Related Experiment Video
Updated: Jul 6, 2026
Quantitative Assessment of Cortical Auditory-tactile Processing in Children with Disabilities
Published on: January 29, 2014
Selecting and assessing quantitative early ultrasound texture measures for their association with cerebral palsy
Tyna A Hope1, Peter H Gregson, Norma C Linney
1Cambridge Research and Instrumentation, Boston, MA 01801, USA. tyna.hope@gmail.com
Insights
Quantitative ultrasound texture analysis may predict cerebral palsy (CP) in preterm infants. Early texture measures from ultrasound images show potential for identifying infants at risk for developing CP, aiding early diagnosis.
Area of Science:
- Neonatal neurology
- Medical imaging analysis
- Developmental pediatrics
Background:
- Cerebral palsy (CP) affects approximately 1 in 10 very preterm infants, often resulting from white matter damage (WMD).
- Current ultrasound (US) screening methods frequently fail to detect early WMD in preterm infants.
- There is a critical need for improved early detection methods for WMD and CP risk.
Purpose of the Study:
- To investigate if quantitative texture measures from early US images can predict the subsequent development of CP.
- To determine the association between early-life WMD detected by US texture analysis and CP outcomes.
- To explore novel quantitative imaging biomarkers for CP risk stratification.
Main Methods:
- Retrospective analysis of US images from very preterm infants within one week of birth.
- Extraction of quantitative texture measures using adaptive processing and high-resolution feature enhancement.
- Development of a predictive model using the random forest algorithm, treating patients as their own controls.
Main Results:
- The random forest model achieved 72% accuracy in predicting CP versus no CP.
- This accuracy significantly outperforms a baseline model that would classify all patients as CP (53% error).
- Quantitative texture features from early US images contain significant diagnostic information for CP development.
Conclusions:
- Quantitative texture analysis of early ultrasound images shows promise as a tool for predicting cerebral palsy in preterm infants.
- These novel imaging biomarkers may improve early detection of WMD and identify infants at high risk for CP.
- Further validation is warranted to integrate this technique into clinical screening protocols for neonatal brain injury.
Abstract:
Cerebral palsy (CP) develops as a consequence of white matter damage (WMD) in approximately one out of every 10 very preterm infants. Ultrasound (US) is widely used to screen for a variety of brain injuries in this patient population, but early US often fails to detect WMD. We hypothesized that quantitative texture measures on US images obtained within one week of birth are associated with the subsequent development of CP. In this retrospective study, using images from a variety of US machines, we extracted unique texture measures by means of adaptive processing and high resolution feature enhancement. We did not standardize the images, but used patients as their own controls. We did not remove speckle, as it may contain information. To test our hypothesis, we used the "random forest" algorithm to create a model. The random forest classifier achieved a 72% match to the health outcome of the patients (CP versus no CP), whereas designating all patients as having CP would have resulted in 53% error. This suggests that quantitative early texture measures contain diagnostic information relevant to the development of CP.
