Name: predicting treatment response to image-guided therapies using machine learning: an example for trans-arterial treatment of hepatocellular carcinoma
Uploaded: 2018-10-10T15:00:00
Description: Watch this Scientific Journal Video about Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma at JoVE.co

他获得了耶鲁医学院学生研究办公室的资助。
L.J.S. 获得来自国立卫生研究院 (NIH/R01CA206180)、Leopoldina 博士后奖学金和贡德放射科学基金会 (德国亚琛) 的赠款。
国家卫生研究院 (NIH/R01CA206180)、飞利浦医疗机构和德国-以色列科研开发基金会 (耶路撒冷、以色列和德国 Neuherberg) 获得赠款;以及来自贡德辐射科学基金会和拉维埃耶柏林健康临床科学家计划 (德国柏林) 的奖学金。
J.S.D. 和 M.L. 获得国立卫生研究院 (NIH/R01CA206180) 和飞利浦医疗 (荷兰最好) 的赠款。
J.F.G. 获得国立卫生研究院 (NIH/R01CA206180)、飞利浦医疗、BTG (伦敦、英国)、波士顿科学 (马尔伯勒、马萨诸塞州) 和支链医疗保健 (维勒班特、法国) 的赠款。

1。机器学习的工作站设置
<ol><li>使用具有以下内容的系统: 英特尔酷睿2双核处理器或更高 CPU 2.0 GHz 4 GB 或更多系统内存 符合 POSIX 的操作系统 (Linux 或 Mac OS) 或微软视窗7 执行程序和保存文件的用户权限</li>
	<li>安装以下工具: 蟒蛇 Python3: https://www.anaconda.com/download DICOM 到 NIfTI 转换器 (dcm2niix)-https://github.com/rordenlab/dcm2niix 崇高文本编辑器: https://www.sublimetext.com/ itk (可选): http://www.it...

<ol>
	<li>Benson, 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=NCCN+clinical+practice+guidelines+in+oncology:+hepatobiliary+cancers.">NCCN clinical practice guidelines in oncology: hepatobiliary cancers.</a> J National Comprehensive Cancer Network. 7 (4), 350-391 (2009).</li><li>Siegel, R., Miller, K., Jemal, A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Cancer+statistics,+2016.">Cancer statistics, 2016.</a> CA Cancer J Clin. 66 (1), 7-30 (2016).</li><li>Bruix, 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=Clinical+management+of+hepatocellular+carcinoma.+Conclusions+of+the+Barcelona-2000+European+Association+for+the+Study+of+the+Liver+conference.">Clinical management of hepatocellular carcinoma. Conclusions of the Barcelona-2000 European Association for the Study of the Liver conference.</a> Journal of Hepatology. 35 (3), 421-430 (2001).</li><li>Eisenhauer, 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=New+response+evaluation+criteria+in+solid+tumours:+revised+RECIST+guideline+(version+1.1).">New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1).</a> European Journal of Cancer. 45 (2), 228-247 (2009).</li><li>Gillmore, R., 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=EASL+and+mRECIST+responses+are+independent+prognostic+factors+for+survival+in+hepatocellular+cancer+patients+treated+with+transarterial+embolization.">EASL and mRECIST responses are independent prognostic factors for survival in hepatocellular cancer patients treated with transarterial embolization.</a> Journal of Hepatology. 55 (6), 1309-1316 (2011).</li><li>Lin, M., 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+and+volumetric+European+Association+for+the+Study+of+the+Liver+and+Response+Evaluation+Criteria+in+Solid+Tumors+measurements:+feasibility+of+a+semiautomated+software+method+to+assess+tumor+response+after+transcatheter+arterial+chemoembolization.">Quantitative and volumetric European Association for the Study of the Liver and Response Evaluation Criteria in Solid Tumors measurements: feasibility of a semiautomated software method to assess tumor response after transcatheter arterial chemoembolization.</a> Journal of Vascular and Interventional Radiology. 23 (12), 1629-1637 (2012).</li><li>Tacher, 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=Comparison+of+Existing+Response+Criteria+in+Patients+with+Hepatocellular+Carcinoma+Treated+with+Transarterial+Chemoembolization+Using+a+3D+Quantitative+Approach.">Comparison of Existing Response Criteria in Patients with Hepatocellular Carcinoma Treated with Transarterial Chemoembolization Using a 3D Quantitative Approach.</a> Radiology. 278 (1), 275-284 (2016).</li><li>Pedregosa, F., 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=Scikit-learn:+Machine+Learning+in+Python.">Scikit-learn: Machine Learning in Python.</a> Journal of Machine Learning Research. 12, 2825-2830 (2011).</li><li>Bishop, C. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=.">.</a> Pattern recognition and machine learning. , 738 (2006).</li><li>Alpaydin, E. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=.">.</a> Introduction to machine learning. Third edition. , 613 (2014).</li><li>Kim, S., Cho, K., Oh, S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Development+of+machine+learning+models+for+diagnosis+of+glaucoma.">Development of machine learning models for diagnosis of glaucoma.</a> PLoS One. 12 (5), (2017).</li><li>Son, Y., Kim, H., Kim, E., Choi, S., Lee, S. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Application+of+support+vector+machine+for+prediction+of+medication+adherence+in+heart+failure+patients.">Application of support vector machine for prediction of medication adherence in heart failure patients.</a> Healthcare Informatics Research. 16 (4), 253-259 (2010).</li><li>Wang, S., Summers, R. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Machine+learning+and+radiology.">Machine learning and radiology.</a> Medical Image Analysis. 16 (5), 933-951 (2012).</li><li>Abajian, 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=Predicting+Treatment+Response+to+Intra-arterial+Therapies+for+Hepatocellular+Carcinoma+with+the+Use+of+Supervised+Machine+Learning-An+Artificial+Intelligence+Concept.">Predicting Treatment Response to Intra-arterial Therapies for Hepatocellular Carcinoma with the Use of Supervised Machine Learning-An Artificial Intelligence Concept.</a> Journal of Vascular and Interventional Radiology. , (2018).</li></ol>

非手术切除的肝癌患者, 均提供动脉内治疗。很少有方法来确定病人是否会做出治疗前的反应。治疗后评估技术依赖于肿瘤大小或肿瘤对比吸收的变化。这些被称为反应标准, 最准确的是定量欧洲协会为研究肝脏 (qEASL) 标准。qEASL 依赖于体积和增强变化后的治疗, 以预测的可能性反应。尽管 qEASL 的优势, 但它仍然是治疗后评价标准, 不能帮助治疗计划。
有必要评估哪些病...

肝细胞癌患者非手术候选者, 提供动脉内治疗1,2,3。没有单一的指标确定患者是否会在治疗前对动脉内的治疗作出反应。本研究的目的是演示一种方法, 预测治疗反应的应用方法, 从机器学习。这些模型为医生和病人选择是否进行治疗提供指导。
该协议需要一个可重复的过程, 用于培训和更新从初级患者数据 (临床笔记、人口统计学、实验室数据和成像) 开始的模型。最初为特定功能分析数据, 每个患者由一组二进制特征和二进制结果目标标签表示。结果标签是确定使用建立的基于成像的反应标准的肝细胞治疗4,5,6,7。这些功能和目标标签被传递给机器学习软件, 在特定学习模式 (逻辑回归或随机林)8、9、10中学习特征和结果之间的映射。类似的技术已经应用于放射学和其他癌症研究领域的诊断和治疗预测11,12,13。
该方法将计算机科学技术应用于介入放射学领域。传统意义上的介入放射学研究和医学一般依赖于单或寡聚特征分析。例如, 终末期肝病的模型纳入了五临床指标, 以评估肝病的程度。建议的方法的好处是能宽松地增加特征;在示例分析中考虑了二十五项功能。可以按需要添加其他功能。
该技术可应用于其他影像干预, 在这些放射治疗前和干预后的成像数据可用。例如, 经皮治疗后的结局可以用类似的方式预测。这项研究的主要局限是需要手工的副牧师特征纳入模型。数据精选和特征抽取对于从业者来说是耗时的, 可能会阻碍这种机器学习模式的临床应用。

<table border="0" cellpadding="0" cellspacing="0" style="width:851px;" width="850">
	<colgroup>
		<col />
		<col />
		<col />
		<col />
	</colgroup>
	<tbody>
		<tr height="105">
			<td height="105" style="height:105px;width:216px;">Computer workstation</td>
			<td style="width:123px;">N/A</td>
			<td style="width:169px;">N/A</td>
			<td style="width:343px;">Intel Core 2 Duo or higher CPU at 2.0 GHz; 4 GB or more system memory; POSIX-compliant operating system (Linux or Mac OS) or Microsoft Windows 7; User permissions for executing programs and saving files</td>
		</tr>
		<tr height="40">
			<td height="40" style="height:40px;width:216px;">Anaconda Python 3</td>
			<td style="width:123px;">Anaconda, Inc.</td>
			<td style="width:169px;">Version 3.6</td>
			<td style="width:343px;">Python 3 system and libraries packaged for scientists and researchers</td>
		</tr>
		<tr height="40">
			<td height="40" style="height:40px;width:216px;">DICOM to NIfTI</td>
			<td style="width:123px;">NeuroImaging Tools &#38; Resources Collaboratory</td>
			<td style="width:169px;">Version 1.0 (4/4/2018 release)</td>
			<td style="width:343px;">Standalone program for converting DICOM imaging files to NIfTI format</td>
		</tr>
		<tr height="33">
			<td height="33" style="height:33px;width:216px;">Sublime Text Editor</td>
			<td style="width:123px;">Sublime HQ Pty Ltd</td>
			<td style="width:169px;">Version 3 (Build 3143)</td>
			<td style="width:343px;">Text-editor for writing Python code</td>
		</tr>
		<tr height="45">
			<td height="45" style="height:45px;width:216px;">Required Python Libraries</td>
			<td style="width:123px;">N/A</td>
			<td style="width:169px;">Version 3.2.25 (nltk) 
			Version 0.19.1 (scikit-learn)</td>
			<td style="width:343px;">Natural Language Toolkit (nltk) 
			Scikit-learn</td>
		</tr>
		<tr height="40">
			<td height="40" style="height:40px;width:216px;">ITK-SNAP</td>
			<td style="width:123px;">N/A</td>
			<td style="width:169px;">Version 3.6.0</td>
			<td style="width:343px;">Optional toolkit for performing segmentation of organ systems in medical images.</td>
		</tr>
	</tbody>
</table>

predicting treatment response to image-guided therapies using machine learning: an example for trans-arterial treatment of hepatocellular carcinoma

动脉内治疗是不能接受手术切除的肝癌患者的护理标准。本研究的目的是建立一种预测干预前动脉内治疗反应的方法。
该方法为预测动脉内治疗前的结局提供了一个总体框架。它包括将临床、人口统计学和影像学数据汇集到一群病人身上, 并利用这些数据来训练机器学习模式。训练后的模型应用于新的患者, 以预测其对动脉内治疗反应的可能性。
该方法需要对已经经历过动脉治疗的N名患者的临床、人口学和影像学数据进行采集和分析。这些数据被分析成离散的特征 (年龄, 性别, 肝硬化, 肿瘤增强程度等) 和二值化成真/假价值 (例如,年龄超过 60, 男性性别, 肿瘤增强超过设定阈值等)。低方差特征和特征与结果的低单变量关联被去除。每个被治疗的患者根据他们是否反应或没有对治疗的反应被标记。因此, 每个训练病人都由一组二进制特征和结果标签表示。机器学习模型是通过对左外病人的1例患者进行训练的。这一过程是重复为每一个N患者。N模型平均到达最后的模型。
该技术是可扩展的, 可以在将来包含其他功能。这也是一个推广的过程, 可用于临床研究问题以外的介入放射学。主要的限制是需要从每个病人手动提取功能。一种流行的现代形式的机器学习称为深入学习不受此限制, 但需要更大的数据集。

将该方法应用于36例肝癌患者的介入治疗。二十五功能被识别和二值化使用步骤1-5。五功能满足方差和单变量关联筛选器 (参见步骤5.1 和 5.2), 并用于模型培训。每个病人在 qEASL 反应标准下被标记为应答器或非应答器。因此, 特征矩阵是一个 36 x 5 数组, 而目标标签向量是 36 x 1。
采用逻辑回归和随机森林分类器进行模型拟合。一...

Watch this Scientific Journal Video about Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma at JoVE.co

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

用机器学习预测图像引导疗法的治疗反应--肝细胞癌的跨动脉治疗实例

动脉内治疗是不能接受手术切除的肝癌患者的护理标准。提出了一种预测这些疗法反应的方法。该技术使用预先程序的临床、人口学和影像学信息来训练能够预测治疗前反应的机器学习模型。

Intra-arterial therapies are the standard of care for patients with hepatocellular carcinoma who cannot undergo surgical resection. The objective of this ...

此方法可以帮助预测对动脉内疗法的反应。介入肿瘤学中的机器学习应用将改变我们使用图像引导疗法治疗肝癌和其他疾病的方式。这种方法有可能改进两个重要决策的制作方式。通常，由于需要生成功能并执行机器学习和代码，对此方法的新功能人员将难以操作。此方法的可视化演示至关重要，因为特征生成步骤需要使用成像掩码提取这些功能。需要有一个注释良好的、具有临床代表性的数据集来训练模型。为了进一步改进这种机器学习算法，需要更多的患者数据和庞大的队列。在确定模型中包括哪些临床特征后，使用适当的自然语言工具包将纯文本临床笔记解析为句子，以便搜索感兴趣的术语。然后将每个患者的功能存储在每行一个功能的文件中。对于非二进制要素，获取所有患者中每个要素的中位数，并基于中位数将每个要素二进制为真值或假值。从医学图像中计算平均肝脏增强功能。隔离含有肝脏的体素后，输入平均肝脏增强命令。要确定肝脏体积功能，请输入指示的命令。然后计算每个成像要素的中值，并按演示的要素二进制。要聚合和减少要素，请首先从考虑中删除低方差要素，并读取二进制矩阵中的要素。接下来，使用方差阈值模型计算至少 20% 的响应方和非响应方中显示的要素，与表中所示的要素类似。删除与结果单变量关联率较低的任何特征，并仅筛选那些通过原始低变型筛选保留 n 要素的要素，其中 n 是患者数量。然后在每个要素的二进制矩阵中阅读，类似于表中所示。将特征二进制化和筛选后，是时候训练模型了。模型培训是一个简单明了的过程，它符合研究结果的特点，可用于预测新患者。在这项对36名接受肝细胞癌跨动脉治疗的患者的代表性分析中，25个特征被识别和二进制，证明有5个特征，既满足了变异，又符合单变量关联过滤器。每个患者被标记为响应者或非反应者根据定量欧洲协会研究肝脏反应标准。如图所示，逻辑回归和随机森林模型都预测了一个整体精度为78%的跨动脉化疗治疗响应。这种机器学习技术可以普遍应用于任何涉及程序前、程序间和程序后成像的疗法。

Research

JoVE Journal

Medicine

The Measurement and Treatment of Suppression in Amblyopia

测量和制止在弱视治疗

Amblyopia, a developmental disorder of the visual cortex, is one of the leading causes of visual dysfunction in the working age population. Current ...

科研

医学

The Goeckerman Regimen for the Treatment of Moderate to Severe Psoriasis

Goeckerman方案用于治疗中度至重度牛皮癣

Psoriasis is a  chronic, immune-mediated inflammatory skin disease affecting approximately 2-3%  of the population. The Goeckerman regimen consists of ...

Ex Vivo Treatment Response of Primary Tumors and/or Associated Metastases for Preclinical and Clinical Development of Therapeutics

Ex Vivo Treatment Response of Primary Tumors and/or Associated Metastases for Preclinical and Clinical Development of Therapeutics

原发性肿瘤和/或转移相关的临床前和治疗的临床开发的离体处理响应

The molecular analysis of established cancer cell lines has been the mainstay of cancer research for the past several decades. Cell culture provides both ...

The In Ovo Chick Chorioallantoic Membrane (CAM) Assay as an Efficient Xenograft Model of Hepatocellular Carcinoma

The In Ovo Chick Chorioallantoic Membrane CAM Assay as an Efficient Xenograft Model of Hepatocellular Carcinoma

该<em&gt;卵内</em&gt;鸡胚尿囊膜（CAM）含量为肝癌的有效异种移植模型

The chick chorioallantoic membrane (CAM) begins to develop by day 7 after fertilization and matures by day 12. The CAM is naturally immunodeficient and ...

Evaluation of the Efficacy of the H. pylori Protein HP-NAP as a Therapeutic Tool for Treatment of Bladder Cancer in an Orthotopic Murine Model

Evaluation of the Efficacy of the H. pylori Protein HP-NAP as a Therapeutic Tool for Treatment of Bladder Cancer in an Orthotopic Murine Model

评价疗效<em&gt;小时。幽门螺杆菌</em&gt;蛋白HP-NAP为膀胱癌的治疗在原位小鼠模型的治疗工具

Bladder cancer is one of the most common malignancies of the urogenital tract. Intravesical injection of Bacillus Calmette-Gu&#233;rin (BCG) is the gold ...

A "Patient-Like" Orthotopic Syngeneic Mouse Model of Hepatocellular Carcinoma Metastasis

“以病人为像”肝癌原位同源小鼠模型的癌转移

The majority of cancer-related deaths are caused by the metastasis of the cancer rather than the primary tumor itself. Yet, the underlying mechanisms of ...

MRI-guided dmPFC-rTMS as a Treatment for Treatment-resistant Major Depressive Disorder

MRI引导dmPFC-rTMS治疗作为治疗难治性抑郁症

Here we outline the protocol for magnetic resonance imaging (MRI) guided repetitive transcranial magnetic stimulation (rTMS) to the dorsal medial ...

Using Micro-computed Tomography for the Assessment of Tumor Development and Follow-up of Response to Treatment in a Mouse Model of Lung Cancer

采用微计算机断层扫描对肿瘤发展的评估和后续反应来治疗肺癌的小鼠模型

Lung cancer is the most lethal cancer in the world. Intensive research is ongoing worldwide to identify new therapies for lung cancer. Several mouse ...