AIM:To study if HER-2 overexpression by locally advanced esophageal cancers increase the chance of brain metastasis following esophagectomy.METHODS:We retrospectively reviewed the medical records of esophageal cancer ...AIM:To study if HER-2 overexpression by locally advanced esophageal cancers increase the chance of brain metastasis following esophagectomy.METHODS:We retrospectively reviewed the medical records of esophageal cancer patients who underwent esophagectomy at University of Iowa Hospitals and Clinics between 2000 and 2010.Data analyzed consisted of demographic and clinical variables.The brain metastasis tissue was assayed for HER-2 overexpression utilizing the FDA approved DAKO Hercept Test.RESULTS:One hundred and forty two patients were reviewed.Median age was 64 years(36-86 years).Eighty eight patients(62%) received neoadjuvant chemoradiotherapy.Pathological complete and partial responses were achieved in 17(19%) and 71(81%) patients.Cancer relapsed in 43/142(30%) patients.The brain was the first site of relapse in 9/43 patients(21%,95% CI:10%-36%).HER-2 immunohistochemistry testing of the brain metastasis tissue showed that 5/9(56%) cases overexpressed HER-2(3+ staining).CONCLUSION:HER-2 overexpression might be associated with increased risk of brain metastasis in esophageal cancer patients following esophagectomy.Further studies will be required to validate this observation.展开更多
Objective The aim of this study was to define the maximum-tolerated dose (MTD) and observe the toxicity of escalating topotecan combined whole brain radiotherapy for brain metastasis in lung cancer.
目的分析基于多模态磁共振成像(Magnetic Resonance Imaging,MRI)影像组学鉴别胶质瘤及单发脑转移瘤的研究进展,得出提升鉴别准确性的要素。方法通过检索PubMed、Web of Science及FMRS外文医学信息资源检索平台3个数据库,根据纳入排除标...目的分析基于多模态磁共振成像(Magnetic Resonance Imaging,MRI)影像组学鉴别胶质瘤及单发脑转移瘤的研究进展,得出提升鉴别准确性的要素。方法通过检索PubMed、Web of Science及FMRS外文医学信息资源检索平台3个数据库,根据纳入排除标准,对纳入的文章提取数据来源、患者数量、MRI设备、MRI序列、肿瘤分割软件、分割方式、分割范围、分割类型、特征提取方法、筛选方法、机器学习分类器、最优的机器学习分类器等数据进行综合分析。结果最终纳入12篇文献进行分析,大多数研究选择MRI传统结构序列,特征筛选方法选择最多的是最小绝对收缩和选择算子,使用最多且表现最佳的机器学习分类器为随机森林。结论MRI影像组学方法在鉴别胶质瘤及单发脑转移瘤方面展现出了较高的准确性,为临床决策提高了较大帮助。展开更多
目的本研究旨在结合传统MRI序列及增强检查,提取多模态高通量影像组学特征并联合语义特征,使用不同的机器学习分类器构建不同的模型并绘制列线图来鉴别高级别胶质瘤(high-grade glioma,HGG)和单发性脑转移瘤(solitary brain metastasis,...目的本研究旨在结合传统MRI序列及增强检查,提取多模态高通量影像组学特征并联合语义特征,使用不同的机器学习分类器构建不同的模型并绘制列线图来鉴别高级别胶质瘤(high-grade glioma,HGG)和单发性脑转移瘤(solitary brain metastasis,SBM)。材料与方法本研究对101名患者的多参数MR图像进行了回顾性分析,由两位资深医师标定肿瘤感兴趣区,然后对每个序列分别提取影像组学特征后进行组合,共提取428组影像组学特征。为消除人为标定差异,进行组内相关系数一致性检验,并运用最大相关最小冗余算法选取最具相关性的特征,然后进一步通过最小绝对收缩和选择算子算法筛除冗余特征。本研究采用支持向量机、逻辑回归、随机森林及K近邻四种算法建立分类模型。结合放射科医生评估的七项语义特征,通过卡方检验和多因素分析去除差异无统计学意义的语义特征。然后结合组学特征建立综合模型并绘制列线图。最终,评价各模型的诊断能力,以确定最优分类器。结果HGG及SBM患者建立的影像组学模型中LR的受试者工作特征曲线下面积(area under the curve,AUC)值最高,训练集与测试集分别为0.90和0.90。语义特征建立的模型中随机森林模型性能最好,训练集和测试集AUC分别为0.82和0.87。语义特征联合影像组学评分后采用逻辑回归建立的模型性能最好,训练集和测试集AUC分别为0.91和0.92。结论本研究使用影像组学机器学习分类器并联合其他图像语义特征绘制列线图对HGG及SBM进行鉴别,这是一种非侵入性方法,具有较好的准确性,为临床决策和实践提供了较大的帮助。展开更多
基金Supported by The Iowa Leukemia and Cancer Research Fund at University of Iowa Hospitals and clinics
文摘AIM:To study if HER-2 overexpression by locally advanced esophageal cancers increase the chance of brain metastasis following esophagectomy.METHODS:We retrospectively reviewed the medical records of esophageal cancer patients who underwent esophagectomy at University of Iowa Hospitals and Clinics between 2000 and 2010.Data analyzed consisted of demographic and clinical variables.The brain metastasis tissue was assayed for HER-2 overexpression utilizing the FDA approved DAKO Hercept Test.RESULTS:One hundred and forty two patients were reviewed.Median age was 64 years(36-86 years).Eighty eight patients(62%) received neoadjuvant chemoradiotherapy.Pathological complete and partial responses were achieved in 17(19%) and 71(81%) patients.Cancer relapsed in 43/142(30%) patients.The brain was the first site of relapse in 9/43 patients(21%,95% CI:10%-36%).HER-2 immunohistochemistry testing of the brain metastasis tissue showed that 5/9(56%) cases overexpressed HER-2(3+ staining).CONCLUSION:HER-2 overexpression might be associated with increased risk of brain metastasis in esophageal cancer patients following esophagectomy.Further studies will be required to validate this observation.
文摘Objective The aim of this study was to define the maximum-tolerated dose (MTD) and observe the toxicity of escalating topotecan combined whole brain radiotherapy for brain metastasis in lung cancer.
文摘目的分析基于多模态磁共振成像(Magnetic Resonance Imaging,MRI)影像组学鉴别胶质瘤及单发脑转移瘤的研究进展,得出提升鉴别准确性的要素。方法通过检索PubMed、Web of Science及FMRS外文医学信息资源检索平台3个数据库,根据纳入排除标准,对纳入的文章提取数据来源、患者数量、MRI设备、MRI序列、肿瘤分割软件、分割方式、分割范围、分割类型、特征提取方法、筛选方法、机器学习分类器、最优的机器学习分类器等数据进行综合分析。结果最终纳入12篇文献进行分析,大多数研究选择MRI传统结构序列,特征筛选方法选择最多的是最小绝对收缩和选择算子,使用最多且表现最佳的机器学习分类器为随机森林。结论MRI影像组学方法在鉴别胶质瘤及单发脑转移瘤方面展现出了较高的准确性,为临床决策提高了较大帮助。
文摘目的本研究旨在结合传统MRI序列及增强检查,提取多模态高通量影像组学特征并联合语义特征,使用不同的机器学习分类器构建不同的模型并绘制列线图来鉴别高级别胶质瘤(high-grade glioma,HGG)和单发性脑转移瘤(solitary brain metastasis,SBM)。材料与方法本研究对101名患者的多参数MR图像进行了回顾性分析,由两位资深医师标定肿瘤感兴趣区,然后对每个序列分别提取影像组学特征后进行组合,共提取428组影像组学特征。为消除人为标定差异,进行组内相关系数一致性检验,并运用最大相关最小冗余算法选取最具相关性的特征,然后进一步通过最小绝对收缩和选择算子算法筛除冗余特征。本研究采用支持向量机、逻辑回归、随机森林及K近邻四种算法建立分类模型。结合放射科医生评估的七项语义特征,通过卡方检验和多因素分析去除差异无统计学意义的语义特征。然后结合组学特征建立综合模型并绘制列线图。最终,评价各模型的诊断能力,以确定最优分类器。结果HGG及SBM患者建立的影像组学模型中LR的受试者工作特征曲线下面积(area under the curve,AUC)值最高,训练集与测试集分别为0.90和0.90。语义特征建立的模型中随机森林模型性能最好,训练集和测试集AUC分别为0.82和0.87。语义特征联合影像组学评分后采用逻辑回归建立的模型性能最好,训练集和测试集AUC分别为0.91和0.92。结论本研究使用影像组学机器学习分类器并联合其他图像语义特征绘制列线图对HGG及SBM进行鉴别,这是一种非侵入性方法,具有较好的准确性,为临床决策和实践提供了较大的帮助。