Early screening of PDAC (pancreatic ductal adenocarcinoma) based on plain CT (computed tomography) images is of great significance. Therefore, this work conducted a radiomics-aided diagnosis analysis of PDAC based on plain CT images. We explored a novel MSTA (multiresolution-statistical texture analysis) architecture to extract texture features and built machine learning models to classify PDACs and HPs (healthy pancreases). We also performed significance tests of differences to analyze the relationships between histopathological characteristics and texture features. The MSTA architecture originates from the analysis of histopathological characteristics and combines multiresolution analysis and statistical analysis to extract texture features. The MSTA architecture achieved better experimental results than the traditional architecture that scales the coefficient matrices of the multiresolution analysis. In the validation of the classifications, the MSTA architecture achieved an accuracy of 81.19% and an AUC (area under the ROC (receiver operating characteristic) curve) of 0.88 (95% confidence interval: 0.84-0.92). In the test of the classifications, it achieved an accuracy of 77.66% and an AUC of 0.79 (95% confidence interval: 0.71-0.87). Moreover, the significance tests of differences showed that the extracted texture features may be relevant to the histopathological characteristics. The MSTA architecture is beneficial for the radiomics-aided diagnosis of PDAC based on plain CT images. Its texture features can potentially enhance radiologists’ imaging interpretation abilities.

中文翻译：

---

一种新颖的多分辨率统计纹理分析体系结构：基于普通CT图像的PDAC放射学辅助诊断。

基于普通CT（计算机断层扫描）图像对PDAC（胰腺导管腺癌）进行早期筛查具有重要意义。因此，这项工作基于普通CT图像对PDAC进行了放射学辅助诊断分析。我们探索了一种新颖的MSTA（多分辨率统计纹理分析）架构来提取纹理特征，并建立了机器学习模型来对PDAC和HP（健康的胰腺）进行分类。我们还进行了差异显着性检验，以分析组织病理学特征与纹理特征之间的关系。MSTA体系结构源自组织病理学特征的分析，并结合了多分辨率分析和统计分析以提取纹理特征。与扩展多分辨率分析的系数矩阵的传统体系结构相比，MSTA体系结构获得了更好的实验结果。在分类验证中，MSTA体系结构的准确度为81.19％，AUC（ROC（接收器工作特性）曲线下的面积）为0.88（95％置信区间：0.84-0.92）。在分类测试中，它的准确度为77.66％，AUC为0.79（95％置信区间：0.71-0.87）。此外，差异的显着性检验表明提取的纹理特征可能与组织病理学特征有关。MSTA体系结构对于基于普通CT图像的PDAC的放射学辅助诊断是有益的。它的纹理特征可以潜在地增强放射科医生的成像解释能力。