Department of Ultrasound, The First Affiliated Hospital of Shantou University Medical College, 57 Changping Road, Longhu District, Shantou, Guangdong, China.
Department of Electronic Engineering, Shantou University, No.243, Daxue Road, Tuo Jiang Street, Jinping District, Shantou City, Guangdong, China.
Comput Methods Programs Biomed. 2022 Oct;225:107052. doi: 10.1016/j.cmpb.2022.107052. Epub 2022 Jul 31.
Breast cancer is a high incidence of gynecological diseases; breast ultrasound screening can effectively reduce the mortality rate of breast cancer. In breast ultrasound images, the localization and segmentation of tumor lesions are important steps for the extraction of lesions, which helps clinicians evaluate breast lesions quantitatively and makes better clinical diagnosis of the disease. However, the segmentation of breast lesions is difficult due to the blurred and uneven edges of some lesions. In this paper, we propose a segmentation framework combining active contour module and deep learning adversarial mechanism and apply it for the segmentation of breast tumor lesions.
We use a conditional adversarial network as the main framework. The generator is a segmentation network consisting of a Deformed U-Net and an active contour module. Here, the Deformed U-Net performs pixel-level segmentation for breast ultrasound images. The active contour module refines the tumor lesion edges, and the refined result provides loss information for Deformed U-Net. Therefore, the Deformed U-Net can better classify the edge pixels. The discriminator is the Markov discriminator; this discriminator provides loss feedback for the segmentation network. We cross-train the discriminator and segmentation network to implement Adversarial Mechanism for getting a more optimized segmentation network.
The segmentation performance of the segmentation network for breast ultrasound images is improved by adding a Markov discriminator to provide discriminant loss training. The proposed method for segmenting the tumor lesions in breast ultrasound image obtains dice coefficient: 89.7%, accuracy: 98.1%, precision: 86.3%, mean-intersection-over-union: 82.2%, recall: 94.7%, specificity: 98.5% and F1score: 89.7%.
Comparing with traditional methods, the proposed method gives better performance. The experimental results show that the proposed method can effectively segment the lesions in breast ultrasound images, and then assist doctors to realize the diagnosis of breast lesions.
乳腺癌是一种高发病率的妇科疾病；乳腺超声筛查可以有效降低乳腺癌死亡率。在乳腺超声图像中，肿瘤病变的定位和分割是提取病变的重要步骤，有助于临床医生对乳腺病变进行定量评估，从而对疾病做出更好的临床诊断。但是，由于一些病变的边缘模糊和不均匀，使得乳腺病变的分割变得困难。本文提出了一种结合主动轮廓模型和深度学习对抗机制的分割框架，并将其应用于乳腺肿瘤病变的分割。
我们使用条件对抗网络作为主要框架。生成器是一个由变形 U-Net 和主动轮廓模型组成的分割网络。这里，变形 U-Net 对乳腺超声图像进行像素级分割。主动轮廓模型细化肿瘤病变的边缘，细化结果为变形 U-Net 提供损失信息。因此，变形 U-Net 可以更好地对边缘像素进行分类。鉴别器是马尔可夫鉴别器；该鉴别器为分割网络提供损失反馈。我们交叉训练鉴别器和分割网络，以实现对抗机制，从而得到更优化的分割网络。
通过添加马尔可夫鉴别器来提供判别损失训练，提高了分割网络对乳腺超声图像的分割性能。所提出的用于分割乳腺超声图像中肿瘤病变的方法获得的骰子系数为 89.7%，准确率为 98.1%，精度为 86.3%，平均交并比为 82.2%，召回率为 94.7%，特异性为 98.5%，F1 得分为 89.7%。
与传统方法相比，该方法具有更好的性能。实验结果表明，该方法能够有效地分割乳腺超声图像中的病变，辅助医生实现对乳腺病变的诊断。
