Visual classification of pulmonary lesions from endobronchial ultrasonography (EBUS) images is performed by radiologists; therefore, results can be subjective. Here, two robust features, called the adaptive weighted-sum of the upper triangular gray-level co-occurrence matrix (GLCM) and the adaptive weighted-sum of the lower triangular GLCM (AWSL), were combined with 22 other standard features and used as initial input data to assist radiologists. The proposed method integrated the kth percentile of the sum of intensities, a genetic algorithm (GA), and support vector machine (SVM) to classify a lesion, and then applied the kth percentile of the sum of intensities to select the optimal window of interest (WOI) where all the features are extracted. After feature extraction, a GA was used to select only relevant features that were then forwarded to SVM to classify the lesion. Efficiency of the proposed features and the proposed method was evaluated using a dataset of 89 EBUS images with 10-fold cross-validation. Optimal classification results were obtained using 16 selected features from the WOI at the fifth percentile with accuracy, sensitivity, specificity, and precision at 86.52%, 87.27%, 85.29%, and 90.57%, respectively. Among the 16 selected features, six were from the proposed features. The proposed method was compared with other existing methods. Results revealed that the proposed features together with the proposed method significantly improved the classification performance of pulmonary lessons, especially for small datasets.

中文翻译：

---

使用上下三角灰度共生矩阵的自适应加权和从支气管内超声图像进行肺部病变分类

放射科医师根据支气管内超声 (EBUS) 图像对肺部病变进行视觉分类；因此，结果可能是主观的。在这里，两个强大的特征，称为上三角灰度共生矩阵的自适应加权和（GLCM）和下三角灰度共生矩阵的自适应加权和（AWSL），与其他 22 个标准特征相结合并使用作为协助放射科医生的初始输入数据。所提出的方法集成了强度总和的第k个百分位数、遗传算法 (GA) 和支持向量机 (SVM) 对病变进行分类，然后应用k强度总和的第 th 个百分位数，以选择提取所有特征的最佳感兴趣窗口 (WOI)。特征提取后，使用遗传算法仅选择相关特征，然后将其转发到 SVM 以对病变进行分类。使用具有 10 倍交叉验证的 89 个 EBUS 图像的数据集来评估所提出的特征和所提出的方法的效率。使用 WOI 中第 5 个百分位数的 16 个选定特征获得最佳分类结果，准确度、灵敏度、特异性和精确度分别为 86.52%、87.27%、85.29% 和 90.57%。在 16 个选定的特征中，有 6 个来自提议的特征。将所提出的方法与其他现有方法进行了比较。