Cerebral Palsy, Periventricular White Matter Abnormalities
Conditions
Keywords
Cerebral palsy, Periventricular white matter injury, MRI, Deep learning
Brief summary
The goal of this study is to determin the MRI features associated with cerebral palsy and to develop prediction models of pediatric disorders by combining MRI with artificial intelligence. The main questions it aims to answer are: * How to achieve features on conventional MRI associated with cerebral palsy? * How to predict the risk of cerebral palsy in infants aged 6 to 2 years based on conventional MRI and deep learning? Researchers will compare characteristics of periventricular white matter injury with cerebral palsy to those without cerebral palsy. Participants will be asked to provide MRI data, clinical diagnoses information, and follow-up outcomes.
Detailed description
Cerebral palsy (CP) is a common group of movement disorders that often results in disability in children. In the context of CP, the importance of early diagnosis is crucial, but current diagnostic modalities often identify cases after the age of 2 years. After initial screening of infants at high risk for CP by behavioral scoring, magnetic resonance imaging (MRI) forms an integral part of the comprehensive evaluation. The training of conventional model of CP risk prediction requires a large investment of time and financial resources. The average sensitivity rate drops to 90%. Up to now, deep learning technology has been widely used in tasks related to image-based disease classification and has shown excellent performance. Periventricular white matter injury (PVWMI) accounts for the largest proportion of various types of brain injuries in cerebral palsy, and the types of brain injuries in cerebral palsy are rich and complex, posing difficulties and challenges to deep learning models. Therefore, this study focuses on PVWMI, the most common type of cerebral palsy, and uses conventional MRI to develop a deep learning prediction model for CP in infants aged 6 months to 2 years old.
Interventions
OTHERNo intervention will be performed in this cohort study
Deep learning classification models will be used for automatic prediction of cerebral palsy. Machines will be used to assist doctors in cerebral palsy risk evaluation.
Sponsors
The First Affiliated Hospital of Henan University of Traditional Chinese Medicine
Shenzhen Children's Hospital
Zunyi Medical College
Wuxi Women's & Children's Hospital
Shanxi Provincial Maternity and Children's Hospital
Chengdu Medical College
First Affiliated Hospital of Xinjiang Medical University
Baoji Central Hospital
Xian Children's Hospital
Guangzhou Women and Children's Medical Center
Third Affiliated Hospital of Zhengzhou University
Henan Provincial People's Hospital
First Affiliated Hospital Xi'an Jiaotong University
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
6 Months to 2 Years
Healthy volunteers
Yes
Inclusion criteria
1. Infants and children at high risk of periventricular white matter injury (PVWMI) (gestational age \<35 weeks, birth weight \<2.6 kg, forceps-assisted delivery/fetal head attraction, Apgar score \<7, hypoglycaemia, sepsis, electrolyte disturbances, premature rupture of membranes); 2. Those who underwent MRI at 6 months of age-2 years, including at least T1WI and T2WI sequences; 3. Upon follow-up, the patient's clinical diagnosis: cerebral palsy, other diagnoses that did not develop into cerebral palsy, or inability to confirm the diagnosis).
Exclusion criteria
1. Incomplete MRI images or unreadable images due to motion artefacts; 2. Incomplete neurobehavioural assessment data (including: gross motor function).
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Accuracy of the model predicting cerebral palsy | From September 2024 to December 2025 | Determine the accuracy of PVWMI classification and cerebral palsy prediction. The higher the value, the better the model performance. |
Countries
China
Contacts
Primary ContactYitong Bian, MD
Outcome results
None listed