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

Classification of Bones

Classification of Bones

The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...

Changes in the Appendicular Skeleton with Age

Changes in the Appendicular Skeleton with Age

The upper and lower limb initially develops as a small bulge called a limb bud, which appears on the lateral side of the early embryo. The upper limb bud appears near the end of the fourth week of development, with the lower limb bud appearing shortly after.
Initially, the limb buds consist of a core of mesenchyme covered by a layer of ectoderm. The ectoderm at the end of the limb bud thickens to form a narrow crest called the apical ectodermal ridge. This ridge stimulates the underlying...

You might also read

Related Articles

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

Sort by

Same author

Early PCR-based DNA identification in a wartime mass-fatality event: archival reconstruction of the 1994 Duboki Jarak explosion.

Croatian medical journal·2026

Same author

Analysis of hyoid bone variations to estimate sex, age, and morphology: A study on the Croatian population for forensic applications.

International journal of legal medicine·2026

Same author

Classifying Sex from MSCT-Derived 3D Mandibular Models Using an Adapted PointNet++ Deep Learning Approach in a Croatian Population.

Journal of imaging·2025

Same author

Deep learning-based sex estimation of 3D hyoid bone models in a Croatian population using adapted PointNet++ network.

Scientific reports·2025

Same author

Tumour-Associated Microangiopathic Haemolytic Anaemia with Thrombocytopenia: A Narrative Review and Case Study.

Journal of clinical medicine·2025

Same author

Age estimation through sternal fusion and costal cartilage ossification using MSCT in a Croatian population: model development and application.

International journal of legal medicine·2025

Search research articles

Related Experiment Video

Updated: May 13, 2026

Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact

Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact

Published on: February 10, 2015

Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.

Nela Ivković¹, Željana Bašić¹, Ivan Jerković¹

¹University Department of Forensic Sciences, University of Split, Split, Croatia.

|November 22, 2024

Summary

Image analysis of medial clavicles using deep neural networks can distinguish age groups. This method achieved over 80% accuracy in classifying individuals younger and older than 30.

More Related Videos

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Published on: January 29, 2018

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

Related Experiment Videos

Last Updated: May 13, 2026

Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact

Measurement of Dynamic Scapular Kinematics Using an Acromion Marker Cluster to Minimize Skin Movement Artifact

Published on: February 10, 2015

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts

Published on: January 29, 2018

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Destabilization of the Medial Meniscus and Cartilage Scratch Murine Model of Accelerated Osteoarthritis

Published on: July 6, 2022

Area of Science:

Forensic Anthropology
Medical Imaging Analysis
Machine Learning in Healthcare

Background:

Accurate age estimation is crucial in forensic and clinical settings.
The medial clavicle offers potential for age-related skeletal analysis.
Developing non-invasive methods for age classification is an ongoing research area.

Purpose of the Study:

To develop and validate image-analysis-based classification models for distinguishing individuals younger and older than 30 years using medial clavicle features.
To assess the accuracy and reliability of machine learning classifiers for this task.

Main Methods:

Extraction of 2D medial clavicle images from multi-slice computed tomography (MSCT) scans.
Image vectorization using a pre-trained deep neural network (Painters model).
Application of Principal Components Analysis (PCA) for dimensionality reduction and data visualization.
Classification using Support Vector Machine (SVM), Logistic Regression (LR), and Neural Network Identity SGD (NNI-SGD) with 5-fold cross-validation and independent testing.

Main Results:

Principal Components Analysis revealed clavicle clustering into distinct age categories (under 30, 40-55, over 80 years).
Classifiers achieved >80% accuracy, with overall accuracy ranging from 82.5% to 92.5% for cross-validation and test sets.
A posterior probability threshold of 0.95 yielded up to 100% classification accuracy, albeit with a reduced number of classified images.

Conclusions:

Image analysis of the medial clavicle, powered by pre-trained deep neural networks, is a viable method for age classification.
The developed models demonstrate significant potential for distinguishing age groups, particularly the <30 and >30 dichotomy.
Further research can refine these techniques for improved forensic and clinical age estimation.