Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Magnetic resonance imaging for diagnosing residual malignancy after excisional biopsy for breast cancer: Comparison with excisional biopsy margin status.

European journal of radiology open·2026

Same author

Exploratory Evaluation of Dual Digital Platforms for Acute Brain Conditions in Medically Underserved Rural Areas : A Chuncheon, Gangwon-do Experience.

Journal of Korean Neurosurgical Society·2026

Same author

Peritonsillar abscess, deep neck infection, and proton pump inhibitor: A nested case-control study.

Auris, nasus, larynx·2026

Same author

Prediction of type 1 complex regional pain syndrome with the presence of diaschisis in hemiplegic supratentorial stroke patients.

Topics in stroke rehabilitation·2026

Same author

Critical illness-related corticosteroid insufficiency after acute brain hemorrhage surgery: a prospective cohort study with a randomized trial of hydrocortisone : HYdrocortisone theraPy in nEurocRitical illness; HYPER study.

Critical care (London, England)·2026

Same author

Factors associated with complication of cranioplasty: CT-based risk assessment for early failure of autologous-bone cranioplasty.

Neurosurgical review·2026

Search research articles

Related Experiment Video

Updated: Jun 20, 2025

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Estimating infant age from skull X-ray images using deep learning.

Heui Seung Lee^1,2, Jaewoong Kang³, So Eui Kim³

¹Department of Neurosurgery, College of Medicine, Hallym University Sacred Heart Hospital, Hallym University, 22, Gwanpyeong-Ro 170Beon-Gil, Dongan-Gu, Anyang-Si, Gyeonggi-Do, 14068, Republic of Korea. antanatia@gmail.com.

Scientific Reports

|July 18, 2024

Summary

This summary is machine-generated.

Deep learning models accurately predict infant postnatal age using skull X-rays, aiding in cranial development assessment. This non-invasive method shows promise for clinical diagnostics and developmental evaluation.

Keywords:

Craniosynostosis Infant age Infantile skull Skull suture X-ray

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 20, 2025

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Pediatrics

Background:

Accurate estimation of postnatal age is crucial for infant development assessment.
Traditional methods for age estimation can be invasive or less precise.
Skull radiographs offer a non-invasive window into infant cranial development.

Purpose of the Study:

To develop and evaluate deep learning models for predicting infant postnatal age from skull radiographs.
To assess the feasibility of using skull X-ray image features for evaluating cranial development.
To identify key radiographic features indicative of cranial development using explainable AI techniques.

Main Methods:

Convolutional neural network (CNN) models, DenseNet-121 and EfficientNet-v2-M, were trained on 4933 skull X-ray images from 1343 infants.
The models predicted postnatal age with a ±1-month error margin.
Gradient-weighted class activation mapping (Grad-CAM) was used to visualize critical discriminative areas in the radiographs.

Main Results:

EfficientNet-v2-M achieved a maximum corrected accuracy of 87.3% for lateral skull views (average 85.1% ± 2.5%) and 79.1% for anteroposterior (AP) views (average 77.0% ± 2.3%).
DenseNet-121 achieved a maximum corrected accuracy of 84.2% for lateral views (average 81.1% ± 2.9%) and 79.4% for AP views (average 78.0% ± 1.5%).
Saliency maps highlighted sutures (coronal, sagittal, metopic, lambdoid) and cortical bone density as key indicators of cranial development.

Conclusions:

Deep learning models demonstrate high accuracy in predicting infant postnatal age from skull radiographs.
The study validates the use of non-invasive radiographic features for assessing cranial development.
These findings support the potential of AI-powered tools for enhancing pediatric clinical diagnostics and developmental monitoring.