Segmentation and recognition of breast ultrasound images based on an expanded U-Net.

This paper establishes a fully automatic real-time image segmentation and recognition system for breast ultrasound intervention robots. It adopts the basic architecture of a U-shaped convolutional network (U-Net), analyses the actual application scenarios of semantic segmentation of breast ultrasoun...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yanjun Guo, Xingguang Duan, Chengyi Wang, Huiqin Guo
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/ac2e9016873a4df3847d12e4527bfb29
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ac2e9016873a4df3847d12e4527bfb29
record_format dspace
spelling oai:doaj.org-article:ac2e9016873a4df3847d12e4527bfb292021-12-02T20:10:39ZSegmentation and recognition of breast ultrasound images based on an expanded U-Net.1932-620310.1371/journal.pone.0253202https://doaj.org/article/ac2e9016873a4df3847d12e4527bfb292021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0253202https://doaj.org/toc/1932-6203This paper establishes a fully automatic real-time image segmentation and recognition system for breast ultrasound intervention robots. It adopts the basic architecture of a U-shaped convolutional network (U-Net), analyses the actual application scenarios of semantic segmentation of breast ultrasound images, and adds dropout layers to the U-Net architecture to reduce the redundancy in texture details and prevent overfitting. The main innovation of this paper is proposing an expanded training approach to obtain an expanded of U-Net. The output map of the expanded U-Net can retain texture details and edge features of breast tumours. Using the grey-level probability labels to train the U-Net is faster than using ordinary labels. The average Dice coefficient (standard deviation) and the average IOU coefficient (standard deviation) are 90.5% (±0.02) and 82.7% (±0.02), respectively, when using the expanded training approach. The Dice coefficient of the expanded U-Net is 7.6 larger than that of a general U-Net, and the IOU coefficient of the expanded U-Net is 11 larger than that of the general U-Net. The context of breast ultrasound images can be extracted, and texture details and edge features of tumours can be retained by the expanded U-Net. Using an expanded U-Net can quickly and automatically achieve precise segmentation and multi-class recognition of breast ultrasound images.Yanjun GuoXingguang DuanChengyi WangHuiqin GuoPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0253202 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Yanjun Guo
Xingguang Duan
Chengyi Wang
Huiqin Guo
Segmentation and recognition of breast ultrasound images based on an expanded U-Net.
description This paper establishes a fully automatic real-time image segmentation and recognition system for breast ultrasound intervention robots. It adopts the basic architecture of a U-shaped convolutional network (U-Net), analyses the actual application scenarios of semantic segmentation of breast ultrasound images, and adds dropout layers to the U-Net architecture to reduce the redundancy in texture details and prevent overfitting. The main innovation of this paper is proposing an expanded training approach to obtain an expanded of U-Net. The output map of the expanded U-Net can retain texture details and edge features of breast tumours. Using the grey-level probability labels to train the U-Net is faster than using ordinary labels. The average Dice coefficient (standard deviation) and the average IOU coefficient (standard deviation) are 90.5% (±0.02) and 82.7% (±0.02), respectively, when using the expanded training approach. The Dice coefficient of the expanded U-Net is 7.6 larger than that of a general U-Net, and the IOU coefficient of the expanded U-Net is 11 larger than that of the general U-Net. The context of breast ultrasound images can be extracted, and texture details and edge features of tumours can be retained by the expanded U-Net. Using an expanded U-Net can quickly and automatically achieve precise segmentation and multi-class recognition of breast ultrasound images.
format article
author Yanjun Guo
Xingguang Duan
Chengyi Wang
Huiqin Guo
author_facet Yanjun Guo
Xingguang Duan
Chengyi Wang
Huiqin Guo
author_sort Yanjun Guo
title Segmentation and recognition of breast ultrasound images based on an expanded U-Net.
title_short Segmentation and recognition of breast ultrasound images based on an expanded U-Net.
title_full Segmentation and recognition of breast ultrasound images based on an expanded U-Net.
title_fullStr Segmentation and recognition of breast ultrasound images based on an expanded U-Net.
title_full_unstemmed Segmentation and recognition of breast ultrasound images based on an expanded U-Net.
title_sort segmentation and recognition of breast ultrasound images based on an expanded u-net.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/ac2e9016873a4df3847d12e4527bfb29
work_keys_str_mv AT yanjunguo segmentationandrecognitionofbreastultrasoundimagesbasedonanexpandedunet
AT xingguangduan segmentationandrecognitionofbreastultrasoundimagesbasedonanexpandedunet
AT chengyiwang segmentationandrecognitionofbreastultrasoundimagesbasedonanexpandedunet
AT huiqinguo segmentationandrecognitionofbreastultrasoundimagesbasedonanexpandedunet
_version_ 1718374965765472256