Cargando…

A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography

Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0–2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early st...

Descripción completa

Detalles Bibliográficos
Autores principales: Tsai, Kuen-Jang, Chou, Mei-Chun, Li, Hao-Ming, Liu, Shin-Tso, Hsu, Jung-Hsiu, Yeh, Wei-Cheng, Hung, Chao-Ming, Yeh, Cheng-Yu, Hwang, Shaw-Hwa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8838754/
https://www.ncbi.nlm.nih.gov/pubmed/35161903
http://dx.doi.org/10.3390/s22031160
_version_ 1784650203494612992
author Tsai, Kuen-Jang
Chou, Mei-Chun
Li, Hao-Ming
Liu, Shin-Tso
Hsu, Jung-Hsiu
Yeh, Wei-Cheng
Hung, Chao-Ming
Yeh, Cheng-Yu
Hwang, Shaw-Hwa
author_facet Tsai, Kuen-Jang
Chou, Mei-Chun
Li, Hao-Ming
Liu, Shin-Tso
Hsu, Jung-Hsiu
Yeh, Wei-Cheng
Hung, Chao-Ming
Yeh, Cheng-Yu
Hwang, Shaw-Hwa
author_sort Tsai, Kuen-Jang
collection PubMed
description Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0–2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early stage. Taiwan government has been urging women without any symptoms, aged between 45 and 69, to have a screening mammogram bi-yearly. This brings about a large workload for radiologists. In light of this, this paper presents a deep neural network (DNN)-based model as an efficient and reliable tool to assist radiologists with mammographic interpretation. For the first time in the literature, mammograms are completely classified into BI-RADS categories 0, 1, 2, 3, 4A, 4B, 4C and 5. The proposed model was trained using block-based images segmented from a mammogram dataset of our own. A block-based image was applied to the model as an input, and a BI-RADS category was predicted as an output. At the end of this paper, the outperformance of this work is demonstrated by an overall accuracy of 94.22%, an average sensitivity of 95.31%, an average specificity of 99.15% and an area under curve (AUC) of 0.9723. When applied to breast cancer screening for Asian women who are more likely to have dense breasts, this model is expected to give a higher accuracy than others in the literature, since it was trained using mammograms taken from Taiwanese women.
format Online
Article
Text
id pubmed-8838754
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88387542022-02-13 A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography Tsai, Kuen-Jang Chou, Mei-Chun Li, Hao-Ming Liu, Shin-Tso Hsu, Jung-Hsiu Yeh, Wei-Cheng Hung, Chao-Ming Yeh, Cheng-Yu Hwang, Shaw-Hwa Sensors (Basel) Article Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0–2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early stage. Taiwan government has been urging women without any symptoms, aged between 45 and 69, to have a screening mammogram bi-yearly. This brings about a large workload for radiologists. In light of this, this paper presents a deep neural network (DNN)-based model as an efficient and reliable tool to assist radiologists with mammographic interpretation. For the first time in the literature, mammograms are completely classified into BI-RADS categories 0, 1, 2, 3, 4A, 4B, 4C and 5. The proposed model was trained using block-based images segmented from a mammogram dataset of our own. A block-based image was applied to the model as an input, and a BI-RADS category was predicted as an output. At the end of this paper, the outperformance of this work is demonstrated by an overall accuracy of 94.22%, an average sensitivity of 95.31%, an average specificity of 99.15% and an area under curve (AUC) of 0.9723. When applied to breast cancer screening for Asian women who are more likely to have dense breasts, this model is expected to give a higher accuracy than others in the literature, since it was trained using mammograms taken from Taiwanese women. MDPI 2022-02-03 /pmc/articles/PMC8838754/ /pubmed/35161903 http://dx.doi.org/10.3390/s22031160 Text en © 2022 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
Tsai, Kuen-Jang
Chou, Mei-Chun
Li, Hao-Ming
Liu, Shin-Tso
Hsu, Jung-Hsiu
Yeh, Wei-Cheng
Hung, Chao-Ming
Yeh, Cheng-Yu
Hwang, Shaw-Hwa
A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography
title A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography
title_full A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography
title_fullStr A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography
title_full_unstemmed A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography
title_short A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography
title_sort high-performance deep neural network model for bi-rads classification of screening mammography
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8838754/
https://www.ncbi.nlm.nih.gov/pubmed/35161903
http://dx.doi.org/10.3390/s22031160
work_keys_str_mv AT tsaikuenjang ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT choumeichun ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT lihaoming ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT liushintso ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT hsujunghsiu ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT yehweicheng ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT hungchaoming ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT yehchengyu ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT hwangshawhwa ahighperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT tsaikuenjang highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT choumeichun highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT lihaoming highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT liushintso highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT hsujunghsiu highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT yehweicheng highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT hungchaoming highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT yehchengyu highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography
AT hwangshawhwa highperformancedeepneuralnetworkmodelforbiradsclassificationofscreeningmammography