arXiv 2407.048882024-07-05eess.IVcs.CV

解开放射组学复杂性：预测建模中实现最优简洁性的策略

Unraveling Radiomics Complexity: Strategies for Optimal Simplicity in Predictive Modeling

Université de Sherbrooke（谢布鲁克大学）；OncoRay – National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology, Helmholtz-Zentrum Dresden-Rossendorf（德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯医学院及大学医院OncoRay肿瘤放射研究国家中心，德累斯顿-罗森多夫亥姆霍兹研究中心）；Cedars-Sinai Medical Center（西达赛奈医疗中心）；University of California San Francisco（加利福尼亚大学旧金山分校）；Stanford University（斯坦福大学）

Mahdi Ait Lhaj Loutfi, Teodora Boblea Podasca, Alex Zwanenburg, Taman Upadhaya, Jorge Barrios, David R. Raleigh, William C. Chen, Dante P. I. Capaldi, Hong Zhen… 展开作者

Mahdi Ait Lhaj Loutfi, Teodora Boblea Podasca, Alex Zwanenburg, Taman Upadhaya, Jorge Barrios, David R. Raleigh, William C. Chen, Dante P. I. Capaldi, Hong Zheng, Olivier Gevaert, Jing Wu, Alvin C. Silva, Paul J. Zhang, Harrison X. Bai, Jan Seuntjens, Steffen Löck, Patrick O. Richard, Olivier Morin, Caroline Reinhold, Martin Lepage, Martin Vallières

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种识别最小预测性放射组学特征集的方法和开源工具MEDimage，在五个癌症数据集上确定不同成像模态对应的最优特征复杂度级别，以简化预测建模。

摘要：

背景：放射组学特征集的高维度、放射组学特征类型的变异性以及潜在的高计算需求，都凸显了需要一种有效方法来识别针对给定临床问题的最小预测特征集。目的：开发一种方法和工具，以识别并解释最小的预测性放射组学特征集。材料与方法：从五个癌症数据集中提取了89,714个放射组学特征：低级别胶质瘤、脑膜瘤、非小细胞肺癌（NSCLC）以及两个肾细胞癌队列（n=2104）。特征按计算复杂度分为形态学、强度、纹理、线性滤波器和非线性滤波器。在每个复杂度级别上使用曲线下面积（AUC）训练和评估模型。识别出最具信息量的特征，并解释其重要性。分别使用系统性统计显著性分析和假发现避免程序来确定最优复杂度级别及与之相关的最具信息量特征。使用一种新的基于树的方法解释其预测重要性。结果：开发了一个新的开源工具MEDimage，以促进放射组学研究。形态学特征对于基于MRI的脑膜瘤（AUC：0.65）和低级别胶质瘤（AUC：0.68）是最优的。强度特征对于基于CECT的肾细胞癌（AUC：0.82）和基于CT的NSCLC（AUC：0.76）是最优的。纹理特征对于基于MRI的肾细胞癌（AUC：0.72）是最优的。调整Hounsfield单位范围改善了基于CECT的肾细胞癌的结果（AUC：0.86）。结论：我们提出的方法和软件可以估计特定医学结局的最优放射组学复杂度级别，从而可能简化放射组学在各种背景下预测建模中的应用。

英文摘要：

Background: The high dimensionality of radiomic feature sets, the variability in radiomic feature types and potentially high computational requirements all underscore the need for an effective method to identify the smallest set of predictive features for a given clinical problem. Purpose: Develop a methodology and tools to identify and explain the smallest set of predictive radiomic features. Materials and Methods: 89,714 radiomic features were extracted from five cancer datasets: low-grade glioma, meningioma, non-small cell lung cancer (NSCLC), and two renal cell carcinoma cohorts (n=2104). Features were categorized by computational complexity into morphological, intensity, texture, linear filters, and nonlinear filters. Models were trained and evaluated on each complexity level using the area under the curve (AUC). The most informative features were identified, and their importance was explained. The optimal complexity level and associated most informative features were identified using systematic statistical significance analyses and a false discovery avoidance procedure, respectively. Their predictive importance was explained using a novel tree-based method. Results: MEDimage, a new open-source tool, was developed to facilitate radiomic studies. Morphological features were optimal for MRI-based meningioma (AUC: 0.65) and low-grade glioma (AUC: 0.68). Intensity features were optimal for CECT-based renal cell carcinoma (AUC: 0.82) and CT-based NSCLC (AUC: 0.76). Texture features were optimal for MRI-based renal cell carcinoma (AUC: 0.72). Tuning the Hounsfield unit range improved results for CECT-based renal cell carcinoma (AUC: 0.86). Conclusion: Our proposed methodology and software can estimate the optimal radiomics complexity level for specific medical outcomes, potentially simplifying the use of radiomics in predictive modeling across various contexts.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。