GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a computer program called GloResNet that uses 3D brain scans (MRIs) to predict brain injuries in premature babies. They designed it to work well even with limited data by training it on related medical images and using special techniques to keep important brain structure details. Their testing showed the program predicted brain injury with about 75% accuracy. This approach could help doctors screen for brain problems in newborns without invasive tests.
Preterm infantsBrain injuryT2-weighted MRI3D convolutional neural networkResNetMedicalNetData normalizationMixup augmentationClass weightingTest-time augmentation
Authors
Boyu Yuan, Jiamiao Lu, Weichuan Zhang, Benqing Wu, Tuo Wang, Changshan Wang, Changming Sun, Liang Guo
Abstract
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