Markus Auf der Mauer

Towards Automated Age Estimation of Young Individuals

A New Computer-Based Approach Using 3D Knee MRI


Front	Back

ISBN:

978-3-8440-7400-0

Series:

Medizinischen Informatik und Bioinformatik

Keywords:

Automated age estimation; MRI; Knee; Machine learning; Convolutional neural networks; Segmentation

Type of publication:

Thesis

Language:

English

Pages:

194 pages

Figures:

68 figures

Weight:

288 g

Format:

21 x 14,8 cm

Binding:

Paperback

Price:

48,80 € / 61,10 SFr

Published:

June 2020

Buy:

DOI:

10.2370/9783844074000 (Online document)

Download:

Available PDF-Files for this title:

You need the Adobe Reader, to open the files. Here you get help and information, for the download.

These files are not printable.


	Document		Abstract
	Type		PDF
	Costs		free
	Action		Display of file - 616 kB (630747 Byte)
	Action		Download of file - 616 kB (630747 Byte)


	Document		Document
	Type		PDF
	Costs		36,60 EUR
	Action		Purchase in obligation and display of file - 26,0 MB (27284109 Byte)
	Action		Purchase in obligation and download of file - 26,0 MB (27284109 Byte)


	Document		Table of contents
	Type		PDF
	Costs		free
	Action		Display of file - 689 kB (705571 Byte)
	Action		Download of file - 689 kB (705571 Byte)

User settings for registered users

You can change your address here or download your paid documents again.

User:	Not logged in.
Actions:	Login / Register Forgotten your password?

Recommendation:

You want to recommend this title?

Review copy:

Here you can order a review copy.

Link:

You want to link this page? Click here.

Export citations:

Text
BibTex
RIS

Abstract:

The purpose of this work is to investigate the age estimation of living individuals on the basis of MRI sequences of the knee. Using a large data collective of young male subjects, a new AI-based approach is developed to automatically detect bone structures in the image and to learn the chronological age based on this information. With a mean absolute error (MAE) of 0.69 ± 0.47 years for the prediction of the age and an accuracy of 90.9% for the majority classification on the 18-year-limit, the results demonstrate the potential of this approach.

Im Rahmen dieser Arbeit wird die Fragestellung der Altersbestimmung bei Lebenden auf Basis von Knie-MRT-Bildsequenzen untersucht. Anhand eines großen Datenkollektivs von jungen männliche Probanden, wird ein neuer KI-basierter Ansatz entwickelt, um Knochenstrukturen automatisch im Bild zu erkennen und darauf basierend das chronologische Alter zu erlernen. Mit einem mittleren absoluten Fehler (MAE) von 0,69 ± 0,47 Jahren für die Vorhersage des Alters und einer Genauigkeit von 90,9% bei der Frage nach der Volljährigkeit, belegen die Ergebnisse das Potential dieses Ansatzes.