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
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
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
With the support of the National Natural Science Foundation of China and the Ministry of Science and Technology of China,the research teams led by Prof.Gao Hua(高华)from Tongji University,and Prof.Filippo Giancotti at...With the support of the National Natural Science Foundation of China and the Ministry of Science and Technology of China,the research teams led by Prof.Gao Hua(高华)from Tongji University,and Prof.Filippo Giancotti at Memorial Sloan Kettering Cancer Center,reported recently on the mechanism of multiorgan site metastatic creactivation,which was published in Cell(2016,166:47—62).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
为解决多器官分割中受大小不一、形状多样、几何结构复杂等因素的影响,提出了一种基于MFSA-Net(multi-scale frequency spatial attention network)的多器官分割方法。利用多层级、多方向频域分解获取不同尺度的多器官频域特征表达,以...为解决多器官分割中受大小不一、形状多样、几何结构复杂等因素的影响,提出了一种基于MFSA-Net(multi-scale frequency spatial attention network)的多器官分割方法。利用多层级、多方向频域分解获取不同尺度的多器官频域特征表达,以有效扩大感受野并提高网络浅层语义特征的辨识性;提出多层次门控注意力机制,实现局部细粒度特征和长距离依赖的融合,聚焦关键目标并抑制背景区域;针对器官的结构差异和多样性,设计了方向增强双分支空间注意力模块,以深度融合边缘像素的空间位置和灰度分布特征,提高模型的空间特性捕获能力。实验结果表明,所提方法可以有效分割尺度差异大、结构复杂的多器官,在Synapse和ACDC数据集的平均DSC分别达到了81.66%和91.61%,优于现有主流方法。展开更多
针对腹部部分注释数据集的嗜铬细胞瘤图像分割缺乏不同器官间的特征学习,导致分割中难以准确区分肿瘤及周边器官边缘的问题,提出一种基于多尺度与空间频率特征的嗜铬细胞瘤图像分割网络(MF-Net)。首先,构建多尺度空间频率通道注意力模块...针对腹部部分注释数据集的嗜铬细胞瘤图像分割缺乏不同器官间的特征学习,导致分割中难以准确区分肿瘤及周边器官边缘的问题,提出一种基于多尺度与空间频率特征的嗜铬细胞瘤图像分割网络(MF-Net)。首先,构建多尺度空间频率通道注意力模块(MSFCA)对图像频域信息和相邻编码器的多尺度特征图进行加权融合,以强化器官间纹理和边界特征的捕捉,从而突出肿瘤区域的特征表示能力;其次,引入上采样多尺度特征融合模块(UMFF)通过结合上采样得到的不同尺度特征图,增强模型对图像中不同大小对象的识别能力;最后,利用自适应目标损失函数(AOb)对有注释腹部器官标签进行损失计算,并根据注释器官类别调整损失权重大小,从而优化分割网络的学习过程。实验结果表明,在腹部器官和嗜铬细胞瘤数据集上,MF-Net的分割准确率相较于单独训练的nnU-Net(no new U-Net)分别提升了3.33和3.18个百分点,而Dice系数(Dice)和归一化表面距离(NSD)分别为89.07%和92.85%;在域外数据集上,MF-Net的Dice和NSD分别为84.66%和90.55%。此外,可视化结果表明,MF-Net能更好地处理嗜铬细胞瘤图像中的复杂背景和模糊边界,为嗜铬细胞瘤的精确诊断和治疗提供了更好的技术支持。展开更多
为探究外界环境因素(光照、大气条件)和传感器参数(光谱与空间分辨率)对不同来源光谱数据反演土壤有机碳(SOC)精度的影响机制,以内蒙古自治区东北部为研究区,采集160个表层土壤(0~20 cm)SOC样品,并同步获取近端高光谱(室内人造光源与室...为探究外界环境因素(光照、大气条件)和传感器参数(光谱与空间分辨率)对不同来源光谱数据反演土壤有机碳(SOC)精度的影响机制,以内蒙古自治区东北部为研究区,采集160个表层土壤(0~20 cm)SOC样品,并同步获取近端高光谱(室内人造光源与室外太阳光源)以及星载多光谱(Landsat-8、Sentinel-2)与高光谱(ZY1-02D)数据,使用随机森林(RF)与支持向量机(SVM)算法,分别构建SOC反演模型,通过系统比较不同数据源的模型性能,分析环境因素与传感器参数对SOC反演精度的影响。结果显示:室内人造光源因光谱信号稳定、可控性强,其反演精度略优于室外太阳光源,但二者差异较小,表明自然光照波动对SOC反演的影响有限;近地高光谱数据反演精度显著高于卫星多光谱与高光谱数据,主要因卫星数据受大气散射、水汽吸收及混合像元等问题干扰;在卫星数据中,高光谱卫星ZY1-02D的反演精度高于多光谱卫星,而Sentinel-2较Landsat-8的空间分辨率提升(10 m vs 30 m)对模型性能改善有限,说明光谱分辨率对SOC精度的贡献大于空间分辨率。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.
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With the support of the National Natural Science Foundation of China and the Ministry of Science and Technology of China,the research teams led by Prof.Gao Hua(高华)from Tongji University,and Prof.Filippo Giancotti at Memorial Sloan Kettering Cancer Center,reported recently on the mechanism of multiorgan site metastatic creactivation,which was published in Cell(2016,166:47—62).
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.
文摘为解决多器官分割中受大小不一、形状多样、几何结构复杂等因素的影响,提出了一种基于MFSA-Net(multi-scale frequency spatial attention network)的多器官分割方法。利用多层级、多方向频域分解获取不同尺度的多器官频域特征表达,以有效扩大感受野并提高网络浅层语义特征的辨识性;提出多层次门控注意力机制,实现局部细粒度特征和长距离依赖的融合,聚焦关键目标并抑制背景区域;针对器官的结构差异和多样性,设计了方向增强双分支空间注意力模块,以深度融合边缘像素的空间位置和灰度分布特征,提高模型的空间特性捕获能力。实验结果表明,所提方法可以有效分割尺度差异大、结构复杂的多器官,在Synapse和ACDC数据集的平均DSC分别达到了81.66%和91.61%,优于现有主流方法。
文摘针对腹部部分注释数据集的嗜铬细胞瘤图像分割缺乏不同器官间的特征学习,导致分割中难以准确区分肿瘤及周边器官边缘的问题,提出一种基于多尺度与空间频率特征的嗜铬细胞瘤图像分割网络(MF-Net)。首先,构建多尺度空间频率通道注意力模块(MSFCA)对图像频域信息和相邻编码器的多尺度特征图进行加权融合,以强化器官间纹理和边界特征的捕捉,从而突出肿瘤区域的特征表示能力;其次,引入上采样多尺度特征融合模块(UMFF)通过结合上采样得到的不同尺度特征图,增强模型对图像中不同大小对象的识别能力;最后,利用自适应目标损失函数(AOb)对有注释腹部器官标签进行损失计算,并根据注释器官类别调整损失权重大小,从而优化分割网络的学习过程。实验结果表明,在腹部器官和嗜铬细胞瘤数据集上,MF-Net的分割准确率相较于单独训练的nnU-Net(no new U-Net)分别提升了3.33和3.18个百分点,而Dice系数(Dice)和归一化表面距离(NSD)分别为89.07%和92.85%;在域外数据集上,MF-Net的Dice和NSD分别为84.66%和90.55%。此外,可视化结果表明,MF-Net能更好地处理嗜铬细胞瘤图像中的复杂背景和模糊边界,为嗜铬细胞瘤的精确诊断和治疗提供了更好的技术支持。
文摘为探究外界环境因素(光照、大气条件)和传感器参数(光谱与空间分辨率)对不同来源光谱数据反演土壤有机碳(SOC)精度的影响机制,以内蒙古自治区东北部为研究区,采集160个表层土壤(0~20 cm)SOC样品,并同步获取近端高光谱(室内人造光源与室外太阳光源)以及星载多光谱(Landsat-8、Sentinel-2)与高光谱(ZY1-02D)数据,使用随机森林(RF)与支持向量机(SVM)算法,分别构建SOC反演模型,通过系统比较不同数据源的模型性能,分析环境因素与传感器参数对SOC反演精度的影响。结果显示:室内人造光源因光谱信号稳定、可控性强,其反演精度略优于室外太阳光源,但二者差异较小,表明自然光照波动对SOC反演的影响有限;近地高光谱数据反演精度显著高于卫星多光谱与高光谱数据,主要因卫星数据受大气散射、水汽吸收及混合像元等问题干扰;在卫星数据中,高光谱卫星ZY1-02D的反演精度高于多光谱卫星,而Sentinel-2较Landsat-8的空间分辨率提升(10 m vs 30 m)对模型性能改善有限,说明光谱分辨率对SOC精度的贡献大于空间分辨率。
