Cargando…
A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis
BACKGROUND: Screening programs use mammography as primary diagnostic tool for detecting breast cancer at an early stage. The diagnosis of some lesions, such as microcalcifications, is still difficult today for radiologists. In this paper, we proposed an automatic binary model for discriminating tiss...
Autores principales: | , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7069158/ https://www.ncbi.nlm.nih.gov/pubmed/32164532 http://dx.doi.org/10.1186/s12859-020-3358-4 |
_version_ | 1783505724928688128 |
---|---|
author | Fanizzi, Annarita Basile, Teresa M. A. Losurdo, Liliana Bellotti, Roberto Bottigli, Ubaldo Dentamaro, Rosalba Didonna, Vittorio Fausto, Alfonso Massafra, Raffaella Moschetta, Marco Popescu, Ondina Tamborra, Pasquale Tangaro, Sabina La Forgia, Daniele |
author_facet | Fanizzi, Annarita Basile, Teresa M. A. Losurdo, Liliana Bellotti, Roberto Bottigli, Ubaldo Dentamaro, Rosalba Didonna, Vittorio Fausto, Alfonso Massafra, Raffaella Moschetta, Marco Popescu, Ondina Tamborra, Pasquale Tangaro, Sabina La Forgia, Daniele |
author_sort | Fanizzi, Annarita |
collection | PubMed |
description | BACKGROUND: Screening programs use mammography as primary diagnostic tool for detecting breast cancer at an early stage. The diagnosis of some lesions, such as microcalcifications, is still difficult today for radiologists. In this paper, we proposed an automatic binary model for discriminating tissue in digital mammograms, as support tool for the radiologists. In particular, we compared the contribution of different methods on the feature selection process in terms of the learning performances and selected features. RESULTS: For each ROI, we extracted textural features on Haar wavelet decompositions and also interest points and corners detected by using Speeded Up Robust Feature (SURF) and Minimum Eigenvalue Algorithm (MinEigenAlg). Then a Random Forest binary classifier is trained on a subset of a sub-set features selected by two different kinds of feature selection techniques, such as filter and embedded methods. We tested the proposed model on 260 ROIs extracted from digital mammograms of the BCDR public database. The best prediction performance for the normal/abnormal and benign/malignant problems reaches a median AUC value of 98.16% and 92.08%, and an accuracy of 97.31% and 88.46%, respectively. The experimental result was comparable with related work performance. CONCLUSIONS: The best performing result obtained with embedded method is more parsimonious than the filter one. The SURF and MinEigen algorithms provide a strong informative content useful for the characterization of microcalcification clusters. |
format | Online Article Text |
id | pubmed-7069158 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-70691582020-03-18 A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis Fanizzi, Annarita Basile, Teresa M. A. Losurdo, Liliana Bellotti, Roberto Bottigli, Ubaldo Dentamaro, Rosalba Didonna, Vittorio Fausto, Alfonso Massafra, Raffaella Moschetta, Marco Popescu, Ondina Tamborra, Pasquale Tangaro, Sabina La Forgia, Daniele BMC Bioinformatics Research BACKGROUND: Screening programs use mammography as primary diagnostic tool for detecting breast cancer at an early stage. The diagnosis of some lesions, such as microcalcifications, is still difficult today for radiologists. In this paper, we proposed an automatic binary model for discriminating tissue in digital mammograms, as support tool for the radiologists. In particular, we compared the contribution of different methods on the feature selection process in terms of the learning performances and selected features. RESULTS: For each ROI, we extracted textural features on Haar wavelet decompositions and also interest points and corners detected by using Speeded Up Robust Feature (SURF) and Minimum Eigenvalue Algorithm (MinEigenAlg). Then a Random Forest binary classifier is trained on a subset of a sub-set features selected by two different kinds of feature selection techniques, such as filter and embedded methods. We tested the proposed model on 260 ROIs extracted from digital mammograms of the BCDR public database. The best prediction performance for the normal/abnormal and benign/malignant problems reaches a median AUC value of 98.16% and 92.08%, and an accuracy of 97.31% and 88.46%, respectively. The experimental result was comparable with related work performance. CONCLUSIONS: The best performing result obtained with embedded method is more parsimonious than the filter one. The SURF and MinEigen algorithms provide a strong informative content useful for the characterization of microcalcification clusters. BioMed Central 2020-03-11 /pmc/articles/PMC7069158/ /pubmed/32164532 http://dx.doi.org/10.1186/s12859-020-3358-4 Text en © The Author(s) 2020 Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated. |
spellingShingle | Research Fanizzi, Annarita Basile, Teresa M. A. Losurdo, Liliana Bellotti, Roberto Bottigli, Ubaldo Dentamaro, Rosalba Didonna, Vittorio Fausto, Alfonso Massafra, Raffaella Moschetta, Marco Popescu, Ondina Tamborra, Pasquale Tangaro, Sabina La Forgia, Daniele A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis |
title | A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis |
title_full | A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis |
title_fullStr | A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis |
title_full_unstemmed | A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis |
title_short | A machine learning approach on multiscale texture analysis for breast microcalcification diagnosis |
title_sort | machine learning approach on multiscale texture analysis for breast microcalcification diagnosis |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7069158/ https://www.ncbi.nlm.nih.gov/pubmed/32164532 http://dx.doi.org/10.1186/s12859-020-3358-4 |
work_keys_str_mv | AT fanizziannarita amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT basileteresama amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT losurdoliliana amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT bellottiroberto amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT bottigliubaldo amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT dentamarorosalba amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT didonnavittorio amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT faustoalfonso amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT massafraraffaella amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT moschettamarco amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT popescuondina amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT tamborrapasquale amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT tangarosabina amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT laforgiadaniele amachinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT fanizziannarita machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT basileteresama machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT losurdoliliana machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT bellottiroberto machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT bottigliubaldo machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT dentamarorosalba machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT didonnavittorio machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT faustoalfonso machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT massafraraffaella machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT moschettamarco machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT popescuondina machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT tamborrapasquale machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT tangarosabina machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis AT laforgiadaniele machinelearningapproachonmultiscaletextureanalysisforbreastmicrocalcificationdiagnosis |