Cargando…

Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks

The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the exper...

Descripción completa

Detalles Bibliográficos
Autores principales: Kalafi, Elham Yousef, Jodeiri, Ata, Setarehdan, Seyed Kamaledin, Lin, Ng Wei, Rahmat, Kartini, Taib, Nur Aishah, Ganggayah, Mogana Darshini, Dhillon, Sarinder Kaur
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534785/
https://www.ncbi.nlm.nih.gov/pubmed/34679557
http://dx.doi.org/10.3390/diagnostics11101859
_version_ 1784587628275826688
author Kalafi, Elham Yousef
Jodeiri, Ata
Setarehdan, Seyed Kamaledin
Lin, Ng Wei
Rahmat, Kartini
Taib, Nur Aishah
Ganggayah, Mogana Darshini
Dhillon, Sarinder Kaur
author_facet Kalafi, Elham Yousef
Jodeiri, Ata
Setarehdan, Seyed Kamaledin
Lin, Ng Wei
Rahmat, Kartini
Taib, Nur Aishah
Ganggayah, Mogana Darshini
Dhillon, Sarinder Kaur
author_sort Kalafi, Elham Yousef
collection PubMed
description The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model.
format Online
Article
Text
id pubmed-8534785
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85347852021-10-23 Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks Kalafi, Elham Yousef Jodeiri, Ata Setarehdan, Seyed Kamaledin Lin, Ng Wei Rahmat, Kartini Taib, Nur Aishah Ganggayah, Mogana Darshini Dhillon, Sarinder Kaur Diagnostics (Basel) Article The reliable classification of benign and malignant lesions in breast ultrasound images can provide an effective and relatively low-cost method for the early diagnosis of breast cancer. The accuracy of the diagnosis is, however, highly dependent on the quality of the ultrasound systems and the experience of the users (radiologists). The use of deep convolutional neural network approaches has provided solutions for the efficient analysis of breast ultrasound images. In this study, we propose a new framework for the classification of breast cancer lesions with an attention module in a modified VGG16 architecture. The adopted attention mechanism enhances the feature discrimination between the background and targeted lesions in ultrasound. We also propose a new ensembled loss function, which is a combination of binary cross-entropy and the logarithm of the hyperbolic cosine loss, to improve the model discrepancy between classified lesions and their labels. This combined loss function optimizes the network more quickly. The proposed model outperformed other modified VGG16 architectures, with an accuracy of 93%, and also, the results are competitive with those of other state-of-the-art frameworks for the classification of breast cancer lesions. Our experimental results show that the choice of loss function is highly important and plays a key role in breast lesion classification tasks. Additionally, by adding an attention block, we could improve the performance of the model. MDPI 2021-10-09 /pmc/articles/PMC8534785/ /pubmed/34679557 http://dx.doi.org/10.3390/diagnostics11101859 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
Kalafi, Elham Yousef
Jodeiri, Ata
Setarehdan, Seyed Kamaledin
Lin, Ng Wei
Rahmat, Kartini
Taib, Nur Aishah
Ganggayah, Mogana Darshini
Dhillon, Sarinder Kaur
Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks
title Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks
title_full Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks
title_fullStr Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks
title_full_unstemmed Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks
title_short Classification of Breast Cancer Lesions in Ultrasound Images by Using Attention Layer and Loss Ensemble in Deep Convolutional Neural Networks
title_sort classification of breast cancer lesions in ultrasound images by using attention layer and loss ensemble in deep convolutional neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534785/
https://www.ncbi.nlm.nih.gov/pubmed/34679557
http://dx.doi.org/10.3390/diagnostics11101859
work_keys_str_mv AT kalafielhamyousef classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks
AT jodeiriata classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks
AT setarehdanseyedkamaledin classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks
AT linngwei classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks
AT rahmatkartini classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks
AT taibnuraishah classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks
AT ganggayahmoganadarshini classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks
AT dhillonsarinderkaur classificationofbreastcancerlesionsinultrasoundimagesbyusingattentionlayerandlossensembleindeepconvolutionalneuralnetworks