Rahbek Sofie, Mahmood Faisal, Tomaszewski Michal R, Hanson Lars G, Madsen Kristoffer H
Department of Health Technology, Technical University of Denmark, Kgs. Lyngby, DK-2800, Denmark.
Department of Clinical Research, University of Southern Denmark, Odense, DK-5000, Denmark.
Phys Med Biol. 2023 Jan 5;68(2). doi: 10.1088/1361-6560/acaa85.
In the field of radiation oncology, the benefit of MRI goes beyond that of providing high soft-tissue contrast images for staging and treatment planning. With the recent clinical introduction of hybrid MRI linear accelerators it has become feasible to map physiological parameters describing diffusion, perfusion, and relaxation during the entire course of radiotherapy, for example. However, advanced data analysis tools are required for extracting qualified prognostic and predictive imaging biomarkers from longitudinal MRI data. In this study, we propose a new prediction framework tailored to exploit temporal dynamics of tissue features from repeated measurements. We demonstrate the framework using a newly developed decomposition method for tumor characterization.Two previously published MRI datasets with multiple measurements during and after radiotherapy, were used for development and testing:-weighted multi-echo images obtained for two mouse models of pancreatic cancer, and diffusion-weighted images for patients with brain metastases. Initially, the data was decomposed using the novel monotonous slope non-negative matrix factorization (msNMF) tailored for MR data. The following processing consisted of a tumor heterogeneity assessment using descriptive statistical measures, robust linear modelling to capture temporal changes of these, and finally logistic regression analysis for stratification of tumors and volumetric outcome.The framework was able to classify the two pancreatic tumor types with an area under curve (AUC) of 0.999,< 0.001 and predict the tumor volume change with a correlation coefficient of 0.513,= 0.034. A classification of the human brain metastases into responders and non-responders resulted in an AUC of 0.74,= 0.065.A general data processing framework for analyses of longitudinal MRI data has been developed and applications were demonstrated by classification of tumor type and prediction of radiotherapy response. Further, as part of the assessment, the merits of msNMF for tumor tissue decomposition were demonstrated.
在放射肿瘤学领域，磁共振成像（MRI）的作用不仅限于为分期和治疗规划提供高软组织对比度图像。例如，随着近期混合MRI直线加速器在临床上的应用，在放射治疗的整个过程中绘制描述扩散、灌注和弛豫的生理参数已成为可能。然而，需要先进的数据分析工具才能从纵向MRI数据中提取合格的预后和预测成像生物标志物。在本研究中，我们提出了一个新的预测框架，旨在利用重复测量中组织特征的时间动态变化。我们使用一种新开发的肿瘤特征分解方法来展示该框架。使用两个先前发表的在放疗期间及之后进行多次测量的MRI数据集进行开发和测试：为两个胰腺癌小鼠模型获取的T加权多回波图像，以及脑转移患者的扩散加权图像。最初，使用专为MR数据量身定制的新型单调斜率非负矩阵分解（msNMF）对数据进行分解。后续处理包括使用描述性统计量进行肿瘤异质性评估、使用稳健线性模型捕捉这些特征的时间变化，最后进行逻辑回归分析以对肿瘤和体积结果进行分层。该框架能够以0.999的曲线下面积（AUC）对两种胰腺肿瘤类型进行分类，<0.001，并以0.513的相关系数预测肿瘤体积变化，=0.034。将人类脑转移瘤分为反应者和无反应者的分类结果AUC为0.74，=0.065。已开发出一个用于分析纵向MRI数据的通用数据处理框架，并通过肿瘤类型分类和放疗反应预测展示了其应用。此外，作为评估的一部分，还展示了msNMF在肿瘤组织分解方面的优点。
