Using ventricular modeling to robustly probe significant deep gray matter pathologies: Application to cerebral palsy

Abstract

Understanding the relationships between the structure and function of the brain largely relies on the qualitative assessment of Magnetic Resonance Images (MRIs) by expert clinicians. Automated analysis systems can support these assessments by providing quantitative measures of brain injury. However, the assessment of deep gray matter structures, which are critical to motor and executive function, remains difficult as a result of large anatomical injuries commonly observed in children with Cerebral Palsy (CP). Hence, this article proposes a robust surrogate marker of the extent of deep gray matter injury based on impingement due to local ventricular enlargement on surrounding anatomy. Local enlargement was computed using a statistical shape model of the lateral ventricles constructed from 44 healthy subjects. Measures of injury on 95 age-matched CP patients were used to train a regression model to predict six clinical measures of function. The robustness of identifying ventricular enlargement was demonstrated by an area under the curve of 0.91 when tested against a dichotomised expert clinical assessment. The measures also showed strong and significant relationships for multiple clinical scores, including: motor function (r = 0.62, P < 0.005), executive function (r = 0.55, P < 0.005), and communication (r = 0.50, P < 0.005), especially compared to using volumes obtained from standard anatomical segmentation approaches. The lack of reliance on accurate anatomical segmentations and its resulting robustness to large anatomical variations is a key feature of the proposed automated approach. This coupled with its strong correlation with clinically meaningful scores, signifies the potential utility to repeatedly assess MRIs for clinicians diagnosing children with CP. Hum Brain Mapp 37:3795-3809, 2016. © 2016 Wiley Periodicals, Inc.

A systematic review of structural MRI biomarkers in autism spectrum disorder: A machine learning perspective

“…Although not technically part of the brain, the cerebrospinal (CSF) plays an important role in circulating nutrients and removing waste products from the brain, as well cushioning the brain to acceleration. However the volume of the CSF may indirectly reflect tissue loss in regions of the brain (Pagnozzi et al, 2016), and so may prove to be an important biomarkers for brain related changes occurring due to ASD. Among the studies that have characterised cerebrospinal (CSF) volumes shown in Supplementary Table 4, there was a consistent finding of increased CSF volumes globally (Katuwal et al, 2016b), in extra‐axial or subarachnoid spaces (Shen et al, 2017, 2013), and in the lateral ventricles (Haar et al, 2016; Turner et al, 2016).…”

Identifying relevant biomarkers of brain injury from structural MRI: Validation using automated approaches in children with unilateral cerebral palsy

“…To this end, this study aims to quantitatively characterise the prevalence and extent of different manifestations of injury in a cohort of 139 children; including 95 children diagnosed with unilateral CP and 44 children with healthy development (CHD), using three previously developed automated approaches. These approaches identify the three main aetiologies of injury based on current classifications [ 11 ]; including a tailored segmentation strategy and cortical shape analysis pipeline to detect cortical malformations [ 12 ], a lesion-as-outlier segmentation strategy using T1- and T2-weighted MRIs for the detection of white and grey matter lesions [ 13 ], and a statistical shape model (SSM) of healthy ventricular shape to detect the secondary enlargement of ventricles [ 14 ]. The quantitative biomarkers derived from these approaches were used to characterise the prevalence of injury in this cohort of children with CP, and to construct regression models, in order to identify those biomarkers that are significantly associated with clinical scores of motor, cognitive, communicative and visual function.…”

Automated injury segmentation to assist in the treatment of children with cerebral palsy

“…This representation of injury is unique to this approach, allows identification of subtle injury on ventricles with a small volume, and avoids false positive detection of enlargement in healthy ventricles with a large volume, compared to a distance from the mean representation of injury used in other SSM studies [Apostolova et al, 2012;Chou et al, 2007;Ferrarini et al, 2008a;Thompson et al, 2004]. This was demonstrated by the improved ROC performance of the residual volume over the magnitude of SSM deformation compared to the manual classification of injury [Pagnozzi et al, 2016c]. The second development was the utilisation of this volume to extract a surrogate marker of injury to surrounding subcortical GM structures, including the caudate nucleus, thalamus and lenticular nucleus, as well as the internal capsule.…”

“…Ventricular enlargement was identified using a SSM of healthy lateral ventricles to extract volumes of enlargement, and compute their impingement on nearby deep grey matter anatomies [Pagnozzi et al, 2016c] …”

“…classifications ; including a tailored segmentation strategy and cortical shape analysis pipeline to detect cortical malformations [Pagnozzi et al, 2016b], a lesion-as-outlier segmentation strategy using T1-and T2-weighted MRIs for the detection of white and grey matter lesions [Pagnozzi et al, 2016a], and a statistical shape model (SSM) of healthy ventricular shape to detect the secondary enlargement of ventricles [Pagnozzi et al, 2016c]. These biomarkers were used to characterise the prevalence of injury in this cohort, and used to construct regression models with several scores of clinical function, including motor, cognitive, communicative and visual ability.…”