Modelling brain development to detect white matter injury in term and preterm born neonates

Abstract

Premature birth occurs during a period of rapid brain growth. In this context, interpreting clinical neuroimaging can be complicated by the typical changes in brain contrast, size and gyrification occurring in the background to any pathology. To model and describe this evolving background in brain shape and contrast, we used a Bayesian regression technique, Gaussian process regression, adapted to multiple correlated outputs. Using MRI, we simultaneously estimated brain tissue intensity on T1- and T2-weighted scans as well as local tissue shape in a large cohort of 408 neonates scanned cross-sectionally across the perinatal period. The resulting model provided a continuous estimate of brain shape and intensity, appropriate to age at scan, degree of prematurity and sex. Next, we investigated the clinical utility of this model to detect focal white matter injury. In individual neonates, we calculated deviations of a neonate’s observed MRI from that predicted by the model to detect punctate white matter lesions with very good accuracy (area under the curve > 0.95). To investigate longitudinal consistency of the model, we calculated model deviations in 46 neonates who were scanned on a second occasion. These infants’ voxelwise deviations from the model could be used to identify them from the other 408 images in 83% (T2-weighted) and 76% (T1-weighted) of cases, indicating an anatomical fingerprint. Our approach provides accurate estimates of non-linear changes in brain tissue intensity and shape with clear potential for radiological use.

Phenotyping the preterm brain: characterising individual deviations from normative volumetric development in two large infant cohorts

“…The argument that essentially every brain is different is not novel, and the expectation that the effects of preterm birth are homogeneous and exactly alike in every infant is equally untenable 7,10 .…”

“…To understand brain development at an individual level, offer accurate prognosis of later outcome, and study the effects of clinical risks and interventions, it is necessary to provide a personalized assessment of cerebral maturation 10 . Indeed, an unwarranted assumption that preterm birth has a homogenous effect on brain development might account for the relatively poor predictive power of neonatal MRI for later outcome, especially in the absence of major focal lesions 11,12 .…”

“…Indeed, an unwarranted assumption that preterm birth has a homogenous effect on brain development might account for the relatively poor predictive power of neonatal MRI for later outcome, especially in the absence of major focal lesions 11,12 . Comparing individuals against robust normative data avoids the requirement to define quasi-homogenous groups in a search for effects common to the group, and offers a powerful alternative to investigate brain maturation with high sensitivity to pathology at an individual infant level 10,13,14 .…”

Predicting age and clinical risk from the neonatal connectome

“…This suggests that the brain maturation index may be a useful tool to capture potential delays and disorders in structural connectivity which may have a lasting impact on later neurological outcomes. Recent studies have shown the potential of normative modelling to find individual alterations in preterm babies (Dimitrova et al, 2020;O'Muircheartaigh et al, 2020), which are characterised by heterogeneous brain changes. In a similar way, we suggest that for an individual subject, a high deviation from the population norm, translating to age predictions significantly lower than true age (negative brain maturation index) can be a marker of potential developmental delay so that these subjects should undergo further tests and may need follow up.…”

Encephalopathy of prematurity

“…Of course, correlations between groups are of less value to the practicing clinician than positive and negative predictive values for individuals, and, as with other similar studies, the individual predictive power of Kline et al ’s measurements is modest, probably largely due to significant intersubject variability. However, new modelling and machine learning techniques are beginning to make personalised image analysis more tractable, and there is hope that a better understanding of the clinical impact of encephalopathy of prematurity in each patient will soon be possible 6. In the meantime, Kline et al remind us again as we stand at the cotside that while haemorrhage and periventricular leucomalacia are not unimportant, we should be increasingly concerned with brain growth and maturation.…”