Automated age estimation from MRI volumes of the hand

Darko Stern, Christian Payer, Martin Urschler

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Highly relevant for both clinical and legal medicine applications, the established radiological methods for estimating unknown age in children and adolescents are based on visual examination of bone ossification in X-ray images of the hand. Our group has initiated the development of fully automatic age estimation methods from 3D MRI scans of the hand, in order to simultaneously overcome the problems of the radiological methods including (1) exposure to ionizing radiation, (2) necessity to define new, MRI specific staging systems, and (3) subjective influence of the examiner. The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation. Based on this theoretical background, we comprehensively evaluate machine learning methods (random forests, deep convolutional neural networks) with different …
Original languageEnglish
Article number 101538
JournalMedical image analysis
Volume58
DOIs
Publication statusPublished - 2019

Fingerprint

Magnetic resonance imaging
Hand
Ionizing radiation
Medicine
Learning systems
Bone
Neural networks
X rays
Forensic Medicine
Clinical Medicine
Ionizing Radiation
Osteogenesis
Magnetic Resonance Imaging
X-Rays
Bone and Bones

Cooperations

  • BioTechMed-Graz

Cite this

Automated age estimation from MRI volumes of the hand. / Stern, Darko; Payer, Christian; Urschler, Martin.

In: Medical image analysis, Vol. 58, 101538, 2019.

Research output: Contribution to journalArticleResearchpeer-review

@article{b288fa07134c422f9944283ba4de95e1,
title = "Automated age estimation from MRI volumes of the hand",
abstract = "Highly relevant for both clinical and legal medicine applications, the established radiological methods for estimating unknown age in children and adolescents are based on visual examination of bone ossification in X-ray images of the hand. Our group has initiated the development of fully automatic age estimation methods from 3D MRI scans of the hand, in order to simultaneously overcome the problems of the radiological methods including (1) exposure to ionizing radiation, (2) necessity to define new, MRI specific staging systems, and (3) subjective influence of the examiner. The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation. Based on this theoretical background, we comprehensively evaluate machine learning methods (random forests, deep convolutional neural networks) with different …",
author = "Darko Stern and Christian Payer and Martin Urschler",
year = "2019",
doi = "10.1016/j.media.2019.101538",
language = "English",
volume = "58",
journal = "Medical image analysis",
issn = "1361-8415",
publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Automated age estimation from MRI volumes of the hand

AU - Stern, Darko

AU - Payer, Christian

AU - Urschler, Martin

PY - 2019

Y1 - 2019

N2 - Highly relevant for both clinical and legal medicine applications, the established radiological methods for estimating unknown age in children and adolescents are based on visual examination of bone ossification in X-ray images of the hand. Our group has initiated the development of fully automatic age estimation methods from 3D MRI scans of the hand, in order to simultaneously overcome the problems of the radiological methods including (1) exposure to ionizing radiation, (2) necessity to define new, MRI specific staging systems, and (3) subjective influence of the examiner. The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation. Based on this theoretical background, we comprehensively evaluate machine learning methods (random forests, deep convolutional neural networks) with different …

AB - Highly relevant for both clinical and legal medicine applications, the established radiological methods for estimating unknown age in children and adolescents are based on visual examination of bone ossification in X-ray images of the hand. Our group has initiated the development of fully automatic age estimation methods from 3D MRI scans of the hand, in order to simultaneously overcome the problems of the radiological methods including (1) exposure to ionizing radiation, (2) necessity to define new, MRI specific staging systems, and (3) subjective influence of the examiner. The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation. Based on this theoretical background, we comprehensively evaluate machine learning methods (random forests, deep convolutional neural networks) with different …

U2 - 10.1016/j.media.2019.101538

DO - 10.1016/j.media.2019.101538

M3 - Article

VL - 58

JO - Medical image analysis

JF - Medical image analysis

SN - 1361-8415

M1 - 101538

ER -