IEEE J Biomed Health Inform. 2015 Sep;19(5):1627-36. doi: 10.1109/JBHI.2015.2425041. Epub 2015 Apr 21.
Automatic localization of the standard plane containing complicated anatomical structures in ultrasound (US) videos remains a challenging problem. In this paper, we present a learning-based approach to locate the fetal abdominal standard plane (FASP) in US videos by constructing a domain transferred deep convolutional neural network (CNN). Compared with previous works based on low-level features, our approach is able to represent the complicated appearance of the FASP and hence achieve better classification performance. More importantly, in order to reduce the overfitting problem caused by the small amount of training samples, we propose a transfer learning strategy, which transfers the knowledge in the low layers of a base CNN trained from a large database of natural images to our task-specific CNN. Extensive experiments demonstrate that our approach outperforms the state-of-the-art method for the FASP localization as well as the CNN only trained on the limited US training samples. The proposed approach can be easily extended to other similar medical image computing problems, which often suffer from the insufficient training samples when exploiting the deep CNN to represent high-level features.
在超声（US）视频中自动定位包含复杂解剖结构的标准平面仍然是一个具有挑战性的问题。在本文中，我们提出了一种基于学习的方法，通过构建域转移深度卷积神经网络（CNN）来定位胎儿腹部标准平面（FASP）。与以前基于底层特征的工作相比，我们的方法能够表示 FASP 的复杂外观，从而实现更好的分类性能。更重要的是，为了减少由于训练样本数量少而导致的过拟合问题，我们提出了一种迁移学习策略，该策略将从大型自然图像数据库中训练的基础 CNN 的低层知识转移到我们特定于任务的 CNN 中。大量实验表明，我们的方法在 FASP 定位方面优于最先进的方法，并且优于仅在有限的 US 训练样本上训练的 CNN。所提出的方法可以很容易地扩展到其他类似的医学图像计算问题，在利用深度 CNN 表示高级特征时，这些问题经常受到训练样本不足的影响。
