An AI can build a perfect 3D model of a child's spine using only MRI data, completely removing the need for dangerous X-rays.
April 23, 2026
Original Paper
AI Approach for MRI-only Full-Spine Vertebral Segmentation and 3D Reconstruction in Paediatric Scoliosis
arXiv · 2604.17846
The Takeaway
Children with scoliosis often require dozens of CT scans and X-rays to monitor their bone growth, exposing them to high doses of radiation. This new framework uses neural networks to see the bone structure hidden within soft tissue MRI images. The resulting 3D reconstruction is just as accurate as a CT scan but carries zero risk of cancer from radiation. This shift makes long term spinal monitoring safe for every pediatric patient.
From the abstract
MRI is preferred over CT in paediatric imaging because it avoids ionising radiation, but its use in spine deformity assessment is largely limited by the lack of automated, high-resolution 3D bony reconstruction, which continues to rely on CT. MRI-based 3D reconstruction remains impractical due to manual workflows and the scarcity of labelled full-spine datasets. This study introduces an AI framework that enables fully automated thoracolumbar spine (T1-L5) segmentation and 3D reconstruction from