Datasheet1_A robust radiomic-based machine learning approach to detect cardiac amyloidosis using cardiac computed tomography.docx

IntroductionCardiac amyloidosis (CA) shares similar clinical and imaging characteristics (e.g., hypertrophic phenotype) with aortic stenosis (AS), but its prognosis is generally worse than severe AS alone. Recent studies suggest that the presence of CA is frequent (1 out of 8 patients) in patients with severe AS. The coexistence of the two diseases complicates the prognosis and therapeutic management of both conditions. Thus, there is an urgent need to standardize and optimize the diagnostic process of CA and AS. The aim of this study is to develop a robust and reliable radiomics-based pipeline to differentiate the two pathologies.
MethodsThirty patients were included in the study, equally divided between CA and AS. For each patient, a cardiac computed tomography (CCT) was analyzed by extracting 107 radiomics features from the LV wall. Feature robustness was evaluated by means of geometrical transformations to the ROIs and intra-class correlation coefficient (ICC) computation. Various correlation thresholds (0.80, 0.85, 0.90, 0.95, 1), feature selection methods [p-value, least absolute shrinkage and selection operator (LASSO), semi-supervised LASSO, principal component analysis (PCA), semi-supervised PCA, sequential forwards selection] and machine learning classifiers (k-nearest neighbors, support vector machine, decision tree, logistic regression and gradient boosting) were assessed using a leave-one-out cross-validation. Data augmentation was performed using the synthetic minority oversampling technique. Finally, explainability analysis was performed by using the SHapley Additive exPlanations (SHAP) method.
ResultsNinety-two radiomic features were selected as robust and used in the further steps. Best performances of classification were obtained using a correlation threshold of 0.95, PCA (keeping 95% of the variance, corresponding to 9 PCs) and support vector machine classifier reaching an accuracy, sensitivity and specificity of 0.93. Four PCs were found to be mainly dependent on textural features, two on first-order statistics and three on shape and size features.
ConclusionThese preliminary results show that radiomics might be used as non-invasive tool able to differentiate CA from AS using clinical routine available images.

引言
心脏淀粉样变性 (Cardiac amyloidosis, CA) 与主动脉瓣狭窄 (Aortic stenosis, AS) 具有相似的临床与影像学特征（如肥厚表型），但其预后通常较单纯性重度主动脉瓣狭窄更差。近期研究显示，在重度主动脉瓣狭窄患者中，合并心脏淀粉样变性的比例较高，每8名患者中即有1名。两种疾病共存会使各自的预后评估与治疗管理变得更为复杂，因此亟需标准化并优化心脏淀粉样变性与主动脉瓣狭窄的诊断流程。本研究旨在开发一套稳健可靠的基于放射组学 (radiomics) 的分析流程，以区分这两种病症。

方法
本研究共纳入30名患者，按心脏淀粉样变性与主动脉瓣狭窄平均分组，每组各15例。针对每名患者的心脏计算机断层扫描 (Cardiac computed tomography, CCT) 图像，研究人员从左心室 (left ventricle, LV) 壁中提取了107个放射组学特征。通过对感兴趣区域 (Regions of Interest, ROIs) 进行几何变换以及计算组内相关系数 (intra-class correlation coefficient, ICC)，评估特征的稳健性。本研究采用留一交叉验证法，对多种相关系数阈值（0.80、0.85、0.90、0.95、1）、特征选择方法[P值法、最小绝对收缩和选择算子 (least absolute shrinkage and selection operator, LASSO)、半监督LASSO、主成分分析 (principal component analysis, PCA)、半监督PCA、序列前向选择法]以及机器学习分类器（k近邻、支持向量机、决策树、逻辑回归与梯度提升模型）进行了评估。本研究采用合成少数类过采样技术 (synthetic minority oversampling technique, SMOTE) 进行数据增强。最后，采用SHAP (SHapley Additive exPlanations) 方法进行可解释性分析。

结果
最终筛选出92个具有稳健性的放射组学特征，用于后续分析步骤。当相关系数阈值设为0.95、采用保留95%方差（对应9个主成分）的PCA以及支持向量机分类器时，分类性能最优，其准确率、灵敏度与特异度均达到0.93。其中4个主成分主要依赖于纹理特征，2个依赖于一阶统计特征，3个依赖于形状与尺寸特征。

结论
本研究的初步结果显示，利用临床常规获取的影像学图像，放射组学可作为区分心脏淀粉样变性与主动脉瓣狭窄的无创工具。