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

This study aimed to develop image-analysis-based classification models for distinguishing individuals younger and older than 30 using the medial clavicle. We extracted 2D images of the medial clavicle from multi-slice computed tomography (MSCT) scans from Clinical Hospital Center Split (n = 204). A...

Full description

Saved in:
Bibliographic Details
Main Authors: Nela Ivković, Željana Bašić, Ivan Jerković
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0311262
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129250262188032
author Nela Ivković
Željana Bašić
Ivan Jerković
author_facet Nela Ivković
Željana Bašić
Ivan Jerković
author_sort Nela Ivković
collection DOAJ
description This study aimed to develop image-analysis-based classification models for distinguishing individuals younger and older than 30 using the medial clavicle. We extracted 2D images of the medial clavicle from multi-slice computed tomography (MSCT) scans from Clinical Hospital Center Split (n = 204). A sample was divided into a training (164 images) and testing (40 images) dataset. The images were loaded into the Orange Data Mining 3.32.0., and transformed into vectors using the pre-trained neural network Painters: A model trained to predict painters from artwork images. We conducted Principal Components Analysis (PCA) to visualize regularities within data and reduce data dimensionality in classification. We employed three classifiers that provided >80% accuracy: Support Vector Machine (SVM), Logistic Regression (LR), and Neutral Network Identity SGD (NNI-SGD). We used 5-fold cross-validation (CV) to obtain optimal variables and performances and validated data on the independent test set, with a standard posterior probabilities (pp) threshold of 0.5 and 0.95. The explainability of the model was accessed visually by analyzing clusters and incorrectly classified images using anthropology field knowledge. Based on the PCA, clavicles clustered into categories under 30 and 40 years, between 40 and 55 years, and over 80 years. The overall accuracy with standard pp ranged from 82.5% to 92.5% for CV and 82.5% to 92.5% for the test set. The posterior probability of 0.95 provided classification accuracy up to 100% but with a lower proportion of images that could be classified. The study showed that image analysis based on a pre-trained deep neural network could contribute to distinguishing clavicles of individuals younger and older than 30.
format Article
id doaj-art-8077c2edd72f490fa514edaaf8d471e7
institution OA Journals
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-8077c2edd72f490fa514edaaf8d471e72025-08-20T02:33:04ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011911e031126210.1371/journal.pone.0311262Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.Nela IvkovićŽeljana BašićIvan JerkovićThis study aimed to develop image-analysis-based classification models for distinguishing individuals younger and older than 30 using the medial clavicle. We extracted 2D images of the medial clavicle from multi-slice computed tomography (MSCT) scans from Clinical Hospital Center Split (n = 204). A sample was divided into a training (164 images) and testing (40 images) dataset. The images were loaded into the Orange Data Mining 3.32.0., and transformed into vectors using the pre-trained neural network Painters: A model trained to predict painters from artwork images. We conducted Principal Components Analysis (PCA) to visualize regularities within data and reduce data dimensionality in classification. We employed three classifiers that provided >80% accuracy: Support Vector Machine (SVM), Logistic Regression (LR), and Neutral Network Identity SGD (NNI-SGD). We used 5-fold cross-validation (CV) to obtain optimal variables and performances and validated data on the independent test set, with a standard posterior probabilities (pp) threshold of 0.5 and 0.95. The explainability of the model was accessed visually by analyzing clusters and incorrectly classified images using anthropology field knowledge. Based on the PCA, clavicles clustered into categories under 30 and 40 years, between 40 and 55 years, and over 80 years. The overall accuracy with standard pp ranged from 82.5% to 92.5% for CV and 82.5% to 92.5% for the test set. The posterior probability of 0.95 provided classification accuracy up to 100% but with a lower proportion of images that could be classified. The study showed that image analysis based on a pre-trained deep neural network could contribute to distinguishing clavicles of individuals younger and older than 30.https://doi.org/10.1371/journal.pone.0311262
spellingShingle Nela Ivković
Željana Bašić
Ivan Jerković
Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.
PLoS ONE
title Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.
title_full Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.
title_fullStr Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.
title_full_unstemmed Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.
title_short Classifying age from medial clavicle using a 30-year threshold: An image analysis based approach.
title_sort classifying age from medial clavicle using a 30 year threshold an image analysis based approach
url https://doi.org/10.1371/journal.pone.0311262
work_keys_str_mv AT nelaivkovic classifyingagefrommedialclavicleusinga30yearthresholdanimageanalysisbasedapproach
AT zeljanabasic classifyingagefrommedialclavicleusinga30yearthresholdanimageanalysisbasedapproach
AT ivanjerkovic classifyingagefrommedialclavicleusinga30yearthresholdanimageanalysisbasedapproach