Molecular Medicine Laboratory, Department of Research, Changhua Christian Hospital, 8F., No. 235, XuGuang Road, Changhua, Taiwan.
Comprehensive Breast Cancer Center, Changhua Christian Hospital, No. 135, NanXiao Street, Changhua, Taiwan.
Comput Med Imaging Graph. 2021 Jan;87:101829. doi: 10.1016/j.compmedimag.2020.101829. Epub 2020 Nov 27.
In this study, a transfer learning method was utilized to recognize and classify benign and malignant breast tumors, using two-dimensional breast ultrasound (US) images, to decrease the effort expended by physicians and improve the quality of clinical diagnosis. The pretrained deep residual network model was utilized for image feature extraction from the convolutional layer of the trained network; whereas, the linear support vector machine (SVM), with a sequential minimal optimization solver, was used to classify the extracted feature. We used an image dataset with 2099 unlabeled two-dimensional breast US images, collected from 543 patients (benign: 302, malignant: 241). The classification performance yielded a sensitivity of 94.34 % and a specificity of 93.22 % for malignant images (Area under curve = 0.938). The positive and negative predictive values were 92.6 and 94.8, respectively. A comparison between the diagnosis made by the physician and the automated classification by a trained classifier, showed that the latter had significantly better outcomes. This indicates the potential applicability of the proposed approach that incorporates both the pretrained deep learning network and a well-trained classifier, to improve the quality and efficacy of clinical diagnosis.
在这项研究中，利用迁移学习方法，使用二维乳腺超声（US）图像识别和分类良性和恶性乳腺肿瘤，以减少医生的工作量并提高临床诊断质量。使用预先训练的深度残差网络模型从训练网络的卷积层提取图像特征；而线性支持向量机（SVM），带有顺序最小优化求解器，用于对提取的特征进行分类。我们使用了一个包含 2099 张未标记二维乳腺超声图像的图像数据集，这些图像来自 543 名患者（良性：302 例，恶性：241 例）。对于恶性图像，分类性能的灵敏度为 94.34%，特异性为 93.22%（曲线下面积=0.938）。阳性预测值和阴性预测值分别为 92.6%和 94.8%。医生诊断和经过训练的分类器自动分类之间的比较表明，后者的结果明显更好。这表明了所提出的方法的潜在适用性，该方法结合了预先训练的深度学习网络和经过良好训练的分类器，以提高临床诊断的质量和效果。
