Cargando…

Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network

Over the past few years, researchers have demonstrated the possibilities to use the Computer-Aided Diagnosis (CAD) to provide a preliminary diagnosis. Recently, it is also becoming increasingly common for doctors and computer practitioners to collaborate on developing CAD. Since the early diagnosis...

Descripción completa

Detalles Bibliográficos
Autores principales: Yu, Kailuo, Chen, Sheng, Chen, Yanghuai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8467674/
https://www.ncbi.nlm.nih.gov/pubmed/34573907
http://dx.doi.org/10.3390/diagnostics11091565
_version_ 1784573458762432512
author Yu, Kailuo
Chen, Sheng
Chen, Yanghuai
author_facet Yu, Kailuo
Chen, Sheng
Chen, Yanghuai
author_sort Yu, Kailuo
collection PubMed
description Over the past few years, researchers have demonstrated the possibilities to use the Computer-Aided Diagnosis (CAD) to provide a preliminary diagnosis. Recently, it is also becoming increasingly common for doctors and computer practitioners to collaborate on developing CAD. Since the early diagnosis of breast cancer is the most critical step, a precise segmentation of breast tumor with accurate edge and shape is vital for accurate diagnoses and reduction in the patients’ pain. In view of the deficient accuracy of existing method, we proposed a novel method based on U-Net to improve the tumor segmentation accuracy in breast ultrasound images. First, Res Path was introduced into the U-Net to reduce the difference between the feature maps of the encoder and decoder. Then, a new connection, dense block from the input of the feature maps in the encoding-to-decoding section, was added to reduce the feature information loss and alleviate the vanishing gradient problem. A breast ultrasound database, which contains 538 tumor images, from Xinhua Hospital in Shanghai and marked by two professional doctors was used to train and test models. We, using ten-fold cross-validation method, compared the U-Net, U-Net with Res Path, and the proposed method to verify the improvements. The results demonstrated an overall improvement by the proposed approach when compared with the other in terms of true-positive rate, false-positive rate, Hausdorff distance indices, Jaccard similarity, and Dice coefficients.
format Online
Article
Text
id pubmed-8467674
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84676742021-09-27 Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network Yu, Kailuo Chen, Sheng Chen, Yanghuai Diagnostics (Basel) Article Over the past few years, researchers have demonstrated the possibilities to use the Computer-Aided Diagnosis (CAD) to provide a preliminary diagnosis. Recently, it is also becoming increasingly common for doctors and computer practitioners to collaborate on developing CAD. Since the early diagnosis of breast cancer is the most critical step, a precise segmentation of breast tumor with accurate edge and shape is vital for accurate diagnoses and reduction in the patients’ pain. In view of the deficient accuracy of existing method, we proposed a novel method based on U-Net to improve the tumor segmentation accuracy in breast ultrasound images. First, Res Path was introduced into the U-Net to reduce the difference between the feature maps of the encoder and decoder. Then, a new connection, dense block from the input of the feature maps in the encoding-to-decoding section, was added to reduce the feature information loss and alleviate the vanishing gradient problem. A breast ultrasound database, which contains 538 tumor images, from Xinhua Hospital in Shanghai and marked by two professional doctors was used to train and test models. We, using ten-fold cross-validation method, compared the U-Net, U-Net with Res Path, and the proposed method to verify the improvements. The results demonstrated an overall improvement by the proposed approach when compared with the other in terms of true-positive rate, false-positive rate, Hausdorff distance indices, Jaccard similarity, and Dice coefficients. MDPI 2021-08-28 /pmc/articles/PMC8467674/ /pubmed/34573907 http://dx.doi.org/10.3390/diagnostics11091565 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yu, Kailuo
Chen, Sheng
Chen, Yanghuai
Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network
title Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network
title_full Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network
title_fullStr Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network
title_full_unstemmed Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network
title_short Tumor Segmentation in Breast Ultrasound Image by Means of Res Path Combined with Dense Connection Neural Network
title_sort tumor segmentation in breast ultrasound image by means of res path combined with dense connection neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8467674/
https://www.ncbi.nlm.nih.gov/pubmed/34573907
http://dx.doi.org/10.3390/diagnostics11091565
work_keys_str_mv AT yukailuo tumorsegmentationinbreastultrasoundimagebymeansofrespathcombinedwithdenseconnectionneuralnetwork
AT chensheng tumorsegmentationinbreastultrasoundimagebymeansofrespathcombinedwithdenseconnectionneuralnetwork
AT chenyanghuai tumorsegmentationinbreastultrasoundimagebymeansofrespathcombinedwithdenseconnectionneuralnetwork