基于全卷积残差神经网络U-Net的乳腺MRI乳腺与纤维腺体组织自动分割
研究用U-net深度学习在286例单侧乳腺癌患者对侧正常乳腺MRI上训练,10折交叉验证后,在28名正常志愿者四种不同MR扫描仪影像上独立验证。训练集乳腺DSC均值0.95±0.02、FGT均值0.91±0.03;验证集224个乳腺乳腺DSC均值0.86±0.05、FGT均值0.83±0.06。U-net算法可在MRI上实现乳腺与FGT的准确分割,可能为乳腺密度定量分析提供可靠高效的方法。
要点
- U-net在训练集10折交叉验证中乳腺分割DSC均值0.95±0.02,FGT均值0.91±0.03。
- 独立验证集224个乳腺乳腺分割DSC均值0.86±0.05,FGT均值0.83±0.06。
- 四种不同MR扫描仪获得的MRI测试结果相当。
核心结论
- 基于U-net的深度学习算法可在MRI上实现乳腺与FGT的准确分割。
- 该方法可能为大批量MR图像的乳腺密度定量分析提供可靠且高效的处理手段。
研究设计与样本
- 研究采用U-net深度学习算法进行乳腺分割,训练集为286例单侧乳腺癌患者的MRI,分割在健侧正常乳腺上进行。
- 乳腺与纤维腺体组织(FGT)的参考标准由基于模板的分割方法获得,最终模型通过10折交叉验证获得。
- 独立验证集为28名正常志愿者的MRI,使用四种不同MR扫描仪采集,共224个测试乳腺。
- 采用Dice相似系数(DSC)、基于体素的准确率和Pearson相关进行性能评价。
诊断标准与关键数值
- 训练集286例10折交叉验证:乳腺DSC范围0.83-0.98(均值0.95±0.02),FGT DSC范围0.73-0.97(均值0.91±0.03)。
- 训练集286例10折交叉验证:乳腺准确率范围0.92-0.99(均值0.98±0.01),FGT准确率范围0.87-0.99(均值0.97±0.01)。
- 验证集28名正常志愿者共224个乳腺:乳腺DSC均值0.86±0.05,FGT DSC均值0.83±0.06。
- 验证集224个乳腺:乳腺准确率均值0.94±0.03,FGT准确率均值0.93±0.04。
- 使用四种不同扫描仪采集的MRI测试结果相当。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
RATIONALE AND OBJECTIVES: Breast segmentation using the U-net architecture was implemented and tested in independent validation datasets to quantify fibroglandular tissue volume in breast MRI.
MATERIALS AND METHODS: Two datasets were used. The training set was MRI of 286 patients with unilateral breast cancer. The segmentation was done on the contralateral normal breasts. The ground truth for the breast and fibroglandular tissue (FGT) was obtained by using a template-based segmentation method. The U-net deep learning algorithm was implemented to analyze the training set, and the final model was obtained using 10-fold cross-validation. The independent validation set was MRI of 28 normal volunteers acquired using four different MR scanners. Dice Similarity Coefficient (DSC), voxel-based accuracy, and Pearson's correlation were used to evaluate the performance.
RESULTS: For the 10-fold cross-validation in the initial training set of 286 patients, the DSC range was 0.83-0.98 (mean 0.95 ± 0.02) for breast and 0.73-0.97 (mean 0.91 ± 0.03) for FGT; and the accuracy range was 0.92-0.99 (mean 0.98 ± 0.01) for breast and 0.87-0.99 (mean 0.97 ± 0.01) for FGT. For the entire 224 testing breasts of the 28 normal volunteers in the validation datasets, the mean DSC was 0.86 ± 0.05 for breast, 0.83 ± 0.06 for FGT; and the mean accuracy was 0.94 ± 0.03 for breast and 0.93 ± 0.04 for FGT. The testing results for MRI acquired using four different scanners were comparable.
CONCLUSION: Deep learning based on the U-net algorithm can achieve accurate segmentation results for the breast and FGT on MRI. It may provide a reliable and efficient method to process large number of MR images for quantitative analysis of breast density.
引用
- Zhang Y, Chen JH, Chang KT, et al. Automatic Breast and Fibroglandular Tissue Segmentation in Breast MRI Using Deep Learning by a Fully-Convolutional Residual Neural Network U-Net. Acad Radiol. 2019. PMID: 30713130. doi:10.1016/j.acra.2019.01.012
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。