Mari State University, Ministry of Education and Science of Russian Federation, 1 Lenin Square, Yoshkar-Ola, 424000, Russia.
Kazan (Volga region) Federal University, Ministry of Education and Science of Russian Federation, 18 Kremlevskaya St., Kazan, 420008, Russia.
Int J Comput Assist Radiol Surg. 2022 Feb;17(2):219-228. doi: 10.1007/s11548-021-02522-x. Epub 2021 Nov 2.
The amount of ultrasound (US) breast examinations continues to grow rapidly because of the wider endorsement of breast cancer screening programs. Cysts are the most commonly diagnosed breast lesions. Atypical breast cysts can be a serious differentiation problem in the US. Our goal was to develop noninvasive automated US grayscale image analysis for the cystic and solid breast lesion differentiation based on mathematical image post-processing.
We used a set of 217 ultrasound images of proven 107 cystic (including 53 atypical) and 110 solid lesions. Empirical statistical and morphological models of the lesions were used to obtain features. The AUC indicator and Student's t test were used to assess the quality of the individual features. The Pearson correlation matrix was used to calculate the correlation between various features. The LASSO and stepwise regression methods were used to determine the most significant features. Finally, the lesion classification was carried out by the various methods.
The use of LASSO regression for the feature selection made it possible to select the most significant features for classification. The sensitivity increased from 87.1% to 89.2% and the specificity-from 92.2 to 94.8%. After the correlation matrix construction, it was found that features with a high value of the correlation coefficient (0.72; 0.75) can also be used to improve the quality of the classification.
The construction of the empirical model of the lesion pixels brightness behavior can provide parameters that are important for the correct classification of ultrasound images. The optimal set of features with the maximum discriminant characteristics may not be consistent with the correlation of features and the value of the AUC index. Features with a low AUC index (in our case 0.72) can also be important for improving the quality of the classification.
由于乳腺癌筛查计划的广泛推广，超声（US）乳房检查的数量继续快速增长。囊肿是最常见的诊断性乳房病变。不典型的乳腺囊肿在 US 中可能是一个严重的鉴别问题。我们的目标是开发基于数学图像后处理的非侵入性自动 US 灰度图像分析，用于囊性和实性乳房病变的鉴别。
我们使用了一组 217 张经证实的 107 个囊性（包括 53 个不典型）和 110 个实性病变的超声图像。使用病变的经验统计和形态学模型来获得特征。使用 AUC 指标和学生 t 检验来评估各个特征的质量。使用 Pearson 相关矩阵来计算各种特征之间的相关性。使用 LASSO 和逐步回归方法来确定最重要的特征。最后，通过各种方法对病变进行分类。
使用 LASSO 回归进行特征选择，可以选择最适合分类的特征。敏感性从 87.1%增加到 89.2%，特异性从 92.2%增加到 94.8%。在构建相关矩阵后，发现相关系数（0.72；0.75）值较高的特征也可以用于提高分类质量。
构建病变像素亮度行为的经验模型可以提供对正确分类超声图像很重要的参数。具有最大鉴别特征的最佳特征集可能与特征的相关性和 AUC 指数的值不一致。AUC 指数较低（在我们的情况下为 0.72）的特征也可能对提高分类质量很重要。
