Accurate segmentation of infant brain images into different regions of interest is one of the most important fundamental steps in studying early brain development. In the isointense phase (approximately 6–8 months of age), white matter and gray matter exhibit similar levels of intensities in magnetic resonance (MR) images, due to the ongoing myelination and maturation. This results in extremely low tissue contrast and thus makes tissue segmentation very challenging. Existing methods for tissue segmentation in this isointense phase usually employ patch-based sparse labeling on single modality. To address the challenge, we propose a novel 3-D multimodal fully convolutional network (FCN) architecture for segmentation of isointense phase brain MR images. Specifically, we extend the conventional FCN architectures from 2-D to 3-D, and, rather than directly using FCN, we intuitively integrate coarse (naturally high-resolution) and dense (highly semantic) feature maps to better model tiny tissue regions, in addition, we further propose a transformation module to better connect the aggregating layers; we also propose a fusion module to better serve the fusion of feature maps. We compare the performance of our approach with several baseline and state-of-the-art methods on two sets of isointense phase brain images. The comparison results show that our proposed 3-D multimodal FCN model outperforms all previous methods by a large margin in terms of segmentation accuracy. In addition, the proposed framework also achieves faster segmentation results compared to all other methods. Our experiments further demonstrate that: 1) carefully integrating coarse and dense feature maps can considerably improve the segmentation performance; 2) batch normalization can speed up the convergence of the networks, especially when hierarchical feature aggregations occur; and 3) integrating multimodal information can further boost the segmentation performance.

中文翻译：

---

用于多模态等强度婴儿脑图像分割的 3-D 全卷积网络

将婴儿大脑图像准确分割成不同的感兴趣区域是研究早期大脑发育的最重要的基本步骤之一。在等信号阶段（大约 6-8 个月大），由于正在进行的髓鞘形成和成熟，白质和灰质在磁共振 (MR) 图像中表现出相似的强度水平。这导致组织对比度极低，从而使组织分割非常具有挑战性。现有的等强度阶段的组织分割方法通常在单一模态上采用基于补丁的稀疏标记。为了应对这一挑战，我们提出了一种新颖的 3D 多模态全卷积网络 (FCN) 架构，用于等强度相位脑 MR 图像的分割。具体来说，我们将传统的 FCN 架构从 2-D 扩展到 3-D，并且我们不是直接使用 FCN，而是直观地集成粗略（自然高分辨率）和密集（高度语义）特征图，以更好地建模微小组织区域，此外，我们进一步提出了一个转换模块来更好地连接聚合层；我们还提出了一个融合模块来更好地服务于特征图的融合。我们在两组等信号相脑图像上将我们的方法的性能与几种基线和最先进的方法进行比较。比较结果表明，我们提出的 3-D 多模态 FCN 模型在分割精度方面大幅优于之前的所有方法。此外，与所有其他方法相比，所提出的框架还实现了更快的分割结果。我们的实验进一步证明：1）仔细整合粗略和密集的特征图可以显着提高分割性能；2）批量归一化可以加速网络的收敛，特别是当发生分层特征聚合时；3）整合多模态信息可以进一步提高分割性能。