Data Utilization, Methodological Frameworks, and Evaluation Metrics in Head Circumference Measurement Research: A Systematic Review
Abstract
Head circumference measurement is a critical indicator for evaluating infant nutritional status and developmental progress. This review analyzes fourteen studies that utilize diverse imaging modalities—including ultrasound, computed tomography, smartphone photogrammetry, structured light scanning, and RGB-D sensors—to obtain 2D images (with resolutions ranging from 416×416 to 800×540 pixels) and 3D data such as scans, models, sequences, or meshes. Measurement methodologies vary, with seven studies employing deep learning techniques (e.g., ResNet-101, geometric CNNs, U-Net, V-Net variants), six using traditional computer vision methods (e.g., Scale-Invariant Feature Transform, Gauss-Newton optimization, thresholding), and one integrating deep learning (YOLOv5) with machine learning (random forest). Validation metrics demonstrate strong performance, including Dice similarity coefficients between 93.6% and 97.9%, Pearson correlations up to 0.98 (r2 up to 0.954), classification accuracies from 60% to 99.0%, Hausdorff distances between 1.29 ± 0.79 mm and 2.16 mm, and mean absolute errors below 0.74 cm to 2.27 mm. Deep learning approaches generally achieve measurement precision comparable or superior to traditional techniques when robust segmentation and artifact minimization are ensured. Challenges remain regarding imaging noise, heterogeneity in acquisition protocols, limited annotated datasets, and hardware calibration. Promising directions include real-time implementation,…
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- In silico toxicology protocols
- QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
- Quantum Informed Machine-Learning Potentials for Molecular Dynamics Simulations of CO2's Chemisorption and Diffusion in Mg-MOF-74
- In-silico strategies in nano-drug design: Bridging nanomaterials and pharmacological applications
- mRNA codon optimization with quantum computers
- The computational power of the human brain
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.