Utilizing Deep Learning for Accurate Infant Age Estimation from Skull X-ray Images

Thursday, 18 July 2024, 09:38

This post explores the development of DenseNet-121 and EfficientNet-v2-M convolutional neural network models to predict the postnatal age of infants through skull X-ray images. Achieving high accuracy rates, the models analyzed a large dataset of 4933 X-ray images from 1343 infants, identifying critical areas such as sutures and bone density for age estimation. The study showcases the precision of deep learning in non-invasively estimating infant age, offering potential advancements in clinical diagnostics and developmental assessments.
Nature
Utilizing Deep Learning for Accurate Infant Age Estimation from Skull X-ray Images

Utilizing Deep Learning Models for Infant Age Estimation

This study employed state-of-the-art convolutional neural networks, DenseNet-121 and EfficientNet-v2-M, to predict the postnatal age of infants using X-ray images of their skulls.

High Accuracy Rates Achieved

  • Accurate Predictions: The models reached maximum corrected accuracy rates of 79.4% to 87.3% for different views, showcasing their effectiveness.
  • Key Areas Identified: Critical areas on the skull X-ray images like sutures and bone density were pinpointed for age estimation.

Precision in Age Estimation

  1. Non-Invasive Methods: Deep learning offers precise age estimation without invasive procedures, aiding in clinical diagnostics.
  2. Developmental Assessment Tools: The study paves the way for improved tools for developmental assessments in infants.

This article was prepared using information from open sources in accordance with the principles of Ethical Policy. The editorial team is not responsible for absolute accuracy, as it relies on data from the sources referenced.


Related posts


Newsletter

Subscribe to our newsletter for the most reliable and up-to-date tech news. Stay informed and elevate your tech expertise effortlessly.

Subscribe