Cargando…

Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study

Deep convolutional neural networks (CNNs) are investigated in the context of computer-aided diagnosis (CADx) of breast cancer. State-of-the-art CNNs are trained and evaluated on two mammographic datasets, consisting of ROIs depicting benign or malignant mass lesions. The performance evaluation of ea...

Descripción completa

Detalles Bibliográficos
Autores principales: Tsochatzidis, Lazaros, Costaridou, Lena, Pratikakis, Ioannis
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8320909/
https://www.ncbi.nlm.nih.gov/pubmed/34460465
http://dx.doi.org/10.3390/jimaging5030037
_version_ 1783730725472698368
author Tsochatzidis, Lazaros
Costaridou, Lena
Pratikakis, Ioannis
author_facet Tsochatzidis, Lazaros
Costaridou, Lena
Pratikakis, Ioannis
author_sort Tsochatzidis, Lazaros
collection PubMed
description Deep convolutional neural networks (CNNs) are investigated in the context of computer-aided diagnosis (CADx) of breast cancer. State-of-the-art CNNs are trained and evaluated on two mammographic datasets, consisting of ROIs depicting benign or malignant mass lesions. The performance evaluation of each examined network is addressed in two training scenarios: the first involves initializing the network with pre-trained weights, while for the second the networks are initialized in a random fashion. Extensive experimental results show the superior performance achieved in the case of fine-tuning a pretrained network compared to training from scratch.
format Online
Article
Text
id pubmed-8320909
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83209092021-08-26 Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study Tsochatzidis, Lazaros Costaridou, Lena Pratikakis, Ioannis J Imaging Article Deep convolutional neural networks (CNNs) are investigated in the context of computer-aided diagnosis (CADx) of breast cancer. State-of-the-art CNNs are trained and evaluated on two mammographic datasets, consisting of ROIs depicting benign or malignant mass lesions. The performance evaluation of each examined network is addressed in two training scenarios: the first involves initializing the network with pre-trained weights, while for the second the networks are initialized in a random fashion. Extensive experimental results show the superior performance achieved in the case of fine-tuning a pretrained network compared to training from scratch. MDPI 2019-03-13 /pmc/articles/PMC8320909/ /pubmed/34460465 http://dx.doi.org/10.3390/jimaging5030037 Text en © 2019 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 (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ).
spellingShingle Article
Tsochatzidis, Lazaros
Costaridou, Lena
Pratikakis, Ioannis
Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study
title Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study
title_full Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study
title_fullStr Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study
title_full_unstemmed Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study
title_short Deep Learning for Breast Cancer Diagnosis from Mammograms—A Comparative Study
title_sort deep learning for breast cancer diagnosis from mammograms—a comparative study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8320909/
https://www.ncbi.nlm.nih.gov/pubmed/34460465
http://dx.doi.org/10.3390/jimaging5030037
work_keys_str_mv AT tsochatzidislazaros deeplearningforbreastcancerdiagnosisfrommammogramsacomparativestudy
AT costaridoulena deeplearningforbreastcancerdiagnosisfrommammogramsacomparativestudy
AT pratikakisioannis deeplearningforbreastcancerdiagnosisfrommammogramsacomparativestudy