Automatic segmentation of brain structures in longitudinal MR images of growing children

Abstract

Purpose or Objective Children treated for brain tumours may suffer long-term cognitive damage and other sequelae after treatment. Neuroscientists have developed open-access sophisticated software packages, such as FreeSurfer, for automatic segmentation of brain sub-regions structures on MR images. Those tools are potentially of great interest for large multicentric studies to retrospectively estimate the dose received by paediatric patients with brain tumours and evaluate structure growth or atrophy. Here, we evaluate 1) the agreement between FreeSurfer structures and radiotherapy-specific segmentation atlases, and 2) the sensitivity of FreeSurfer to capture volume changes due to aging. Materials and Methods 20 healthy children, each imaged at approximately 5, 7 and 9 years, were selected from OpenNeuro data. All 60 T1- weighted MR images (non-contrast, 1mm slice) were corrected for image inhomogeneity before automatic segmentation of 47 structures using FreeSurfer v7.1.1. The list of FreeSurfer structures was compared to the European Particle Therapy Network atlas (EPTN, Eekers 2021) for concordance in definition. Segmentation quality was visually assessed by a single observer for each image. Volumes of all substructures were calculated for each time point. Results 15/47 FreeSurfer structures could be matched with the EPTN atlas: brainstem (divided into pons, midbrain, medulla oblongata), optic chiasm, cerebellum, corpus callosum, ventricles (enabling the definition of the periventricular space), and left/right hippocampi, caudate nuclei, thalami, and amygdalas. Segmentation quality was judged satisfactory for retrospective dose estimation. Small volume changes were captured for the brainstem, bilateral hippocampi, bilateral thalami and right amygdala, where volume increased between ages 5 and 9 years by 9%, 5%, 4% and 6% respectively (average between left and right for bilateral structures). The bilateral accumbens and caudate volumes appeared to decrease with age, but the association was not significant, suggesting these structure volumes are relatively stable between these ages. Whole brain volume was 10% larger in males vs females, leading to significantly smaller structures in females (p<0.05), in the brainstem (6%), left accumbens (11%) as well as bilateral amygdalas (average 12%), hippocampi (average 9%), putamens (average 7%) and thalami (average 8%) Conclusion The quality of FreeSurfer segmentations was promising, and there was a modest overlap with EPTN atlas structures. The comprehensive list of sub-regions (including e.g. grey and white matter segmentations) available in FreeSurfer could be of interest for post-radiation outcome studies. The performance of FreeSurfer in the presence of tissue deformations (e.g. tumour, surgery, treatment-related effects) is being investigated. In the future, we expect to use tools like FreeSurfer to extract dose to substructures and sequential volume changes including brain atrophy post radiotherapy in large cohorts of patients.