Thomas Hannah Mary T, Wang Helen Y C, Varghese Amal Joseph, Donovan Ellen M, South Chris P, Saxby Helen, Nisbet Andrew, Prakash Vineet, Sasidharan Balu Krishna, Pavamani Simon Pradeep, Devadhas Devakumar, Mathew Manu, Isiah Rajesh Gunasingam, Evans Philip M
Department of Radiation Oncology, Christian Medical College Vellore, Vellore 632004, Tamil Nadu, India.
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford GU2 7XH, UK.
Appl Sci (Basel). 2024 Feb 20;166(1). doi: 10.3390/app13127291.
Radiomics involves the extraction of information from medical images that are not visible to the human eye. There is evidence that these features can be used for treatment stratification and outcome prediction. However, there is much discussion about the reproducibility of results between different studies. This paper studies the reproducibility of CT texture features used in radiomics, comparing two feature extraction implementations, namely the MATLAB toolkit and Pyradiomics, when applied to independent datasets of CT scans of patients: (i) the open access RIDER dataset containing a set of repeat CT scans taken 15 min apart for 31 patients (RIDER Scan 1 and Scan 2, respectively) treated for lung cancer; and (ii) the open access HN1 dataset containing 137 patients treated for head and neck cancer. Gross tumor volume (GTV), manually outlined by an experienced observer available on both datasets, was used. The 43 common radiomics features available in MATLAB and Pyradiomics were calculated using two intensity-level quantization methods with and without an intensity threshold. Cases were ranked for each feature for all combinations of quantization parameters, and the Spearman's rank coefficient, , calculated. Reproducibility was defined when a highly correlated feature in the RIDER dataset also correlated highly in the HN1 dataset, and vice versa. A total of 29 out of the 43 reported stable features were found to be highly reproducible between MATLAB and Pyradiomics implementations, having a consistently high correlation in rank ordering for RIDER Scan 1 and RIDER Scan 2 ( > 0.8). 18/43 reported features were common in the RIDER and HN1 datasets, suggesting they may be agnostic to disease site. Useful radiomics features should be selected based on reproducibility. This study identified a set of features that meet this requirement and validated the methodology for evaluating reproducibility between datasets.
放射组学涉及从人眼不可见的医学图像中提取信息。有证据表明，这些特征可用于治疗分层和结果预测。然而，关于不同研究结果的可重复性存在很多讨论。本文研究了放射组学中使用的CT纹理特征的可重复性，比较了两种特征提取方法，即MATLAB工具包和Pyradiomics，将它们应用于患者CT扫描的独立数据集时：(i) 开放获取的RIDER数据集，包含31例接受肺癌治疗的患者间隔15分钟进行的一组重复CT扫描（分别为RIDER扫描1和扫描2）；(ii) 开放获取的HN1数据集，包含137例接受头颈癌治疗的患者。使用了由两个数据集上的经验丰富的观察者手动勾勒出的大体肿瘤体积（GTV）。使用有和没有强度阈值的两种强度级量化方法计算了MATLAB和Pyradiomics中可用的43个常见放射组学特征。针对量化参数的所有组合，对每个特征的病例进行排名，并计算斯皮尔曼等级系数。当RIDER数据集中高度相关的特征在HN1数据集中也高度相关时，反之亦然，则定义为具有可重复性。在MATLAB和Pyradiomics实现之间，发现报告的43个稳定特征中有29个具有高度可重复性，在RIDER扫描1和RIDER扫描2的排名顺序中具有一致的高相关性（>0.8）。报告的43个特征中有18个在RIDER和HN1数据集中是常见的，这表明它们可能与疾病部位无关。应基于可重复性选择有用的放射组学特征。本研究确定了一组满足此要求的特征，并验证了评估数据集之间可重复性的方法。
