Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis

Abstract Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Livija Jakaite, Vitaly Schetinin, Jiří Hladůvka, Sergey Minaev, Aziz Ambia, Wojtek Krzanowski
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/ea0ab033e796475aa16be1641f1a5396
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ea0ab033e796475aa16be1641f1a5396
record_format	dspace
spelling	oai:doaj.org-article:ea0ab033e796475aa16be1641f1a53962021-12-02T10:48:03ZDeep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis10.1038/s41598-021-81786-42045-2322https://doaj.org/article/ea0ab033e796475aa16be1641f1a53962021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81786-4https://doaj.org/toc/2045-2322Abstract Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper we explore the ability of machine learning (ML) methods to design a radiology test of Osteoarthritis (OA) at early stage when the number of patients’ cases is small. In our experiments we use high-resolution X-ray images of knees in patients which were identified with Kellgren–Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of patients’ cases will be available.Livija JakaiteVitaly SchetininJiří HladůvkaSergey MinaevAziz AmbiaWojtek KrzanowskiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Livija Jakaite Vitaly Schetinin Jiří Hladůvka Sergey Minaev Aziz Ambia Wojtek Krzanowski Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis
description	Abstract Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper we explore the ability of machine learning (ML) methods to design a radiology test of Osteoarthritis (OA) at early stage when the number of patients’ cases is small. In our experiments we use high-resolution X-ray images of knees in patients which were identified with Kellgren–Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of patients’ cases will be available.
format	article
author	Livija Jakaite Vitaly Schetinin Jiří Hladůvka Sergey Minaev Aziz Ambia Wojtek Krzanowski
author_facet	Livija Jakaite Vitaly Schetinin Jiří Hladůvka Sergey Minaev Aziz Ambia Wojtek Krzanowski
author_sort	Livija Jakaite
title	Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis
title_short	Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis
title_full	Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis
title_fullStr	Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis
title_full_unstemmed	Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis
title_sort	deep learning for early detection of pathological changes in x-ray bone microstructures: case of osteoarthritis
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/ea0ab033e796475aa16be1641f1a5396
work_keys_str_mv	AT livijajakaite deeplearningforearlydetectionofpathologicalchangesinxraybonemicrostructurescaseofosteoarthritis AT vitalyschetinin deeplearningforearlydetectionofpathologicalchangesinxraybonemicrostructurescaseofosteoarthritis AT jirihladuvka deeplearningforearlydetectionofpathologicalchangesinxraybonemicrostructurescaseofosteoarthritis AT sergeyminaev deeplearningforearlydetectionofpathologicalchangesinxraybonemicrostructurescaseofosteoarthritis AT azizambia deeplearningforearlydetectionofpathologicalchangesinxraybonemicrostructurescaseofosteoarthritis AT wojtekkrzanowski deeplearningforearlydetectionofpathologicalchangesinxraybonemicrostructurescaseofosteoarthritis
_version_	1718396681990438912

Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis

Ejemplares similares