A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs

Abstract Musculoskeletal disorders affect the locomotor system and are the leading contributor to disability worldwide. Patients suffer chronic pain and limitations in mobility, dexterity, and functional ability. Musculoskeletal (bone) X-ray is an essential tool in diagnosing the abnormalities. In r...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Minliang He, Xuming Wang, Yijun Zhao
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/d37be2c024164cde9ab10471a91000f2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d37be2c024164cde9ab10471a91000f2
record_format	dspace
spelling	oai:doaj.org-article:d37be2c024164cde9ab10471a91000f22021-12-02T17:16:05ZA calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs10.1038/s41598-021-88578-w2045-2322https://doaj.org/article/d37be2c024164cde9ab10471a91000f22021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88578-whttps://doaj.org/toc/2045-2322Abstract Musculoskeletal disorders affect the locomotor system and are the leading contributor to disability worldwide. Patients suffer chronic pain and limitations in mobility, dexterity, and functional ability. Musculoskeletal (bone) X-ray is an essential tool in diagnosing the abnormalities. In recent years, deep learning algorithms have increasingly been applied in musculoskeletal radiology and have produced remarkable results. In our study, we introduce a new calibrated ensemble of deep learners for the task of identifying abnormal musculoskeletal radiographs. Our model leverages the strengths of three baseline deep neural networks (ConvNet, ResNet, and DenseNet), which are typically employed either directly or as the backbone architecture in the existing deep learning-based approaches in this domain. Experimental results based on the public MURA dataset demonstrate that our proposed model outperforms three individual models and a traditional ensemble learner, achieving an overall performance of (AUC: 0.93, Accuracy: 0.87, Precision: 0.93, Recall: 0.81, Cohen’s kappa: 0.74). The model also outperforms expert radiologists in three out of the seven upper extremity anatomical regions with a leading performance of (AUC: 0.97, Accuracy: 0.93, Precision: 0.90, Recall:0.97, Cohen’s kappa: 0.85) in the humerus region. We further apply the class activation map technique to highlight the areas essential to our model’s decision-making process. Given that the best radiologist performance is between 0.73 and 0.78 in Cohen’s kappa statistic, our study provides convincing results supporting the utility of a calibrated ensemble approach for assessing abnormalities in musculoskeletal X-rays.Minliang HeXuming WangYijun ZhaoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Minliang He Xuming Wang Yijun Zhao A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs
description	Abstract Musculoskeletal disorders affect the locomotor system and are the leading contributor to disability worldwide. Patients suffer chronic pain and limitations in mobility, dexterity, and functional ability. Musculoskeletal (bone) X-ray is an essential tool in diagnosing the abnormalities. In recent years, deep learning algorithms have increasingly been applied in musculoskeletal radiology and have produced remarkable results. In our study, we introduce a new calibrated ensemble of deep learners for the task of identifying abnormal musculoskeletal radiographs. Our model leverages the strengths of three baseline deep neural networks (ConvNet, ResNet, and DenseNet), which are typically employed either directly or as the backbone architecture in the existing deep learning-based approaches in this domain. Experimental results based on the public MURA dataset demonstrate that our proposed model outperforms three individual models and a traditional ensemble learner, achieving an overall performance of (AUC: 0.93, Accuracy: 0.87, Precision: 0.93, Recall: 0.81, Cohen’s kappa: 0.74). The model also outperforms expert radiologists in three out of the seven upper extremity anatomical regions with a leading performance of (AUC: 0.97, Accuracy: 0.93, Precision: 0.90, Recall:0.97, Cohen’s kappa: 0.85) in the humerus region. We further apply the class activation map technique to highlight the areas essential to our model’s decision-making process. Given that the best radiologist performance is between 0.73 and 0.78 in Cohen’s kappa statistic, our study provides convincing results supporting the utility of a calibrated ensemble approach for assessing abnormalities in musculoskeletal X-rays.
format	article
author	Minliang He Xuming Wang Yijun Zhao
author_facet	Minliang He Xuming Wang Yijun Zhao
author_sort	Minliang He
title	A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs
title_short	A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs
title_full	A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs
title_fullStr	A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs
title_full_unstemmed	A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs
title_sort	calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/d37be2c024164cde9ab10471a91000f2
work_keys_str_mv	AT minlianghe acalibrateddeeplearningensembleforabnormalitydetectioninmusculoskeletalradiographs AT xumingwang acalibrateddeeplearningensembleforabnormalitydetectioninmusculoskeletalradiographs AT yijunzhao acalibrateddeeplearningensembleforabnormalitydetectioninmusculoskeletalradiographs AT minlianghe calibrateddeeplearningensembleforabnormalitydetectioninmusculoskeletalradiographs AT xumingwang calibrateddeeplearningensembleforabnormalitydetectioninmusculoskeletalradiographs AT yijunzhao calibrateddeeplearningensembleforabnormalitydetectioninmusculoskeletalradiographs
_version_	1718381229509705728

A calibrated deep learning ensemble for abnormality detection in musculoskeletal radiographs

Ejemplares similares