Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.

The aim of the study was to use a previously proposed mask region-based convolutional neural network (Mask R-CNN) for automatic abnormal liver density detection and segmentation based on hepatocellular carcinoma (HCC) computed tomography (CT) datasets from a radiological perspective. Training and te...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ching-Juei Yang, Chien-Kuo Wang, Yu-Hua Dean Fang, Jing-Yao Wang, Fong-Chin Su, Hong-Ming Tsai, Yih-Jyh Lin, Hung-Wen Tsai, Lee-Ren Yeh
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/dfaeedd751594b4385b21073abf16088
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dfaeedd751594b4385b21073abf16088
record_format	dspace
spelling	oai:doaj.org-article:dfaeedd751594b4385b21073abf160882021-12-02T20:18:26ZClinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.1932-620310.1371/journal.pone.0255605https://doaj.org/article/dfaeedd751594b4385b21073abf160882021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0255605https://doaj.org/toc/1932-6203The aim of the study was to use a previously proposed mask region-based convolutional neural network (Mask R-CNN) for automatic abnormal liver density detection and segmentation based on hepatocellular carcinoma (HCC) computed tomography (CT) datasets from a radiological perspective. Training and testing datasets were acquired retrospectively from two hospitals of Taiwan. The training dataset contained 10,130 images of liver tumor densities of 11,258 regions of interest (ROIs). The positive testing dataset contained 1,833 images of liver tumor densities with 1,874 ROIs, and negative testing data comprised 20,283 images without abnormal densities in liver parenchyma. The Mask R-CNN was used to generate a medical model, and areas under the curve, true positive rates, false positive rates, and Dice coefficients were evaluated. For abnormal liver CT density detection, in each image, we identified the mean area under the curve, true positive rate, and false positive rate, which were 0.9490, 91.99%, and 13.68%, respectively. For segmentation ability, the highest mean Dice coefficient obtained was 0.8041. This study trained a Mask R-CNN on various HCC images to construct a medical model that serves as an auxiliary tool for alerting radiologists to abnormal CT density in liver scans; this model can simultaneously detect liver lesions and perform automatic instance segmentation.Ching-Juei YangChien-Kuo WangYu-Hua Dean FangJing-Yao WangFong-Chin SuHong-Ming TsaiYih-Jyh LinHung-Wen TsaiLee-Ren YehPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 8, p e0255605 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ching-Juei Yang Chien-Kuo Wang Yu-Hua Dean Fang Jing-Yao Wang Fong-Chin Su Hong-Ming Tsai Yih-Jyh Lin Hung-Wen Tsai Lee-Ren Yeh Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.
description	The aim of the study was to use a previously proposed mask region-based convolutional neural network (Mask R-CNN) for automatic abnormal liver density detection and segmentation based on hepatocellular carcinoma (HCC) computed tomography (CT) datasets from a radiological perspective. Training and testing datasets were acquired retrospectively from two hospitals of Taiwan. The training dataset contained 10,130 images of liver tumor densities of 11,258 regions of interest (ROIs). The positive testing dataset contained 1,833 images of liver tumor densities with 1,874 ROIs, and negative testing data comprised 20,283 images without abnormal densities in liver parenchyma. The Mask R-CNN was used to generate a medical model, and areas under the curve, true positive rates, false positive rates, and Dice coefficients were evaluated. For abnormal liver CT density detection, in each image, we identified the mean area under the curve, true positive rate, and false positive rate, which were 0.9490, 91.99%, and 13.68%, respectively. For segmentation ability, the highest mean Dice coefficient obtained was 0.8041. This study trained a Mask R-CNN on various HCC images to construct a medical model that serves as an auxiliary tool for alerting radiologists to abnormal CT density in liver scans; this model can simultaneously detect liver lesions and perform automatic instance segmentation.
format	article
author	Ching-Juei Yang Chien-Kuo Wang Yu-Hua Dean Fang Jing-Yao Wang Fong-Chin Su Hong-Ming Tsai Yih-Jyh Lin Hung-Wen Tsai Lee-Ren Yeh
author_facet	Ching-Juei Yang Chien-Kuo Wang Yu-Hua Dean Fang Jing-Yao Wang Fong-Chin Su Hong-Ming Tsai Yih-Jyh Lin Hung-Wen Tsai Lee-Ren Yeh
author_sort	Ching-Juei Yang
title	Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.
title_short	Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.
title_full	Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.
title_fullStr	Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.
title_full_unstemmed	Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.
title_sort	clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/dfaeedd751594b4385b21073abf16088
work_keys_str_mv	AT chingjueiyang clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT chienkuowang clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT yuhuadeanfang clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT jingyaowang clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT fongchinsu clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT hongmingtsai clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT yihjyhlin clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT hungwentsai clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets AT leerenyeh clinicalapplicationofmaskregionbasedconvolutionalneuralnetworkfortheautomaticdetectionandsegmentationofabnormalliverdensitybasedonhepatocellularcarcinomacomputedtomographydatasets
_version_	1718374317646938112

Clinical application of mask region-based convolutional neural network for the automatic detection and segmentation of abnormal liver density based on hepatocellular carcinoma computed tomography datasets.

Ejemplares similares