A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks

Radiology experts often face difficulties in mammography mass lesion labeling, which may lead to conclusive yet unnecessary and expensive breast biopsies. This paper focuses on building an automated diagnosis tool that supports radiologists in identifying and classifying mammography mass lesions. Th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Meteb M. Altaf
Formato:	article
Lenguaje:	EN
Publicado:	AIMS Press 2021
Materias:	breast cancer diagnosis pcnn cnn deep learning model transfer learning Biotechnology TP248.13-248.65 Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/7341837a9fe54afdad9933670845e4ba
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7341837a9fe54afdad9933670845e4ba
record_format	dspace
spelling	oai:doaj.org-article:7341837a9fe54afdad9933670845e4ba2021-11-08T03:06:55ZA hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks10.3934/mbe.20212561551-0018https://doaj.org/article/7341837a9fe54afdad9933670845e4ba2021-06-01T00:00:00Zhttps://www.aimspress.com/article/doi/10.3934/mbe.2021256?viewType=HTMLhttps://doaj.org/toc/1551-0018Radiology experts often face difficulties in mammography mass lesion labeling, which may lead to conclusive yet unnecessary and expensive breast biopsies. This paper focuses on building an automated diagnosis tool that supports radiologists in identifying and classifying mammography mass lesions. The paper's main contribution is to design a hybrid model based on Pulse-Coupled Neural Networks (PCNN) and Deep Convolutional Neural Networks (CNN). Due to the need for large datasets to train and tune CNNs, which are not available for medical images, Transfer Learning (TL) was exploited in this research. TL can be an effective approach when working with small-sized datasets. The paper's implementation was tested on three public benchmark datasets: DDMS, INbreast, and BCDR datasets for training and testing and MIAS for testing only. The results indicated the enhancement that PCNN provides when combined with CNN compared to other methods for the same public datasets. The hybrid model achieved 98.72% accuracy for DDMS, 97.5% for INbreast, and 96.94% for BCDR. To avoid overfitting, the proposed hybrid model was tested on an unseen MIAS dataset, achieving 98.77% accuracy. Other evaluation metrics are reported in the results section.Meteb M. Altaf AIMS Pressarticlebreast cancer diagnosispcnncnndeep learning modeltransfer learningBiotechnologyTP248.13-248.65MathematicsQA1-939ENMathematical Biosciences and Engineering, Vol 18, Iss 5, Pp 5029-5046 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	breast cancer diagnosis pcnn cnn deep learning model transfer learning Biotechnology TP248.13-248.65 Mathematics QA1-939
spellingShingle	breast cancer diagnosis pcnn cnn deep learning model transfer learning Biotechnology TP248.13-248.65 Mathematics QA1-939 Meteb M. Altaf A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks
description	Radiology experts often face difficulties in mammography mass lesion labeling, which may lead to conclusive yet unnecessary and expensive breast biopsies. This paper focuses on building an automated diagnosis tool that supports radiologists in identifying and classifying mammography mass lesions. The paper's main contribution is to design a hybrid model based on Pulse-Coupled Neural Networks (PCNN) and Deep Convolutional Neural Networks (CNN). Due to the need for large datasets to train and tune CNNs, which are not available for medical images, Transfer Learning (TL) was exploited in this research. TL can be an effective approach when working with small-sized datasets. The paper's implementation was tested on three public benchmark datasets: DDMS, INbreast, and BCDR datasets for training and testing and MIAS for testing only. The results indicated the enhancement that PCNN provides when combined with CNN compared to other methods for the same public datasets. The hybrid model achieved 98.72% accuracy for DDMS, 97.5% for INbreast, and 96.94% for BCDR. To avoid overfitting, the proposed hybrid model was tested on an unseen MIAS dataset, achieving 98.77% accuracy. Other evaluation metrics are reported in the results section.
format	article
author	Meteb M. Altaf
author_facet	Meteb M. Altaf
author_sort	Meteb M. Altaf
title	A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks
title_short	A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks
title_full	A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks
title_fullStr	A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks
title_full_unstemmed	A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks
title_sort	hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks
publisher	AIMS Press
publishDate	2021
url	https://doaj.org/article/7341837a9fe54afdad9933670845e4ba
work_keys_str_mv	AT metebmaltaf ahybriddeeplearningmodelforbreastcancerdiagnosisbasedontransferlearningandpulsecoupledneuralnetworks AT metebmaltaf hybriddeeplearningmodelforbreastcancerdiagnosisbasedontransferlearningandpulsecoupledneuralnetworks
_version_	1718443011769106432

A hybrid deep learning model for breast cancer diagnosis based on transfer learning and pulse-coupled neural networks

Ejemplares similares