[论文解读] Intensity Normalization Techniques and Their Effect on the Robustness and Predictive Power of Breast MRI Radiomics

Florian Schwarzhans, Geevarghese George+5 more|arXiv (Cornell University)|Jun 3, 2024

Radiomics and Machine Learning in Medical ImagingMedicine被引用 3

一句话总结

本研究评估了在乳腺MRI放射组学中应用强度归一化技术，以提升特征的稳健性与预测能力。基于I-SPY TRIAL和PARTNER试验数据集，研究结果表明，将偏置场校正与分段线性直方图归一化相结合，能显著提高跨扫描仪的特征一致性，优于其他方法，在降低扫描仪引起的变异方面表现更优。

ABSTRACT

Radiomics analysis has emerged as a promising approach for extracting quantitative features from medical images to aid in cancer diagnosis and treatment. However, radiomics research currently lacks standardization, and radiomics features can be highly dependent on the acquisition and pre-processing techniques used. In this study, we aim to investigate the effect of various intensity normalization techniques on the robustness of radiomics features extracted from MRI scans of breast cancer patients. The images used are from the publicly available I-SPY TRIAL dataset, which contains MRI scans of stage 2 or 3 breast cancer patients and from the Platinum and PARP inhibitor for Neoadjuvant treatment of Triple Negative and / or BRCA positive breast cancer (PARTNER) trial. We compared the effect of commonly used intensity normalization techniques on the robustness of radiomics features using Intraclass Correlation Coefficient (ICC) between multiple combinations of normalization approaches, identified categories that are robust and therefore could be compared between studies regardless of the pre-processing used. We were able to show that while systematic differences between MRI scanners can significantly affect many radiomics features, a combination of Bias Field correction with piecewise linear histogram normalization can mitigate some of the effects compared to other normalization methods investigated in this paper. We were able to demonstrate the importance of carefully selecting and standardizing normalization methods for accurate and reliable radiomics analysis in breast MRI scans.

研究动机与目标

• 评估不同强度归一化技术对乳腺MRI放射组学特征稳健性的影响。
• 识别能最小化因扫描仪特定采集差异导致的变异的归一化策略。
• 提高多中心研究中放射组学特征的可重复性与可比性。
• 利用I-SPY和PARTNER试验的临床结局，评估归一化后放射组学特征的预测性能。
• 建立标准化的预处理流程，以提升乳腺MRI放射组学研究的可靠性。

提出的方法

• 使用来自I-SPY TRIAL和PARTNER试验数据集的T1加权动态对比增强（DCE-MRI）扫描。
• 应用多种强度归一化技术：直方图匹配、N4偏置场校正、分段线性归一化和z分数归一化。
• 将归一化方法按顺序组合成处理流程（例如N4 + 分段线性），以评估其叠加效应。
• 计算组内相关系数（ICC）以量化不同归一化组合下特征的稳健性。
• 利用临床结局（如病理完全缓解）评估归一化特征的预测能力。
• 进行统计分析，比较不同归一化策略下特征的稳定性与预测性能。

实验结果

研究问题

• RQ1 不同强度归一化技术如何影响乳腺MRI放射组学特征的稳健性？
• RQ2 哪种归一化组合在跨扫描仪的放射组学特征上产生最高的组内相关系数（ICC）？
• RQ3 归一化在多大程度上提升了放射组学特征对乳腺癌临床结局的预测能力？
• RQ4 哪种归一化方法最有效地减轻放射组学特征中的扫描仪相关变异？
• RQ5 标准化的归一化流程能否实现乳腺MRI放射组学特征在跨研究比较中的可靠性？

主要发现

• MRI扫描仪之间的系统性差异显著影响了大多数放射组学特征，降低了其可重复性。
• N4偏置场校正后接续分段线性直方图归一化的组合方法产生了最高的ICC值，表明其具有更优的稳健性。
• 该组合方法在降低扫描仪间变异方面，优于单一归一化技术或其他组合方式。
• 经N4 + 分段线性归一化处理流程提取的特征在不同采集协议下表现出更高的稳定性。
• 本研究识别出特定的归一化类别，可维持特征稳定性，从而实现多中心研究中可靠比较。
• 稳健的归一化显著提升了放射组学特征对临床结局（如病理完全缓解）的预测能力。