Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN

Abstract Fecal samples can easily be collected and are representative of a person’s current health state; therefore, the demand for routine fecal examination has increased sharply. However, manual operation may pollute the samples, and low efficiency limits the general examination speed; therefore,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jing Zhang, Xiangzhou Wang, Guangming Ni, Juanxiu Liu, Ruqian Hao, Lin Liu, Yong Liu, Xiaohui Du, Fan Xu
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/95c125c38d2d43c6b0dde166b82e2915
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:95c125c38d2d43c6b0dde166b82e2915
record_format	dspace
spelling	oai:doaj.org-article:95c125c38d2d43c6b0dde166b82e29152021-12-02T16:50:22ZFast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN10.1038/s41598-021-89863-42045-2322https://doaj.org/article/95c125c38d2d43c6b0dde166b82e29152021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-89863-4https://doaj.org/toc/2045-2322Abstract Fecal samples can easily be collected and are representative of a person’s current health state; therefore, the demand for routine fecal examination has increased sharply. However, manual operation may pollute the samples, and low efficiency limits the general examination speed; therefore, automatic analysis is needed. Nevertheless, recognition exhaustion time and accuracy remain major challenges in automatic testing. Here, we introduce a fast and efficient cell-detection algorithm based on the Faster-R-CNN technique: the Resnet-152 convolutional neural network architecture. Additionally, a region proposal network and a network combined with principal component analysis are proposed for cell location and recognition in microscopic images. Our algorithm achieved a mean average precision of 84% and a 723 ms detection time per sample for 40,560 fecal images. Thus, this approach may provide a solid theoretical basis for real-time detection in routine clinical examinations while accelerating the process to satisfy increasing demand.Jing ZhangXiangzhou WangGuangming NiJuanxiu LiuRuqian HaoLin LiuYong LiuXiaohui DuFan XuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jing Zhang Xiangzhou Wang Guangming Ni Juanxiu Liu Ruqian Hao Lin Liu Yong Liu Xiaohui Du Fan Xu Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN
description	Abstract Fecal samples can easily be collected and are representative of a person’s current health state; therefore, the demand for routine fecal examination has increased sharply. However, manual operation may pollute the samples, and low efficiency limits the general examination speed; therefore, automatic analysis is needed. Nevertheless, recognition exhaustion time and accuracy remain major challenges in automatic testing. Here, we introduce a fast and efficient cell-detection algorithm based on the Faster-R-CNN technique: the Resnet-152 convolutional neural network architecture. Additionally, a region proposal network and a network combined with principal component analysis are proposed for cell location and recognition in microscopic images. Our algorithm achieved a mean average precision of 84% and a 723 ms detection time per sample for 40,560 fecal images. Thus, this approach may provide a solid theoretical basis for real-time detection in routine clinical examinations while accelerating the process to satisfy increasing demand.
format	article
author	Jing Zhang Xiangzhou Wang Guangming Ni Juanxiu Liu Ruqian Hao Lin Liu Yong Liu Xiaohui Du Fan Xu
author_facet	Jing Zhang Xiangzhou Wang Guangming Ni Juanxiu Liu Ruqian Hao Lin Liu Yong Liu Xiaohui Du Fan Xu
author_sort	Jing Zhang
title	Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN
title_short	Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN
title_full	Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN
title_fullStr	Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN
title_full_unstemmed	Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN
title_sort	fast and accurate automated recognition of the dominant cells from fecal images based on faster r-cnn
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/95c125c38d2d43c6b0dde166b82e2915
work_keys_str_mv	AT jingzhang fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT xiangzhouwang fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT guangmingni fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT juanxiuliu fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT ruqianhao fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT linliu fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT yongliu fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT xiaohuidu fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn AT fanxu fastandaccurateautomatedrecognitionofthedominantcellsfromfecalimagesbasedonfasterrcnn
_version_	1718383053060964352

Fast and accurate automated recognition of the dominant cells from fecal images based on Faster R-CNN

Ejemplares similares