biotoxicity,and high transport efficiency.The tFNAs also have a relative long-term maintenance for structural stability and excellent endocytosis capacity.We therefore synthesized a tFNA-based delivery system of AMF for multi-organ radioprotection(tFNAs@AMF,also termed nanosuit).By establishing the mice models of accidental total body irradiation(TBI)and radiotherapy model of Lewis lung cancer,we demonstrated that the nanosuit could shield normal cells from IR-induced DNA damage by regulating the molecular biomarkers of anti-apoptosis and anti-oxidative stress.In the accidental total body irradiation(TBI)mice model,the nanosuit pretreated mice exhibited satisfactory alteration of superoxide dismutase(SOD)activities and malondialdehyde(MDA)contents,and functional recovery of hematopoietic system,reducing IRinduced pathological damages of multi-organ and safeguarding mice from lethal radiation.More importantly,the nanosuit showed a selective radioprotection of the normal organs without interferences of tumor control in the radiotherapy model of Lewis lung cancer.Based on a conveniently available DNA tetrahedron-based nanocarrier,this work presents a high-efficiency delivery system of AMF with the prolonged half-life and enhanced radioprotection for multi-organs.Such nanosuit pioneers a promising strategy with great clinical translation potential for radioactivity protection.
文摘Accurate plant species classification is essential for many applications,such as biodiversity conservation,ecological research,and sustainable agricultural practices.Traditional morphological classification methods are inherently slow,labour-intensive,and prone to inaccuracies,especiallywhen distinguishing between species exhibiting visual similarities or high intra-species variability.To address these limitations and to overcome the constraints of imageonly approaches,we introduce a novel Artificial Intelligence-driven framework.This approach integrates robust Vision Transformer(ViT)models for advanced visual analysis with a multi-modal data fusion strategy,incorporating contextual metadata such as precise environmental conditions,geographic location,and phenological traits.This combination of visual and ecological cues significantly enhances classification accuracy and robustness,proving especially vital in complex,heterogeneous real-world environments.The proposedmodel achieves an impressive 97.27%of test accuracy,andMean Reciprocal Rank(MRR)of 0.9842 that demonstrates strong generalization capabilities.Furthermore,efficient utilization of high-performance GPU resources(RTX 3090,18 GB memory)ensures scalable processing of highdimensional data.Comparative analysis consistently confirms that ourmetadata fusion approach substantially improves classification performance,particularly formorphologically similar species,and through principled self-supervised and transfer learning from ImageNet,the model adapts efficiently to new species,ensuring enhanced generalization.This comprehensive approach holds profound practical implications for precise conservation initiatives,rigorous ecological monitoring,and advanced agricultural management.
文摘BACKGROUND Single-ventricle congenital heart disease often requires the Fontan procedure,which can lead to Fontan-associated liver disease(FALD)and multi-organ failure.Combined heart-liver transplantation(CHLT)is a potential lifesaving option for these patients.AIMTo investigate the outcomes and complications of CHLT in patients with failing Fontan physiology.METHODSSeven retrospective studies of 121 patients undergoing CHLT were systematically reviewed. Quality was assessedwith the Newcastle-Ottawa Scale. A meta-analysis using random-effects models to calculate odds ratios (ORs) ormean differences (MDs) with 95% confidence intervals.RESULTSThe pooled 30-day, 1-year, 5-year, and 10-year survival rates after CHLT were 92.6%, 86.78%, 81.17%, and 77.8%,respectively. The mean intensive care unit and total hospital lengths of stay were 8.46 and 28.16 days. Meanischemic time was 267.29 minutes, while cardiopulmonary bypass time was 260.27 minutes. Infections (30%), renalreplacement therapy (36.84%), and graft rejection (12.34%) were notable complications. Compared to orthotopicheart transplantation (OHT), CHLT significantly reduced mortality (OR: 0.30, P = 0.009) and ischemic time (MD:–65.93 minutes), with no major differences in perioperative morbidity.CONCLUSIONCHLT offers a survival advantage over OHT for patients with FALD and failing Fontan physiology. Futureprospective studies are warranted to refine eligibility and improve long-term survival.
基金funded by the Henan Science and Technology research project(222103810042)Support by the open project of scientific research platform of grain information processing center of Henan University of Technology(KFJJ-2021-108)+1 种基金Support by the innovative funds plan of Henan University of Technology(2021ZKCJ14)Henan University of Technology Youth Backbone Teacher Program.
文摘The application of transformer networks and feature fusion models in medical image segmentation has aroused considerable attention within the academic circle.Nevertheless,two main obstacles persist:(1)the restrictions of the Transformer network in dealing with locally detailed features,and(2)the considerable loss of feature information in current feature fusion modules.To solve these issues,this study initially presents a refined feature extraction approach,employing a double-branch feature extraction network to capture complex multi-scale local and global information from images.Subsequently,we proposed a low-loss feature fusion method-Multi-branch Feature Fusion Enhancement Module(MFFEM),which realizes effective feature fusion with minimal loss.Simultaneously,the cross-layer cross-attention fusion module(CLCA)is adopted to further achieve adequate feature fusion by enhancing the interaction between encoders and decoders of various scales.Finally,the feasibility of our method was verified using the Synapse and ACDC datasets,demonstrating its competitiveness.The average DSC(%)was 83.62 and 91.99 respectively,and the average HD95(mm)was reduced to 19.55 and 1.15 respectively.
