Gender Classification With Hand-Wrist Radiographs Using the Deep Learning Method

Objective: Before dental procedures, hand-wrist radiographs are used to plan treatment time and determine skeletal maturity. This study aims to determine gender from hand-wrist radiographs using different deep-learning methods.Methods: The left hand-wrist radiographs of 1044 individuals (534 males a...

Full description

Saved in:
Bibliographic Details
Main Authors: İbrahim Yücel Özbek, Mustafa Taha Güller, Zeynep Turanli Tosun, Nida Kumbasar, Özkan Miloğlu
Format: Article
Language:English
Published: Atatürk University 2025-01-01
Series:Current Research in Dental Sciences
Subjects:
Online Access:https://dergipark.org.tr/tr/download/article-file/4516648
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Objective: Before dental procedures, hand-wrist radiographs are used to plan treatment time and determine skeletal maturity. This study aims to determine gender from hand-wrist radiographs using different deep-learning methods.Methods: The left hand-wrist radiographs of 1044 individuals (534 males and 510 females) were pre-processed to clarify the image and adjust the contrast. In the gender classification problem, AlexNet, VGG16 and VGG19 transfer learning methods were both used as separate classifiers, and the features taken from these methods were combined and given to the support vector machine (SVM) classifier.Results: The results revealed that image analysis and deep learning techniques provided 91.1% accuracy in gender determination.Conclusion: Hand-wrist radiographs exhibited sexual dimorphism and could be used in gender prediction.Keywords: Deep learning; İmage analysis; Hand-wrist radiographs; Gender determination
ISSN:2822-2555