Lesion classification in mammograms using convolutional neural networks and transfer learning
Main Author: | |
---|---|
Publication Date: | 2018 |
Other Authors: | , |
Format: | Article |
Language: | eng |
Source: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Download full: | http://hdl.handle.net/10400.6/8144 |
Summary: | Convolutional neural networks (CNNs) have recently been successfully used in the medical field to detect and classify pathologies in different imaging modalities, including in mammography. One disadvantage of CNNs is the need for large training datasets, which are particularly difficult to obtain in the medical domain. One way to solve this problem is using a transfer learning approach, in which a CNN, previously pre-trained with a large amount of labelled non-medical data, is subsequently finetuned using a smaller dataset of medical data. In this paper, we use such a transfer learning approach, which is applied to three different networks that were pre-trained using the Imagenet dataset. We investigate how the performance of these pre-trained CNNs to classify lesions in mammograms is affected by the use, or not, of normalised images during the fine-tuning stage. We also assess the performance of a support vector machine fed with features extracted from the CNN and the combined use of handcrafted features to complement the CNN-extracted features. The obtained results are encouraging. |
id |
RCAP_44266b51c4641d9acc7ba269eb3596f3 |
---|---|
oai_identifier_str |
oai:ubibliorum.ubi.pt:10400.6/8144 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Lesion classification in mammograms using convolutional neural networks and transfer learningMammographic imageConvolutional neuralNetworkTransfer learningSupport vector machineBreast cancerLesion classificationConvolutional neural networks (CNNs) have recently been successfully used in the medical field to detect and classify pathologies in different imaging modalities, including in mammography. One disadvantage of CNNs is the need for large training datasets, which are particularly difficult to obtain in the medical domain. One way to solve this problem is using a transfer learning approach, in which a CNN, previously pre-trained with a large amount of labelled non-medical data, is subsequently finetuned using a smaller dataset of medical data. In this paper, we use such a transfer learning approach, which is applied to three different networks that were pre-trained using the Imagenet dataset. We investigate how the performance of these pre-trained CNNs to classify lesions in mammograms is affected by the use, or not, of normalised images during the fine-tuning stage. We also assess the performance of a support vector machine fed with features extracted from the CNN and the combined use of handcrafted features to complement the CNN-extracted features. The obtained results are encouraging.uBibliorumPerre, Ana CatarinaAlexandre, LuísFreire, Luís C.2020-01-09T10:24:14Z20182018-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.6/8144eng10.1080/21681163.2018.1498392info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-12-15T09:47:54Zoai:ubibliorum.ubi.pt:10400.6/8144Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:48:32.933504Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Lesion classification in mammograms using convolutional neural networks and transfer learning |
title |
Lesion classification in mammograms using convolutional neural networks and transfer learning |
spellingShingle |
Lesion classification in mammograms using convolutional neural networks and transfer learning Perre, Ana Catarina Mammographic image Convolutional neural Network Transfer learning Support vector machine Breast cancer Lesion classification |
title_short |
Lesion classification in mammograms using convolutional neural networks and transfer learning |
title_full |
Lesion classification in mammograms using convolutional neural networks and transfer learning |
title_fullStr |
Lesion classification in mammograms using convolutional neural networks and transfer learning |
title_full_unstemmed |
Lesion classification in mammograms using convolutional neural networks and transfer learning |
title_sort |
Lesion classification in mammograms using convolutional neural networks and transfer learning |
author |
Perre, Ana Catarina |
author_facet |
Perre, Ana Catarina Alexandre, Luís Freire, Luís C. |
author_role |
author |
author2 |
Alexandre, Luís Freire, Luís C. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
uBibliorum |
dc.contributor.author.fl_str_mv |
Perre, Ana Catarina Alexandre, Luís Freire, Luís C. |
dc.subject.por.fl_str_mv |
Mammographic image Convolutional neural Network Transfer learning Support vector machine Breast cancer Lesion classification |
topic |
Mammographic image Convolutional neural Network Transfer learning Support vector machine Breast cancer Lesion classification |
description |
Convolutional neural networks (CNNs) have recently been successfully used in the medical field to detect and classify pathologies in different imaging modalities, including in mammography. One disadvantage of CNNs is the need for large training datasets, which are particularly difficult to obtain in the medical domain. One way to solve this problem is using a transfer learning approach, in which a CNN, previously pre-trained with a large amount of labelled non-medical data, is subsequently finetuned using a smaller dataset of medical data. In this paper, we use such a transfer learning approach, which is applied to three different networks that were pre-trained using the Imagenet dataset. We investigate how the performance of these pre-trained CNNs to classify lesions in mammograms is affected by the use, or not, of normalised images during the fine-tuning stage. We also assess the performance of a support vector machine fed with features extracted from the CNN and the combined use of handcrafted features to complement the CNN-extracted features. The obtained results are encouraging. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018 2018-01-01T00:00:00Z 2020-01-09T10:24:14Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.6/8144 |
url |
http://hdl.handle.net/10400.6/8144 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1080/21681163.2018.1498392 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799136379748220928 |