IEEE Trans Med Imaging. 2018 Sep;37(9):2137-2148. doi: 10.1109/TMI.2018.2820742. Epub 2018 Mar 29.
We propose a method based on deep learning to perform cardiac segmentation on short axis Magnetic resonance imaging stacks iteratively from the top slice (around the base) to the bottom slice (around the apex). At each iteration, a novel variant of the U-net is applied to propagate the segmentation of a slice to the adjacent slice below it. In other words, the prediction of a segmentation of a slice is dependent upon the already existing segmentation of an adjacent slice. The 3-D consistency is hence explicitly enforced. The method is trained on a large database of 3078 cases from the U.K. Biobank. It is then tested on the 756 different cases from the U.K. Biobank and three other state-of-the-art cohorts (ACDC with 100 cases, Sunnybrook with 30 cases, and RVSC with 16 cases). Results comparable or even better than the state of the art in terms of distance measures are achieved. They also emphasize the assets of our method, namely, enhanced spatial consistency (currently neither considered nor achieved by the state of the art), and the generalization ability to unseen cases even from other databases.
我们提出了一种基于深度学习的方法，从顶部切片（靠近基底）到底部切片（靠近心尖）迭代地对短轴磁共振成像堆栈进行心脏分割。在每次迭代中，应用一种新的 U 型网络变体将一个切片的分割传播到其下方的相邻切片。换句话说，一个切片的分割预测依赖于已经存在的相邻切片的分割。因此，明确地强制执行了 3D 一致性。该方法在来自英国生物库的 3078 个案例的大型数据库上进行训练。然后在英国生物库的 756 个不同案例以及其他三个最先进的队列（ACDC 有 100 个案例，Sunnybrook 有 30 个案例，RVSC 有 16 个案例）上进行测试。在距离度量方面，我们的方法达到了与最先进技术相当甚至更好的结果。它们还强调了我们方法的优势，即增强的空间一致性（目前既未被最先进技术考虑也未实现），以及对即使来自其他数据库的未见病例的泛化能力。
