Dynamic NIR Fluorescence Imaging and Machine Learning Framework for Stratifying High vs. Low Notch-Dll4 Expressing Host Microenvironment in Triple-Negative Breast Cancer.
Dynamic NIR Fluorescence Imaging and Machine Learning Framework for Stratifying High vs. Low Notch-Dll4 Expressing Host Microenvironment in Triple-Negative Breast Cancer.
复制标题
作者：
乳腺癌是一种受肿瘤细胞和宿主环境影响的疾病。众所周知，由于快速血管生成，肿瘤血管在结构和功能上发生异常，并且这种异常的血管系统在乳腺癌的药物递送和治疗反应中起主要作用。Dll4是一种有助于控制肿瘤血管生长的蛋白质。这项研究使用近红外光学成像和一种新的机器学习框架来确定Dll4水平是否可以通过简单的非侵入性成像检测来预测。这项研究的最终结果可能有助于医生决定一个给定的三阴性乳腺癌患者是否会受益于Dll4靶向治疗。已知肿瘤中的δ样典型缺口配体4（Dll 4）表达水平影响癌症疗法的功效。本研究旨在开发一种模型，以预测肿瘤中Dll 4的表达水平，使用动态增强近红外（NIR）成像与吲哚菁绿色（ICG）。研究了具有不同Dll 4表达水平的两种基于大鼠的乳腺癌同源异种移植（CXM）株和八种同源异种移植株。主成分分析（PCA）用于可视化和分割肿瘤，改进的PCA技术识别和分析肿瘤和正常感兴趣区域（ROI）。根据每个时间间隔的像素亮度计算每个ROI的平均NIR强度，产生易于解释的特征，包括初始ICG摄取的斜率、达到峰值灌注的时间和达到半最大强度后ICG强度变化的速率。应用机器学习算法来选择用于分类的判别特征，并使用混淆矩阵、受试者工作特征曲线和曲线下面积来评估模型性能。所选择的机器学习方法准确地鉴定了宿主Dll4表达改变，灵敏度和特异性高于90%。这可以使得能够对Dll4靶向疗法的患者进行分层。使用ICG的NIR成像可以非侵入性地评估肿瘤中Dll4的表达水平，并有助于癌症治疗的有效决策。
Breast cancer is a disease that is affected by both the tumor cells and the host environment. It is well known that the tumor blood vessels are aberrant in structure and function due to rapid angiogenesis, and this aberrant vasculature plays a major role in drug delivery and therapy response of breast cancer. Dll4 is a protein that helps control the growth of blood vessels in tumors. This study used near-infrared optical imaging and a novel machine learning framework to determine if Dll4 levels can be predicted from simple noninvasive imaging assays. The eventual results of this study may help physicians decide if a given triple-negative breast cancer patient will benefit from a Dll4 targeted therapy. Delta like canonical notch ligand 4 (Dll4) expression levels in tumors are known to affect the efficacy of cancer therapies. This study aimed to develop a model to predict Dll4 expression levels in tumors using dynamic enhanced near-infrared (NIR) imaging with indocyanine green (ICG). Two rat-based consomic xenograft (CXM) strains of breast cancer with different Dll4 expression levels and eight congenic xenograft strains were studied. Principal component analysis (PCA) was used to visualize and segment tumors, and modified PCA techniques identified and analyzed tumor and normal regions of interest (ROIs). The average NIR intensity for each ROI was calculated from pixel brightness at each time interval, yielding easily interpretable features including the slope of initial ICG uptake, time to peak perfusion, and rate of ICG intensity change after reaching half-maximum intensity. Machine learning algorithms were applied to select discriminative features for classification, and model performance was evaluated with a confusion matrix, receiver operating characteristic curve, and area under the curve. The selected machine learning methods accurately identified host Dll4 expression alterations with sensitivity and specificity above 90%. This may enable stratification of patients for Dll4 targeted therapies. NIR imaging with ICG can noninvasively assess Dll4 expression levels in tumors and aid in effective decision making for cancer therapy.
登录
查看更多内容
影响因子：
8.3
作者：
Flister, Michael J.;Hoffman, Matthew J.;Moreno, Carol
通讯作者：
Moreno, Carol
侵入性手术程序对原发性肿瘤生长和转移的潜在影响。
影响因子：
4
作者：
Alieva M;van Rheenen J;Broekman MLD
通讯作者：
Broekman MLD
DOI：
10.1038/nrclinonc.2011.58
发表时间：
2011-06
期刊：
Nature reviews. Clinical oncology
影响因子：
--
作者：
通讯作者：
--
评估癌症临床药物反应的基于分子的预测。
影响因子：
5.8
作者：
Ding, Zijian;Zu, Songpeng;Gu, Jin
通讯作者：
Gu, Jin
影响因子：
3.8
作者：
Flister MJ;Tsaih SW;Stoddard A;Plasterer C;Jagtap J;Parchur AK;Sharma G;Prisco AR;Lemke A;Murphy D;Al-Gizawiy M;Straza M;Ran S;Geurts AM;Dwinell MR;Greene AS;Bergom C;LaViolette PS;Joshi A
通讯作者：
Joshi A