Andrade Diego, Gifford Howard C, Das Mini
Department of Biomedical Engineering, University of Houston, 4800 Calhoun Rd, Houston, TX 77004, USA.
Department of Electrical and Computer Engineering, University of Houston, 4800 Calhoun Rd, Houston, TX 77004, USA.
Tomography. 2025 Jul 31;11(8):87. doi: 10.3390/tomography11080087.
There is significant interest in using texture features to extract hidden image-based information. In medical imaging applications using radiomics, AI, or personalized medicine, the quest is to extract patient or disease specific information while being insensitive to other system or processing variables. While we use digital breast tomosynthesis (DBT) to show these effects, our results would be generally applicable to a wider range of other imaging modalities and applications. We examine factors in texture estimation methods, such as quantization, pixel distance offset, and region of interest (ROI) size, that influence the magnitudes of these readily computable and widely used image texture features (specifically Haralick's gray level co-occurrence matrix (GLCM) textural features). Our results indicate that quantization is the most influential of these parameters, as it controls the size of the GLCM and range of values. We propose a new multi-resolution normalization (by either fixing ROI size or pixel offset) that can significantly reduce quantization magnitude disparities. We show reduction in mean differences in feature values by orders of magnitude; for example, reducing it to 7.34% between quantizations of 8-128, while preserving trends. When combining images from multiple vendors in a common analysis, large variations in texture magnitudes can arise due to differences in post-processing methods like filters. We show that significant changes in GLCM magnitude variations may arise simply due to the filter type or strength. These trends can also vary based on estimation variables (like offset distance or ROI) that can further complicate analysis and robustness. We show pathways to reduce sensitivity to such variations due to estimation methods while increasing the desired sensitivity to patient-specific information such as breast density. Finally, we show that our results obtained from simulated DBT images are consistent with what we see when applied to clinical DBT images.
人们对使用纹理特征来提取基于图像的隐藏信息有着浓厚的兴趣。在使用放射组学、人工智能或个性化医疗的医学成像应用中，目标是提取患者或疾病特定的信息，同时对其他系统或处理变量不敏感。虽然我们使用数字乳腺断层合成（DBT）来展示这些效果，但我们的结果通常适用于更广泛的其他成像模态和应用。我们研究了纹理估计方法中的因素，如量化、像素距离偏移和感兴趣区域（ROI）大小，这些因素会影响这些易于计算且广泛使用的图像纹理特征（特别是哈勒克灰度共生矩阵（GLCM）纹理特征）的大小。我们的结果表明，量化是这些参数中最具影响力的，因为它控制着GLCM的大小和值的范围。我们提出了一种新的多分辨率归一化方法（通过固定ROI大小或像素偏移），可以显著减少量化幅度差异。我们展示了特征值平均差异降低了几个数量级；例如，在8 - 128量化之间将其降低到7.34%，同时保留趋势。当在共同分析中组合来自多个供应商的图像时，由于诸如滤波器等后处理方法的差异，纹理大小可能会出现很大变化。我们表明，GLCM大小变化的显著变化可能仅仅由于滤波器类型或强度而产生。这些趋势也可能因估计变量（如偏移距离或ROI）而有所不同，这会进一步使分析和稳健性变得复杂。我们展示了降低对因估计方法导致的此类变化的敏感性的途径，同时提高对患者特定信息（如乳腺密度）的期望敏感性。最后，我们表明从模拟DBT图像获得的结果与应用于临床DBT图像时所看到的结果一致。
