Correlation between a semiautomated method based on ultrasound texture analysis and standard ultrasound diagnosis using white matter damage in preterm neonates as a model.

Objectives: Diagnosis of white matter damage by cranial ultrasound imaging is still subject to interobserver variability and has limited sensitivity for predicting abnormal neurodevelopment later in life. In this study, we evaluated the ability of a semiautomated method based on ultrasound texture analysis to identify patterns that correlate with the ultrasound diagnosis of white matter damage.
Methods: The study included 44 very preterm neonates born at a median gestational age of 29 weeks 3 days (range, 26 weeks-31 weeks 6 days). Patients underwent cranial ultrasound scans within 1 week of birth and between 14 and 31 days of life. Periventricular leukomalacia was diagnosed by experienced clinicians on the 14- to 31-day scan according to standard criteria. To perform the texture analysis, 4 regions of interest were delineated in stored images: left and right periventricular areas and choroid plexuses. A classification algorithm was developed on the basis of the best combination of texture coefficients to correlate with the clinical diagnosis, and the ability of this algorithm to predict a later diagnosis of periventricular leukomalacia on the first scan was evaluated using a leave-one-out cross-validation.
Results: Periventricular leukomalacia was diagnosed by the standard procedure in 14 of 44 neonates. The texture classification algorithm performed on the first scan could identify cases with a later diagnosis of periventricular leukomalacia with sensitivity of 100% and accuracy of 97.7%.
Conclusions: These data support the notion that semiautomated quantitative ultrasound analysis achieves early identification of changes in subclinical stages and warrant further investigation of the role of ultrasound texture analysis methods to improve early detection of neonatal brain damage.