Sex prediction with morphometric measurements of first and fifth metatarsal and phalanx obtained from X-ray images by using machine learning algorithms

Aug 5, 2026

Upload by Jiven

Study objective focused on predicting sex by applying machine learning (ML) to morphometric measurements from radiological images of the first and fifth metatarsal and phalanx. Retrospective analysis included 263 individuals (135 female, 128 male) aged 27–60. DICOM images were evaluated using a radiological workstation tool to obtain length and width measurements, and selected phalanx/metatarsal ratios. Decision Tree produced the highest performance, with accuracy and discrimination metrics reaching about 0.85 accuracy and 0.86 specificity.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Background

Materials and methods

Results

Conclusions

Introduction

Sex determination in forensic and medical contexts

Role of bones and limitations

Alternatives to DNA and ML overview

ONLINE FIRST This is a provisional PDF only. Copyedited and fully formatted version will be made available soon. ISSN: 0015-5659 e-ISSN: 1644-3284 Sex prediction with morphometric measurements of first and fifth metatarsal and phalanx obtained from X-ray images by using machine learning algorithms Authors: D. Senol, F. Bodur, Y. Seçgin, R. S. Bakıcı, N. E. Sahin, S. Toy, S. Öner, Z. Oner DOI: 10. 5603/FM.a2022 .0052 Article type: Original article Submitted: 2022-03-24 Accepted: 2022-05-11 Published online: 2022-05-20 This article has been peer reviewed and published immediately upon acceptance. It is an open access article, which means that it can be downloaded, printed, and distributed freely, provided the work is properly cited. Articles in "Folia Morphologica" are listed in PubMed. Sex prediction with morphometric measurements of first and fifth metatarsal and phalanx obtained from X-ray images by using machine learning algorithms D. Senol et al., Sex prediction from metatarsal and phalanx by using machine learning algorithms D. Senol1, F. Bodur1, Y. Secgın2, R. S. Bakıcı2, N.E. Sahin2, S. Toy2, S. Oner3, Z. Oner4 1Düzce University Faculty of Medicine Department of Anatomy, Düzce, Turkey 2Karabük University Faculty of Medicine Department of Anatomy, Karabük, Turkey 3İzmir Bakırçay University Faculty of Medicine Department of Radiology, İzmir, Turkey 4İzmir Bakırçay University Faculty of Medicine Department of Anatomy, İzmir, Turkey Address for correspondence: D. Senol, Düzce University Faculty of Medicine Department of Anatomy, Düzce, Turkey, e-mail: [denizanatomi@gmail.com](denizanatomi@gmail.com) Abstract Background: The aim of this study is to predict sex with machine learning (ML) algorithms by making morphometric measurements on radiological images of the first and fifth metatarsal and phalanx bones. Materials and methods: In this study, radiologic images of 263 individuals (135 female, 128 male) between the ages of 27 and 60 were analyzed retrospectively. The images in Digital Imaging and Communications in Medicine (DICOM) format were transferred to personal workstation Radiant DICOM Viewer program. Length and width measurements of the first and fifth metatarsal and foot phalanx bones were performed on the transferred images. In addition, the ratios of the total length of the first proximal and distal phalanx and length of the first metatarsal and total length of fifth proximal, middle, and distal phalanx and maximum length of fifth metatarsal were calculated. Results: As a result of machine learning (ML) algorithms, highest accuracy (Acc), specificity (Spe), sensitivity (Sen), Matthews correlation coefficient (Mcc) values were found as 0.85, 0.86, 0.85 and 0.71, respectively with Decision Tree algorithm. It was found that accuracy rates of other algorithms varied between 0.74 and 0.83. Conclusions: As a result of our study, it was found that sex estimation was made with high accuracy rate by using ML algorithms on X-ray images of the first and fifth metatarsal and foot phalanx. We think that in cases when pelvis, cranium and long bones are harmed and examination is difficult, bones of the first and fifth metatarsal and foot phalanx can be used for sex estimation. Key words: decision tree, machine learning algorithms, metatarsus, phalanx, radiography, sex prediction, X-ray INTRODUCTION For years, sex has been one of the most important parameters used for identity determination. In medical and forensic cases, especially anthropometric measurements taken from the parts of an unidentified decomposed or decayed body are important in terms of predicting the height, sex and age of the individual [34] . These anthropometric measurements are frequently used in sex determination and data obtained as a result of studies are very useful especially in terms of identity determination of victims of large-scale disasters and deadly attacks [20] . In identity determination,

FAQs

What data and measurements were used to predict sex?

Radiologic X-ray images in DICOM format were used, with morphometric length and width measurements from the first and fifth metatarsal and foot phalanx. Ratios based on specific phalanx and metatarsal lengths were also calculated.

How many individuals were analyzed and what were the sex distribution details?

The retrospective dataset included 263 individuals, consisting of 135 females and 128 males, aged between 27 and 60.

Which machine learning approach achieved the best accuracy?

The Decision Tree algorithm delivered the highest reported performance, with accuracy around 0.85 and specificity around 0.86 (and sensitivity around 0.85).

Aug 5, 2026

Upload by Jiven