Department of Body Imaging, The University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Department of Radiology, Trinity Health Mid-Atlantic, Mercy Catholic Medical Center, Darby, PA, USA.
Abdom Radiol (NY). 2021 Oct;46(10):4853-4863. doi: 10.1007/s00261-021-03136-2. Epub 2021 Jun 3.
To evaluate the ability of radiomic feature extraction and a machine learning algorithm to differentiate between benign and malignant indeterminate adrenal lesions on contrast-enhanced computed tomography (CT) studies.
Adrenal "incidentalomas" are adrenal lesions that are accidentally discovered during workup not related to the adrenal glands; they have an incidence as high as 5%. Small adrenal incidentalomas (< 4 cm) with high attenuation values on pre-contrast CT(> 10 HU) need further evaluation to calculate the absolute percentage of washout (APW). If the APW is < 60%, these lesions are considered non-adenomas and commonly classified as indeterminate adrenal lesions. Further workup for indeterminate lesions includes more complicated and expensive radiological studies or invasive procedures like biopsy or surgical resection.
We searched our institutional database for indeterminate adrenal lesions with the following characteristics: < 4 cm, pre-attenuation value > 10 HU, and APW < 60%. Exclusion criteria included pheochromocytoma and no histopathological examination. CT images were converted to Nifti format, and adrenal tumors were segmented using Amira software. Radiomic features from the adrenal mask were extracted using PyRadiomics software after removing redundant features (highly pairwise correlated features and low-variance features) using recursive feature extraction to select the final discriminative set of features. Lastly, the final features were used to build a binary classification model using a random forest algorithm, which was validated and tested using leave-one-out cross-validation, confusion matrix, and receiver operating characteristic curve.
We found 40 indeterminate adrenal lesions (21 benign and 19 malignant). Feature extraction resulted in 3947 features, which reduced down to 62 features after removing redundancies. Recursive feature elimination resulted in the following top 4 discriminative features: gray-level size zone matrix-derived size zone non-uniformity from pre-contrast and delayed phases, gray-level dependency matrix-derived large dependence high gray-level emphasis from venous-phase, and gray-level co-occurrence matrix-derived cluster shade from delayed-phase. A binary classification model with leave-one-out cross-validation showed AUC = 0.85, sensitivity = 84.2%, and specificity = 71.4%.
Machine learning and radiomic features extraction can differentiate between benign and malignant indeterminate adrenal tumors and can be used to direct further workup with high sensitivity and specificity.
评估基于放射组学特征提取和机器学习算法在区分增强 CT 研究中良性和恶性不确定肾上腺病变的能力。
偶然发现的肾上腺“偶发瘤”是在与肾上腺无关的检查中意外发现的肾上腺病变，其发生率高达 5%。增强 CT 平扫期（pre-contrast CT）衰减值高（>10 HU）、<4cm 的小肾上腺偶发瘤需要进一步评估，以计算绝对洗脱百分比（APW）。如果 APW<60%，这些病变被认为是非腺瘤，通常被归类为不确定的肾上腺病变。进一步检查不确定的病变包括更复杂和昂贵的影像学研究或有创程序，如活检或手术切除。
我们在机构数据库中搜索具有以下特征的不确定肾上腺病变：<4cm、平扫期衰减值>10 HU 和 APW<60%。排除标准包括嗜铬细胞瘤和无组织病理学检查。将 CT 图像转换为 Nifti 格式，并使用 Amira 软件对肾上腺肿瘤进行分割。使用 PyRadiomics 软件从肾上腺掩模中提取放射组学特征，然后使用递归特征消除（recursive feature elimination）去除冗余特征（高度两两相关的特征和低方差特征），选择最终有鉴别力的特征集。最后，使用随机森林算法构建二分类模型，使用留一法交叉验证、混淆矩阵和受试者工作特征曲线进行验证和测试。
我们发现了 40 个不确定的肾上腺病变（21 个良性和 19 个恶性）。特征提取产生了 3947 个特征，去除冗余后减少到 62 个特征。递归特征消除得到以下前 4 个有鉴别力的特征：来自平扫期和延迟期的灰度大小区域矩阵衍生的大小区域非均匀性、来自静脉期的灰度依赖矩阵衍生的大依赖性高灰度强调、来自延迟期的灰度共生矩阵衍生的聚类阴影。使用留一法交叉验证的二分类模型显示 AUC=0.85、敏感性=84.2%和特异性=71.4%。
机器学习和放射组学特征提取可以区分良性和恶性不确定的肾上腺肿瘤，并可以通过高敏感性和特异性来指导进一步检查。
