Diagnostic accuracy of early magnetic resonance imaging to determine motor outcomes in infants born preterm: a systematic review and meta‐analysis

George, Joanne M.; Pannek, Kerstin; Rose, Stephen; Ware, Robert S.; Colditz, Paul B.; Boyd, Roslyn N.

doi:10.1111/dmcn.13611

Cited by 18 publications

(13 citation statements)

References 73 publications

(217 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, clinical data to predict neurodevelopmental outcomes have only achieved modest prediction accuracy with an area under the curve (AUC) of 0.68 56 . Therefore, there is a need to examine the incremental value of brain MRI biomarkers over clinical factors [57][58][59][60][61] .…”

Section: Discussionmentioning

confidence: 99%

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants

Wang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Survivors following very premature birth (i.e., ≤ 32 weeks gestational age) remain at high risk for neurodevelopmental impairments. Recent advances in deep learning techniques have made it possible to aid the early diagnosis and prognosis of neurodevelopmental deficits. Deep learning models typically require training on large datasets, and unfortunately, large neuroimaging datasets with clinical outcome annotations are typically limited, especially in neonates. Transfer learning represents an important step to solve the fundamental problem of insufficient training data in deep learning. In this work, we developed a multi-task, multi-stage deep transfer learning framework using the fusion of brain connectome and clinical data for early joint prediction of multiple abnormal neurodevelopmental (cognitive, language and motor) outcomes at 2 years corrected age in very preterm infants. The proposed framework maximizes the value of both available annotated and non-annotated data in model training by performing both supervised and unsupervised learning. We first pre-trained a deep neural network prototype in a supervised fashion using 884 older children and adult subjects, and then re-trained this prototype using 291 neonatal subjects without supervision. Finally, we fine-tuned and validated the pre-trained model using 33 preterm infants. Our proposed model identified very preterm infants at high-risk for cognitive, language, and motor deficits at 2 years corrected age with an area under the receiver operating characteristic curve of 0.86, 0.66 and 0.84, respectively. Employing such a deep learning model, once externally validated, may facilitate risk stratification at term-equivalent age for early identification of long-term neurodevelopmental deficits and targeted early interventions to improve clinical outcomes in very preterm infants.

show abstract

Section: Discussionmentioning

confidence: 99%

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants

Wang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Meta-analyses are unfortunately hampered by heterogeneous study populations, variable scanning techniques and differences in radiological analysis and interpretation. One systematic review concluded that MRI should preferably be performed at term-equivalent age,32 while another found that structural MRI before 36 weeks postmenstrual age has reasonable sensitivity and specificity to predict outcome of cerebral palsy 33. Very early scanning has been found to have limited value for predicting outcome in a preterm cohort born at a median of 27+4 weeks and imaged at just 2 days of life 34.…”

Section: Translation Of Research Into Clinical Practicementioning

confidence: 99%

Advances in neonatal MRI of the brain: from research to practice

Kelly

Hughes

Rutherford

et al. 2018

Arch Dis Child Educ Pract Ed

View full text Add to dashboard Cite

“…Например, в 2018 г. опубликованы результаты метаанализа 31 исследования диагностических возможностей раннего выполнения МРТ у недоношенных детей (< 36 нед) с использованием количественной оценки томограмм. Метаанализ показал, что глобальная оценка рано выполненной структурной МРТ обладает у недоношенных детей высокими чувствительностью и специфичностью как в отношении прогнозирования последующего развития ДЦП (100 и 93% соответственно), так и двигательных ограничений (89 и 98% соответственно) [49]. Глобальная оценка МРТ давала более точный прогноз двигательного исхода, чем оценка только белого вещества [49].…”

Section: прогностическое значение мр-находокunclassified

Possibilities of Magnetic Resonance Imaging of the Brain in Infantile Cerebral Palsy

Белова

Шейко

Клюев

et al. 2018

Vopr. sovr. pediatr.

View full text Add to dashboard Cite

Infantile cerebral palsy (ICP) is the main cause of childhood disability and is characterized by a non-progressive lesion and/or impaired development of the brain in a foetus or newborn. Magnetic resonance imaging (MRI) is a modern non-invasive method with extensive capabilities for diagnosing brain damage in ICP. The review focuses on anatomical structural MR patterns of brain damage in ICP and gives the present-day classification of MR changes in this disease. The role of MRI in determining the duration of brain damage in ICP has been considered. Data on the ratio of ICP phenotypes to pathological MR findings has been presented. Neuroimaging prognostic biomarkers are discussed. It is emphasized that many questions regarding the prognostic significance of MR findings remain unresolved; prospects are associated with the use of new MRI modalities such as functional and diffusiontensor MRI.

show abstract

Diagnostic accuracy of early magnetic resonance imaging to determine motor outcomes in infants born preterm: a systematic review and meta‐analysis

Cited by 18 publications

References 73 publications

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants

A multi-task, multi-stage deep transfer learning model for early prediction of neurodevelopment in very preterm infants

Advances in neonatal MRI of the brain: from research to practice

Possibilities of Magnetic Resonance Imaging of the Brain in Infantile Cerebral Palsy

Contact Info

Product

Resources

About