MRI Imaging Omics and Risk Factors Analysis of PWMD in Premature Infants Based on Fuzzy Clustering Algorithm

Area of Science:

• Neonatal neurology
• Pediatric radiology
• Medical imaging analysis

Background:

• Periventricular white matter damage (PWMD) is a significant concern in premature infants, impacting neurodevelopmental outcomes.
• Accurate characterization of PWMD using Magnetic Resonance Imaging (MRI) is crucial for early intervention.

Purpose of the Study:

• To explore the MRI characteristics of PWMD in premature infants using the fuzzy c-means clustering algorithm (FCM).
• To identify clinical factors influencing the development of PWMD in this vulnerable population.

Main Methods:

• Retrospective analysis of 100 premature infants (50 with PWMD, 50 without) using MRI.
• Analysis of MRI signal characteristics and apparent diffusion coefficient (ADC) values.
• Multivariate regression analysis of clinical data to determine risk factors.

Main Results:

• PWMD manifested as punctate, clustered, and linear high T1 signal lesions on MRI.
• A downward trend in ADC values was observed in infants with PWMD.
• Risk factors identified include respiratory distress, low birth weight, premature rupture of membranes, and respiratory tract infection.

Conclusions:

• FCM algorithm aids in characterizing PWMD on MRI in premature infants.
• Specific MRI findings (punctate, clustered, linear T1 signals, reduced ADC) are indicative of PWMD.
• Several clinical factors are significantly associated with the occurrence of PWMD, highlighting the need for vigilant monitoring and management.