Related Experiment Video
Updated: Feb 25, 2026
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
Published on: December 15, 2023
Identifying relevant biomarkers of brain injury from structural MRI: Validation using automated approaches in
Alex M Pagnozzi1,2, Nicholas Dowson1, James Doecke1
1CSIRO Health and Biosecurity, The Australian e-Health Research Centre, Brisbane, Australia.
Insights
Automated quantification of brain injuries from structural MRI in children with cerebral palsy (CP) shows strong links to clinical function. This approach can improve early assessment and understanding of CP.
Area of Science:
- Neuroimaging
- Pediatric Neurology
- Biomarkers
Background:
- Structural Magnetic Resonance Imaging (sMRI) is crucial for assessing brain injury in children with cerebral palsy (CP).
- Current qualitative assessments of sMRI findings limit its clinical utility.
- Quantifying brain injuries like cortical malformations, white/grey matter lesions, and ventricular enlargement is underexploited.
Purpose of the Study:
- To develop and validate automated techniques for quantifying three classes of brain injury from sMRI in children.
- To identify injury severity biomarkers predictive of clinical function in children with CP.
- To assess the association between quantified sMRI injuries and clinical outcomes.
Main Methods:
- Developed automated quantification techniques for cortical malformations, white/grey matter lesions, and ventricular enlargement.
- Utilized a feature selection approach on a training dataset (n=97) to identify predictive biomarkers.
- Validated the best models on an independent test dataset (n=42) from a cohort of 139 children (aged 5-17) with unilateral CP.
Main Results:
- Automated quantification of ventricular enlargement (70%), white/grey matter lesions (55%), and cortical malformations (30%) was performed.
- Cortical shape and regional lesion burden emerged as key biomarkers associated with clinical function (motor, cognitive, communicative, visual).
- Validated models showed significant correlations (0.545-0.795, p<0.008) between quantified injuries and clinical function.
Conclusions:
- Automated quantification of brain injuries from sMRI is feasible and provides objective measures.
- Quantified sMRI injury metrics are significantly associated with clinical function in children with CP.
- This approach supports the early characterization of brain injury from sMRI as part of standard clinical assessment for CP.
Abstract:
Previous studies have proposed that the early elucidation of brain injury from structural Magnetic Resonance Images (sMRI) is critical for the clinical assessment of children with cerebral palsy (CP). Although distinct aetiologies, including cortical maldevelopments, white and grey matter lesions and ventricular enlargement, have been categorised, these injuries are commonly only assessed in a qualitative fashion. As a result, sMRI remains relatively underexploited for clinical assessments, despite its widespread use. In this study, several automated and validated techniques to automatically quantify these three classes of injury were generated in a large cohort of children (n = 139) aged 5-17, including 95 children diagnosed with unilateral CP. Using a feature selection approach on a training data set (n = 97) to find severity of injury biomarkers predictive of clinical function (motor, cognitive, communicative and visual function), cortical shape and regional lesion burden were most often chosen associated with clinical function. Validating the best models on the unseen test data (n = 42), correlation values ranged between 0.545 and 0.795 (p<0.008), indicating significant associations with clinical function. The measured prevalence of injury, including ventricular enlargement (70%), white and grey matter lesions (55%) and cortical malformations (30%), were similar to the prevalence observed in other cohorts of children with unilateral CP. These findings support the early characterisation of injury from sMRI into previously defined aetiologies as part of standard clinical assessment. Furthermore, the strong and significant association between quantifications of injury observed on structural MRI and multiple clinical scores accord with empirically established structure-function relationships.
