Chang Jie-Fan, Huang Chiun-Sheng, Chang Ruey-Feng
Department of Computer Science and Information Engineering, National Taiwan University, Taipei 10617, Taiwan.
Department of Surgery, National Taiwan University Hospital, Taipei 100, Taiwan.
Comput Methods Programs Biomed. 2020 Dec;197:105727. doi: 10.1016/j.cmpb.2020.105727. Epub 2020 Aug 26.
Women with higher breast densities have a relatively higher risk to be diagnosed with breast cancer. Hand-held ultrasound (HHUS) can provide precise screening results and detect masses in dense breasts. However, its lack of position information and automatic extraction of breast area hinder the implementation of density estimation. To facilitate reliable breast density evaluation, this study proposed an upgraded version of our whole-breast ultrasound (WBUS) system, which not only can provide precise position information, but also can extract precise breast area automatically based on deep learning method.
WBUS images with probe position information were collected from 117 women. For each case, an automatic breast region segmentation by DeepResUnet was conducted, then fibroglandular tissues were extracted from breast region using fuzzy c-mean (FCM) classifier. Finally, the percentage of breast density and breast area of the DeepResUnet predicted region and the breast region of the ground truth were calculated and compared.
The average and standard deviation of each breast case for DeepResUnet predicted breast region of 10-fold in Accuracy (ACC) was 0.963±0.054. Sensitivity (SENS) was 0.928±0.11. Specificity (SPEC) was 0.967±0.054. Dice coefficient (Dice) was 0.916±0.98. Region intersection over union (IoU) was 0.856±0.134. Significant and very high correlations of breast density, fibroglandular tissue area and breast area (R = 0.843, R= 0.822 and R = 0.984, all p values < 0.001) were found between the ground truth and the result of the proposed method for ultrasound images.
Breast density, fibroglandular tissue, and breast volume evaluated based on the proposed method and WBUS system have significant correlations with ground truth, indicating that the proposed method and WBUS system has the potential to be an alternative modality for breast screening and density estimation in clinical use.
乳腺密度较高的女性被诊断出患有乳腺癌的风险相对较高。手持超声（HHUS）能够提供精确的筛查结果，并检测致密乳腺中的肿块。然而，其缺乏位置信息以及乳腺区域的自动提取功能阻碍了密度估计的实施。为了便于进行可靠的乳腺密度评估，本研究提出了我们全乳腺超声（WBUS）系统的升级版，该系统不仅可以提供精确的位置信息，还能够基于深度学习方法自动提取精确的乳腺区域。
从117名女性中收集了带有探头位置信息的WBUS图像。对于每个病例，使用深度残差U型网络（DeepResUnet）进行自动乳腺区域分割，然后使用模糊C均值（FCM）分类器从乳腺区域中提取纤维腺体组织。最后，计算并比较DeepResUnet预测区域和真实乳腺区域的乳腺密度百分比以及乳腺面积。
DeepResUnet预测乳腺区域的10倍交叉验证中，每个乳腺病例的准确率（ACC）平均值和标准差为0.963±0.054。灵敏度（SENS）为0.928±0.11。特异性（SPEC）为0.967±0.054。骰子系数（Dice）为0.916±0.98。区域交并比（IoU）为0.856±0.134。在真实情况与所提出的超声图像方法的结果之间，发现乳腺密度、纤维腺体组织面积和乳腺面积具有显著且非常高的相关性（R = 0.843，R = 0.822和R = 0.984，所有p值<0.001）。
基于所提出的方法和WBUS系统评估的乳腺密度、纤维腺体组织和乳腺体积与真实情况具有显著相关性，表明所提出的方法和WBUS系统有可能成为临床应用中乳腺筛查和密度估计的替代方式。
