L van Eijk1,2, M Seidel1,2, K Pannek3, J M George4, S Fiori5, A Guzzetta5,6, A Coulthard7,8, J Bursle7, R S Ware9, D Bradford1, S Rose1, P B Colditz10,11, R N Boyd4, J Fripp1. 1. From The Australian e-Health Research Centre (L.v.E., M.S., K.P., D.B., S.R., J.F.), Health and Biosecurity, Commonwealth Scientific and Industrial Research Organisation, Brisbane, Australia. 2. Faculty of Medicine (L.V.E., M.S.), The University of Queensland, Brisbane, Australia. 3. From The Australian e-Health Research Centre (L.v.E., M.S., K.P., D.B., S.R., J.F.), Health and Biosecurity, Commonwealth Scientific and Industrial Research Organisation, Brisbane, Australia Kerstin.Pannek@csiro.au. 4. Queensland Cerebral Palsy and Rehabilitation Research Centre (J.M.G., R.N.B.), Centre for Children's Health Research, The University of Queensland, Brisbane, Australia. 5. Department of Developmental Neuroscience (S.F., A.G.), Istituto di Ricovero e Cura a Carattere Scientifico Stella Maris, Pisa, Italy. 6. Department of Clinical and Experimental Medicine (A.G.), University of Pisa, Pisa, Italy. 7. Department of Medical Imaging (A.C., J.B.), Royal Brisbane and Women's Hospital, Brisbane, Australia. 8. Discipline of Medical Imaging (A.C.), The University of Queensland, Brisbane, Australia. 9. Menzies Health Institute Queensland (R.S.W.), Griffith University, Brisbane, Australia. 10. Perinatal Research Centre (P.B.C.), University of Queenland Centre for Clinical Research, Faculty of Medicine, The University of Queensland, Brisbane, Australia. 11. Perinatal Research Centre, Brisbane and Women's Hospital (P.B.C.), Brisbane, Australia.
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.
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.
Authors: Antonios Makropoulos; Emma C Robinson; Andreas Schuh; Robert Wright; Sean Fitzgibbon; Jelena Bozek; Serena J Counsell; Johannes Steinweg; Katy Vecchiato; Jonathan Passerat-Palmbach; Gregor Lenz; Filippo Mortari; Tencho Tenev; Eugene P Duff; Matteo Bastiani; Lucilio Cordero-Grande; Emer Hughes; Nora Tusor; Jacques-Donald Tournier; Jana Hutter; Anthony N Price; Rui Pedro A G Teixeira; Maria Murgasova; Suresh Victor; Christopher Kelly; Mary A Rutherford; Stephen M Smith; A David Edwards; Joseph V Hajnal; Mark Jenkinson; Daniel Rueckert Journal: Neuroimage Date: 2018-01-31 Impact factor: 6.556
Authors: Ioannis S Gousias; A David Edwards; Mary A Rutherford; Serena J Counsell; Jo V Hajnal; Daniel Rueckert; Alexander Hammers Journal: Neuroimage Date: 2012-06-17 Impact factor: 6.556
Authors: Joanne M George; Simona Fiori; Jurgen Fripp; Kerstin Pannek; Andrea Guzzetta; Michael David; Robert S Ware; Stephen E Rose; Paul B Colditz; Roslyn N Boyd Journal: Early Hum Dev Date: 2018-01-23 Impact factor: 2.079
Authors: Margaretha J Brouwer; Karina J Kersbergen; Britt J M van Kooij; Manon J N L Benders; Ingrid C van Haastert; Corine Koopman-Esseboom; Jeffrey J Neil; Linda S de Vries; Hiroyuki Kidokoro; Terrie E Inder; Floris Groenendaal Journal: PLoS One Date: 2017-05-09 Impact factor: 3.240
Authors: J Allotey; J Zamora; F Cheong-See; M Kalidindi; D Arroyo-Manzano; E Asztalos; Jam van der Post; B W Mol; D Moore; D Birtles; K S Khan; S Thangaratinam Journal: BJOG Date: 2017-10-11 Impact factor: 6.531