Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA; A.A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA; A.A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
Med Image Anal. 2022 Aug;80:102469. doi: 10.1016/j.media.2022.102469. Epub 2022 May 13.
Training deep learning models that segment an image in one step typically requires a large collection of manually annotated images that captures the anatomical variability in a cohort. This poses challenges when anatomical variability is extreme but training data is limited, as when segmenting cardiac structures in patients with congenital heart disease (CHD). In this paper, we propose an iterative segmentation model and show that it can be accurately learned from a small dataset. Implemented as a recurrent neural network, the model evolves a segmentation over multiple steps, from a single user click until reaching an automatically determined stopping point. We develop a novel loss function that evaluates the entire sequence of output segmentations, and use it to learn model parameters. Segmentations evolve predictably according to growth dynamics encapsulated by training data, which consists of images, partially completed segmentations, and the recommended next step. The user can easily refine the final segmentation by examining those that are earlier or later in the output sequence. Using a dataset of 3D cardiac MR scans from patients with a wide range of CHD types, we show that our iterative model offers better generalization to patients with the most severe heart malformations.
训练能够一步分割图像的深度学习模型通常需要大量手动标注的图像，这些图像要能捕捉到队列中的解剖结构变化。当解剖结构变化非常极端但训练数据有限时，例如在先天性心脏病 (CHD) 患者的心脏结构分割中，这就带来了挑战。在本文中，我们提出了一种迭代分割模型，并证明它可以从小数据集准确地学习。该模型实现为递归神经网络，在多个步骤中逐渐生成分割，从用户的单次点击开始，直到达到自动确定的停止点。我们开发了一种新的损失函数，可以评估整个输出分割序列，并使用它来学习模型参数。分割根据训练数据中包含的增长动态进行可预测的演变，这些数据包括图像、部分完成的分割以及推荐的下一步。用户可以通过检查输出序列中更早或更晚的分割来轻松细化最终分割。我们使用来自患有各种 CHD 类型的患者的 3D 心脏 MR 扫描数据集，表明我们的迭代模型对心脏畸形最严重的患者具有更好的泛化能力。
