Cargando…

BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images

Ultrasound (US) imaging is a main modality for breast disease screening. Automatically detecting the lesions in US images is essential for developing the artificial-intelligence-based diagnostic support technologies. However, the intrinsic characteristics of ultrasound imaging, like speckle noise an...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Yujie, Gu, Hong, Wang, Hongyu, Qin, Pan, Wang, Jia
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8989926/
https://www.ncbi.nlm.nih.gov/pubmed/35402269
http://dx.doi.org/10.3389/fonc.2022.848271
_version_ 1784683277706067968
author Li, Yujie
Gu, Hong
Wang, Hongyu
Qin, Pan
Wang, Jia
author_facet Li, Yujie
Gu, Hong
Wang, Hongyu
Qin, Pan
Wang, Jia
author_sort Li, Yujie
collection PubMed
description Ultrasound (US) imaging is a main modality for breast disease screening. Automatically detecting the lesions in US images is essential for developing the artificial-intelligence-based diagnostic support technologies. However, the intrinsic characteristics of ultrasound imaging, like speckle noise and acoustic shadow, always degenerate the detection accuracy. In this study, we developed a deep learning model called BUSnet to detect the breast tumor lesions in US images with high accuracy. We first developed a two-stage method including the unsupervised region proposal and bounding-box regression algorithms. Then, we proposed a post-processing method to enhance the detecting accuracy further. The proposed method was used to a benchmark dataset, which includes 487 benign samples and 210 malignant samples. The results proved the effectiveness and accuracy of the proposed method.
format Online
Article
Text
id pubmed-8989926
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-89899262022-04-09 BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images Li, Yujie Gu, Hong Wang, Hongyu Qin, Pan Wang, Jia Front Oncol Oncology Ultrasound (US) imaging is a main modality for breast disease screening. Automatically detecting the lesions in US images is essential for developing the artificial-intelligence-based diagnostic support technologies. However, the intrinsic characteristics of ultrasound imaging, like speckle noise and acoustic shadow, always degenerate the detection accuracy. In this study, we developed a deep learning model called BUSnet to detect the breast tumor lesions in US images with high accuracy. We first developed a two-stage method including the unsupervised region proposal and bounding-box regression algorithms. Then, we proposed a post-processing method to enhance the detecting accuracy further. The proposed method was used to a benchmark dataset, which includes 487 benign samples and 210 malignant samples. The results proved the effectiveness and accuracy of the proposed method. Frontiers Media S.A. 2022-03-25 /pmc/articles/PMC8989926/ /pubmed/35402269 http://dx.doi.org/10.3389/fonc.2022.848271 Text en Copyright © 2022 Li, Gu, Wang, Qin and Wang https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Li, Yujie
Gu, Hong
Wang, Hongyu
Qin, Pan
Wang, Jia
BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images
title BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images
title_full BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images
title_fullStr BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images
title_full_unstemmed BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images
title_short BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images
title_sort busnet: a deep learning model of breast tumor lesion detection for ultrasound images
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8989926/
https://www.ncbi.nlm.nih.gov/pubmed/35402269
http://dx.doi.org/10.3389/fonc.2022.848271
work_keys_str_mv AT liyujie busnetadeeplearningmodelofbreasttumorlesiondetectionforultrasoundimages
AT guhong busnetadeeplearningmodelofbreasttumorlesiondetectionforultrasoundimages
AT wanghongyu busnetadeeplearningmodelofbreasttumorlesiondetectionforultrasoundimages
AT qinpan busnetadeeplearningmodelofbreasttumorlesiondetectionforultrasoundimages
AT wangjia busnetadeeplearningmodelofbreasttumorlesiondetectionforultrasoundimages