Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning

Abstract We examined the feasibility of explainable computer-aided detection of cardiomegaly in routine clinical practice using segmentation-based methods. Overall, 793 retrospectively acquired posterior–anterior (PA) chest X-ray images (CXRs) of 793 patients were used to train deep learning (DL) mo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mu Sook Lee, Yong Soo Kim, Minki Kim, Muhammad Usman, Shi Sub Byon, Sung Hyun Kim, Byoung Il Lee, Byoung-Dai Lee
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/045bddf4643c4bf69c3789b38e685aee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:045bddf4643c4bf69c3789b38e685aee
record_format	dspace
spelling	oai:doaj.org-article:045bddf4643c4bf69c3789b38e685aee2021-12-02T17:08:23ZEvaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning10.1038/s41598-021-96433-12045-2322https://doaj.org/article/045bddf4643c4bf69c3789b38e685aee2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96433-1https://doaj.org/toc/2045-2322Abstract We examined the feasibility of explainable computer-aided detection of cardiomegaly in routine clinical practice using segmentation-based methods. Overall, 793 retrospectively acquired posterior–anterior (PA) chest X-ray images (CXRs) of 793 patients were used to train deep learning (DL) models for lung and heart segmentation. The training dataset included PA CXRs from two public datasets and in-house PA CXRs. Two fully automated segmentation-based methods using state-of-the-art DL models for lung and heart segmentation were developed. The diagnostic performance was assessed and the reliability of the automatic cardiothoracic ratio (CTR) calculation was determined using the mean absolute error and paired t-test. The effects of thoracic pathological conditions on performance were assessed using subgroup analysis. One thousand PA CXRs of 1000 patients (480 men, 520 women; mean age 63 ± 23 years) were included. The CTR values derived from the DL models and diagnostic performance exhibited excellent agreement with reference standards for the whole test dataset. Performance of segmentation-based methods differed based on thoracic conditions. When tested using CXRs with lesions obscuring heart borders, the performance was lower than that for other thoracic pathological findings. Thus, segmentation-based methods using DL could detect cardiomegaly; however, the feasibility of computer-aided detection of cardiomegaly without human intervention was limited.Mu Sook LeeYong Soo KimMinki KimMuhammad UsmanShi Sub ByonSung Hyun KimByoung Il LeeByoung-Dai LeeNature 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 Mu Sook Lee Yong Soo Kim Minki Kim Muhammad Usman Shi Sub Byon Sung Hyun Kim Byoung Il Lee Byoung-Dai Lee Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning
description	Abstract We examined the feasibility of explainable computer-aided detection of cardiomegaly in routine clinical practice using segmentation-based methods. Overall, 793 retrospectively acquired posterior–anterior (PA) chest X-ray images (CXRs) of 793 patients were used to train deep learning (DL) models for lung and heart segmentation. The training dataset included PA CXRs from two public datasets and in-house PA CXRs. Two fully automated segmentation-based methods using state-of-the-art DL models for lung and heart segmentation were developed. The diagnostic performance was assessed and the reliability of the automatic cardiothoracic ratio (CTR) calculation was determined using the mean absolute error and paired t-test. The effects of thoracic pathological conditions on performance were assessed using subgroup analysis. One thousand PA CXRs of 1000 patients (480 men, 520 women; mean age 63 ± 23 years) were included. The CTR values derived from the DL models and diagnostic performance exhibited excellent agreement with reference standards for the whole test dataset. Performance of segmentation-based methods differed based on thoracic conditions. When tested using CXRs with lesions obscuring heart borders, the performance was lower than that for other thoracic pathological findings. Thus, segmentation-based methods using DL could detect cardiomegaly; however, the feasibility of computer-aided detection of cardiomegaly without human intervention was limited.
format	article
author	Mu Sook Lee Yong Soo Kim Minki Kim Muhammad Usman Shi Sub Byon Sung Hyun Kim Byoung Il Lee Byoung-Dai Lee
author_facet	Mu Sook Lee Yong Soo Kim Minki Kim Muhammad Usman Shi Sub Byon Sung Hyun Kim Byoung Il Lee Byoung-Dai Lee
author_sort	Mu Sook Lee
title	Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning
title_short	Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning
title_full	Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning
title_fullStr	Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning
title_full_unstemmed	Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning
title_sort	evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/045bddf4643c4bf69c3789b38e685aee
work_keys_str_mv	AT musooklee evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning AT yongsookim evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning AT minkikim evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning AT muhammadusman evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning AT shisubbyon evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning AT sunghyunkim evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning AT byoungillee evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning AT byoungdailee evaluationofthefeasibilityofexplainablecomputeraideddetectionofcardiomegalyonchestradiographsusingdeeplearning
_version_	1718381535882641408

Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning

Ejemplares similares