AI-Powered Measurement of Ultrasonic Axial-Transmission Velocity for Pediatric Skeletal Development Evaluation

Bone health assessment is commonly used to evaluate skeletal development and maturation and to diagnose neonatal growth disorders. Implementing an automated ultrasonic system for pediatric bone evaluation, which is radiation-free and cost-effective, to complement conventional radiography is significant for clinical applications. This study mainly proposes a method, which combines the ReliefF algorithm with fuzzy C-means clustering, for fully automatic detection of wave arrival time and estimation of ultrasonic velocity from axial transmission waveforms measured from the bone of infants without the need for signal preprocessing. The results of in-vivo velocity measurement show good consistency with the ground truth modality, indicating the feasibility of the proposed method for further clinical studies and usages.

[1]  Hanpeng Wang,et al.  First Arrival Picking on Microseismic Signals Based on K-Means with a ReliefF Algorithm , 2021, Symmetry.

[2]  N. Shaw,et al.  Neonatal Bone Disorders , 2021, Frontiers in Pediatrics.

[3]  Jubran Akram,et al.  Automatic seismic phase picking based on unsupervised machine-learning classification and content information analysis , 2021 .

[4]  F. Chiarelli,et al.  Evaluation of Bone Age in Children: A Mini-Review , 2021, Frontiers in Pediatrics.

[5]  M. Szalecki,et al.  Traditional and New Methods of Bone Age Assessment-An Overview , 2020, Journal of clinical research in pediatric endocrinology.

[6]  Yangkang Chen,et al.  Automatic microseismic event picking via unsupervised machine learning , 2020, Geophysical Journal International.

[7]  P. Anderberg,et al.  Bone age assessment with various machine learning techniques: A systematic literature review and meta-analysis , 2019, PloS one.

[8]  W. Schwenk,et al.  Bone Age: A Handy Tool for Pediatric Providers , 2017, Pediatrics.

[9]  Chao Zhang,et al.  Automatic Time Picking for Microseismic Data Based on a Fuzzy C-Means Clustering Algorithm , 2016, IEEE Geoscience and Remote Sensing Letters.

[10]  Sebastián Ventura,et al.  Scalable extensions of the ReliefF algorithm for weighting and selecting features on the multi-label learning context , 2015, Neurocomputing.

[11]  M. Sacchi,et al.  Imaging ultrasonic dispersive guided wave energy in long bones using linear radon transform. , 2014, Ultrasound in medicine & biology.

[12]  A. Akbari,et al.  The Analysis of Social Ecology and Physical Development Process of Cities (Towns) Case Study: Alvand City , 2013 .

[13]  Jong-Myon Kim,et al.  An analysis of content-based classification of audio signals using a fuzzy c-means algorithm , 2013, Multimedia Tools and Applications.

[14]  Tahir Ahmad,et al.  Detection of Epilepsy from EEG Signal During Seizure Using Entropy-Based Fuzzy c-Means , 2012 .

[15]  Igor Kononenko,et al.  Estimating Attributes: Analysis and Extensions of RELIEF , 1994, ECML.

[16]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[17]  Bone Quantitative Ultrasound: New Horizons , 2022, Advances in Experimental Medicine and Biology.