{"ID":2923525,"CreatedAt":"2026-06-02T04:05:25.881865328Z","UpdatedAt":"2026-06-04T13:12:39.622923895Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.02498","arxiv_id":"2606.02498","title":"GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction","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","short_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...","url_abs":"https://arxiv.org/abs/2606.02498","url_pdf":"https://arxiv.org/pdf/2606.02498v1","authors":"[\"Boyu Yuan\",\"Jiamiao Lu\",\"Weichuan Zhang\",\"Benqing Wu\",\"Tuo Wang\",\"Changshan Wang\",\"Changming Sun\",\"Liang Guo\"]","published":"2026-06-01T17:04:43Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":612663,"CreatedAt":"2026-06-02T04:05:25.881865328Z","UpdatedAt":"2026-06-02T04:05:25.881865328Z","DeletedAt":null,"paper_id":2923525,"paper_url":"https://arxiv.org/abs/2606.02498","paper_title":"GloResNet: A lightweight 3D CNN with global topological features for preterm brain injury prediction","repo_url":"https://github.com/ICL-SUST/GloResNet-Preterm-Brain","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}