Skip to content
Open access

A deep learning framework for automated cervical spinal cord vertebral labeling and morphometric extraction from brain MRI with large-scale multicenter validation

Oct 2026 · npj Digital Medicine · 0 citations

TL;DR

This pipeline enables scalable, reliable vertebral labeling and morphometric extraction of the upper cervical SC for multicenter studies and supports biomarker development in neurodegenerative diseases.

Abstract

This study aimed to develop and validate a fully automated pipeline for vertebral level identification (C1–C3) of the upper cervical spinal cord (SC) in T1-weighted brain MRI with a quality control module to assess the generated masks. MRI data from 998 controls and 879 patients with hereditary ataxias (32 sites; age 5–85 years; 46% male) were used to train deep learning models (nnU-Net, U-Net with deep supervision, SwinUNETR) for automatic vertebral labeling of C1–C3 levels. A secondary model based on VGG, ResNet, and EfficientNet architectures was trained to identify vertebral labeling errors. The pipeline also generates image quality metrics including signal-to-noise ratio, contrast-to-noise ratio, coefficient of joint variation, and entropy focus criterion. External validation was performed using 2737 MRIs from four public datasets, and clinical utility was demonstrated in a longitudinal cohort of 51 patients with multiple sclerosis. The nnU-Net achieved the highest performance (Dice: C1 = 0.85, C2 = 0.89, C3 = 0.89), labeling 95.8% of mislabeled cases from the Spinal Cord Toolbox. The VGG-based classifier achieved 97.9% accuracy and 98.7% sensitivity. External validation showed labeling accuracies exceeding 92% in four of five datasets and sensitivity to longitudinal SC atrophy in multiple sclerosis. This pipeline enables scalable, reliable vertebral labeling and morphometric extraction of the upper cervical SC for multicenter studies and supports biomarker development in neurodegenerative diseases.

Read PDF

Similar papers

Open access Oct 2026

Construction and validation of a unified 3D convolutional neural network framework for automated identification of cervical spinal cord injury based on CT imaging

To construct and validate a standardized three-dimensional convolutional neural network (3D CNN) framework based on cervical spine CT imaging for automated identification of cervical spinal cord injury (CSCI), and to evaluate its stability across multicenter data and potential clinical applicability. Cervical spine CT...

De-Yan Ou, Yong-Xin Mo, Yu Huang et al. · 0 citations
Review Open access Apr 2026

Deep learning-based detection of focal cortical dysplasia in children: External validation of the MELD Graph and 3D-nnUNet pipelines

Two recently developed deep-learning approaches for FCD detection, MELD Graph and 3D-nnUNet, are externally validated in a pediatric cohort, indicating that they are valuable decision-support tools but cannot replace expert neuroradiological evaluation.

A. Dell'Orco, E. De Vita, F. D'Arco et al. · 0 citations
#graph neural networks Review Open access Oct 2026

Multi-centre validation of MELD-graph for automated focal cortical dysplasia detection using 7T compared to paired 3T MRI

Background: Software tools can support MRI diagnosis of focal cortical dysplasias (FCDs) - subtle, surgically-treatable lesions that underlie drug-resistant focal epilepsy (DRFE). MELD-graph, a widely used open-source tool combining surface-based morphometry with a convolutional neural network, was developed using 1.5T...

C. Kronlage, M. Ripart, R. Piper et al. · 0 citations
Conference Open access Sep 2026

Explainable Deep Learning for High-Grade Glioma Detection in Multi-Sequence Brain MRI

An explainable framework using the Gazi Brains 2020 dataset, comprising 50 patients with high-grade glioma and 50 normal controls, is presented, which combines leakage-aware evaluation, quantitative explanation validation, shortcut testing, and external generalization analysis.

Melih Koyunçal, Semih Koyunçal, Cemil Zalluhoğlu · 0 citations
Open access Oct 2026

Impact of DWI quality and tumor complexity on deep learning-based segmentation of rectal cancer using multicenter MRI data

Deep learning-based segmentation achieved performance comparable to expert reader agreement; increased tumor complexity reduced segmentation performance, whereas DWI quality had no significant impact.

J. V. van Griethuysen, D. Lambregts, N. Schurink et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.