Cargando…

Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset

Cancer is the second leading cause of death globally, and breast cancer (BC) is the second most reported cancer. Although the incidence rate is reducing in developed countries, the reverse is the case in low- and middle-income countries. Early detection has been found to contain cancer growth, preve...

Descripción completa

Detalles Bibliográficos
Autores principales: Adedigba, Adeyinka P., Adeshina, Steve A., Aibinu, Abiodun M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9027584/
https://www.ncbi.nlm.nih.gov/pubmed/35447721
http://dx.doi.org/10.3390/bioengineering9040161
_version_ 1784691402503880704
author Adedigba, Adeyinka P.
Adeshina, Steve A.
Aibinu, Abiodun M.
author_facet Adedigba, Adeyinka P.
Adeshina, Steve A.
Aibinu, Abiodun M.
author_sort Adedigba, Adeyinka P.
collection PubMed
description Cancer is the second leading cause of death globally, and breast cancer (BC) is the second most reported cancer. Although the incidence rate is reducing in developed countries, the reverse is the case in low- and middle-income countries. Early detection has been found to contain cancer growth, prevent metastasis, ease treatment, and reduce mortality by 25%. The digital mammogram is one of the most common, cheapest, and most effective BC screening techniques capable of early detection of up to 90% BC incidence. However, the mammogram is one of the most difficult medical images to analyze. In this paper, we present a method of training a deep learning model for BC diagnosis. We developed a discriminative fine-tuning method which dynamically assigns different learning rates to each layer of the deep CNN. In addition, the model was trained using mixed-precision training to ease the computational demand of training deep learning models. Lastly, we present data augmentation methods for mammograms. The discriminative fine-tuning algorithm enables rapid convergence of the model loss; hence, the models were trained to attain their best performance within 50 epochs. Comparing the results, DenseNet achieved the highest accuracy of 0.998, while AlexNet obtained 0.988.
format Online
Article
Text
id pubmed-9027584
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90275842022-04-23 Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset Adedigba, Adeyinka P. Adeshina, Steve A. Aibinu, Abiodun M. Bioengineering (Basel) Article Cancer is the second leading cause of death globally, and breast cancer (BC) is the second most reported cancer. Although the incidence rate is reducing in developed countries, the reverse is the case in low- and middle-income countries. Early detection has been found to contain cancer growth, prevent metastasis, ease treatment, and reduce mortality by 25%. The digital mammogram is one of the most common, cheapest, and most effective BC screening techniques capable of early detection of up to 90% BC incidence. However, the mammogram is one of the most difficult medical images to analyze. In this paper, we present a method of training a deep learning model for BC diagnosis. We developed a discriminative fine-tuning method which dynamically assigns different learning rates to each layer of the deep CNN. In addition, the model was trained using mixed-precision training to ease the computational demand of training deep learning models. Lastly, we present data augmentation methods for mammograms. The discriminative fine-tuning algorithm enables rapid convergence of the model loss; hence, the models were trained to attain their best performance within 50 epochs. Comparing the results, DenseNet achieved the highest accuracy of 0.998, while AlexNet obtained 0.988. MDPI 2022-04-06 /pmc/articles/PMC9027584/ /pubmed/35447721 http://dx.doi.org/10.3390/bioengineering9040161 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
Adedigba, Adeyinka P.
Adeshina, Steve A.
Aibinu, Abiodun M.
Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset
title Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset
title_full Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset
title_fullStr Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset
title_full_unstemmed Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset
title_short Performance Evaluation of Deep Learning Models on Mammogram Classification Using Small Dataset
title_sort performance evaluation of deep learning models on mammogram classification using small dataset
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9027584/
https://www.ncbi.nlm.nih.gov/pubmed/35447721
http://dx.doi.org/10.3390/bioengineering9040161
work_keys_str_mv AT adedigbaadeyinkap performanceevaluationofdeeplearningmodelsonmammogramclassificationusingsmalldataset
AT adeshinastevea performanceevaluationofdeeplearningmodelsonmammogramclassificationusingsmalldataset
AT aibinuabiodunm performanceevaluationofdeeplearningmodelsonmammogramclassificationusingsmalldataset