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: this https URL
GloResNet：一种用于早产儿脑损伤预测的轻量级3D卷积神经网络（结合全局拓扑特征） / GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction
该研究提出了一种名为GloResNet的轻量级3D神经网络，通过引入全局流形映射保留脑部全局拓扑结构，结合数据增强和类别平衡策略，在T2加权MRI上以较高准确率（平均75.18%）实现了早产儿脑损伤的无创预测，为临床筛查提供了一种高效、低计算成本的自动化工具。
源自 arXiv: 2606.02498
