用深度学习精准分割早产儿脑部灰白质，助力早期神经发育评估
Deep learning-based neurodevelopmental assessment in preterm infants
- 设计层级密集注意力网络，增强低对比度脑影像的组织区分能力
- 在早产儿脑MRI上实现优于现有方法的灰白质分割精度
- 发现早产儿灰白质体积显著小于足月儿，支持早产神经发育迟缓论
早产儿（孕周28至37周）存在较高的神经发育迟缓风险，早期识别对及时干预至关重要。尽管基于深度学习的脑部MRI体积分割为新生儿神经发育评估提供了前景，但因早产儿大脑早期灰质与白质信号强度相近（等信号外观），准确分割仍具挑战。为此，我们提出一种新型分割神经网络——分层密集注意力网络（Hierarchical Dense Attention Network）。该架构融合三维空间-通道注意力机制与注意力引导的密集上采样策略，以提升低对比度体数据中的特征判别力。定量实验表明，本方法在分割性能上优于当前最先进基准，有效解决了等信号组织的区分难题。进一步应用显示，早产儿灰质与白质体积显著低于足月儿，为早产导致神经发育迟缓提供了新的影像学证据。代码已开源：https://github.com/ICL-SUST/HDAN。
原文摘要 · Abstract (English)
Preterm infants (born between 28 and 37 weeks of gestation) face elevated risks of neurodevelopmental delays, making early identification crucial for timely intervention. While deep learning-based volumetric segmentation of brain MRI scans offers a promising avenue for assessing neonatal neurodevelopment, achieving accurate segmentation of white matter (WM) and gray matter (GM) in preterm infants remains challenging due to their comparable signal intensities (isointense appearance) on MRI during early brain development. To address this, we propose a novel segmentation neural network, named Hierarchical Dense Attention Network. Our architecture incorporates a 3D spatial-channel attention mechanism combined with an attention-guided dense upsampling strategy to enhance feature discrimination in low-contrast volumetric data. Quantitative experiments demonstrate that our method achieves superior segmentation performance compared to state-of-the-art baselines, effectively tackling the challenge of isointense tissue differentiation. Furthermore, application of our algorithm confirms that WM and GM volumes in preterm infants are significantly lower than those in term infants, providing additional imaging evidence of the neurodevelopmental delays associated with preterm birth. The code is available at: https://github.com/ICL-SUST/HDAN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。