Automating Quantitative Measures of an Established Conventional MRI Scoring System for Preterm-Born Infants Scanned between 29 and 47 Weeks’ Postmenstrual Age

L. van Eijk; M. Seidel; K. Pannek; J.M. George; S. Fiori; A. Guzzetta; A. Coulthard; J. Bursle; R.S. Ware; D. Bradford; S. Rose; P.B. Colditz; R.N. Boyd; J. Fripp

doi:10.3174/ajnr.A7230

Abstract

BACKGROUND AND PURPOSE: Conventional MR imaging scoring is a valuable tool for risk stratification and prognostication of outcomes, but manual scoring is time-consuming, operator-dependent, and requires high-level expertise. This study aimed to automate the regional measurements of an established brain MR imaging scoring system for preterm neonates scanned between 29 and 47 weeks’ postmenstrual age.

MATERIALS AND METHODS: This study used T2WI from the longitudinal Prediction of PREterm Motor Outcomes cohort study and the developing Human Connectome Project. Measures of biparietal width, interhemispheric distance, callosal thickness, transcerebellar diameter, lateral ventricular diameter, and deep gray matter area were extracted manually (Prediction of PREterm Motor Outcomes study only) and automatically. Scans with poor quality, failure of automated analysis, or severe pathology were excluded. Agreement, reliability, and associations between manual and automated measures were assessed and compared against statistics for manual measures. Associations between measures with postmenstrual age, gestational age at birth, and birth weight were examined (Pearson correlation) in both cohorts.

RESULTS: A total of 652 MRIs (86%) were suitable for analysis. Automated measures showed good-to-excellent agreement and good reliability with manual measures, except for interhemispheric distance at early MR imaging (scanned between 29 and 35 weeks, postmenstrual age; in line with poor manual reliability) and callosal thickness measures. All measures were positively associated with postmenstrual age (r = 0.11–0.94; R² = 0.01–0.89). Negative and positive associations were found with gestational age at birth (r = –0.26–0.71; R² = 0.05–0.52) and birth weight (r = –0.25–0.75; R² = 0.06–0.56). Automated measures were successfully extracted for 80%–99% of suitable scans.

CONCLUSIONS: Measures of brain injury and impaired brain growth can be automatically extracted from neonatal MR imaging, which could assist with clinical reporting.

ABBREVIATIONS:

DGMA: deep gray matter area
dHCP: developing Human Connectome Project
GA: gestational age at birth
ICC: intraclass correlation coefficient
LoA: 95% limits of agreement
LVD: lateral ventricular diameter
PMA: postmenstrual age
PPREMO: Prediction of PREterm Motor Outcomes study
SEM: standard error of measurement
TEA: term-equivalent age

Footnotes

L.v.E now works for the Department of Psychology, College of Healthcare Sciences, Division of Tropical Health and Medicine, James Cook University, Townsville, Australia.
The Prediction of PREterm Motor Outcomes study was funded by the Cerebral Palsy Alliance Research Foundation (IRG1413), Financial Markets Foundation for Children (2014-074), and Queensland Government (Smart State; Health Practitioner Stimulus Grant). The developing Human Connectome Project (King’s College London-Imperial-Oxford Consortium) was funded by the European Research Council under the European Union Seventh Framework Program (FP/2007-2013)/European Research Council Grant Agreement No. 319456, In addition, the authors were supported by the University of Queensland (University of Queensland Research Scholarship [J.M.G.], Centennial Scholarship [K.P.], International Postgraduate Research Scholarship [K.P.]), and National Health and Medical Research Council (Research Fellowship 103887 [R.N.B.]).
Disclosures: Liza van Eijk—RELATED: Grant: Various, Comments: Prediction of PREterm Motor Outcomes Study–Cerebral Palsy Alliance Research Foundation (IRG1413), Financial Markets Foundation for Children (2014-074), Queensland Government (Smart State; Health Practitioner Stimulus Grant), developing Human Connectome Project (KCL-Imperial-Oxford Consortium), European Research Council under the European Union Seventh Framework Program (FP/2007-2013)/European Research Council Grant Agreement no. [319456], The University of Queensland (University of Queensland Research Scholarship [JMG], Centennial Scholarship [KP], International Postgraduate Research Scholarship [KP]), and National Health and Medical Research Council (Research Fellowship 103887 [RNB]).* UNRELATED: Employment: The University of Queensland (12/2020). Kerstin Pannek—RELATED: Grant: various, Comments: grants from the Cerebral Palsy Alliance Research Foundation (IRG1413), the Financial Markets Foundation for Children (2014-074), and the Queensland Government (Smart State; Health Practitioner Stimulus Grant) supported this project*; UNRELATED: Grants/Grants Pending: National Health and Medical Research Council, Comments: APP1078877, APP1084032, APP1120031, APP1144846, APP1152800, APP1182938.* Joanne M. George—UNRELATED: Employment: The University of Queensland. Dana Bradford—RELATED: Grant: Prediction of PREterm Motor Outcomes study funded by the Cerebral Palsy Alliance Research Foundation (IRG1413), Financial Markets Foundation for Children (2014-074), Queensland Government (Smart State; Health Practitioner Stimulus Grant)*; Other: author scholarships: Centennial Scholarship (KP), International Postgraduate Research Scholarship (KP)*; UNRELATED: Employment: Commonwealth Scientific and Industrial Research Organisation, Comments: salary. Jurgen Fripp—RELATED: Grant: National Health and Medical Research Council, Comments: The National Health and Medical Research Council (https://www.nhmrc.gov.au/) funded the cohort study on which this article was based*; UNRELATED: Grants/Grants Pending: National Health and Medical Research Council, Comments: We are involved in a range of National Health and Medical Research Council–funded grants in collaboration with the University of Queensland in the field of Cerebral Palsy and Neurodevelopment.* *Money paid to the institution.