Two-stage deep learning pipeline detects neonatal brain pathologies from MRI with 0.919 AUC
Dr_Alex_Crimi · x · 2026-10-30
A new Frontiers in Neuroimaging paper presents a hierarchical two-stage deep learning pipeline that emulates clinical reasoning on paired T1/T2-weighted neonatal brain MRI.
- Stage 1: a 3D ResNet-18 brain-age gap regressor screens for myelination delay (R² = 0.941)
- Stage 2: a second 3D ResNet-18 classifies normal vs HIE vs hydrocephalus, achieving AUC 0.919 ± 0.024
- Motivation: preterm myelination delay can mask concurrent structural pathologies, which flat classifiers discard
- Dataset: 566 normal, 56 HIE, 38 hydrocephalus, 27 preterm cases
- Models and code are open-sourced
Related event: Two-stage 3D ResNet screens neonatal brain disorders from MRI(2 posts)→
More from Research
- Stanford study: walking boosts creative thinking scores in 81% of participants — beechinour · 2026-10-31
- New monograph argues 20-watt neuromorphic AI can complement power-hungry transformers — ziv_ravid · 2026-10-31
- Study: none of today's SOTA latent world models faithfully model environment dynamics — udmrzn · 2026-10-31
- kalomaze shares LoRA finetuning loss curves: 3 epochs plus WSD decay beats 1-epoch regime — kalomaze · 2026-10-31
- Fused Zip-NeRF: CUDA rewrite trains 6-7x faster, renders 10x faster on a 5090 — jon_barron · 2026-10-31
- Simulated eval reliably detects direction of model gains, not magnitude — SRSchmidgall · 2026-10-31