瑞秋是由罗莎莉 b ·海特研究生奖学金和美国军团辅助奖学金资助的。卡洛斯卡德纳斯已由伊尔克什坦博士在生物医学科学研究金的资助。野生山羊的发展由 R03 CA178495 的资助。

1. 安装山羊
注意: 要安装源代码版本, 请转到步骤1.1。或者, 要安装 stand-alone 版本, 请转到步骤1.2。
<ol><li>
源代码版本
	<ol>
<li>转到野山羊源代码版本网站3。下载 "IBEX_Source. zip" 和 "How_to_use pdf" 文件。在 "How_to_use pdf" 文件中查找必备使用最新的野山羊版本。 注意: 野山羊只在32位和64位 Matlab 版本中分别工作2011a 和2014b。</li>
		<li>下载完成后, 解压 "IBEX_Source. zip", 并将 \n IBEX_Source 文件夹添加到本地路径。 注意: 有关如何添加路径的说明, 可在 "添加路径"26的 "软件引用" 页上找到。</li>
		<li>在命令窗口中键入 "IBEXMain" 以启动野山羊。</li>
	</ol>
</li>
	<li>
独立版本
	<ol>
<li>去 stand-alone 版本网站4。如果第一次安装野山羊, 请转到 "依赖性" 文件夹并下载/安装 "MCRInstaller.exe"、"vc2005redist_x86_new" 和 "vc2012redist_x86 .exe" 文件。从主页, 下载 "IBEX.exe", "野山羊", "野山羊" 和 "How_to_use. pdf" 文件到同一个文件夹。查看 "How_to_use pdf" 文件, 必备使用最新的野山羊版本。</li>
		<li>双击 "IBEX.exe" 以启动野山羊。</li>
	</ol>
</li>
</ol>2. 设置位置
注意: 图像被导入到这个集合位置, 并且这项研究的数据也存储在这里。在重新时, 野山羊使用最以前应用的位置作为默认位置。
<ol><li>单击 "位置" 图标 (图 1)。</li>
	<li>选择用户或双击 "新用户" 以创建新的用户文件夹。如果创建新的用户文件夹, 请在新窗口中输入名称, 然后单击 "确定" 按钮。</li>
	<li>选择所选用户的站点或双击 "新建站点" 以创建新的站点文件夹。如果创建新的用户文件夹, 请在新窗口中输入名称, 然后单击 "确定" 按钮。</li>
	<li>单击底部的 "确定" 按钮。</li>
</ol>3. 导入图像
<ol><li>单击 "导入" 图标 (图 1)。</li>
	<li>通过单击格式的名称, 选择 DICOM 或 Pinnacle9 (顶峰文件版本 9) 格式。要导入 DICOM 图像, 可进入步骤3.3.1。导入 Pinnacle9 文件转到步骤3.3.2。</li>
	<li>单击 "下一步" 按钮。<ol>
<li>导入 DICOM 图像 注意: 要单独导入患者, 请到步骤3.3.1.1。同时导入多个患者去3.3.1.2。<ol>
<li>通过目录选择病人文件夹, 逐个导入患者。<ol>
<li>单击列出的目录旁边的 "..." 按钮, 选择包含 dicom 图像和辐射结构的患者文件夹 (可选)。 注意: 尽管使用患者文件导入结构集只是可选的, 但强烈建议您这样做。野山羊在它里面有一个轮廓平台, 但是对于大型数据集来说这有点不切实际。野山羊可以容纳从商业软件平台的结构集, 这是熟悉的轮廓工具的辐射肿瘤学家, 这使得工作流程更容易。这通常是如何在研究中使用野山羊。</li>
				<li>单击左下角的 "导入" 按钮一旦野山羊完成了 DICOM 文件的搜索, 患者和详细信息框将被填充。</li>
				<li>对每个病人重复步骤 3.3. 1.1. 1-2。</li>
				<li>在所有患者导入后, 单击 "退出" 按钮。</li>
			</ol>
</li>
			<li>通过检查右上角的 "批处理文件夹" 框, 立即导入所有患者。 注: 所有患者必须有一个单独的文件夹, 其中包含各自的 DICOM 文件。<ol>
<li>单击列出的目录旁边的 "..." 按钮以选择包含所有患者文件夹的文件夹, 其相应的 dicom 图像和辐射结构设置了 dicom 文件 (可选)。</li>
				<li>单击 "导入" 按钮。患者将按顺序导入。在所有患者导入后, 单击 "退出" 按钮。</li>
			</ol>
</li>
		</ol>
</li>
		<li>顶点文件<ol>
<li>在 "\n 进出口 \n ImportModule \ Pinnacle9 \ Pinnacle9ImportMain. INI" 文件中配置 "顶级主机和数据库"。在 "导入模块" 框中选择 "顶点" 之前, 单击 "配置" 按钮。</li>
			<li>选择合适的顶点主机和数据库。</li>
			<li>输入患者的林、姓氏或名字, 然后单击窗口中的其他位置。</li>
			<li>单击 "查询" 按钮。</li>
			<li>在新窗口中选择病人, 然后单击 "转移" 按钮。</li>
			<li>单击新窗口中该患者所需图像集的框, 然后单击 "确定" 按钮。</li>
			<li>在标记为 "成功导入数据" 的新窗口中单击 "确定" 按钮。</li>
			<li>在所有患者导入后, 单击 "退出" 按钮。</li>
		</ol>
</li>
	</ol>
</li>
</ol>4. 观看图片和感兴趣的区域 (roi)
<ol><li>单击 "数据" 图标 (图 1)。点击所需的病人文件打开在 "选择病人" 部分的 GUI (上半)。</li>
	<li>单击所需病人文件的图像集, 在 GUI 的 "选择图像集 (s)" 部分打开 (下半部)。单击 "打开" 按钮。</li>
	<li>使用图像下方的箭头滚动图像, 这是显示在轴向, 冠状, 和矢状视图 (从左到右)。</li>
	<li>单击 "缩放" 按钮 (图 2) 可放大图像。在图像平面上绘制一个框以进行缩放。右键单击可缩小。</li>
	<li>通过选择 "交集" 按钮 (图 2) 打开本地化。 注意: 显示的线条显示该切片在每个平面中的位置。使用箭头滚动时, 这些线条会移动。</li>
	<li>单击 "标尺" 按钮 (图 2) 以测量距离。点击并按住鼠标左键测量两个点之间的兴趣。松开鼠标以从显示区域中移除测量值。</li>
	<li>单击 "CT Num" 按钮 (图 2) 以测量体素的值。单击并按住鼠标左键对感兴趣的体素, 该值将弹出在 GUI 的左侧, 在颜色刻度下面。松开鼠标以从显示区域中移除测量值。</li>
	<li>单击 "W/L" 按钮 (图 2) 以窗口/级别显示图像。另一个窗口会弹出。将左侧和右侧拖动到所需区域, 或在新窗口底部的窗口和级别框中手动输入窗口/级别。使用左侧的第一个下拉菜单选择不同的窗口/级别 (图 2): 有8的 CT 和1的 PET。</li>
	<li>使用左侧的第二个下拉菜单选择不同的颜色刻度 (图 2): 有9选项可供选择。</li>
	<li>通过单击 ROI 旁边的框以使其在图像上可见, 或者单击 "所有 roi" 按钮打开所有患者 roi, 可以直观显示 roi。</li>
</ol>5. 编辑 ROI
<ol><li>通过单击左上角或底部中心的 "编辑 roi" 按钮来编辑 roi。通过单击其名称旁边的框来选择要编辑的轮廓。</li>
	<li>使用 "微移轮廓" 按钮 (图 3) 可按已绘制的轮廓来按下或出。调整在 "微移轮廓" 按钮旁边标记为 "D" 的框中使用的圆的大小。</li>
	<li>使用 "剪切轮廓" 按钮 (图 3) 删除整个轮廓切片。单击并按住鼠标左键并在要移除的 ROI 周围绘制一个框。</li>
	<li>绘制轮廓 注意: 转到步骤 5.4.1, 通过连接点绘制轮廓。通过自由手去5.4.2 画轮廓。<ol>
<li>连接点: 使用 "绘制轮廓 (1)" 按钮 (图 3) 在每个切片上绘制轮廓, 通过单击轮廓线周围的点以直线连接。单击所绘制的第一个点, 完成该切片的 ROI。</li>
		<li>自由手: 使用 "绘制轮廓 (2)" 按钮 (图 3) 以自由手绘制轮廓。按住鼠标左键在切片上绘制轮廓。通过返回到绘制 ROI 的开始处, 然后松开鼠标左键, 完成该切片上的轮廓。</li>
	</ol>
</li>
	<li>单击 "插补轮廓" 按钮 (图 3) 可在切片之间插入 roi。</li>
	<li>点击 "复制 roi" 按钮来复制 roi。</li>
	<li>通过选择多个 roi, 然后单击 "合并 ROI" 按钮, 合并 roi。</li>
	<li>单击 "删除 roi" 按钮以删除当前选定的 roi。</li>
	<li>单击 "创建 roi" 以创建新的 roi, 这将导致弹出窗口。输入 ROI 的名称, 然后单击 "确定" 按钮。单击 "保存" 按钮。单击 "退出" 按钮返回患者查看器。</li>
</ol>6. 数据集中的轮廓
<ol><li>查看数据集中的轮廓<ol>
<li>单击 "显示数据集" 按钮以查看数据集中的轮廓。单击要查看的数据集的名称。单击 "打开" 按钮。使用其名称旁边的框选择患者轮廓。单击 "删除"、"移动" 或 "复制" 按钮, 具体取决于该轮廓所需的功能。完成查看数据集后, 关闭数据集窗口。</li>
	</ol>
</li>
	<li>向数据集添加轮廓<ol>
<li>选择要添加到数据集的等高线, 请单击其名称旁边的复选框, 然后单击 "添加到数据集" 按钮。单击数据集的名称以添加轮廓或单击新数据集的 "新建" 按钮。如果选择了 "新建", 请在新窗口中输入数据集的名称。单击 "确定" 按钮。</li>
	</ol>
</li>
	<li>单击 "导入 roi" 按钮导入一个顶点版本 9. 如果在3节中未加载等高线, roi 文件。<ol>
<li>单击 "..." 按钮以选择该文件。单击 "导入" 按钮。</li>
	</ol>
</li>
	<li>单击 "导出 roi" 按钮导出 roi。<ol>
<li>单击 "..." 按钮以选择将在其中放置导出的 roi 的目录。单击为导出的 roi 首选的格式的名称。如果首选, 请输入匿名信息。单击 "导出" 按钮。 注意: 预设不匿名执行。</li>
	</ol>
</li>
	<li>单击 "退出" 按钮返回患者和扫描列表。</li>
</ol>7. 创建功能集
<ol><li>点击 "功能" 图标。</li>
	<li>如果需要, 添加预处理。<ol>
<li>单击 "Step1: 预处理" 下的 "添加" 按钮。从新窗口中的下拉菜单中选择 "预处理" 选项。</li>
		<li>点击 "i" 下的 "段" 来选择预处理参数。单击参数新窗口中 "值" 列下的数字以更改它。键入新参数值, 然后单击 "确定" 按钮。</li>
		<li>单击右上角的 "问号" 按钮, 以描述预处理方法和特定参数的预处理。</li>
		<li>单击 "添加" 按钮。选择预处理步骤, 然后单击 "删除" 按钮以删除不需要的预处理步骤。</li>
	</ol>
</li>
	<li>添加所需的功能。<ol>
<li>从 "步骤 2: 功能类别:" 下拉菜单中选择功能类别。对多个类别重复步骤。 注意: 一次只能添加一种功能类别。如果需要, 可以将预处理和特征类别的不同组合添加到同一功能集。<ol>
<li>选取 "GrayLevelCooccurenceMatrix25" 和 "NeighborIntensityDifference25" 特征类别分别计算2.5D 中的灰度共生矩阵和邻域强度差矩阵, 并通过计算矩阵分别在每个切片上, 然后汇总所有矩阵。</li>
			<li>选取 "GrayLevelCooccurenceMatrix3" 和 "NeighborIntensityDifference3" 特征类别分别计算3D 中的灰度共生矩阵和邻域强度差分矩阵。</li>
		</ol>
</li>
		<li>单击 "i" 在 "段落" 下, 为该预处理选择的参数。单击右上角的 "问号" 按钮, 以描述预处理方法和参数。<ol>
<li>键入新参数值, 然后单击 "确定" 按钮。</li>
		</ol>
</li>
		<li>单击 "测试" 按钮以查看功能类别或特定功能。单击所需功能或类别旁边的按钮。<ol>
<li>选择要查看测试的数据集, 然后单击 "打开" 按钮。选中所选数据集中的患者旁边的复选框, 查看测试, 然后单击 "测试" 按钮。</li>
		</ol>
</li>
		<li>取消选中所选类别的不需要的功能;选择类别后, 将选择所有功能。单击 "功能:" 下的 "Step2: 功能" 下的单词, 取消选中所有功能。</li>
		<li>单击 "添加到功能集" 按钮, 添加所有选定的预处理功能。<ol>
<li>选择要添加功能的功能集, 然后单击 "打开" 按钮, 或单击 "新建" 按钮将功能添加到新功能集。如果创建新的功能集, 请在新窗口中输入功能集的名称, 然后单击 "确定" 按钮。</li>
		</ol>
</li>
	</ol>
</li>
	<li>单击 "显示功能集" 按钮以查看具有相应预处理技术的功能, 以查看功能集中的功能。<ol>
<li>选择要查看的功能集, 然后单击 "打开" 按钮, 或单击 "新建" 按钮以创建新的功能集。如果创建新的功能集, 请在新窗口中输入功能集的名称, 然后单击 "确定" 按钮。</li>
	</ol>
</li>
	<li>单击 "显示数据集" 按钮以查看当前数据集。<ol>
<li>选择要查看的数据集, 然后单击 "打开" 按钮, 或单击 "新建" 按钮以创建新的数据集。如果创建新的数据集, 请在新窗口中输入数据集的名称, 然后单击 "确定" 按钮。</li>
	</ol>
</li>
	<li>单击 "退出" 按钮。</li>
</ol>8. 输出特性
<ol><li>单击 "结果" 图标。单击数据集以运行 "步骤 1: 数据集" 下的功能。单击功能集以在 "步骤 2: 功能集" 下的选定数据上运行。</li>
	<li>单击 "查看数据" 按钮以查看选定的数据集。单击 "查看功能" 按钮可查看所选功能集。</li>
	<li>单击 "计算 & 保存结果" 按钮。输入结果的文件名, 然后单击 "保存" 按钮。</li>
</ol>9. 统计模型的建立
<ol><li>打开保存的结果文件。 注意: 除非在步骤8.4 中另行指定, 否则通常在 C: \n DataIbex \ [步骤2.2 中的选定用户] \ [步骤2.3 中的选定站点] \n 1FeatureResultSet_Result 下。</li>
	<li>使用软件中所需的统计测试或模型构建中的不同选项卡中的数据。 注意: 协议可以在任何时候暂停。但是, 在完成特定图标所需的所有步骤后, 最方便的方法是例如, 完成功能图标下的所有7节。</li>
</ol>

<ol>
	<li>Lambin, P., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Radiomics:+extracting+more+information+from+medical+images+using+advanced+feature+analysis.">Radiomics: extracting more information from medical images using advanced feature analysis.</a> EJC. 48, 441-446 (2012).</li><li>Zhang, L., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=IBEX:+an+open+infrastructure+software+platform+to+facilitate+collaborative+work+in+radiomics.">IBEX: an open infrastructure software platform to facilitate collaborative work in radiomics.</a> Med Phys. 42, 1341-1353 (2015).</li><li>Haralick, R. M., Shanmugam, K. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Textural+features+for+image+classification.">Textural features for image classification.</a> IEEE Trans Syst Man Cybern. , 610-621 (1973).</li><li>Galloway, M. M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Texture+analysis+using+gray+level+run+lengths.">Texture analysis using gray level run lengths.</a> Comp Graphics and Im Proc. 4, 172-179 (1975).</li><li>Tang, X. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Texture+information+in+run-length+matrices.">Texture information in run-length matrices.</a> IEEE Trans on Im Proc. 7, 1602-1609 (1998).</li><li>Amadasun, M., King, R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Textural+features+corresponding+to+textural+properties.">Textural features corresponding to textural properties.</a> IEEE Trans Syst Man Cybern. 19, 1264-1274 (1989).</li><li>Fave, X., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Preliminary+investigation+into+sources+of+uncertainty+in+quantitative+imaging+features.">Preliminary investigation into sources of uncertainty in quantitative imaging features.</a> Comp Med Imaging Graph. 44, 54-61 (2015).</li><li>Fave, X., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Can+radiomics+features+be+reproducibly+measured+from+CBCT+images+for+patients+with+non-small+cell+lung+cancer.">Can radiomics features be reproducibly measured from CBCT images for patients with non-small cell lung cancer.</a> Med Phys. 42, 6784-6797 (2015).</li><li>Fave, X., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Impact+of+image+preprocessing+on+the+volume+dependence+and+prognostic+potential+of+radiomics+features+in+non-small+cell+lung+cancer.">Impact of image preprocessing on the volume dependence and prognostic potential of radiomics features in non-small cell lung cancer.</a> Trans Cancer Res. 5, 349-363 (2016).</li><li>Fave, X., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Delta-radiomics+features+for+the+prediction+of+patient+outcomes+in+non-small+cell+lung+cancer.">Delta-radiomics features for the prediction of patient outcomes in non-small cell lung cancer.</a> Scientific Reports. 7, 588 (2017).</li><li>Fried, D. V., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Stage+III+Non-Small+Cell+Lung+Cancer:+Prognostic+Value+of+FDG+PET+Quantitative+Imaging+Features+Combined+with+Clinical+Prognostic+Factors.">Stage III Non-Small Cell Lung Cancer: Prognostic Value of FDG PET Quantitative Imaging Features Combined with Clinical Prognostic Factors.</a> Radiology. 278, 214-222 (2016).</li><li>Fried, D. V., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Potential+Use+of+(18)F-fluorodeoxyglucose+Positron+Emission+Tomography-Based+Quantitative+Imaging+Features+for+Guiding+Dose+Escalation+in+Stage+III+Non-Small+Cell+Lung+Cancer.">Potential Use of (18)F-fluorodeoxyglucose Positron Emission Tomography-Based Quantitative Imaging Features for Guiding Dose Escalation in Stage III Non-Small Cell Lung Cancer.</a> IJROBP. 94, 368-376 (2016).</li><li>Mackin, D., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Measuring+Computed+Tomography+Scanner+Variability+of+Radiomics+Features.">Measuring Computed Tomography Scanner Variability of Radiomics Features.</a> Invest radiol. 50, 757-765 (2015).</li><li>Yang, J., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Uncertainty+analysis+of+quantitative+imaging+features+extracted+from+contrast-enhanced+CT+in+lung+tumors.">Uncertainty analysis of quantitative imaging features extracted from contrast-enhanced CT in lung tumors.</a> Comp Med Imaging Graph. 48, 1-8 (2016).</li><li>van Rossum, P. S., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=The+incremental+value+of+subjective+and+quantitative+assessment+of+18F-FDG+PET+for+the+prediction+of+pathologic+complete+response+to+preoperative+chemoradiotherapy+in+esophageal+cancer.">The incremental value of subjective and quantitative assessment of 18F-FDG PET for the prediction of pathologic complete response to preoperative chemoradiotherapy in esophageal cancer.</a> JNM. 57, 691-700 (2016).</li><li>Hunter, L. A., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=NSCLC+tumor+shrinkage+prediction+using+quantitative+image+features.">NSCLC tumor shrinkage prediction using quantitative image features.</a> Comp Med Imaging Graph. 49, 29-36 (2016).</li><li>Hunter, L. A., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=High+quality+machine-robust+image+features:+identification+in+nonsmall+cell+lung+cancer+computed+tomography+images.">High quality machine-robust image features: identification in nonsmall cell lung cancer computed tomography images.</a> Med Phys. 40, 121916 (2013).</li><li>Fried, D. V., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Prognostic+value+and+reproducibility+of+pretreatment+CT+texture+features+in+stage+III+non-small+cell+lung+cancer.">Prognostic value and reproducibility of pretreatment CT texture features in stage III non-small cell lung cancer.</a> IJROBP. 90, 834-842 (2014).</li><li>Gan, J., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=MO-DE-207B-09:+A+Consistent+Test+for+Radiomics+Softwares.">MO-DE-207B-09: A Consistent Test for Radiomics Softwares.</a> Med Phys. 43, 3706-3706 (2016).</li><li>Klawikowski, S., Christian, J., Schott, D., Zhang, M., Li, X. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=SU-D-207B-07:+Development+of+a+CT-Radiomics+Based+Early+Response+Prediction+Model+During+Delivery+of+Chemoradiation+Therapy+for+Pancreatic+Cancer.">SU-D-207B-07: Development of a CT-Radiomics Based Early Response Prediction Model During Delivery of Chemoradiation Therapy for Pancreatic Cancer.</a> Med Phys. 43, 3350-3350 (2016).</li><li>Huang, W., Tu, S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=SU-F-R-22:+Malignancy+Classification+for+Small+Pulmonary+Nodules+with+Radiomics+and+Logistic+Regression.">SU-F-R-22: Malignancy Classification for Small Pulmonary Nodules with Radiomics and Logistic Regression.</a> Med Phys. 43, 3377-3378 (2016).</li><li>Hanania, A. N., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Quantitative+imaging+to+evaluate+malignant+potential+of+IPMNs.">Quantitative imaging to evaluate malignant potential of IPMNs.</a> Oncotarget. 7, 85776-85784 (2016).</li><li>Court, L. E., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Computational+resources+for+radiomics.">Computational resources for radiomics.</a> Trans Cancer Res. 5, 340-348 (2016).</li><li>. Matlab Add path Available from: <a target="_blank" href="https://www.mathworks.com/help/matlab/ref/addpath.html">https://www.mathworks.com/help/matlab/ref/addpath.html</a> (2017)</li><li>Zhao, B., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Reproducibility+of+radiomics+for+deciphering+tumor+phenotype+with+imaging.">Reproducibility of radiomics for deciphering tumor phenotype with imaging.</a> Sci Rep. 6, 23428 (2016).</li><li>Owens, C., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Reproducibility+and+Robustness+of+Radiomic+Features+Extracted+with+Semi-Automatic+Segmentation+Tools.">Reproducibility and Robustness of Radiomic Features Extracted with Semi-Automatic Segmentation Tools.</a> Med Phys. , (2017).</li><li>Kassner, A., Liu, F., Thornhill, R. E., Tomlinson, G., Mikulis, D. J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Prediction+of+hemorrhagic+transformation+in+acute+ischemic+stroke+using+texture+analysis+of+postcontrast+T1-weighted+MR+images.">Prediction of hemorrhagic transformation in acute ischemic stroke using texture analysis of postcontrast T1-weighted MR images.</a> JMRI. 30, 933-941 (2009).</li><li>. IBEX Google Forum Available from: <a target="_blank" href="https://groups.google.com/forum/#!forum/ibex_users">https://groups.google.com/forum/#!forum/ibex_users</a> (2017)</li></ol>

作者没有竞争的财务利益透露。

野山羊是医学影像 radiomics 研究的有力工具。迄今为止, 它主要用于放射肿瘤学的目的, 由 MD 安德森 radiomics 组进行的研究。野山羊允许操作的 roi 和计算功能在5主要特征类别。源代码版本的野山羊允许用户设计的应用程序, 是不是已经部分的野山羊, 如灰度级区域矩阵的功能。
roi 的主要步骤包括图像的导入、轮廓的绘制、数据集的 roi 选择以及特征集的创建。精确的轮廓是必?...

在医学上, 患者疾病诊断通常包含大量的诊断检查, 如 x 光、超声、计算机断层扫描 (CT)、磁共振成像 (MRI) 和正电子发射断层成像 (PET), 以协助确定病人护理的过程。虽然医生使用这些图像定性地评估病人的诊断, 可能有额外的数量特征, 可以提取, 以指导病人的护理。其基本原理是, 这些特征可能代表了在宏观尺度1上表达的蛋白质和基因组模式。将这些量化信息与当前的临床信息 (如、患者的人口统计数据) 相结合, 可能会允许更多的个性化病人护理。这是 radiomics 背后的理论: 体素水平上的图像特征分析。特征通常分为5大类: 灰度共生矩阵、灰度级运行长度矩阵、邻域强度差分矩阵、直方图和形状。
成像生物标记资源管理器 (野山羊) 是一个开源工具, 用于 radiomics 工作2。图形用户界面 (GUI) 是在 MD 安德森癌症中心开发的, 目的是促进定量特征的提取和计算, 以帮助癌症治疗中的决策。在线可以使用源代码3和 stand-alone4版本。野山羊计算医疗 radiomics 中使用的5种最常见的功能类别, 并可为每个功能类别设置参数。类别有: 灰度共生矩阵5、灰度级运行长度矩阵6、7、强度、邻域强度差矩阵8和形状。由于野山羊是开源的, 它允许跨机构统一的特征提取结果, 以方便地比较不同的 radiomics 研究。在张et al.的初始文件中描述了野山羊中的所有特征2
这份手稿的目的是提供指导, 如何使用野山羊和演示其应用通过同行评议发表的研究从 MD 安德森 radiomics 集团。自2015年向公众发布以来, 野山羊已被用来计算 CT、PET 和 MRI 扫描图像的特征, MD 安德森 radiomics 组, 典型的调查功能, 以改善临床生存模式9,10, 11,12,13,14,15,16,17,18,19,20并由外部机构21、22、23、24。在法院et al.中可以找到可用于 radiomics 研究中未包括在野山羊中的步骤的其他软件工具指南25
对山羊的工作流程的一般介绍将帮助组织数据正确之前开始 radiomics 项目利用野山羊。如果导入 dicom 图像, 则要求每个患者都有自己的 dicom 图像文件夹。DICOM 辐射结构集是可选的, 包括在病人的文件夹, 但建议, 而不是使用的轮廓平台在山羊。为了帮助所有病人导入一个特定的研究, 所有的病人文件夹都可以放在一个文件夹中, 以便所有的数据都可以只用一个步骤导入到野山羊中。如果从顶点导入病人, 最好是将患者计划的结构设置好。由于患者可能有多个图像集和计划在顶峰, 最好是知道哪个图像集和计划是正确的, 然后再导入。如果计算时间是一个问题, 减少病人的图像切片数量可以大大缩短时间。例如, 如果只有肝脏是研究的兴趣, 但病人有全身 CT 扫描, 减少 dicom 切片只在感兴趣的区域范围内可以缩短计算时间 (例如, 将 dicom 从300切片减少到50切片可以采取 1/6 t时间)。有不同的工具可用于执行此切片减少, 从手动到半自动。

<table><tbody><tr><td>Excel</td><td>Microsoft Office</td><td></td><td>Any version of excel should work.</td></tr><tr><td>Matlab</td><td>MathWorks</td><td></td><td>Only use IBEX on 32 bit Matlab 2011a or 64 bit Matlab 2014b.</td></tr></tbody></table>

guidelines and experience using imaging biomarker explorer (ibex) for radiomics

成像生物标志物探险家 (野山羊) 是一个开源工具的医学成像 radiomics 工作。本文的目的是描述如何使用山羊的图形用户界面 (GUI), 并说明如何在临床研究中使用了野山羊的计算功能。野山羊允许输入 dicom 图像与 dicom 辐射治疗结构文件或顶点文件。一旦图像被导入, 在数据选择 GUI 中, 野山羊就有工具来操纵图像的查看, 测量体素值和距离, 并创建和编辑轮廓。野山羊有27预处理和132功能选择来设计特征集。每个预处理和特征类别都有可以更改的参数。从野山羊的输出是一个电子表格, 包含: 1) 每一个功能, 从功能集计算每个轮廓的数据集, 2) 的图像信息的每个轮廓在一个数据集, 和 3) 的预处理和功能与他们所选择的使用摘要参数.从野山羊身上计算的特征已经用于研究不同成像条件和生存模式下的特征的变异性, 以改善目前的临床模型。

来自野山羊的输出是一个电子表格 (参见图 4), 其中包含3选项卡。"结果" 选项卡包含数据集中每个 ROI 的功能值 (图 4A)。"数据信息" 选项卡包含有关从数据集中的每个 ROI 中获取的图像的信息 (图 4B)。"功能信息" 选项卡包含与为特征类别选择的参数和用于该功能类别的预处理 (<strong...

Watch this Scientific Journal Video about Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics at JoVE.com

Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

我们描述了一种用于医学影像 radiomics 研究的开源工具, 以及如何使用这个工具。此外, 一些已出版的作品, 已使用野山羊的不确定性分析和模型建设展示。

使用成像生物标志物探险家 (野山羊) Radiomics 的指南和经验

Imaging Biomarker Explorer (IBEX) is an open-source tool for medical imaging radiomics work. The purpose of this paper is to describe how to use IBEX's ...

guidelines-experience-using-imaging-biomarker-explorer-ibex-for

Research

JoVE Journal

Engineering

Guidelines and Experience Using Imaging Biomarker Explorer (IBEX) for Radiomics

13.1K 次观看.  The University of Texas MD Anderson Cancer Center. 我们描述了一种用于医学影像 radiomics 研究的开源工具, 以及如何使用这个工具。此外, 一些已出版的作品, 已使用野山羊的不确定性分析和模型建设展示。

视频: Guidelines and Experience Using Imaging Biomarker Explorer IBEX for Radiomics

Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring

Nanomedications can be carried by blood borne monocyte-macrophages into the reticuloendothelial system (RES; spleen, liver, lymph nodes) and to end organs. The latter include the lung, RES, and brain and are operative during human immunodeficiency virus type one (HIV-1) infection. Macrophage entry into tissues is notable in areas of active HIV-1 replication and sites of inflammation. In order to assess the potential of macrophages as nanocarriers, superparamagnetic iron-oxide and/or drug laden particles coated with surfactants were parenterally injected into HIV-1 encephalitic mice. This was done to quantitatively assess particle and drug biodistribution. Magnetic resonance imaging (MRI) test results were validated by histological coregistration and enhanced image processing. End organ disease as typified by altered brain histology were assessed by MRI. The demonstration of robust migration of nanoformulations into areas of focal encephalitis provides '"proof of concept" for the use of advanced bioimaging techniques to monitor macrophage migration. Importantly, histopathological aberrations in brain correlate with bioimaging parameters making the general utility of MRI in studies of cell distribution in disease feasible. We posit that using such methods can provide a real time index of disease burden and therapeutic efficacy with translational potential to humans.

Bioimaging methods used to assess cell biodistribution of nanoparticles are applicable for therapeutic and diagnostic monitoring of nanoformulated compounds. The methods described herein are sensitive and specific when assessed by histological coregistration. The methodologies provide a translational pathway from rodent to human applications.

注册生物成像，纳米材料可用于诊断和治疗监测

Nanomedications can be carried by blood borne monocyte-macrophages into the reticuloendothelial system (RES; spleen, liver, lymph nodes) and to end ...

科研

生物工程

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Biomarker detection is one of the more important biomedical questions for high-throughput &#39;omics&#39; researchers, and almost all existing biomarker detection algorithms generate one biomarker subset with the optimized performance measurement for a given dataset. However, a recent study demonstrated the existence of multiple biomarker subsets with similarly effective or even identical classification performances. This protocol presents a simple and straightforward methodology for detecting biomarker subsets with binary classification performances, better than a user-defined cutoff. The protocol consists of data preparation and loading, baseline information summarization, parameter tuning, biomarker screening, result visualization and interpretation, biomarker gene annotations, and result and visualization exportation at publication quality. The proposed biomarker screening strategy is intuitive and demonstrates a general rule for developing biomarker detection algorithms. A user-friendly graphical user interface (GUI) was developed using the programming language Python, allowing biomedical researchers to have direct access to their results. The source code and manual of kSolutionVis can be downloaded from http://www.healthinformaticslab.org/supp/resources.php.

Existing algorithms generate one solution for a biomarker detection dataset. This protocol demonstrates the existence of multiple similarly effective solutions and presents a user-friendly software to help biomedical researchers investigate their datasets for the proposed challenge. Computer scientists may also provide this feature in their biomarker detection algorithms.

用相似有效的二元分类性能选择多个生物标记子集

Biomarker detection is one of the more important biomedical questions for high-throughput &#39;omics&#39; researchers, and almost all existing biomarker ...

癌症研究

Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases

In recent years, emerging databases were designed to lower the barriers for approaching the intricate cancer genomic datasets, thereby, facilitating investigators to analyze and interpret genes, samples and clinical data across different types of cancer. Herein, we describe a practical operation procedure, taking ID1 (Inhibitor of DNA binding proteins 1) as an example, to characterize the expression patterns of biomarker and survival predictors of breast cancer based on pooled clinical datasets derived from online accessible databases, including ONCOMINE, bcGenExMiner v4.0 (Breast cancer gene-expression miner v4.0), GOBO (Gene expression-based Outcome for Breast cancer Online), HPA (The human protein atlas), and Kaplan-Meier plotter. The analysis began with querying the expression pattern of the gene of interest (e.g., ID1) in cancerous samples vs. normal samples. Then, the correlation analysis between ID1 and clinicopathological characteristics in breast cancer was performed. Next, the expression profiles of ID1 was stratified according to different subgroups. Finally, the association between ID1 expression and survival outcome was analyzed. The operation procedure simplifies the concept to integrate multidimensional data types at the gene level from different databases and test hypotheses regarding recurrence and genomic context of gene alteration events in breast cancer. This method can improve the credibility and representativeness of the conclusions, thereby, present informative perspective on a gene of interest.

Here, we present a protocol to explore the biomarker and survival predictor of breast cancer based on the comprehensive analysis of pooled clinical datasets derived from a variety of publicly accessible databases, using the strategy of expression, correlation and survival analysis step by step.

利用多个可公开访问的数据库对乳腺癌生物标志物进行数据挖掘和综合分析

In recent years, emerging databases were designed to lower the barriers for approaching the intricate cancer genomic datasets, thereby, facilitating ...

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine learning (ML) algorithms permit the integration of different features into a model to perform classification or regression tasks with an accuracy exceeding its constituents. This protocol describes the development of an ML algorithm to predict the growth of breast cancer bone macrometastases in a rat model before any abnormalities are observable with standard imaging methods. Such an algorithm can facilitate the detection of early metastatic disease (i.e., micrometastasis) that is regularly missed during staging examinations.
The applied metastasis model is site-specific, meaning that the rats develop metastases exclusively in their right hind leg. The model&#8217;s tumor-take rate is 60%&#8211;80%, with macrometastases becoming visible in magnetic resonance imaging (MRI) and positron emission tomography/computed tomography (PET/CT) in a subset of animals 30 days after induction, whereas a second subset of animals exhibit no tumor growth.
Starting from image examinations acquired at an earlier time point, this protocol describes the extraction of features that indicate tissue vascularization detected by MRI, glucose metabolism by PET/CT, and the subsequent determination of the most relevant features for the prediction of macrometastatic disease. These features are then fed into a model-averaged neural network (avNNet) to classify the animals into one of two groups: one that will develop metastases and the other that will not develop any tumors. The protocol also describes the calculation of standard diagnostic parameters, such as overall accuracy, sensitivity, specificity, negative/positive predictive values, likelihood ratios, and the development of a receiver operating characteristic. An advantage of the proposed protocol is its flexibility, as it can be easily adapted to train a plethora of different ML algorithms with adjustable combinations of an unlimited number of features. Moreover, it can be used to analyze different problems in oncology, infection, and inflammation.

This protocol was designed to train a machine learning algorithm to use a combination of imaging parameters derived from magnetic resonance imaging (MRI) and positron emission tomography/computed tomography (PET/CT) in a rat model of breast cancer bone metastases to detect early metastatic disease and predict subsequent progression to macrometastases.

实验鼠模型中骨代谢的早期检测机器学习算法

Machine learning (ML) algorithms permit the integration of different features into a model to perform classification or regression tasks with an accuracy ...

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Obtaining in vivo human brain tissue volumetrics from MRI is often complicated by various technical and biological issues. These challenges are exacerbated when significant brain atrophy and age-related white matter changes (e.g. Leukoaraiosis) are present. Lesion Explorer (LE) is an accurate and reliable neuroimaging pipeline specifically developed to address such issues commonly observed on MRI of Alzheimer's disease and normal elderly. The pipeline is a complex set of semi-automatic procedures which has been previously validated in a series of internal and external reliability tests1,2. However, LE's accuracy and reliability is highly dependent on properly trained manual operators to execute commands, identify distinct anatomical landmarks, and manually edit/verify various computer-generated segmentation outputs.
LE can be divided into 3 main components, each requiring a set of commands and manual operations: 1) Brain-Sizer, 2) SABRE, and 3) Lesion-Seg. Brain-Sizer's manual operations involve editing of the automatic skull-stripped total intracranial vault (TIV) extraction mask, designation of ventricular cerebrospinal fluid (vCSF), and removal of subtentorial structures. The SABRE component requires checking of image alignment along the anterior and posterior commissure (ACPC) plane, and identification of several anatomical landmarks required for regional parcellation. Finally, the Lesion-Seg component involves manual checking of the automatic lesion segmentation of subcortical hyperintensities (SH) for false positive errors.
While on-site training of the LE pipeline is preferable, readily available visual teaching tools with interactive training images are a viable alternative. Developed to ensure a high degree of accuracy and reliability, the following is a step-by-step, video-guided, standardized protocol for LE's manual procedures.

Lesion Explorer (LE) is a semi-automatic, image-processing pipeline developed to obtain regional brain tissue and subcortical hyperintensity lesion volumetrics from structural MRI of Alzheimer's disease and normal elderly. To ensure a high level of accuracy and reliability, the following is a video-guided, standardized protocol for LE's manual procedures.

病变资源管理器:一个视频引导，标准化为老年痴呆症准确，可靠的MRI衍生Volumetrics和正常老年人协议

Obtaining in vivo human brain tissue volumetrics from MRI is often complicated by various technical and biological issues. These challenges are ...

医学

A Robust Discovery Platform for the Identification of Novel Mediators of Melanoma Metastasis

Metastasis is a complex process, requiring cells to overcome barriers that are only incompletely modeled by in vitro assays. A systematic workflow was established using robust, reproducible in vivo models and standardized methods to identify novel players in melanoma metastasis. This approach allows for data inference at specific experimental stages to precisely characterize a gene's role in metastasis. Models are established by introducing genetically modified melanoma cells via intracardiac, intradermal, or subcutaneous injections into mice, followed by monitoring with serial in vivo imaging. Once preestablished endpoints are reached, primary tumors and/or metastases-bearing organs are harvested and processed for various analyses. Tumor cells can be sorted and subjected to any of several 'omics' platforms, including single-cell RNA sequencing. Organs undergo imaging and immunohistopathological analyses to quantify the overall burden of metastases and map their specific anatomic location. This optimized pipeline, including standardized protocols for engraftment, monitoring, tissue harvesting, processing, and analysis, can be adopted for patient-derived, short-term cultures and established human and murine cell lines of various solid cancer types.

This article describes a workflow of techniques employed for testing novel candidate mediators of melanoma metastasis and their mechanism(s) of action.

用于鉴定黑色素瘤转移新介质的强大发现平台

Metastasis is a complex process, requiring cells to overcome barriers that are only incompletely modeled by in vitro assays. A systematic workflow was ...

Digital Spatial Profiling for Characterization of the Microenvironment in Adult-Type Diffusely Infiltrating Glioma

Diffusely infiltrating gliomas are associated with high morbidity and mortality due to the infiltrative nature of tumor spread. They are morphologically complex tumors, with a high degree of proteomic variability across both the tumor itself and its heterogenous microenvironment. The malignant potential of these tumors is enhanced by the dysregulation of proteins involved in several key pathways, including processes that maintain cellular stability and preserve the structural integrity of the microenvironment. Although there have been numerous bulk and single-cell glioma analyses, there is a relative paucity of spatial stratification of these proteomic data. Understanding differences in spatial distribution of tumorigenic factors and immune cell populations between the intrinsic tumor, invasive edge, and microenvironment offers valuable insight into the mechanisms underlying tumor proliferation and propagation. Digital spatial profiling (DSP) represents a powerful technology that can form the foundation for these important multilayer analyses.
DSP is a method that efficiently quantifies protein expression within user-specified spatial regions in a tissue specimen. DSP is ideal for studying the differential expression of multiple proteins within and across regions of distinction, enabling multiple levels of quantitative and qualitative analysis. The DSP protocol is systematic and user-friendly, allowing for customized spatial analysis of proteomic data. In this experiment, tissue microarrays are constructed from archived glioblastoma core biopsies. Next, a panel of antibodies is selected, targeting proteins of interest within the sample. The antibodies, which are preconjugated to UV-photocleavable DNA oligonucleotides, are then incubated with the tissue sample overnight. Under fluorescence microscopy visualization of the antibodies, regions of interest (ROIs) within which to quantify protein expression are defined with the samples. UV light is then directed at each ROI, cleaving the DNA oligonucleotides. The oligonucleotides are microaspirated and counted within each ROI, quantifying the corresponding protein on a spatial basis.

Proteomic dysregulation plays an important role in the spread of diffusely infiltrating gliomas, but several relevant proteins remain unidentified. Digital spatial processing (DSP) offers an efficient, high-throughput approach for characterizing the differential expression of candidate proteins that may contribute to the invasion and migration of infiltrative gliomas.

用于表征成人型弥漫性浸润性胶质瘤微环境的数字空间剖析

Diffusely infiltrating gliomas are associated with high morbidity and mortality due to the infiltrative nature of tumor spread. They are morphologically ...

<meta charset="utf8"></head><body>使用克隆形成测定法检测患者来源的肿瘤类器官的放射反应

Live Imaging to Quantify Cellular Radiosensitivity in Patient-Derived Tumor Organoids

Radiation therapy (RT) is one of the mainstays of modern clinical cancer management. However, not all cancer types are equally sensitive to irradiation, often (but not always) because of differences in the ability of malignant cells to repair oxidative DNA damage as elicited by ionizing rays. Clonogenic assays have been employed for decades to assess the sensitivity of cultured cancer cells to ionizing irradiation, largely because irradiated cancer cells often die in a delayed manner that is difficult to quantify with short-term flow cytometry- or microscopy-assisted techniques. Unfortunately, clonogenic assays cannot be employed as such for more complex tumor models, such as patient-derived tumor organoids (PDTOs). Indeed, irradiating established PDTOs may not necessarily abrogate their growth as multicellular units, unless their stem-like compartment is completely eradicated. Moreover, irradiating PDTO-derived single-cell suspensions may not properly recapitulate the sensitivity of malignant cells to RT in the context of established PDTOs. Here, we detail an adaptation of conventional clonogenic assays that involves exposure of established PDTOs to ionizing radiation, followed by single-cell dissociation, replating in suitable culture conditions and live imaging. Non-irradiated (control) PDTO-derived stem-like cells reform growing PDTOs with a PDTO-specific efficiency, which is negatively influenced by irradiation in a dose-dependent manner. In these conditions, PDTO-forming efficiency and growth rate can be quantified as a measure of radiosensitivity on time-lapse images collected until control PDTOs achieve a predefined space occupancy.

<meta charset="utf8"></head><body>作者聚焦:用于推进癌症研究和个性化医疗的放射治疗和克隆形成检测

Here, we detail a straightforward live imaging approach for quantifying the sensitivity of patient-derived tumor organoids to ionizing radiation.

实时成像量化患者来源的肿瘤类器官中的细胞放射敏感性

Radiation therapy (RT) is one of the mainstays of modern clinical cancer management. However, not all cancer types are equally sensitive to irradiation, ...

使用成像生物标志物探险家 (野山羊) Radiomics 的指南和经验

摘要

探索更多视频

此视频中的章节

注册生物成像，纳米材料可用于诊断和治疗监测

用相似有效的二元分类性能选择多个生物标记子集

利用多个可公开访问的数据库对乳腺癌生物标志物进行数据挖掘和综合分析

实验鼠模型中骨代谢的早期检测机器学习算法

病变资源管理器:一个视频引导，标准化为老年痴呆症准确，可靠的MRI衍生Volumetrics和正常老年人协议

用于鉴定黑色素瘤转移新介质的强大发现平台

用于表征成人型弥漫性浸润性胶质瘤微环境的数字空间剖析

实时成像量化患者来源的肿瘤类器官中的细胞放射敏感性

实时成像量化患者来源的肿瘤类器官中的细胞放射敏感性

实时成像量化患者来源的肿瘤类器官中的细胞放射敏感性