Vicomtech Foundation, San Sebastián, Spain.
Vicomtech Foundation, San Sebastián, Spain.
Comput Methods Programs Biomed. 2021 Nov;211:106368. doi: 10.1016/j.cmpb.2021.106368. Epub 2021 Aug 31.
Breast density refers to the proportion of glandular and fatty tissue in the breast and is recognized as a useful factor assessing breast cancer risk. Moreover, the segmentation of the high-density glandular tissue from mammograms can assist medical professionals visualizing and localizing areas that may require additional attention. Developing robust methods to segment breast tissues is challenging due to the variations in mammographic acquisition systems and protocols. Deep learning methods are effective in medical image segmentation but they often require large quantities of labelled data. Unsupervised domain adaptation is an area of research that employs unlabelled data to improve model performance on variations of samples derived from different sources.
First, a U-Net architecture was used to perform segmentation of the fatty and glandular tissues with labelled data from a single acquisition device. Then, adversarial-based unsupervised domain adaptation methods were used to incorporate single unlabelled target domains, consisting of images from a different machine, into the training. Finally, the domain adaptation model was extended to include multiple unlabelled target domains by combining a reconstruction task with adversarial training.
The adversarial training was found to improve the generalization of the initial model on new domain data, demonstrating clearly improved segmentation of the breast tissues. For training with multiple unlabelled domains, combining a reconstruction task with adversarial training improved the stability of the training and yielded adequate segmentation results across all domains with a single model.
Results demonstrated the potential for adversarial-based domain adaptation with U-Net architectures for segmentation of breast tissue in mammograms coming from several devices and demonstrated that domain-adapted models could achieve a similar agreement with manual segmentations. It has also been found that combining adversarial and reconstruction-based methods can provide a simple and effective solution for training with multiple unlabelled target domains.
乳腺密度是指乳腺中腺体和脂肪组织的比例，被认为是评估乳腺癌风险的有用因素。此外，从乳房 X 光片中对高密度腺体组织进行分割可以帮助医学专业人员可视化和定位需要额外关注的区域。由于乳腺 X 光采集系统和协议的变化，开发用于分割乳腺组织的健壮方法具有挑战性。深度学习方法在医学图像分割中非常有效，但它们通常需要大量标记数据。无监督域自适应是一个研究领域，它使用未标记的数据来提高模型在来自不同来源的样本变化上的性能。
首先，使用 U-Net 架构使用来自单个采集设备的标记数据对脂肪和腺体组织进行分割。然后，使用基于对抗的无监督域自适应方法将单个未标记的目标域（由来自不同机器的图像组成）纳入训练中。最后，通过将重建任务与对抗训练相结合，将域自适应模型扩展到包含多个未标记的目标域。
对抗训练被发现可以提高初始模型在新域数据上的泛化能力，明显改善了乳腺组织的分割。对于使用多个未标记的目标域进行训练，将重建任务与对抗训练相结合可以提高训练的稳定性，并使用单个模型在所有域中获得足够的分割结果。
结果表明，基于对抗的 U-Net 架构的域自适应在来自多个设备的乳房 X 光片中分割乳腺组织具有潜力，并表明适应域的模型可以与手动分割达到相似的一致性。还发现，结合对抗和基于重建的方法可以为使用多个未标记的目标域提供一种简单有效的训练解决方案。
