轻量3D卷积网络结合拓扑特征，提升早产儿脑损伤预测准确率
GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction
- 基于ResNet-10设计轻量3D CNN，融合全局拓扑保持策略
- 在dHCP数据集上达75.18%平均准确率，最高81.82%
- 适合医学影像分析与新生儿脑损伤筛查场景
本研究提出一种自动化深度学习框架，基于T2加权MRI（dHCP数据集）预测早产儿脑损伤（BI）。我们设计了轻量级3D CNN模型GloResNet，基于ResNet-10，并在MedicalNet上预训练以应对数据稀缺。采用全局流形映射策略：先将每例3D图像重采样至128×128×128，再进行受试者级别的z-score强度归一化，从而在标准化外观的同时保留全局拓扑结构。训练中引入mixup、类别权重和测试时增强以提升鲁棒性。在五折交叉验证中，GloResNet平均准确率达75.18%（峰值81.82%），特异性0.81，敏感性0.76。结果表明，具备拓扑感知能力的轻量3D CNN可有效预测新生儿脑损伤，提供一种非侵入性筛查工具。源代码见GitHub：https://github.com/ICL-SUST/GloResNet-Preterm-Brain
原文摘要 · Abstract (English)
This study introduces an automated deep learning framework for predicting brain injury (BI) in preterm infants from T2-weighted MRI (dHCP dataset). We propose GloResNet, a lightweight 3D CNN based on ResNet-10, pretrained on MedicalNet to address data scarcity. A global manifold mapping strategy first resamples each 3D volume to 128x128x128 and then applies subject-wise z-score intensity normalization, thereby preserving global topology while standardizing appearance. Training integrates mixup, class weighting, and test-time augmentation for robustness. In 5-fold cross-validation, GloResNet achieved 75.18% average accuracy (peak 81.82%), with specificity 0.81 and sensitivity 0.76. Results demonstrate that a topology-aware lightweight CNN has the capability to effectively predict neonatal BI, offering a non-invasive screening tool. The source code of this paper can be obtained from the GitHub repository: https://github.com/ICL-SUST/GloResNet-Preterm-Brain
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。