Cargando…

Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation

The aim of this study was to use geometric features and texture analysis to discriminate between healthy and unhealthy femurs and to identify the most influential features. We scanned proximal femoral bone (PFB) of 284 Iranian cases (21 to 83 years old) using different dual-energy X-ray absorptiomet...

Descripción completa

Detalles Bibliográficos
Autores principales: Najafi, Mojtaba, Yousefi Rezaii, Tohid, Danishvar, Sebelan, Razavi, Seyed Naser
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490574/
https://www.ncbi.nlm.nih.gov/pubmed/37688068
http://dx.doi.org/10.3390/s23177612
_version_ 1785103871057592320
author Najafi, Mojtaba
Yousefi Rezaii, Tohid
Danishvar, Sebelan
Razavi, Seyed Naser
author_facet Najafi, Mojtaba
Yousefi Rezaii, Tohid
Danishvar, Sebelan
Razavi, Seyed Naser
author_sort Najafi, Mojtaba
collection PubMed
description The aim of this study was to use geometric features and texture analysis to discriminate between healthy and unhealthy femurs and to identify the most influential features. We scanned proximal femoral bone (PFB) of 284 Iranian cases (21 to 83 years old) using different dual-energy X-ray absorptiometry (DEXA) scanners and magnetic resonance imaging (MRI) machines. Subjects were labeled as “healthy” (T-score > −0.9) and “unhealthy” based on the results of DEXA scans. Based on the geometry and texture of the PFB in MRI, 204 features were retrieved. We used support vector machine (SVM) with different kernels, decision tree, and logistic regression algorithms as classifiers and the Genetic algorithm (GA) to select the best set of features and to maximize accuracy. There were 185 participants classified as healthy and 99 as unhealthy. The SVM with radial basis function kernels had the best performance (89.08%) and the most influential features were geometrical ones. Even though our findings show the high performance of this model, further investigation with more subjects is suggested. To our knowledge, this is the first study that investigates qualitative classification of PFBs based on MRI with reference to DEXA scans using machine learning methods and the GA.
format Online
Article
Text
id pubmed-10490574
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104905742023-09-09 Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation Najafi, Mojtaba Yousefi Rezaii, Tohid Danishvar, Sebelan Razavi, Seyed Naser Sensors (Basel) Article The aim of this study was to use geometric features and texture analysis to discriminate between healthy and unhealthy femurs and to identify the most influential features. We scanned proximal femoral bone (PFB) of 284 Iranian cases (21 to 83 years old) using different dual-energy X-ray absorptiometry (DEXA) scanners and magnetic resonance imaging (MRI) machines. Subjects were labeled as “healthy” (T-score > −0.9) and “unhealthy” based on the results of DEXA scans. Based on the geometry and texture of the PFB in MRI, 204 features were retrieved. We used support vector machine (SVM) with different kernels, decision tree, and logistic regression algorithms as classifiers and the Genetic algorithm (GA) to select the best set of features and to maximize accuracy. There were 185 participants classified as healthy and 99 as unhealthy. The SVM with radial basis function kernels had the best performance (89.08%) and the most influential features were geometrical ones. Even though our findings show the high performance of this model, further investigation with more subjects is suggested. To our knowledge, this is the first study that investigates qualitative classification of PFBs based on MRI with reference to DEXA scans using machine learning methods and the GA. MDPI 2023-09-02 /pmc/articles/PMC10490574/ /pubmed/37688068 http://dx.doi.org/10.3390/s23177612 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Najafi, Mojtaba
Yousefi Rezaii, Tohid
Danishvar, Sebelan
Razavi, Seyed Naser
Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation
title Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation
title_full Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation
title_fullStr Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation
title_full_unstemmed Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation
title_short Qualitative Classification of Proximal Femoral Bone Using Geometric Features and Texture Analysis in Collected MRI Images for Bone Density Evaluation
title_sort qualitative classification of proximal femoral bone using geometric features and texture analysis in collected mri images for bone density evaluation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490574/
https://www.ncbi.nlm.nih.gov/pubmed/37688068
http://dx.doi.org/10.3390/s23177612
work_keys_str_mv AT najafimojtaba qualitativeclassificationofproximalfemoralboneusinggeometricfeaturesandtextureanalysisincollectedmriimagesforbonedensityevaluation
AT yousefirezaiitohid qualitativeclassificationofproximalfemoralboneusinggeometricfeaturesandtextureanalysisincollectedmriimagesforbonedensityevaluation
AT danishvarsebelan qualitativeclassificationofproximalfemoralboneusinggeometricfeaturesandtextureanalysisincollectedmriimagesforbonedensityevaluation
AT razaviseyednaser qualitativeclassificationofproximalfemoralboneusinggeometricfeaturesandtextureanalysisincollectedmriimagesforbonedensityevaluation